From 3e91ea10437fa2bb890ee962f417563398189113 Mon Sep 17 00:00:00 2001 From: Khadija Date: Tue, 8 Sep 2026 16:12:51 +0500 Subject: [PATCH 1/2] fix config file: rename configurations -> config.py, moved from checks/ to package root, added audit_report.html and report.json(example) files --- audit_report.html | 349 ++++++++++++++++++ .../{checks/configurations => config.py} | 0 report.json | 101 +++++ 3 files changed, 450 insertions(+) create mode 100644 audit_report.html rename inference_audit/{checks/configurations => config.py} (100%) create mode 100644 report.json diff --git a/audit_report.html b/audit_report.html new file mode 100644 index 0000000..953d97f --- /dev/null +++ b/audit_report.html @@ -0,0 +1,349 @@ + + + + + + inference-audit Report — C:\Users\User\Downloads\ruemocorp_silver.csv + + + + +
+

inference-audit Report

+
+ Dataset: C:\Users\User\Downloads\ruemocorp_silver.csv  ·  + 134053 rows  ·  + Generated 2026-09-05T16:56:41.250442  ·  + vdev +
+
+ +
+ + +
76
+ + +

Overall Score (weighted average across all checks)

+
+ +
+

Check Results

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
CheckScoreNotes
label distribution + + 68.64 + + + + Class imbalance detected: 'joy' has 28389 samples, 'surprise' has only 4080 (ratio 7.0:1). + +
+
+ + total rows: 134053  ·  + + num classes: 7  ·  + + class counts: {'joy': 28389, 'none': 28167, 'disgust': 25959, 'sadness': 22570, 'anger': 18275, 'fear': 6613, 'surprise': 4080}  ·  + + majority count: 28389  ·  + + minority count: 4080  ·  + + imbalance ratio: 6.96  ·  + + max acceptable ratio: 20.0  ·  + + null count: 0  ·  + + null rate: 0.0 + +
+
near duplicates + + 56.24 + + + + 46180 candidate duplicate pair(s) found among 134053 rows (58665 rows involved). 247 row(s) skipped (text shorter than 3 characters -- too short to compare reliably). + +
+
+ + total rows: 134053  ·  + + candidate pair count: 46180  ·  + + flagged row count: 58665  ·  + + skipped short count: 247  ·  + + duplicate rate: 0.4376  ·  + + threshold: 0.8  ·  + + num perm: 128  ·  + + example pairs: [{'row_a': 'Us waqat tak naqad unhen aik filmi showpiece hi shumar kar rahe the', 'row_b': 'Us waqat tak naqad unhen aik filmi showpiece hi shumar kar rahe the'}, {'row_a': 'Nice', 'row_b': 'Nice'}, {'row_a': 'darbari', 'row_b': 'darbari'}, {'row_a': 'hahahaha', 'row_b': 'Hahah'}, {'row_a': 'na krn na lala ap to kbi ksi ko nh rulaty aj kyn zid kr rhy . ;(', 'row_b': 'na krn na lala ap to kbi ksi ko nh rulaty aj kyn zid kr rhy . ;('}] + +
+
language contamination + + 90.69 + + + + 12438/133670 detectable rows (9.3%) confidently detected as a concern-list language (en, hi). 383 row(s) skipped (text too short/empty for language detection). + +
+
+ + total rows: 134053  ·  + + unique text count: 109191  ·  + + detectable count: 133670  ·  + + skipped undetectable count: 383  ·  + + contamination count: 12438  ·  + + contamination rate: 0.0931  ·  + + concern languages: ['en', 'hi']  ·  + + confidence threshold: 0.9 + +
+
missing values + + 99.82 + + + + 247/134053 rows (0.2%) flagged: 130 null, 0 whitespace-only, 117 below 3-character threshold. + +
+
+ + total rows: 134053  ·  + + flagged count: 247  ·  + + null count: 130  ·  + + whitespace only count: 0  ·  + + too short count: 117  ·  + + missing rate: 0.0018  ·  + + min length threshold: 3 + +
+
annotation consistency + + — + + + + Skipped — No confidence column provided — annotation consistency check skipped. + +
+
+ + error: no_confidence_column + +
+
+
+ +
+

Score Overview

+ + Bar chart of per-check scores + +
+ + + + + \ No newline at end of file diff --git a/inference_audit/checks/configurations b/inference_audit/config.py similarity index 100% rename from inference_audit/checks/configurations rename to inference_audit/config.py diff --git a/report.json b/report.json new file mode 100644 index 0000000..4e4b3b2 --- /dev/null +++ b/report.json @@ -0,0 +1,101 @@ +{ + "inference_audit_version": "dev", + "dataset": "C:\\Users\\User\\Downloads\\ruemocorp_silver.csv", + "rows": 134053, + "label_col": "predicted_emotion", + "text_col": "message", + "audit_timestamp": "2026-09-05T17:23:07.654317", + "overall_score": 78, + "checks": { + "label_distribution": { + "score": 68.64, + "warning": "Class imbalance detected: 'joy' has 28389 samples, 'surprise' has only 4080 (ratio 7.0:1).", + "total_rows": 134053, + "num_classes": 7, + "class_counts": { + "joy": 28389, + "none": 28167, + "disgust": 25959, + "sadness": 22570, + "anger": 18275, + "fear": 6613, + "surprise": 4080 + }, + "majority_count": 28389, + "minority_count": 4080, + "imbalance_ratio": 6.96, + "max_acceptable_ratio": 20.0, + "null_count": 0, + "null_rate": 0.0 + }, + "near_duplicates": { + "score": 56.24, + "warning": "46180 candidate duplicate pair(s) found among 134053 rows (58665 rows involved). 247 row(s) skipped (text shorter than 3 characters -- too short to compare reliably).", + "total_rows": 134053, + "candidate_pair_count": 46180, + "flagged_row_count": 58665, + "skipped_short_count": 247, + "duplicate_rate": 0.4376, + "threshold": 0.8, + "num_perm": 128, + "example_pairs": [ + { + "row_a": "good", + "row_b": "Good" + }, + { + "row_a": "munir hussain ne apne ashron par mushtamil taweel filmy career mein films ke liy", + "row_b": "Munir Hussain ne apne 4 ashron par mushtamil taweel filmy career mein 163 films " + }, + { + "row_a": "jaisayy program ( kon banay gaa meera ka pati ) main drama chala same waisa hi y", + "row_b": "jaisayy program ( kon banay gaa meera ka pati ) main drama chala same waisa hi y" + }, + { + "row_a": "shukria bhai", + "row_b": "shukria bhai" + }, + { + "row_a": "yeh mqm ka bhi pithu hai aur noon league ka bhi mulazim", + "row_b": "yeh mqm ka bhi pithu hai aur noon league ka bhi mulazim" + } + ] + }, + "language_contamination": { + "score": 90.69, + "warning": "12438/133670 detectable rows (9.3%) confidently detected as a concern-list language (en, hi). 383 row(s) skipped (text too short/empty for language detection).", + "total_rows": 134053, + "unique_text_count": 109191, + "detectable_count": 133670, + "skipped_undetectable_count": 383, + "contamination_count": 12438, + "contamination_rate": 0.0931, + "concern_languages": [ + "en", + "hi" + ], + "confidence_threshold": 0.9 + }, + "missing_values": { + "score": 99.82, + "warning": "247/134053 rows (0.2%) flagged: 130 null, 0 whitespace-only, 117 below 3-character threshold.", + "total_rows": 134053, + "flagged_count": 247, + "null_count": 130, + "whitespace_only_count": 0, + "too_short_count": 117, + "missing_rate": 0.0018, + "min_length_threshold": 3 + }, + "annotation_consistency": { + "score": 87.83, + "warning": "16320/134053 annotated samples (12.2%) have confidence below 0.6.", + "total_rows": 134053, + "non_null_count": 134053, + "null_count": 0, + "low_confidence_count": 16320, + "low_confidence_rate": 0.1217, + "confidence_threshold": 0.6 + } + } +} \ No newline at end of file From 5a9ea5b2dce1d8cb327bf650b0541644f285e47b Mon Sep 17 00:00:00 2001 From: Khadija Date: Tue, 8 Sep 2026 22:34:57 +0500 Subject: [PATCH 2/2] fix config file: rename configurations -> config.py, moved from checks/ to package root, added audit_report.html and report.json(example) files,adds tests fixtures --- conftest.py | 0 tests/fixtures/balanced.csv | 1001 +++++++++++++++++++++++++++ tests/fixtures/clean_dataset.csv | 501 ++++++++++++++ tests/fixtures/clean_urdu.csv | 501 ++++++++++++++ tests/fixtures/contaminated.csv | 501 ++++++++++++++ tests/fixtures/dirty_dataset.csv | 501 ++++++++++++++ tests/fixtures/high_confidence.csv | 501 ++++++++++++++ tests/fixtures/low_confidence.csv | 501 ++++++++++++++ tests/fixtures/no_duplicates.csv | 501 ++++++++++++++ tests/fixtures/severe_imbalance.csv | 1001 +++++++++++++++++++++++++++ tests/fixtures/with_duplicates.csv | 501 ++++++++++++++ 11 files changed, 6010 insertions(+) create mode 100644 conftest.py create mode 100644 tests/fixtures/balanced.csv create mode 100644 tests/fixtures/clean_dataset.csv create mode 100644 tests/fixtures/clean_urdu.csv create mode 100644 tests/fixtures/contaminated.csv create mode 100644 tests/fixtures/dirty_dataset.csv create mode 100644 tests/fixtures/high_confidence.csv create mode 100644 tests/fixtures/low_confidence.csv create mode 100644 tests/fixtures/no_duplicates.csv create mode 100644 tests/fixtures/severe_imbalance.csv create mode 100644 tests/fixtures/with_duplicates.csv diff --git a/conftest.py b/conftest.py new file mode 100644 index 0000000..e69de29 diff --git a/tests/fixtures/balanced.csv b/tests/fixtures/balanced.csv new file mode 100644 index 0000000..a99da08 --- /dev/null +++ b/tests/fixtures/balanced.csv @@ -0,0 +1,1001 @@ +text,label +Sample text class_3 number 176 with enough length to detect,class_3 +Sample text class_2 number 107 with enough length to detect,class_2 +Sample text class_4 number 95 with enough length to detect,class_4 +Sample text class_4 number 122 with enough length to detect,class_4 +Sample text class_0 number 33 with enough length to detect,class_0 +Sample text class_2 number 83 with enough length to detect,class_2 +Sample text class_0 number 85 with enough length to detect,class_0 +Sample text class_3 number 150 with enough length to detect,class_3 +Sample text class_1 number 154 with enough length to detect,class_1 +Sample text class_2 number 123 with enough length to detect,class_2 +Sample text class_0 number 184 with enough length to detect,class_0 +Sample text class_4 number 9 with enough length to detect,class_4 +Sample text class_2 number 18 with enough length to detect,class_2 +Sample text class_3 number 15 with enough length to detect,class_3 +Sample text class_3 number 82 with enough length to detect,class_3 +Sample text class_2 number 101 with enough length to detect,class_2 +Sample text class_3 number 160 with enough length to detect,class_3 +Sample text class_0 number 49 with enough length to detect,class_0 +Sample text class_3 number 132 with enough length to detect,class_3 +Sample text class_1 number 136 with enough length to detect,class_1 +Sample text class_2 number 50 with enough length to detect,class_2 +Sample text class_3 number 190 with enough length to detect,class_3 +Sample text class_1 number 150 with enough length to detect,class_1 +Sample text class_2 number 67 with enough length to detect,class_2 +Sample text class_3 number 22 with enough length to detect,class_3 +Sample text class_2 number 76 with enough length to detect,class_2 +Sample text class_3 number 14 with enough length to detect,class_3 +Sample text class_2 number 154 with enough length to detect,class_2 +Sample text class_1 number 165 with enough length to detect,class_1 +Sample text class_3 number 170 with enough length to detect,class_3 +Sample text class_3 number 30 with enough length to detect,class_3 +Sample text class_4 number 140 with enough length to detect,class_4 +Sample text class_3 number 197 with enough length to detect,class_3 +Sample text class_2 number 96 with enough length to detect,class_2 +Sample text class_4 number 124 with enough length to detect,class_4 +Sample text class_1 number 169 with enough length to detect,class_1 +Sample text class_2 number 196 with enough length to detect,class_2 +Sample text class_3 number 120 with enough length to detect,class_3 +Sample text class_0 number 53 with enough length to detect,class_0 +Sample text class_2 number 26 with enough length to detect,class_2 +Sample text class_0 number 56 with enough length to detect,class_0 +Sample text class_1 number 64 with enough length to detect,class_1 +Sample text class_3 number 172 with enough length to detect,class_3 +Sample text class_0 number 185 with enough length to detect,class_0 +Sample text class_2 number 66 with enough length to detect,class_2 +Sample text class_3 number 189 with enough length to detect,class_3 +Sample text class_0 number 174 with enough length to detect,class_0 +Sample text class_0 number 150 with enough length to detect,class_0 +Sample text class_3 number 141 with enough length to detect,class_3 +Sample text class_0 number 113 with enough length to detect,class_0 +Sample text class_2 number 28 with enough length to detect,class_2 +Sample text class_4 number 165 with enough length to detect,class_4 +Sample text class_0 number 18 with enough length to detect,class_0 +Sample text class_0 number 189 with enough length to detect,class_0 +Sample text class_2 number 14 with enough length to detect,class_2 +Sample text class_2 number 189 with enough length to detect,class_2 +Sample text class_3 number 66 with enough length to detect,class_3 +Sample text class_3 number 163 with enough length to detect,class_3 +Sample text class_1 number 21 with enough length to detect,class_1 +Sample text class_2 number 186 with enough length to detect,class_2 +Sample text class_2 number 181 with enough length to detect,class_2 +Sample text class_1 number 99 with enough length to detect,class_1 +Sample text class_3 number 38 with enough length to detect,class_3 +Sample text class_1 number 186 with enough length to detect,class_1 +Sample text class_1 number 164 with enough length to detect,class_1 +Sample text class_4 number 79 with enough length to detect,class_4 +Sample text class_1 number 134 with enough length to detect,class_1 +Sample text class_0 number 16 with enough length to detect,class_0 +Sample text class_1 number 2 with enough length to detect,class_1 +Sample text class_0 number 1 with enough length to detect,class_0 +Sample text class_0 number 38 with enough length to detect,class_0 +Sample text class_1 number 90 with enough length to detect,class_1 +Sample text class_2 number 93 with enough length to detect,class_2 +Sample text class_1 number 47 with enough length to detect,class_1 +Sample text class_2 number 106 with enough length to detect,class_2 +Sample text class_4 number 96 with enough length to detect,class_4 +Sample text class_3 number 113 with enough length to detect,class_3 +Sample text class_4 number 91 with enough length to detect,class_4 +Sample text class_0 number 76 with enough length to detect,class_0 +Sample text class_4 number 111 with enough length to detect,class_4 +Sample text class_3 number 192 with enough length to detect,class_3 +Sample text class_2 number 108 with enough length to detect,class_2 +Sample text class_0 number 177 with enough length to detect,class_0 +Sample text class_4 number 42 with enough length to detect,class_4 +Sample text class_1 number 0 with enough length to detect,class_1 +Sample text class_3 number 165 with enough length to detect,class_3 +Sample text class_4 number 109 with enough length to detect,class_4 +Sample text class_1 number 93 with enough length to detect,class_1 +Sample text class_2 number 138 with enough length to detect,class_2 +Sample text class_0 number 24 with enough length to detect,class_0 +Sample text class_3 number 94 with enough length to detect,class_3 +Sample text class_1 number 10 with enough length to detect,class_1 +Sample text class_2 number 24 with enough length to detect,class_2 +Sample text class_2 number 128 with enough length to detect,class_2 +Sample text class_0 number 34 with enough length to detect,class_0 +Sample text class_4 number 128 with enough length to detect,class_4 +Sample text class_1 number 198 with enough length to detect,class_1 +Sample text class_3 number 7 with enough length to detect,class_3 +Sample text class_1 number 98 with enough length to detect,class_1 +Sample text class_4 number 48 with enough length to detect,class_4 +Sample text class_3 number 68 with enough length to detect,class_3 +Sample text class_1 number 82 with enough length to detect,class_1 +Sample text class_4 number 139 with enough length to detect,class_4 +Sample text class_4 number 144 with enough length to detect,class_4 +Sample text class_3 number 6 with enough length to detect,class_3 +Sample text class_4 number 159 with enough length to detect,class_4 +Sample text class_4 number 134 with enough length to detect,class_4 +Sample text class_3 number 131 with enough length to detect,class_3 +Sample text class_1 number 87 with enough length to detect,class_1 +Sample text class_2 number 127 with enough length to detect,class_2 +Sample text class_4 number 7 with enough length to detect,class_4 +Sample text class_1 number 29 with enough length to detect,class_1 +Sample text class_2 number 36 with enough length to detect,class_2 +Sample text class_0 number 28 with enough length to detect,class_0 +Sample text class_1 number 174 with enough length to detect,class_1 +Sample text class_4 number 19 with enough length to detect,class_4 +Sample text class_1 number 116 with enough length to detect,class_1 +Sample text class_2 number 160 with enough length to detect,class_2 +Sample text class_1 number 41 with enough length to detect,class_1 +Sample text class_0 number 149 with enough length to detect,class_0 +Sample text class_2 number 116 with enough length to detect,class_2 +Sample text class_2 number 17 with enough length to detect,class_2 +Sample text class_3 number 60 with enough length to detect,class_3 +Sample text class_0 number 198 with enough length to detect,class_0 +Sample text class_2 number 185 with enough length to detect,class_2 +Sample text class_1 number 125 with enough length to detect,class_1 +Sample text class_4 number 23 with enough length to detect,class_4 +Sample text class_3 number 102 with enough length to detect,class_3 +Sample text class_4 number 149 with enough length to detect,class_4 +Sample text class_2 number 115 with enough length to detect,class_2 +Sample text class_4 number 64 with enough length to detect,class_4 +Sample text class_4 number 36 with enough length to detect,class_4 +Sample text class_4 number 77 with enough length to detect,class_4 +Sample text class_1 number 159 with enough length to detect,class_1 +Sample text class_2 number 194 with enough length to detect,class_2 +Sample text class_3 number 188 with enough length to detect,class_3 +Sample text class_0 number 188 with enough length to detect,class_0 +Sample text class_0 number 66 with enough length to detect,class_0 +Sample text class_1 number 155 with enough length to detect,class_1 +Sample text class_3 number 199 with enough length to detect,class_3 +Sample text class_4 number 102 with enough length to detect,class_4 +Sample text class_4 number 120 with enough length to detect,class_4 +Sample text class_4 number 142 with enough length to detect,class_4 +Sample text class_1 number 130 with enough length to detect,class_1 +Sample text class_3 number 127 with enough length to detect,class_3 +Sample text class_1 number 196 with enough length to detect,class_1 +Sample text class_2 number 63 with enough length to detect,class_2 +Sample text class_1 number 193 with enough length to detect,class_1 +Sample text class_1 number 111 with enough length to detect,class_1 +Sample text class_3 number 80 with enough length to detect,class_3 +Sample text class_3 number 144 with enough length to detect,class_3 +Sample text class_4 number 121 with enough length to detect,class_4 +Sample text class_2 number 61 with enough length to detect,class_2 +Sample text class_2 number 122 with enough length to detect,class_2 +Sample text class_3 number 31 with enough length to detect,class_3 +Sample text class_2 number 90 with enough length to detect,class_2 +Sample text class_0 number 195 with enough length to detect,class_0 +Sample text class_1 number 56 with enough length to detect,class_1 +Sample text class_3 number 93 with enough length to detect,class_3 +Sample text class_3 number 140 with enough length to detect,class_3 +Sample text class_2 number 177 with enough length to detect,class_2 +Sample text class_0 number 157 with enough length to detect,class_0 +Sample text class_3 number 12 with enough length to detect,class_3 +Sample text class_1 number 192 with enough length to detect,class_1 +Sample text class_4 number 169 with enough length to detect,class_4 +Sample text class_3 number 88 with enough length to detect,class_3 +Sample text class_1 number 161 with enough length to detect,class_1 +Sample text class_4 number 16 with enough length to detect,class_4 +Sample text class_2 number 1 with enough length to detect,class_2 +Sample text class_0 number 92 with enough length to detect,class_0 +Sample text class_4 number 117 with enough length to detect,class_4 +Sample text class_2 number 89 with enough length to detect,class_2 +Sample text class_2 number 51 with enough length to detect,class_2 +Sample text class_1 number 51 with enough length to detect,class_1 +Sample text class_3 number 53 with enough length to detect,class_3 +Sample text class_3 number 169 with enough length to detect,class_3 +Sample text class_3 number 70 with enough length to detect,class_3 +Sample text class_0 number 129 with enough length to detect,class_0 +Sample text class_3 number 37 with enough length to detect,class_3 +Sample text class_4 number 191 with enough length to detect,class_4 +Sample text class_1 number 142 with enough length to detect,class_1 +Sample text class_1 number 108 with enough length to detect,class_1 +Sample text class_0 number 136 with enough length to detect,class_0 +Sample text class_0 number 88 with enough length to detect,class_0 +Sample text class_1 number 127 with enough length to detect,class_1 +Sample text class_2 number 75 with enough length to detect,class_2 +Sample text class_4 number 181 with enough length to detect,class_4 +Sample text class_4 number 50 with enough length to detect,class_4 +Sample text class_4 number 92 with enough length to detect,class_4 +Sample text class_1 number 175 with enough length to detect,class_1 +Sample text class_0 number 178 with enough length to detect,class_0 +Sample text class_0 number 26 with enough length to detect,class_0 +Sample text class_1 number 149 with enough length to detect,class_1 +Sample text class_2 number 99 with enough length to detect,class_2 +Sample text class_2 number 74 with enough length to detect,class_2 +Sample text class_3 number 17 with enough length to detect,class_3 +Sample text class_3 number 97 with enough length to detect,class_3 +Sample text class_0 number 50 with enough length to detect,class_0 +Sample text class_1 number 11 with enough length to detect,class_1 +Sample text class_1 number 181 with enough length to detect,class_1 +Sample text class_4 number 83 with enough length to detect,class_4 +Sample text class_0 number 173 with enough length to detect,class_0 +Sample text class_0 number 147 with enough length to detect,class_0 +Sample text class_2 number 19 with enough length to detect,class_2 +Sample text class_4 number 161 with enough length to detect,class_4 +Sample text class_0 number 148 with enough length to detect,class_0 +Sample text class_4 number 175 with enough length to detect,class_4 +Sample text class_0 number 79 with enough length to detect,class_0 +Sample text class_3 number 175 with enough length to detect,class_3 +Sample text class_1 number 102 with enough length to detect,class_1 +Sample text class_4 number 195 with enough length to detect,class_4 +Sample text class_2 number 125 with enough length to detect,class_2 +Sample text class_3 number 174 with enough length to detect,class_3 +Sample text class_1 number 31 with enough length to detect,class_1 +Sample text class_3 number 25 with enough length to detect,class_3 +Sample text class_4 number 0 with enough length to detect,class_4 +Sample text class_2 number 161 with enough length to detect,class_2 +Sample text class_2 number 109 with enough length to detect,class_2 +Sample text class_4 number 40 with enough length to detect,class_4 +Sample text class_2 number 94 with enough length to detect,class_2 +Sample text class_0 number 119 with enough length to detect,class_0 +Sample text class_2 number 77 with enough length to detect,class_2 +Sample text class_0 number 144 with enough length to detect,class_0 +Sample text class_0 number 29 with enough length to detect,class_0 +Sample text class_4 number 110 with enough length to detect,class_4 +Sample text class_0 number 121 with enough length to detect,class_0 +Sample text class_3 number 5 with enough length to detect,class_3 +Sample text class_0 number 61 with enough length to detect,class_0 +Sample text class_4 number 71 with enough length to detect,class_4 +Sample text class_2 number 172 with enough length to detect,class_2 +Sample text class_0 number 5 with enough length to detect,class_0 +Sample text class_4 number 126 with enough length to detect,class_4 +Sample text class_3 number 39 with enough length to detect,class_3 +Sample text class_2 number 39 with enough length to detect,class_2 +Sample text class_3 number 129 with enough length to detect,class_3 +Sample text class_0 number 193 with enough length to detect,class_0 +Sample text class_3 number 152 with enough length to detect,class_3 +Sample text class_3 number 26 with enough length to detect,class_3 +Sample text class_2 number 171 with enough length to detect,class_2 +Sample text class_0 number 17 with enough length to detect,class_0 +Sample text class_3 number 142 with enough length to detect,class_3 +Sample text class_4 number 114 with enough length to detect,class_4 +Sample text class_2 number 110 with enough length to detect,class_2 +Sample text class_2 number 173 with enough length to detect,class_2 +Sample text class_0 number 138 with enough length to detect,class_0 +Sample text class_0 number 191 with enough length to detect,class_0 +Sample text class_0 number 4 with enough length to detect,class_0 +Sample text class_2 number 43 with enough length to detect,class_2 +Sample text class_0 number 20 with enough length to detect,class_0 +Sample text class_1 number 13 with enough length to detect,class_1 +Sample text class_0 number 64 with enough length to detect,class_0 +Sample text class_2 number 11 with enough length to detect,class_2 +Sample text class_1 number 101 with enough length to detect,class_1 +Sample text class_1 number 133 with enough length to detect,class_1 +Sample text class_0 number 192 with enough length to detect,class_0 +Sample text class_3 number 64 with enough length to detect,class_3 +Sample text class_1 number 62 with enough length to detect,class_1 +Sample text class_3 number 47 with enough length to detect,class_3 +Sample text class_4 number 10 with enough length to detect,class_4 +Sample text class_1 number 32 with enough length to detect,class_1 +Sample text class_3 number 195 with enough length to detect,class_3 +Sample text class_3 number 81 with enough length to detect,class_3 +Sample text class_4 number 4 with enough length to detect,class_4 +Sample text class_2 number 82 with enough length to detect,class_2 +Sample text class_1 number 160 with enough length to detect,class_1 +Sample text class_4 number 38 with enough length to detect,class_4 +Sample text class_1 number 36 with enough length to detect,class_1 +Sample text class_3 number 27 with enough length to detect,class_3 +Sample text class_4 number 157 with enough length to detect,class_4 +Sample text class_2 number 182 with enough length to detect,class_2 +Sample text class_1 number 72 with enough length to detect,class_1 +Sample text class_1 number 1 with enough length to detect,class_1 +Sample text class_0 number 13 with enough length to detect,class_0 +Sample text class_2 number 27 with enough length to detect,class_2 +Sample text class_1 number 39 with enough length to detect,class_1 +Sample text class_0 number 84 with enough length to detect,class_0 +Sample text class_2 number 132 with enough length to detect,class_2 +Sample text class_0 number 172 with enough length to detect,class_0 +Sample text class_1 number 89 with enough length to detect,class_1 +Sample text class_2 number 85 with enough length to detect,class_2 +Sample text class_1 number 129 with enough length to detect,class_1 +Sample text class_3 number 83 with enough length to detect,class_3 +Sample text class_1 number 118 with enough length to detect,class_1 +Sample text class_2 number 54 with enough length to detect,class_2 +Sample text class_1 number 49 with enough length to detect,class_1 +Sample text class_4 number 46 with enough length to detect,class_4 +Sample text class_1 number 79 with enough length to detect,class_1 +Sample text class_2 number 55 with enough length to detect,class_2 +Sample text class_4 number 101 with enough length to detect,class_4 +Sample text class_3 number 161 with enough length to detect,class_3 +Sample text class_2 number 147 with enough length to detect,class_2 +Sample text class_0 number 180 with enough length to detect,class_0 +Sample text class_2 number 157 with enough length to detect,class_2 +Sample text class_3 number 28 with enough length to detect,class_3 +Sample text class_2 number 23 with enough length to detect,class_2 +Sample text class_4 number 43 with enough length to detect,class_4 +Sample text class_0 number 10 with enough length to detect,class_0 +Sample text class_0 number 199 with enough length to detect,class_0 +Sample text class_2 number 25 with enough length to detect,class_2 +Sample text class_2 number 134 with enough length to detect,class_2 +Sample text class_0 number 31 with enough length to detect,class_0 +Sample text class_2 number 179 with enough length to detect,class_2 +Sample text class_2 number 4 with enough length to detect,class_2 +Sample text class_1 number 77 with enough length to detect,class_1 +Sample text class_2 number 44 with enough length to detect,class_2 +Sample text class_3 number 171 with enough length to detect,class_3 +Sample text class_1 number 172 with enough length to detect,class_1 +Sample text class_3 number 122 with enough length to detect,class_3 +Sample text class_2 number 0 with enough length to detect,class_2 +Sample text class_0 number 78 with enough length to detect,class_0 +Sample text class_2 number 137 with enough length to detect,class_2 +Sample text class_2 number 175 with enough length to detect,class_2 +Sample text class_2 number 148 with enough length to detect,class_2 +Sample text class_3 number 110 with enough length to detect,class_3 +Sample text class_0 number 41 with enough length to detect,class_0 +Sample text class_4 number 85 with enough length to detect,class_4 +Sample text class_3 number 32 with enough length to detect,class_3 +Sample text class_4 number 58 with enough length to detect,class_4 +Sample text class_0 number 139 with enough length to detect,class_0 +Sample text class_1 number 185 with enough length to detect,class_1 +Sample text class_2 number 56 with enough length to detect,class_2 +Sample text class_4 number 132 with enough length to detect,class_4 +Sample text class_4 number 13 with enough length to detect,class_4 +Sample text class_0 number 140 with enough length to detect,class_0 +Sample text class_3 number 24 with enough length to detect,class_3 +Sample text class_1 number 120 with enough length to detect,class_1 +Sample text class_3 number 108 with enough length to detect,class_3 +Sample text class_2 number 57 with enough length to detect,class_2 +Sample text class_4 number 73 with enough length to detect,class_4 +Sample text class_1 number 126 with enough length to detect,class_1 +Sample text class_0 number 126 with enough length to detect,class_0 +Sample text class_0 number 132 with enough length to detect,class_0 +Sample text class_4 number 17 with enough length to detect,class_4 +Sample text class_1 number 197 with enough length to detect,class_1 +Sample text class_4 number 115 with enough length to detect,class_4 +Sample text class_4 number 193 with enough length to detect,class_4 +Sample text class_2 number 15 with enough length to detect,class_2 +Sample text class_2 number 195 with enough length to detect,class_2 +Sample text class_1 number 58 with enough length to detect,class_1 +Sample text class_1 number 113 with enough length to detect,class_1 +Sample text class_2 number 9 with enough length to detect,class_2 +Sample text class_0 number 162 with enough length to detect,class_0 +Sample text class_1 number 104 with enough length to detect,class_1 +Sample text class_1 number 86 with enough length to detect,class_1 +Sample text class_3 number 44 with enough length to detect,class_3 +Sample text class_3 number 35 with enough length to detect,class_3 +Sample text class_1 number 153 with enough length to detect,class_1 +Sample text class_0 number 68 with enough length to detect,class_0 +Sample text class_3 number 78 with enough length to detect,class_3 +Sample text class_4 number 33 with enough length to detect,class_4 +Sample text class_4 number 135 with enough length to detect,class_4 +Sample text class_3 number 79 with enough length to detect,class_3 +Sample text class_3 number 119 with enough length to detect,class_3 +Sample text class_1 number 37 with enough length to detect,class_1 +Sample text class_1 number 65 with enough length to detect,class_1 +Sample text class_0 number 90 with enough length to detect,class_0 +Sample text class_4 number 35 with enough length to detect,class_4 +Sample text class_4 number 62 with enough length to detect,class_4 +Sample text class_0 number 54 with enough length to detect,class_0 +Sample text class_3 number 57 with enough length to detect,class_3 +Sample text class_4 number 143 with enough length to detect,class_4 +Sample text class_2 number 6 with enough length to detect,class_2 +Sample text class_1 number 180 with enough length to detect,class_1 +Sample text class_0 number 124 with enough length to detect,class_0 +Sample text class_2 number 91 with enough length to detect,class_2 +Sample text class_4 number 2 with enough length to detect,class_4 +Sample text class_4 number 100 with enough length to detect,class_4 +Sample text class_2 number 30 with enough length to detect,class_2 +Sample text class_4 number 145 with enough length to detect,class_4 +Sample text class_3 number 103 with enough length to detect,class_3 +Sample text class_1 number 94 with enough length to detect,class_1 +Sample text class_4 number 78 with enough length to detect,class_4 +Sample text class_1 number 12 with enough length to detect,class_1 +Sample text class_4 number 118 with enough length to detect,class_4 +Sample text class_0 number 37 with enough length to detect,class_0 +Sample text class_4 number 60 with enough length to detect,class_4 +Sample text class_4 number 98 with enough length to detect,class_4 +Sample text class_0 number 125 with enough length to detect,class_0 +Sample text class_0 number 23 with enough length to detect,class_0 +Sample text class_4 number 39 with enough length to detect,class_4 +Sample text class_4 number 176 with enough length to detect,class_4 +Sample text class_0 number 101 with enough length to detect,class_0 +Sample text class_0 number 115 with enough length to detect,class_0 +Sample text class_2 number 35 with enough length to detect,class_2 +Sample text class_4 number 150 with enough length to detect,class_4 +Sample text class_0 number 120 with enough length to detect,class_0 +Sample text class_1 number 184 with enough length to detect,class_1 +Sample text class_0 number 47 with enough length to detect,class_0 +Sample text class_0 number 171 with enough length to detect,class_0 +Sample text class_1 number 117 with enough length to detect,class_1 +Sample text class_1 number 124 with enough length to detect,class_1 +Sample text class_4 number 80 with enough length to detect,class_4 +Sample text class_1 number 63 with enough length to detect,class_1 +Sample text class_0 number 145 with enough length to detect,class_0 +Sample text class_0 number 43 with enough length to detect,class_0 +Sample text class_2 number 104 with enough length to detect,class_2 +Sample text class_0 number 86 with enough length to detect,class_0 +Sample text class_1 number 176 with enough length to detect,class_1 +Sample text class_2 number 130 with enough length to detect,class_2 +Sample text class_4 number 184 with enough length to detect,class_4 +Sample text class_4 number 51 with enough length to detect,class_4 +Sample text class_1 number 145 with enough length to detect,class_1 +Sample text class_2 number 3 with enough length to detect,class_2 +Sample text class_1 number 26 with enough length to detect,class_1 +Sample text class_4 number 187 with enough length to detect,class_4 +Sample text class_0 number 164 with enough length to detect,class_0 +Sample text class_1 number 135 with enough length to detect,class_1 +Sample text class_3 number 0 with enough length to detect,class_3 +Sample text class_4 number 116 with enough length to detect,class_4 +Sample text class_2 number 72 with enough length to detect,class_2 +Sample text class_2 number 47 with enough length to detect,class_2 +Sample text class_0 number 107 with enough length to detect,class_0 +Sample text class_4 number 56 with enough length to detect,class_4 +Sample text class_0 number 155 with enough length to detect,class_0 +Sample text class_2 number 58 with enough length to detect,class_2 +Sample text class_1 number 80 with enough length to detect,class_1 +Sample text class_1 number 7 with enough length to detect,class_1 +Sample text class_0 number 154 with enough length to detect,class_0 +Sample text class_2 number 187 with enough length to detect,class_2 +Sample text class_3 number 157 with enough length to detect,class_3 +Sample text class_4 number 185 with enough length to detect,class_4 +Sample text class_1 number 183 with enough length to detect,class_1 +Sample text class_4 number 1 with enough length to detect,class_4 +Sample text class_3 number 48 with enough length to detect,class_3 +Sample text class_4 number 6 with enough length to detect,class_4 +Sample text class_2 number 136 with enough length to detect,class_2 +Sample text class_2 number 103 with enough length to detect,class_2 +Sample text class_3 number 137 with enough length to detect,class_3 +Sample text class_2 number 159 with enough length to detect,class_2 +Sample text class_2 number 144 with enough length to detect,class_2 +Sample text class_1 number 156 with enough length to detect,class_1 +Sample text class_1 number 6 with enough length to detect,class_1 +Sample text class_4 number 88 with enough length to detect,class_4 +Sample text class_3 number 11 with enough length to detect,class_3 +Sample text class_3 number 111 with enough length to detect,class_3 +Sample text class_2 number 131 with enough length to detect,class_2 +Sample text class_1 number 59 with enough length to detect,class_1 +Sample text class_0 number 153 with enough length to detect,class_0 +Sample text class_4 number 52 with enough length to detect,class_4 +Sample text class_0 number 63 with enough length to detect,class_0 +Sample text class_2 number 34 with enough length to detect,class_2 +Sample text class_1 number 139 with enough length to detect,class_1 +Sample text class_2 number 113 with enough length to detect,class_2 +Sample text class_3 number 148 with enough length to detect,class_3 +Sample text class_2 number 87 with enough length to detect,class_2 +Sample text class_2 number 124 with enough length to detect,class_2 +Sample text class_4 number 93 with enough length to detect,class_4 +Sample text class_4 number 152 with enough length to detect,class_4 +Sample text class_0 number 186 with enough length to detect,class_0 +Sample text class_3 number 73 with enough length to detect,class_3 +Sample text class_1 number 143 with enough length to detect,class_1 +Sample text class_1 number 177 with enough length to detect,class_1 +Sample text class_4 number 103 with enough length to detect,class_4 +Sample text class_1 number 168 with enough length to detect,class_1 +Sample text class_2 number 168 with enough length to detect,class_2 +Sample text class_1 number 75 with enough length to detect,class_1 +Sample text class_3 number 90 with enough length to detect,class_3 +Sample text class_1 number 66 with enough length to detect,class_1 +Sample text class_3 number 182 with enough length to detect,class_3 +Sample text class_4 number 137 with enough length to detect,class_4 +Sample text class_2 number 133 with enough length to detect,class_2 +Sample text class_0 number 22 with enough length to detect,class_0 +Sample text class_2 number 142 with enough length to detect,class_2 +Sample text class_0 number 97 with enough length to detect,class_0 +Sample text class_1 number 95 with enough length to detect,class_1 +Sample text class_2 number 60 with enough length to detect,class_2 +Sample text class_0 number 197 with enough length to detect,class_0 +Sample text class_3 number 107 with enough length to detect,class_3 +Sample text class_1 number 61 with enough length to detect,class_1 +Sample text class_1 number 110 with enough length to detect,class_1 +Sample text class_4 number 179 with enough length to detect,class_4 +Sample text class_0 number 160 with enough length to detect,class_0 +Sample text class_2 number 2 with enough length to detect,class_2 +Sample text class_2 number 139 with enough length to detect,class_2 +Sample text class_0 number 176 with enough length to detect,class_0 +Sample text class_3 number 126 with enough length to detect,class_3 +Sample text class_3 number 193 with enough length to detect,class_3 +Sample text class_4 number 18 with enough length to detect,class_4 +Sample text class_3 number 178 with enough length to detect,class_3 +Sample text class_3 number 156 with enough length to detect,class_3 +Sample text class_1 number 97 with enough length to detect,class_1 +Sample text class_0 number 91 with enough length to detect,class_0 +Sample text class_4 number 129 with enough length to detect,class_4 +Sample text class_2 number 49 with enough length to detect,class_2 +Sample text class_3 number 45 with enough length to detect,class_3 +Sample text class_0 number 14 with enough length to detect,class_0 +Sample text class_2 number 80 with enough length to detect,class_2 +Sample text class_4 number 196 with enough length to detect,class_4 +Sample text class_4 number 68 with enough length to detect,class_4 +Sample text class_2 number 31 with enough length to detect,class_2 +Sample text class_3 number 95 with enough length to detect,class_3 +Sample text class_2 number 102 with enough length to detect,class_2 +Sample text class_1 number 60 with enough length to detect,class_1 +Sample text class_1 number 128 with enough length to detect,class_1 +Sample text class_0 number 179 with enough length to detect,class_0 +Sample text class_2 number 164 with enough length to detect,class_2 +Sample text class_1 number 195 with enough length to detect,class_1 +Sample text class_2 number 95 with enough length to detect,class_2 +Sample text class_0 number 35 with enough length to detect,class_0 +Sample text class_2 number 42 with enough length to detect,class_2 +Sample text class_4 number 127 with enough length to detect,class_4 +Sample text class_3 number 59 with enough length to detect,class_3 +Sample text class_3 number 36 with enough length to detect,class_3 +Sample text class_0 number 98 with enough length to detect,class_0 +Sample text class_1 number 137 with enough length to detect,class_1 +Sample text class_0 number 12 with enough length to detect,class_0 +Sample text class_3 number 84 with enough length to detect,class_3 +Sample text class_0 number 116 with enough length to detect,class_0 +Sample text class_2 number 46 with enough length to detect,class_2 +Sample text class_2 number 7 with enough length to detect,class_2 +Sample text class_4 number 15 with enough length to detect,class_4 +Sample text class_1 number 112 with enough length to detect,class_1 +Sample text class_1 number 158 with enough length to detect,class_1 +Sample text class_2 number 71 with enough length to detect,class_2 +Sample text class_1 number 4 with enough length to detect,class_1 +Sample text class_1 number 27 with enough length to detect,class_1 +Sample text class_2 number 81 with enough length to detect,class_2 +Sample text class_0 number 39 with enough length to detect,class_0 +Sample text class_1 number 191 with enough length to detect,class_1 +Sample text class_0 number 110 with enough length to detect,class_0 +Sample text class_4 number 32 with enough length to detect,class_4 +Sample text class_4 number 12 with enough length to detect,class_4 +Sample text class_4 number 162 with enough length to detect,class_4 +Sample text class_2 number 21 with enough length to detect,class_2 +Sample text class_1 number 140 with enough length to detect,class_1 +Sample text class_0 number 183 with enough length to detect,class_0 +Sample text class_4 number 197 with enough length to detect,class_4 +Sample text class_2 number 22 with enough length to detect,class_2 +Sample text class_0 number 181 with enough length to detect,class_0 +Sample text class_4 number 104 with enough length to detect,class_4 +Sample text class_4 number 61 with enough length to detect,class_4 +Sample text class_3 number 49 with enough length to detect,class_3 +Sample text class_3 number 145 with enough length to detect,class_3 +Sample text class_3 number 100 with enough length to detect,class_3 +Sample text class_0 number 105 with enough length to detect,class_0 +Sample text class_4 number 119 with enough length to detect,class_4 +Sample text class_3 number 51 with enough length to detect,class_3 +Sample text class_1 number 166 with enough length to detect,class_1 +Sample text class_3 number 19 with enough length to detect,class_3 +Sample text class_4 number 105 with enough length to detect,class_4 +Sample text class_1 number 115 with enough length to detect,class_1 +Sample text class_0 number 42 with enough length to detect,class_0 +Sample text class_0 number 130 with enough length to detect,class_0 +Sample text class_2 number 40 with enough length to detect,class_2 +Sample text class_0 number 151 with enough length to detect,class_0 +Sample text class_2 number 188 with enough length to detect,class_2 +Sample text class_0 number 36 with enough length to detect,class_0 +Sample text class_0 number 152 with enough length to detect,class_0 +Sample text class_3 number 76 with enough length to detect,class_3 +Sample text class_4 number 160 with enough length to detect,class_4 +Sample text class_3 number 1 with enough length to detect,class_3 +Sample text class_2 number 37 with enough length to detect,class_2 +Sample text class_2 number 52 with enough length to detect,class_2 +Sample text class_3 number 185 with enough length to detect,class_3 +Sample text class_1 number 68 with enough length to detect,class_1 +Sample text class_0 number 133 with enough length to detect,class_0 +Sample text class_1 number 141 with enough length to detect,class_1 +Sample text class_4 number 3 with enough length to detect,class_4 +Sample text class_0 number 45 with enough length to detect,class_0 +Sample text class_1 number 83 with enough length to detect,class_1 +Sample text class_3 number 52 with enough length to detect,class_3 +Sample text class_4 number 148 with enough length to detect,class_4 +Sample text class_0 number 52 with enough length to detect,class_0 +Sample text class_4 number 21 with enough length to detect,class_4 +Sample text class_3 number 179 with enough length to detect,class_3 +Sample text class_4 number 177 with enough length to detect,class_4 +Sample text class_2 number 199 with enough length to detect,class_2 +Sample text class_1 number 8 with enough length to detect,class_1 +Sample text class_1 number 151 with enough length to detect,class_1 +Sample text class_1 number 15 with enough length to detect,class_1 +Sample text class_1 number 88 with enough length to detect,class_1 +Sample text class_1 number 78 with enough length to detect,class_1 +Sample text class_4 number 153 with enough length to detect,class_4 +Sample text class_4 number 20 with enough length to detect,class_4 +Sample text class_0 number 109 with enough length to detect,class_0 +Sample text class_0 number 118 with enough length to detect,class_0 +Sample text class_4 number 141 with enough length to detect,class_4 +Sample text class_0 number 137 with enough length to detect,class_0 +Sample text class_0 number 106 with enough length to detect,class_0 +Sample text class_1 number 106 with enough length to detect,class_1 +Sample text class_4 number 172 with enough length to detect,class_4 +Sample text class_0 number 8 with enough length to detect,class_0 +Sample text class_4 number 22 with enough length to detect,class_4 +Sample text class_1 number 109 with enough length to detect,class_1 +Sample text class_2 number 156 with enough length to detect,class_2 +Sample text class_3 number 143 with enough length to detect,class_3 +Sample text class_3 number 34 with enough length to detect,class_3 +Sample text class_1 number 91 with enough length to detect,class_1 +Sample text class_1 number 178 with enough length to detect,class_1 +Sample text class_4 number 89 with enough length to detect,class_4 +Sample text class_3 number 29 with enough length to detect,class_3 +Sample text class_1 number 157 with enough length to detect,class_1 +Sample text class_3 number 112 with enough length to detect,class_3 +Sample text class_3 number 20 with enough length to detect,class_3 +Sample text class_2 number 118 with enough length to detect,class_2 +Sample text class_3 number 62 with enough length to detect,class_3 +Sample text class_2 number 150 with enough length to detect,class_2 +Sample text class_0 number 75 with enough length to detect,class_0 +Sample text class_0 number 102 with enough length to detect,class_0 +Sample text class_2 number 176 with enough length to detect,class_2 +Sample text class_4 number 57 with enough length to detect,class_4 +Sample text class_0 number 9 with enough length to detect,class_0 +Sample text class_0 number 74 with enough length to detect,class_0 +Sample text class_4 number 151 with enough length to detect,class_4 +Sample text class_2 number 68 with enough length to detect,class_2 +Sample text class_1 number 107 with enough length to detect,class_1 +Sample text class_0 number 134 with enough length to detect,class_0 +Sample text class_4 number 59 with enough length to detect,class_4 +Sample text class_4 number 84 with enough length to detect,class_4 +Sample text class_1 number 44 with enough length to detect,class_1 +Sample text class_3 number 41 with enough length to detect,class_3 +Sample text class_1 number 9 with enough length to detect,class_1 +Sample text class_1 number 67 with enough length to detect,class_1 +Sample text class_4 number 70 with enough length to detect,class_4 +Sample text class_2 number 135 with enough length to detect,class_2 +Sample text class_2 number 178 with enough length to detect,class_2 +Sample text class_4 number 45 with enough length to detect,class_4 +Sample text class_4 number 168 with enough length to detect,class_4 +Sample text class_0 number 83 with enough length to detect,class_0 +Sample text class_0 number 40 with enough length to detect,class_0 +Sample text class_3 number 8 with enough length to detect,class_3 +Sample text class_2 number 192 with enough length to detect,class_2 +Sample text class_4 number 53 with enough length to detect,class_4 +Sample text class_2 number 183 with enough length to detect,class_2 +Sample text class_0 number 122 with enough length to detect,class_0 +Sample text class_2 number 13 with enough length to detect,class_2 +Sample text class_1 number 40 with enough length to detect,class_1 +Sample text class_3 number 123 with enough length to detect,class_3 +Sample text class_3 number 9 with enough length to detect,class_3 +Sample text class_3 number 166 with enough length to detect,class_3 +Sample text class_0 number 190 with enough length to detect,class_0 +Sample text class_0 number 82 with enough length to detect,class_0 +Sample text class_2 number 120 with enough length to detect,class_2 +Sample text class_4 number 76 with enough length to detect,class_4 +Sample text class_4 number 5 with enough length to detect,class_4 +Sample text class_3 number 183 with enough length to detect,class_3 +Sample text class_2 number 114 with enough length to detect,class_2 +Sample text class_2 number 88 with enough length to detect,class_2 +Sample text class_4 number 47 with enough length to detect,class_4 +Sample text class_3 number 72 with enough length to detect,class_3 +Sample text class_0 number 58 with enough length to detect,class_0 +Sample text class_1 number 121 with enough length to detect,class_1 +Sample text class_3 number 91 with enough length to detect,class_3 +Sample text class_2 number 155 with enough length to detect,class_2 +Sample text class_2 number 193 with enough length to detect,class_2 +Sample text class_4 number 37 with enough length to detect,class_4 +Sample text class_1 number 22 with enough length to detect,class_1 +Sample text class_1 number 103 with enough length to detect,class_1 +Sample text class_3 number 116 with enough length to detect,class_3 +Sample text class_0 number 158 with enough length to detect,class_0 +Sample text class_2 number 98 with enough length to detect,class_2 +Sample text class_2 number 169 with enough length to detect,class_2 +Sample text class_4 number 97 with enough length to detect,class_4 +Sample text class_1 number 92 with enough length to detect,class_1 +Sample text class_2 number 65 with enough length to detect,class_2 +Sample text class_4 number 188 with enough length to detect,class_4 +Sample text class_1 number 199 with enough length to detect,class_1 +Sample text class_0 number 2 with enough length to detect,class_0 +Sample text class_4 number 86 with enough length to detect,class_4 +Sample text class_0 number 168 with enough length to detect,class_0 +Sample text class_3 number 125 with enough length to detect,class_3 +Sample text class_4 number 69 with enough length to detect,class_4 +Sample text class_1 number 18 with enough length to detect,class_1 +Sample text class_2 number 92 with enough length to detect,class_2 +Sample text class_3 number 115 with enough length to detect,class_3 +Sample text class_3 number 151 with enough length to detect,class_3 +Sample text class_0 number 170 with enough length to detect,class_0 +Sample text class_1 number 42 with enough length to detect,class_1 +Sample text class_4 number 180 with enough length to detect,class_4 +Sample text class_0 number 15 with enough length to detect,class_0 +Sample text class_2 number 153 with enough length to detect,class_2 +Sample text class_3 number 67 with enough length to detect,class_3 +Sample text class_0 number 51 with enough length to detect,class_0 +Sample text class_4 number 189 with enough length to detect,class_4 +Sample text class_2 number 163 with enough length to detect,class_2 +Sample text class_2 number 53 with enough length to detect,class_2 +Sample text class_0 number 77 with enough length to detect,class_0 +Sample text class_1 number 55 with enough length to detect,class_1 +Sample text class_4 number 112 with enough length to detect,class_4 +Sample text class_3 number 117 with enough length to detect,class_3 +Sample text class_0 number 187 with enough length to detect,class_0 +Sample text class_4 number 29 with enough length to detect,class_4 +Sample text class_0 number 143 with enough length to detect,class_0 +Sample text class_4 number 166 with enough length to detect,class_4 +Sample text class_4 number 14 with enough length to detect,class_4 +Sample text class_3 number 105 with enough length to detect,class_3 +Sample text class_4 number 123 with enough length to detect,class_4 +Sample text class_1 number 54 with enough length to detect,class_1 +Sample text class_0 number 111 with enough length to detect,class_0 +Sample text class_1 number 147 with enough length to detect,class_1 +Sample text class_2 number 12 with enough length to detect,class_2 +Sample text class_0 number 62 with enough length to detect,class_0 +Sample text class_0 number 100 with enough length to detect,class_0 +Sample text class_3 number 61 with enough length to detect,class_3 +Sample text class_3 number 69 with enough length to detect,class_3 +Sample text class_3 number 89 with enough length to detect,class_3 +Sample text class_0 number 55 with enough length to detect,class_0 +Sample text class_2 number 78 with enough length to detect,class_2 +Sample text class_2 number 20 with enough length to detect,class_2 +Sample text class_3 number 155 with enough length to detect,class_3 +Sample text class_1 number 162 with enough length to detect,class_1 +Sample text class_2 number 41 with enough length to detect,class_2 +Sample text class_3 number 74 with enough length to detect,class_3 +Sample text class_4 number 146 with enough length to detect,class_4 +Sample text class_0 number 96 with enough length to detect,class_0 +Sample text class_0 number 194 with enough length to detect,class_0 +Sample text class_2 number 16 with enough length to detect,class_2 +Sample text class_3 number 109 with enough length to detect,class_3 +Sample text class_1 number 48 with enough length to detect,class_1 +Sample text class_2 number 84 with enough length to detect,class_2 +Sample text class_2 number 190 with enough length to detect,class_2 +Sample text class_2 number 184 with enough length to detect,class_2 +Sample text class_0 number 135 with enough length to detect,class_0 +Sample text class_3 number 153 with enough length to detect,class_3 +Sample text class_1 number 19 with enough length to detect,class_1 +Sample text class_3 number 167 with enough length to detect,class_3 +Sample text class_3 number 85 with enough length to detect,class_3 +Sample text class_1 number 85 with enough length to detect,class_1 +Sample text class_1 number 43 with enough length to detect,class_1 +Sample text class_2 number 126 with enough length to detect,class_2 +Sample text class_3 number 128 with enough length to detect,class_3 +Sample text class_1 number 138 with enough length to detect,class_1 +Sample text class_4 number 72 with enough length to detect,class_4 +Sample text class_0 number 69 with enough length to detect,class_0 +Sample text class_4 number 74 with enough length to detect,class_4 +Sample text class_0 number 60 with enough length to detect,class_0 +Sample text class_3 number 46 with enough length to detect,class_3 +Sample text class_3 number 124 with enough length to detect,class_3 +Sample text class_0 number 72 with enough length to detect,class_0 +Sample text class_0 number 7 with enough length to detect,class_0 +Sample text class_4 number 167 with enough length to detect,class_4 +Sample text class_3 number 134 with enough length to detect,class_3 +Sample text class_1 number 35 with enough length to detect,class_1 +Sample text class_2 number 167 with enough length to detect,class_2 +Sample text class_3 number 2 with enough length to detect,class_3 +Sample text class_0 number 21 with enough length to detect,class_0 +Sample text class_1 number 146 with enough length to detect,class_1 +Sample text class_4 number 27 with enough length to detect,class_4 +Sample text class_1 number 30 with enough length to detect,class_1 +Sample text class_1 number 53 with enough length to detect,class_1 +Sample text class_0 number 123 with enough length to detect,class_0 +Sample text class_2 number 62 with enough length to detect,class_2 +Sample text class_2 number 129 with enough length to detect,class_2 +Sample text class_2 number 48 with enough length to detect,class_2 +Sample text class_4 number 31 with enough length to detect,class_4 +Sample text class_4 number 171 with enough length to detect,class_4 +Sample text class_3 number 87 with enough length to detect,class_3 +Sample text class_4 number 44 with enough length to detect,class_4 +Sample text class_1 number 119 with enough length to detect,class_1 +Sample text class_3 number 130 with enough length to detect,class_3 +Sample text class_1 number 5 with enough length to detect,class_1 +Sample text class_3 number 106 with enough length to detect,class_3 +Sample text class_4 number 138 with enough length to detect,class_4 +Sample text class_3 number 184 with enough length to detect,class_3 +Sample text class_4 number 66 with enough length to detect,class_4 +Sample text class_2 number 33 with enough length to detect,class_2 +Sample text class_3 number 21 with enough length to detect,class_3 +Sample text class_2 number 140 with enough length to detect,class_2 +Sample text class_4 number 55 with enough length to detect,class_4 +Sample text class_0 number 169 with enough length to detect,class_0 +Sample text class_2 number 162 with enough length to detect,class_2 +Sample text class_2 number 86 with enough length to detect,class_2 +Sample text class_3 number 75 with enough length to detect,class_3 +Sample text class_0 number 131 with enough length to detect,class_0 +Sample text class_0 number 128 with enough length to detect,class_0 +Sample text class_2 number 145 with enough length to detect,class_2 +Sample text class_0 number 70 with enough length to detect,class_0 +Sample text class_2 number 97 with enough length to detect,class_2 +Sample text class_3 number 149 with enough length to detect,class_3 +Sample text class_0 number 87 with enough length to detect,class_0 +Sample text class_4 number 133 with enough length to detect,class_4 +Sample text class_4 number 65 with enough length to detect,class_4 +Sample text class_1 number 46 with enough length to detect,class_1 +Sample text class_0 number 59 with enough length to detect,class_0 +Sample text class_1 number 45 with enough length to detect,class_1 +Sample text class_1 number 114 with enough length to detect,class_1 +Sample text class_1 number 171 with enough length to detect,class_1 +Sample text class_4 number 8 with enough length to detect,class_4 +Sample text class_0 number 19 with enough length to detect,class_0 +Sample text class_2 number 100 with enough length to detect,class_2 +Sample text class_1 number 131 with enough length to detect,class_1 +Sample text class_3 number 13 with enough length to detect,class_3 +Sample text class_0 number 0 with enough length to detect,class_0 +Sample text class_2 number 143 with enough length to detect,class_2 +Sample text class_2 number 152 with enough length to detect,class_2 +Sample text class_0 number 165 with enough length to detect,class_0 +Sample text class_3 number 198 with enough length to detect,class_3 +Sample text class_1 number 182 with enough length to detect,class_1 +Sample text class_4 number 34 with enough length to detect,class_4 +Sample text class_4 number 173 with enough length to detect,class_4 +Sample text class_4 number 94 with enough length to detect,class_4 +Sample text class_3 number 196 with enough length to detect,class_3 +Sample text class_4 number 199 with enough length to detect,class_4 +Sample text class_1 number 105 with enough length to detect,class_1 +Sample text class_3 number 40 with enough length to detect,class_3 +Sample text class_0 number 108 with enough length to detect,class_0 +Sample text class_2 number 119 with enough length to detect,class_2 +Sample text class_0 number 182 with enough length to detect,class_0 +Sample text class_3 number 180 with enough length to detect,class_3 +Sample text class_2 number 112 with enough length to detect,class_2 +Sample text class_4 number 130 with enough length to detect,class_4 +Sample text class_3 number 136 with enough length to detect,class_3 +Sample text class_3 number 139 with enough length to detect,class_3 +Sample text class_0 number 3 with enough length to detect,class_0 +Sample text class_4 number 108 with enough length to detect,class_4 +Sample text class_0 number 161 with enough length to detect,class_0 +Sample text class_2 number 45 with enough length to detect,class_2 +Sample text class_4 number 131 with enough length to detect,class_4 +Sample text class_4 number 198 with enough length to detect,class_4 +Sample text class_4 number 155 with enough length to detect,class_4 +Sample text class_3 number 56 with enough length to detect,class_3 +Sample text class_3 number 187 with enough length to detect,class_3 +Sample text class_4 number 99 with enough length to detect,class_4 +Sample text class_3 number 168 with enough length to detect,class_3 +Sample text class_4 number 136 with enough length to detect,class_4 +Sample text class_3 number 98 with enough length to detect,class_3 +Sample text class_0 number 117 with enough length to detect,class_0 +Sample text class_3 number 138 with enough length to detect,class_3 +Sample text class_4 number 30 with enough length to detect,class_4 +Sample text class_0 number 11 with enough length to detect,class_0 +Sample text class_2 number 166 with enough length to detect,class_2 +Sample text class_1 number 57 with enough length to detect,class_1 +Sample text class_2 number 141 with enough length to detect,class_2 +Sample text class_2 number 79 with enough length to detect,class_2 +Sample text class_4 number 163 with enough length to detect,class_4 +Sample text class_1 number 190 with enough length to detect,class_1 +Sample text class_1 number 194 with enough length to detect,class_1 +Sample text class_0 number 65 with enough length to detect,class_0 +Sample text class_3 number 10 with enough length to detect,class_3 +Sample text class_4 number 156 with enough length to detect,class_4 +Sample text class_3 number 96 with enough length to detect,class_3 +Sample text class_4 number 11 with enough length to detect,class_4 +Sample text class_4 number 158 with enough length to detect,class_4 +Sample text class_3 number 42 with enough length to detect,class_3 +Sample text class_0 number 156 with enough length to detect,class_0 +Sample text class_0 number 112 with enough length to detect,class_0 +Sample text class_0 number 48 with enough length to detect,class_0 +Sample text class_3 number 173 with enough length to detect,class_3 +Sample text class_0 number 93 with enough length to detect,class_0 +Sample text class_2 number 105 with enough length to detect,class_2 +Sample text class_2 number 121 with enough length to detect,class_2 +Sample text class_0 number 141 with enough length to detect,class_0 +Sample text class_4 number 81 with enough length to detect,class_4 +Sample text class_4 number 125 with enough length to detect,class_4 +Sample text class_2 number 8 with enough length to detect,class_2 +Sample text class_2 number 197 with enough length to detect,class_2 +Sample text class_2 number 38 with enough length to detect,class_2 +Sample text class_2 number 198 with enough length to detect,class_2 +Sample text class_3 number 164 with enough length to detect,class_3 +Sample text class_1 number 69 with enough length to detect,class_1 +Sample text class_2 number 151 with enough length to detect,class_2 +Sample text class_4 number 174 with enough length to detect,class_4 +Sample text class_3 number 162 with enough length to detect,class_3 +Sample text class_1 number 52 with enough length to detect,class_1 +Sample text class_4 number 192 with enough length to detect,class_4 +Sample text class_1 number 71 with enough length to detect,class_1 +Sample text class_0 number 146 with enough length to detect,class_0 +Sample text class_2 number 69 with enough length to detect,class_2 +Sample text class_3 number 58 with enough length to detect,class_3 +Sample text class_2 number 5 with enough length to detect,class_2 +Sample text class_2 number 111 with enough length to detect,class_2 +Sample text class_3 number 71 with enough length to detect,class_3 +Sample text class_1 number 17 with enough length to detect,class_1 +Sample text class_1 number 122 with enough length to detect,class_1 +Sample text class_3 number 135 with enough length to detect,class_3 +Sample text class_2 number 180 with enough length to detect,class_2 +Sample text class_1 number 16 with enough length to detect,class_1 +Sample text class_0 number 67 with enough length to detect,class_0 +Sample text class_1 number 74 with enough length to detect,class_1 +Sample text class_2 number 10 with enough length to detect,class_2 +Sample text class_1 number 123 with enough length to detect,class_1 +Sample text class_4 number 24 with enough length to detect,class_4 +Sample text class_4 number 182 with enough length to detect,class_4 +Sample text class_4 number 41 with enough length to detect,class_4 +Sample text class_1 number 34 with enough length to detect,class_1 +Sample text class_0 number 57 with enough length to detect,class_0 +Sample text class_3 number 194 with enough length to detect,class_3 +Sample text class_3 number 186 with enough length to detect,class_3 +Sample text class_4 number 63 with enough length to detect,class_4 +Sample text class_1 number 132 with enough length to detect,class_1 +Sample text class_3 number 101 with enough length to detect,class_3 +Sample text class_1 number 24 with enough length to detect,class_1 +Sample text class_2 number 170 with enough length to detect,class_2 +Sample text class_3 number 104 with enough length to detect,class_3 +Sample text class_3 number 55 with enough length to detect,class_3 +Sample text class_1 number 76 with enough length to detect,class_1 +Sample text class_1 number 188 with enough length to detect,class_1 +Sample text class_2 number 73 with enough length to detect,class_2 +Sample text class_0 number 167 with enough length to detect,class_0 +Sample text class_4 number 194 with enough length to detect,class_4 +Sample text class_3 number 146 with enough length to detect,class_3 +Sample text class_2 number 146 with enough length to detect,class_2 +Sample text class_0 number 175 with enough length to detect,class_0 +Sample text class_4 number 107 with enough length to detect,class_4 +Sample text class_3 number 23 with enough length to detect,class_3 +Sample text class_0 number 73 with enough length to detect,class_0 +Sample text class_3 number 63 with enough length to detect,class_3 +Sample text class_3 number 99 with enough length to detect,class_3 +Sample text class_4 number 170 with enough length to detect,class_4 +Sample text class_1 number 73 with enough length to detect,class_1 +Sample text class_3 number 86 with enough length to detect,class_3 +Sample text class_1 number 14 with enough length to detect,class_1 +Sample text class_1 number 163 with enough length to detect,class_1 +Sample text class_1 number 179 with enough length to detect,class_1 +Sample text class_0 number 166 with enough length to detect,class_0 +Sample text class_1 number 173 with enough length to detect,class_1 +Sample text class_4 number 54 with enough length to detect,class_4 +Sample text class_3 number 50 with enough length to detect,class_3 +Sample text class_2 number 64 with enough length to detect,class_2 +Sample text class_4 number 154 with enough length to detect,class_4 +Sample text class_4 number 147 with enough length to detect,class_4 +Sample text class_0 number 103 with enough length to detect,class_0 +Sample text class_4 number 87 with enough length to detect,class_4 +Sample text class_4 number 178 with enough length to detect,class_4 +Sample text class_4 number 75 with enough length to detect,class_4 +Sample text class_0 number 81 with enough length to detect,class_0 +Sample text class_1 number 96 with enough length to detect,class_1 +Sample text class_3 number 191 with enough length to detect,class_3 +Sample text class_1 number 33 with enough length to detect,class_1 +Sample text class_3 number 77 with enough length to detect,class_3 +Sample text class_0 number 46 with enough length to detect,class_0 +Sample text class_0 number 71 with enough length to detect,class_0 +Sample text class_3 number 121 with enough length to detect,class_3 +Sample text class_0 number 196 with enough length to detect,class_0 +Sample text class_2 number 191 with enough length to detect,class_2 +Sample text class_1 number 170 with enough length to detect,class_1 +Sample text class_4 number 82 with enough length to detect,class_4 +Sample text class_4 number 106 with enough length to detect,class_4 +Sample text class_3 number 33 with enough length to detect,class_3 +Sample text class_3 number 43 with enough length to detect,class_3 +Sample text class_4 number 49 with enough length to detect,class_4 +Sample text class_1 number 100 with enough length to detect,class_1 +Sample text class_2 number 165 with enough length to detect,class_2 +Sample text class_0 number 80 with enough length to detect,class_0 +Sample text class_1 number 187 with enough length to detect,class_1 +Sample text class_0 number 127 with enough length to detect,class_0 +Sample text class_2 number 149 with enough length to detect,class_2 +Sample text class_2 number 70 with enough length to detect,class_2 +Sample text class_3 number 147 with enough length to detect,class_3 +Sample text class_0 number 44 with enough length to detect,class_0 +Sample text class_4 number 26 with enough length to detect,class_4 +Sample text class_1 number 70 with enough length to detect,class_1 +Sample text class_3 number 18 with enough length to detect,class_3 +Sample text class_1 number 152 with enough length to detect,class_1 +Sample text class_4 number 67 with enough length to detect,class_4 +Sample text class_1 number 167 with enough length to detect,class_1 +Sample text class_0 number 99 with enough length to detect,class_0 +Sample text class_1 number 189 with enough length to detect,class_1 +Sample text class_0 number 94 with enough length to detect,class_0 +Sample text class_4 number 190 with enough length to detect,class_4 +Sample text class_1 number 144 with enough length to detect,class_1 +Sample text class_3 number 181 with enough length to detect,class_3 +Sample text class_1 number 20 with enough length to detect,class_1 +Sample text class_0 number 159 with enough length to detect,class_0 +Sample text class_4 number 164 with enough length to detect,class_4 +Sample text class_1 number 148 with enough length to detect,class_1 +Sample text class_4 number 183 with enough length to detect,class_4 +Sample text class_3 number 114 with enough length to detect,class_3 +Sample text class_0 number 163 with enough length to detect,class_0 +Sample text class_4 number 25 with enough length to detect,class_4 +Sample text class_3 number 177 with enough length to detect,class_3 +Sample text class_0 number 6 with enough length to detect,class_0 +Sample text class_4 number 90 with enough length to detect,class_4 +Sample text class_4 number 28 with enough length to detect,class_4 +Sample text class_1 number 84 with enough length to detect,class_1 +Sample text class_3 number 3 with enough length to detect,class_3 +Sample text class_2 number 59 with enough length to detect,class_2 +Sample text class_1 number 25 with enough length to detect,class_1 +Sample text class_2 number 29 with enough length to detect,class_2 +Sample text class_4 number 186 with enough length to detect,class_4 +Sample text class_3 number 118 with enough length to detect,class_3 +Sample text class_3 number 65 with enough length to detect,class_3 +Sample text class_3 number 133 with enough length to detect,class_3 +Sample text class_1 number 3 with enough length to detect,class_1 +Sample text class_2 number 174 with enough length to detect,class_2 +Sample text class_0 number 27 with enough length to detect,class_0 +Sample text class_3 number 16 with enough length to detect,class_3 +Sample text class_2 number 117 with enough length to detect,class_2 +Sample text class_1 number 38 with enough length to detect,class_1 +Sample text class_1 number 23 with enough length to detect,class_1 +Sample text class_0 number 95 with enough length to detect,class_0 +Sample text class_0 number 30 with enough length to detect,class_0 +Sample text class_0 number 32 with enough length to detect,class_0 +Sample text class_2 number 32 with enough length to detect,class_2 +Sample text class_3 number 4 with enough length to detect,class_3 +Sample text class_0 number 89 with enough length to detect,class_0 +Sample text class_2 number 158 with enough length to detect,class_2 +Sample text class_4 number 113 with enough length to detect,class_4 +Sample text class_3 number 158 with enough length to detect,class_3 +Sample text class_3 number 92 with enough length to detect,class_3 +Sample text class_0 number 104 with enough length to detect,class_0 +Sample text class_3 number 154 with enough length to detect,class_3 +Sample text class_0 number 142 with enough length to detect,class_0 +Sample text class_1 number 28 with enough length to detect,class_1 +Sample text class_1 number 50 with enough length to detect,class_1 +Sample text class_1 number 81 with enough length to detect,class_1 +Sample text class_3 number 159 with enough length to detect,class_3 +Sample text class_0 number 25 with enough length to detect,class_0 +Sample text class_0 number 114 with enough length to detect,class_0 +Sample text class_3 number 54 with enough length to detect,class_3 diff --git a/tests/fixtures/clean_dataset.csv b/tests/fixtures/clean_dataset.csv new file mode 100644 index 0000000..6855882 --- /dev/null +++ b/tests/fixtures/clean_dataset.csv @@ -0,0 +1,501 @@ +text,label +This is a valid sample sentence number 0 with real content,pos +This is a valid sample sentence number 1 with real content,pos +This is a valid sample sentence number 2 with real content,pos +This is a valid sample sentence number 3 with real content,pos +This is a valid sample sentence number 4 with real content,pos +This is a valid sample sentence number 5 with real content,pos +This is a valid sample sentence number 6 with real content,pos +This is a valid sample sentence number 7 with real content,pos +This is a valid sample sentence number 8 with real content,pos +This is a valid sample sentence number 9 with real content,pos +This is a valid sample sentence number 10 with real content,pos +This is a valid sample sentence number 11 with real content,pos +This is a valid sample sentence number 12 with real content,pos +This is a valid sample sentence number 13 with real content,pos +This is a valid sample sentence number 14 with real content,pos +This is a valid sample sentence number 15 with real content,pos +This is a valid sample sentence number 16 with real content,pos +This is a valid sample sentence number 17 with real content,pos +This is a valid sample sentence number 18 with real content,pos +This is a valid sample sentence number 19 with real content,pos +This is a valid sample sentence number 20 with real content,pos +This is a valid sample sentence number 21 with real content,pos +This is a valid sample sentence number 22 with real content,pos +This is a valid sample sentence number 23 with real content,pos +This is a valid sample sentence number 24 with real content,pos +This is a valid sample sentence number 25 with real content,pos +This is a valid sample sentence number 26 with real content,pos +This is a valid sample sentence number 27 with real content,pos +This is a valid sample sentence number 28 with real content,pos +This is a valid sample sentence number 29 with real content,pos +This is a valid sample sentence number 30 with real content,pos +This is a valid sample sentence number 31 with real content,pos +This is a valid sample sentence number 32 with real content,pos +This is a valid sample sentence number 33 with real content,pos +This is a valid sample sentence number 34 with real content,pos +This is a valid sample sentence number 35 with real content,pos +This is a valid sample sentence number 36 with real content,pos +This is a valid sample sentence number 37 with real content,pos +This is a valid sample sentence number 38 with real content,pos +This is a valid sample sentence number 39 with real content,pos +This is a valid sample sentence number 40 with real content,pos +This is a valid sample sentence number 41 with real content,pos +This is a valid sample sentence number 42 with real content,pos +This is a valid sample sentence number 43 with real content,pos +This is a valid sample sentence number 44 with real content,pos +This is a valid sample sentence number 45 with real content,pos +This is a valid sample sentence number 46 with real content,pos +This is a valid sample sentence number 47 with real content,pos +This is a valid sample sentence number 48 with real content,pos +This is a valid sample sentence number 49 with real content,pos +This is a valid sample sentence number 50 with real content,pos +This is a valid sample sentence number 51 with real content,pos +This is a valid sample sentence number 52 with real content,pos +This is a valid sample sentence number 53 with real content,pos +This is a valid sample sentence number 54 with real content,pos +This is a valid sample sentence number 55 with real content,pos +This is a valid sample sentence number 56 with real content,pos +This is a valid sample sentence number 57 with real content,pos +This is a valid sample sentence number 58 with real content,pos +This is a valid sample sentence number 59 with real content,pos +This is a valid sample sentence number 60 with real content,pos +This is a valid sample sentence number 61 with real content,pos +This is a valid sample sentence number 62 with real content,pos +This is a valid sample sentence number 63 with real content,pos +This is a valid sample sentence number 64 with real content,pos +This is a valid sample sentence number 65 with real content,pos +This is a valid sample sentence number 66 with real content,pos +This is a valid sample sentence number 67 with real content,pos +This is a valid sample sentence number 68 with real content,pos +This is a valid sample sentence number 69 with real content,pos +This is a valid sample sentence number 70 with real content,pos +This is a valid sample sentence number 71 with real content,pos +This is a valid sample sentence number 72 with real content,pos +This is a valid sample sentence number 73 with real content,pos +This is a valid sample sentence number 74 with real content,pos +This is a valid sample sentence number 75 with real content,pos +This is a valid sample sentence number 76 with real content,pos +This is a valid sample sentence number 77 with real content,pos +This is a valid sample sentence number 78 with real content,pos +This is a valid sample sentence number 79 with real content,pos +This is a valid sample sentence number 80 with real content,pos +This is a valid sample sentence number 81 with real content,pos +This is a valid sample sentence number 82 with real content,pos +This is a valid sample sentence number 83 with real content,pos +This is a valid sample sentence number 84 with real content,pos +This is a valid sample sentence number 85 with real content,pos +This is a valid sample sentence number 86 with real content,pos +This is a valid sample sentence number 87 with real content,pos +This is a valid sample sentence number 88 with real content,pos +This is a valid sample sentence number 89 with real content,pos +This is a valid sample sentence number 90 with real content,pos +This is a valid sample sentence number 91 with real content,pos +This is a valid sample sentence number 92 with real content,pos +This is a valid sample sentence number 93 with real content,pos +This is a valid sample sentence number 94 with real content,pos +This is a valid sample sentence number 95 with real content,pos +This is a valid sample sentence number 96 with real content,pos +This is a valid sample sentence number 97 with real content,pos +This is a valid sample sentence number 98 with real content,pos +This is a valid sample sentence number 99 with real content,pos +This is a valid sample sentence number 100 with real content,pos +This is a valid sample sentence number 101 with real content,pos +This is a valid sample sentence number 102 with real content,pos +This is a valid sample sentence number 103 with real content,pos +This is a valid sample sentence number 104 with real content,pos +This is a valid sample sentence number 105 with real content,pos +This is a valid sample sentence number 106 with real content,pos +This is a valid sample sentence number 107 with real content,pos +This is a valid sample sentence number 108 with real content,pos +This is a valid sample sentence number 109 with real content,pos +This is a valid sample sentence number 110 with real content,pos +This is a valid sample sentence number 111 with real content,pos +This is a valid sample sentence number 112 with real content,pos +This is a valid sample sentence number 113 with real content,pos +This is a valid sample sentence number 114 with real content,pos +This is a valid sample sentence number 115 with real content,pos +This is a valid sample sentence number 116 with real content,pos +This is a valid sample sentence number 117 with real content,pos +This is a valid sample sentence number 118 with real content,pos +This is a valid sample sentence number 119 with real content,pos +This is a valid sample sentence number 120 with real content,pos +This is a valid sample sentence number 121 with real content,pos +This is a valid sample sentence number 122 with real content,pos +This is a valid sample sentence number 123 with real content,pos +This is a valid sample sentence number 124 with real content,pos +This is a valid sample sentence number 125 with real content,pos +This is a valid sample sentence number 126 with real content,pos +This is a valid sample sentence number 127 with real content,pos +This is a valid sample sentence number 128 with real content,pos +This is a valid sample sentence number 129 with real content,pos +This is a valid sample sentence number 130 with real content,pos +This is a valid sample sentence number 131 with real content,pos +This is a valid sample sentence number 132 with real content,pos +This is a valid sample sentence number 133 with real content,pos +This is a valid sample sentence number 134 with real content,pos +This is a valid sample sentence number 135 with real content,pos +This is a valid sample sentence number 136 with real content,pos +This is a valid sample sentence number 137 with real content,pos +This is a valid sample sentence number 138 with real content,pos +This is a valid sample sentence number 139 with real content,pos +This is a valid sample sentence number 140 with real content,pos +This is a valid sample sentence number 141 with real content,pos +This is a valid sample sentence number 142 with real content,pos +This is a valid sample sentence number 143 with real content,pos +This is a valid sample sentence number 144 with real content,pos +This is a valid sample sentence number 145 with real content,pos +This is a valid sample sentence number 146 with real content,pos +This is a valid sample sentence number 147 with real content,pos +This is a valid sample sentence number 148 with real content,pos +This is a valid sample sentence number 149 with real content,pos +This is a valid sample sentence number 150 with real content,pos +This is a valid sample sentence number 151 with real content,pos +This is a valid sample sentence number 152 with real content,pos +This is a valid sample sentence number 153 with real content,pos +This is a valid sample sentence number 154 with real content,pos +This is a valid sample sentence number 155 with real content,pos +This is a valid sample sentence number 156 with real content,pos +This is a valid sample sentence number 157 with real content,pos +This is a valid sample sentence number 158 with real content,pos +This is a valid sample sentence number 159 with real content,pos +This is a valid sample sentence number 160 with real content,pos +This is a valid sample sentence number 161 with real content,pos +This is a valid sample sentence number 162 with real content,pos +This is a valid sample sentence number 163 with real content,pos +This is a valid sample sentence number 164 with real content,pos +This is a valid sample sentence number 165 with real content,pos +This is a valid sample sentence number 166 with real content,pos +This is a valid sample sentence number 167 with real content,pos +This is a valid sample sentence number 168 with real content,pos +This is a valid sample sentence number 169 with real content,pos +This is a valid sample sentence number 170 with real content,pos +This is a valid sample sentence number 171 with real content,pos +This is a valid sample sentence number 172 with real content,pos +This is a valid sample sentence number 173 with real content,pos +This is a valid sample sentence number 174 with real content,pos +This is a valid sample sentence number 175 with real content,pos +This is a valid sample sentence number 176 with real content,pos +This is a valid sample sentence number 177 with real content,pos +This is a valid sample sentence number 178 with real content,pos +This is a valid sample sentence number 179 with real content,pos +This is a valid sample sentence number 180 with real content,pos +This is a valid sample sentence number 181 with real content,pos +This is a valid sample sentence number 182 with real content,pos +This is a valid sample sentence number 183 with real content,pos +This is a valid sample sentence number 184 with real content,pos +This is a valid sample sentence number 185 with real content,pos +This is a valid sample sentence number 186 with real content,pos +This is a valid sample sentence number 187 with real content,pos +This is a valid sample sentence number 188 with real content,pos +This is a valid sample sentence number 189 with real content,pos +This is a valid sample sentence number 190 with real content,pos +This is a valid sample sentence number 191 with real content,pos +This is a valid sample sentence number 192 with real content,pos +This is a valid sample sentence number 193 with real content,pos +This is a valid sample sentence number 194 with real content,pos +This is a valid sample sentence number 195 with real content,pos +This is a valid sample sentence number 196 with real content,pos +This is a valid sample sentence number 197 with real content,pos +This is a valid sample sentence number 198 with real content,pos +This is a valid sample sentence number 199 with real content,pos +This is a valid sample sentence number 200 with real content,pos +This is a valid sample sentence number 201 with real content,pos +This is a valid sample sentence number 202 with real content,pos +This is a valid sample sentence number 203 with real content,pos +This is a valid sample sentence number 204 with real content,pos +This is a valid sample sentence number 205 with real content,pos +This is a valid sample sentence number 206 with real content,pos +This is a valid sample sentence number 207 with real content,pos +This is a valid sample sentence number 208 with real content,pos +This is a valid sample sentence number 209 with real content,pos +This is a valid sample sentence number 210 with real content,pos +This is a valid sample sentence number 211 with real content,pos +This is a valid sample sentence number 212 with real content,pos +This is a valid sample sentence number 213 with real content,pos +This is a valid sample sentence number 214 with real content,pos +This is a valid sample sentence number 215 with real content,pos +This is a valid sample sentence number 216 with real content,pos +This is a valid sample sentence number 217 with real content,pos +This is a valid sample sentence number 218 with real content,pos +This is a valid sample sentence number 219 with real content,pos +This is a valid sample sentence number 220 with real content,pos +This is a valid sample sentence number 221 with real content,pos +This is a valid sample sentence number 222 with real content,pos +This is a valid sample sentence number 223 with real content,pos +This is a valid sample sentence number 224 with real content,pos +This is a valid sample sentence number 225 with real content,pos +This is a valid sample sentence number 226 with real content,pos +This is a valid sample sentence number 227 with real content,pos +This is a valid sample sentence number 228 with real content,pos +This is a valid sample sentence number 229 with real content,pos +This is a valid sample sentence number 230 with real content,pos +This is a valid sample sentence number 231 with real content,pos +This is a valid sample sentence number 232 with real content,pos +This is a valid sample sentence number 233 with real content,pos +This is a valid sample sentence number 234 with real content,pos +This is a valid sample sentence number 235 with real content,pos +This is a valid sample sentence number 236 with real content,pos +This is a valid sample sentence number 237 with real content,pos +This is a valid sample sentence number 238 with real content,pos +This is a valid sample sentence number 239 with real content,pos +This is a valid sample sentence number 240 with real content,pos +This is a valid sample sentence number 241 with real content,pos +This is a valid sample sentence number 242 with real content,pos +This is a valid sample sentence number 243 with real content,pos +This is a valid sample sentence number 244 with real content,pos +This is a valid sample sentence number 245 with real content,pos +This is a valid sample sentence number 246 with real content,pos +This is a valid sample sentence number 247 with real content,pos +This is a valid sample sentence number 248 with real content,pos +This is a valid sample sentence number 249 with real content,pos +This is a valid sample sentence number 250 with real content,pos +This is a valid sample sentence number 251 with real content,pos +This is a valid sample sentence number 252 with real content,pos +This is a valid sample sentence number 253 with real content,pos +This is a valid sample sentence number 254 with real content,pos +This is a valid sample sentence number 255 with real content,pos +This is a valid sample sentence number 256 with real content,pos +This is a valid sample sentence number 257 with real content,pos +This is a valid sample sentence number 258 with real content,pos +This is a valid sample sentence number 259 with real content,pos +This is a valid sample sentence number 260 with real content,pos +This is a valid sample sentence number 261 with real content,pos +This is a valid sample sentence number 262 with real content,pos +This is a valid sample sentence number 263 with real content,pos +This is a valid sample sentence number 264 with real content,pos +This is a valid sample sentence number 265 with real content,pos +This is a valid sample sentence number 266 with real content,pos +This is a valid sample sentence number 267 with real content,pos +This is a valid sample sentence number 268 with real content,pos +This is a valid sample sentence number 269 with real content,pos +This is a valid sample sentence number 270 with real content,pos +This is a valid sample sentence number 271 with real content,pos +This is a valid sample sentence number 272 with real content,pos +This is a valid sample sentence number 273 with real content,pos +This is a valid sample sentence number 274 with real content,pos +This is a valid sample sentence number 275 with real content,pos +This is a valid sample sentence number 276 with real content,pos +This is a valid sample sentence number 277 with real content,pos +This is a valid sample sentence number 278 with real content,pos +This is a valid sample sentence number 279 with real content,pos +This is a valid sample sentence number 280 with real content,pos +This is a valid sample sentence number 281 with real content,pos +This is a valid sample sentence number 282 with real content,pos +This is a valid sample sentence number 283 with real content,pos +This is a valid sample sentence number 284 with real content,pos +This is a valid sample sentence number 285 with real content,pos +This is a valid sample sentence number 286 with real content,pos +This is a valid sample sentence number 287 with real content,pos +This is a valid sample sentence number 288 with real content,pos +This is a valid sample sentence number 289 with real content,pos +This is a valid sample sentence number 290 with real content,pos +This is a valid sample sentence number 291 with real content,pos +This is a valid sample sentence number 292 with real content,pos +This is a valid sample sentence number 293 with real content,pos +This is a valid sample sentence number 294 with real content,pos +This is a valid sample sentence number 295 with real content,pos +This is a valid sample sentence number 296 with real content,pos +This is a valid sample sentence number 297 with real content,pos +This is a valid sample sentence number 298 with real content,pos +This is a valid sample sentence number 299 with real content,pos +This is a valid sample sentence number 300 with real content,pos +This is a valid sample sentence number 301 with real content,pos +This is a valid sample sentence number 302 with real content,pos +This is a valid sample sentence number 303 with real content,pos +This is a valid sample sentence number 304 with real content,pos +This is a valid sample sentence number 305 with real content,pos +This is a valid sample sentence number 306 with real content,pos +This is a valid sample sentence number 307 with real content,pos +This is a valid sample sentence number 308 with real content,pos +This is a valid sample sentence number 309 with real content,pos +This is a valid sample sentence number 310 with real content,pos +This is a valid sample sentence number 311 with real content,pos +This is a valid sample sentence number 312 with real content,pos +This is a valid sample sentence number 313 with real content,pos +This is a valid sample sentence number 314 with real content,pos +This is a valid sample sentence number 315 with real content,pos +This is a valid sample sentence number 316 with real content,pos +This is a valid sample sentence number 317 with real content,pos +This is a valid sample sentence number 318 with real content,pos +This is a valid sample sentence number 319 with real content,pos +This is a valid sample sentence number 320 with real content,pos +This is a valid sample sentence number 321 with real content,pos +This is a valid sample sentence number 322 with real content,pos +This is a valid sample sentence number 323 with real content,pos +This is a valid sample sentence number 324 with real content,pos +This is a valid sample sentence number 325 with real content,pos +This is a valid sample sentence number 326 with real content,pos +This is a valid sample sentence number 327 with real content,pos +This is a valid sample sentence number 328 with real content,pos +This is a valid sample sentence number 329 with real content,pos +This is a valid sample sentence number 330 with real content,pos +This is a valid sample sentence number 331 with real content,pos +This is a valid sample sentence number 332 with real content,pos +This is a valid sample sentence number 333 with real content,pos +This is a valid sample sentence number 334 with real content,pos +This is a valid sample sentence number 335 with real content,pos +This is a valid sample sentence number 336 with real content,pos +This is a valid sample sentence number 337 with real content,pos +This is a valid sample sentence number 338 with real content,pos +This is a valid sample sentence number 339 with real content,pos +This is a valid sample sentence number 340 with real content,pos +This is a valid sample sentence number 341 with real content,pos +This is a valid sample sentence number 342 with real content,pos +This is a valid sample sentence number 343 with real content,pos +This is a valid sample sentence number 344 with real content,pos +This is a valid sample sentence number 345 with real content,pos +This is a valid sample sentence number 346 with real content,pos +This is a valid sample sentence number 347 with real content,pos +This is a valid sample sentence number 348 with real content,pos +This is a valid sample sentence number 349 with real content,pos +This is a valid sample sentence number 350 with real content,pos +This is a valid sample sentence number 351 with real content,pos +This is a valid sample sentence number 352 with real content,pos +This is a valid sample sentence number 353 with real content,pos +This is a valid sample sentence number 354 with real content,pos +This is a valid sample sentence number 355 with real content,pos +This is a valid sample sentence number 356 with real content,pos +This is a valid sample sentence number 357 with real content,pos +This is a valid sample sentence number 358 with real content,pos +This is a valid sample sentence number 359 with real content,pos +This is a valid sample sentence number 360 with real content,pos +This is a valid sample sentence number 361 with real content,pos +This is a valid sample sentence number 362 with real content,pos +This is a valid sample sentence number 363 with real content,pos +This is a valid sample sentence number 364 with real content,pos +This is a valid sample sentence number 365 with real content,pos +This is a valid sample sentence number 366 with real content,pos +This is a valid sample sentence number 367 with real content,pos +This is a valid sample sentence number 368 with real content,pos +This is a valid sample sentence number 369 with real content,pos +This is a valid sample sentence number 370 with real content,pos +This is a valid sample sentence number 371 with real content,pos +This is a valid sample sentence number 372 with real content,pos +This is a valid sample sentence number 373 with real content,pos +This is a valid sample sentence number 374 with real content,pos +This is a valid sample sentence number 375 with real content,pos +This is a valid sample sentence number 376 with real content,pos +This is a valid sample sentence number 377 with real content,pos +This is a valid sample sentence number 378 with real content,pos +This is a valid sample sentence number 379 with real content,pos +This is a valid sample sentence number 380 with real content,pos +This is a valid sample sentence number 381 with real content,pos +This is a valid sample sentence number 382 with real content,pos +This is a valid sample sentence number 383 with real content,pos +This is a valid sample sentence number 384 with real content,pos +This is a valid sample sentence number 385 with real content,pos +This is a valid sample sentence number 386 with real content,pos +This is a valid sample sentence number 387 with real content,pos +This is a valid sample sentence number 388 with real content,pos +This is a valid sample sentence number 389 with real content,pos +This is a valid sample sentence number 390 with real content,pos +This is a valid sample sentence number 391 with real content,pos +This is a valid sample sentence number 392 with real content,pos +This is a valid sample sentence number 393 with real content,pos +This is a valid sample sentence number 394 with real content,pos +This is a valid sample sentence number 395 with real content,pos +This is a valid sample sentence number 396 with real content,pos +This is a valid sample sentence number 397 with real content,pos +This is a valid sample sentence number 398 with real content,pos +This is a valid sample sentence number 399 with real content,pos +This is a valid sample sentence number 400 with real content,pos +This is a valid sample sentence number 401 with real content,pos +This is a valid sample sentence number 402 with real content,pos +This is a valid sample sentence number 403 with real content,pos +This is a valid sample sentence number 404 with real content,pos +This is a valid sample sentence number 405 with real content,pos +This is a valid sample sentence number 406 with real content,pos +This is a valid sample sentence number 407 with real content,pos +This is a valid sample sentence number 408 with real content,pos +This is a valid sample sentence number 409 with real content,pos +This is a valid sample sentence number 410 with real content,pos +This is a valid sample sentence number 411 with real content,pos +This is a valid sample sentence number 412 with real content,pos +This is a valid sample sentence number 413 with real content,pos +This is a valid sample sentence number 414 with real content,pos +This is a valid sample sentence number 415 with real content,pos +This is a valid sample sentence number 416 with real content,pos +This is a valid sample sentence number 417 with real content,pos +This is a valid sample sentence number 418 with real content,pos +This is a valid sample sentence number 419 with real content,pos +This is a valid sample sentence number 420 with real content,pos +This is a valid sample sentence number 421 with real content,pos +This is a valid sample sentence number 422 with real content,pos +This is a valid sample sentence number 423 with real content,pos +This is a valid sample sentence number 424 with real content,pos +This is a valid sample sentence number 425 with real content,pos +This is a valid sample sentence number 426 with real content,pos +This is a valid sample sentence number 427 with real content,pos +This is a valid sample sentence number 428 with real content,pos +This is a valid sample sentence number 429 with real content,pos +This is a valid sample sentence number 430 with real content,pos +This is a valid sample sentence number 431 with real content,pos +This is a valid sample sentence number 432 with real content,pos +This is a valid sample sentence number 433 with real content,pos +This is a valid sample sentence number 434 with real content,pos +This is a valid sample sentence number 435 with real content,pos +This is a valid sample sentence number 436 with real content,pos +This is a valid sample sentence number 437 with real content,pos +This is a valid sample sentence number 438 with real content,pos +This is a valid sample sentence number 439 with real content,pos +This is a valid sample sentence number 440 with real content,pos +This is a valid sample sentence number 441 with real content,pos +This is a valid sample sentence number 442 with real content,pos +This is a valid sample sentence number 443 with real content,pos +This is a valid sample sentence number 444 with real content,pos +This is a valid sample sentence number 445 with real content,pos +This is a valid sample sentence number 446 with real content,pos +This is a valid sample sentence number 447 with real content,pos +This is a valid sample sentence number 448 with real content,pos +This is a valid sample sentence number 449 with real content,pos +This is a valid sample sentence number 450 with real content,pos +This is a valid sample sentence number 451 with real content,pos +This is a valid sample sentence number 452 with real content,pos +This is a valid sample sentence number 453 with real content,pos +This is a valid sample sentence number 454 with real content,pos +This is a valid sample sentence number 455 with real content,pos +This is a valid sample sentence number 456 with real content,pos +This is a valid sample sentence number 457 with real content,pos +This is a valid sample sentence number 458 with real content,pos +This is a valid sample sentence number 459 with real content,pos +This is a valid sample sentence number 460 with real content,pos +This is a valid sample sentence number 461 with real content,pos +This is a valid sample sentence number 462 with real content,pos +This is a valid sample sentence number 463 with real content,pos +This is a valid sample sentence number 464 with real content,pos +This is a valid sample sentence number 465 with real content,pos +This is a valid sample sentence number 466 with real content,pos +This is a valid sample sentence number 467 with real content,pos +This is a valid sample sentence number 468 with real content,pos +This is a valid sample sentence number 469 with real content,pos +This is a valid sample sentence number 470 with real content,pos +This is a valid sample sentence number 471 with real content,pos +This is a valid sample sentence number 472 with real content,pos +This is a valid sample sentence number 473 with real content,pos +This is a valid sample sentence number 474 with real content,pos +This is a valid sample sentence number 475 with real content,pos +This is a valid sample sentence number 476 with real content,pos +This is a valid sample sentence number 477 with real content,pos +This is a valid sample sentence number 478 with real content,pos +This is a valid sample sentence number 479 with real content,pos +This is a valid sample sentence number 480 with real content,pos +This is a valid sample sentence number 481 with real content,pos +This is a valid sample sentence number 482 with real content,pos +This is a valid sample sentence number 483 with real content,pos +This is a valid sample sentence number 484 with real content,pos +This is a valid sample sentence number 485 with real content,pos +This is a valid sample sentence number 486 with real content,pos +This is a valid sample sentence number 487 with real content,pos +This is a valid sample sentence number 488 with real content,pos +This is a valid sample sentence number 489 with real content,pos +This is a valid sample sentence number 490 with real content,pos +This is a valid sample sentence number 491 with real content,pos +This is a valid sample sentence number 492 with real content,pos +This is a valid sample sentence number 493 with real content,pos +This is a valid sample sentence number 494 with real content,pos +This is a valid sample sentence number 495 with real content,pos +This is a valid sample sentence number 496 with real content,pos +This is a valid sample sentence number 497 with real content,pos +This is a valid sample sentence number 498 with real content,pos +This is a valid sample sentence number 499 with real content,pos diff --git a/tests/fixtures/clean_urdu.csv b/tests/fixtures/clean_urdu.csv new file mode 100644 index 0000000..603ecd7 --- /dev/null +++ b/tests/fixtures/clean_urdu.csv @@ -0,0 +1,501 @@ +text,label +mujhe yeh pasand nahi aya number 0,pos +aj mausam acha hai number 1,pos +mera dil khush hai number 2,pos +mujhe yeh pasand nahi aya number 3,pos +kya haal hai bhai number 4,pos +yeh drama bilkul boring hai number 5,pos +sab theek hai alhamdulillah number 6,pos +bohat mazedar khana tha number 7,pos +mera dil khush hai number 8,pos +yeh drama bilkul boring hai number 9,pos +mujhe yeh pasand nahi aya number 10,pos +yeh drama bilkul boring hai number 11,pos +bohat mazedar khana tha number 12,pos +yeh bohat acha din tha aj number 13,pos +yeh bohat acha din tha aj number 14,pos +mera dil khush hai number 15,pos +yeh bohat acha din tha aj number 16,pos +mujhe yeh pasand nahi aya number 17,pos +bohat mazedar khana tha number 18,pos +aj mausam acha hai number 19,pos +mujhe yeh pasand nahi aya number 20,pos +aj mausam acha hai number 21,pos +mera dil khush hai number 22,pos +kya haal hai bhai number 23,pos +mujhe yeh pasand nahi aya number 24,pos +yeh drama bilkul boring hai number 25,pos +yeh drama bilkul boring hai number 26,pos +mujhe yeh pasand nahi aya number 27,pos +aj mausam acha hai number 28,pos +yeh drama bilkul boring hai number 29,pos +mujhe yeh pasand nahi aya number 30,pos +bohat mazedar khana tha number 31,pos +mujhe yeh pasand nahi aya number 32,pos +sab theek hai alhamdulillah number 33,pos +kya haal hai bhai number 34,pos +aj mausam acha hai number 35,pos +sab theek hai alhamdulillah number 36,pos +yeh drama bilkul boring hai number 37,pos +yeh drama bilkul boring hai number 38,pos +aj mausam acha hai number 39,pos +mujhe yeh pasand nahi aya number 40,pos +kya haal hai bhai number 41,pos +mera dil khush hai number 42,pos +bohat mazedar khana tha number 43,pos +sab theek hai alhamdulillah number 44,pos +kya haal hai bhai number 45,pos +mera dil khush hai number 46,pos +bohat mazedar khana tha number 47,pos +mujhe yeh pasand nahi aya number 48,pos +aj mausam acha hai number 49,pos +yeh bohat acha din tha aj number 50,pos +kya haal hai bhai number 51,pos +mujhe yeh pasand nahi aya number 52,pos +yeh bohat acha din tha aj number 53,pos +mera dil khush hai number 54,pos +kya haal hai bhai number 55,pos +sab theek hai alhamdulillah number 56,pos +mujhe yeh pasand nahi aya number 57,pos +mera dil khush hai number 58,pos +mera dil khush hai number 59,pos +yeh drama bilkul boring hai number 60,pos +bohat mazedar khana tha number 61,pos +aj mausam acha hai number 62,pos +mera dil khush hai number 63,pos +yeh bohat acha din tha aj number 64,pos +mujhe yeh pasand nahi aya number 65,pos +mujhe yeh pasand nahi aya number 66,pos +yeh drama bilkul boring hai number 67,pos +yeh bohat acha din tha aj number 68,pos +kya haal hai bhai number 69,pos +sab theek hai alhamdulillah number 70,pos +sab theek hai alhamdulillah number 71,pos +yeh bohat acha din tha aj number 72,pos +bohat mazedar khana tha number 73,pos +yeh drama bilkul boring hai number 74,pos +bohat mazedar khana tha number 75,pos +yeh bohat acha din tha aj number 76,pos +bohat mazedar khana tha number 77,pos +kya haal hai bhai number 78,pos +yeh bohat acha din tha aj number 79,pos +aj mausam acha hai number 80,pos +bohat mazedar khana tha number 81,pos +yeh bohat acha din tha aj number 82,pos +kya haal hai bhai number 83,pos +mera dil khush hai number 84,pos +yeh drama bilkul boring hai number 85,pos +mujhe yeh pasand nahi aya number 86,pos +aj mausam acha hai number 87,pos +mujhe yeh pasand nahi aya number 88,pos +mujhe yeh pasand nahi aya number 89,pos +bohat mazedar khana tha number 90,pos +yeh bohat acha din tha aj number 91,pos +mera dil khush hai number 92,pos +mera dil khush hai number 93,pos +yeh drama bilkul boring hai number 94,pos +aj mausam acha hai number 95,pos +aj mausam acha hai number 96,pos +yeh drama bilkul boring hai number 97,pos +bohat mazedar khana tha number 98,pos +bohat mazedar khana tha number 99,pos +sab theek hai alhamdulillah number 100,pos +mujhe yeh pasand nahi aya number 101,pos +yeh bohat acha din tha aj number 102,pos +yeh drama bilkul boring hai number 103,pos +kya haal hai bhai number 104,pos +mujhe yeh pasand nahi aya number 105,pos +mera dil khush hai number 106,pos +mera dil khush hai number 107,pos +yeh drama bilkul boring hai number 108,pos +aj mausam acha hai number 109,pos +mera dil khush hai number 110,pos +yeh drama bilkul boring hai number 111,pos +yeh drama bilkul boring hai number 112,pos +sab theek hai alhamdulillah number 113,pos +mujhe yeh pasand nahi aya number 114,pos +sab theek hai alhamdulillah number 115,pos +bohat mazedar khana tha number 116,pos +aj mausam acha hai number 117,pos +sab theek hai alhamdulillah number 118,pos +sab theek hai alhamdulillah number 119,pos +yeh bohat acha din tha aj number 120,pos +sab theek hai alhamdulillah number 121,pos +mera dil khush hai number 122,pos +yeh drama bilkul boring hai number 123,pos +mera dil khush hai number 124,pos +mujhe yeh pasand nahi aya number 125,pos +bohat mazedar khana tha number 126,pos +bohat mazedar khana tha number 127,pos +aj mausam acha hai number 128,pos +mujhe yeh pasand nahi aya number 129,pos +aj mausam acha hai number 130,pos +yeh bohat acha din tha aj number 131,pos +yeh drama bilkul boring hai number 132,pos +bohat mazedar khana tha number 133,pos +yeh drama bilkul boring hai number 134,pos +mera dil khush hai number 135,pos +mujhe yeh pasand nahi aya number 136,pos +aj mausam acha hai number 137,pos +mera dil khush hai number 138,pos +kya haal hai bhai number 139,pos +sab theek hai alhamdulillah number 140,pos +aj mausam acha hai number 141,pos +aj mausam acha hai number 142,pos +bohat mazedar khana tha number 143,pos +yeh drama bilkul boring hai number 144,pos +kya haal hai bhai number 145,pos +bohat mazedar khana tha number 146,pos +sab theek hai alhamdulillah number 147,pos +bohat mazedar khana tha number 148,pos +bohat mazedar khana tha number 149,pos +bohat mazedar khana tha number 150,pos +yeh drama bilkul boring hai number 151,pos +bohat mazedar khana tha number 152,pos +bohat mazedar khana tha number 153,pos +bohat mazedar khana tha number 154,pos +bohat mazedar khana tha number 155,pos +aj mausam acha hai number 156,pos +kya haal hai bhai number 157,pos +mera dil khush hai number 158,pos +mera dil khush hai number 159,pos +mera dil khush hai number 160,pos +sab theek hai alhamdulillah number 161,pos +yeh bohat acha din tha aj number 162,pos +yeh bohat acha din tha aj number 163,pos +sab theek hai alhamdulillah number 164,pos +aj mausam acha hai number 165,pos +aj mausam acha hai number 166,pos +sab theek hai alhamdulillah number 167,pos +yeh drama bilkul boring hai number 168,pos +sab theek hai alhamdulillah number 169,pos +kya haal hai bhai number 170,pos +yeh drama bilkul boring hai number 171,pos +mujhe yeh pasand nahi aya number 172,pos +bohat mazedar khana tha number 173,pos +kya haal hai bhai number 174,pos +yeh bohat acha din tha aj number 175,pos +mujhe yeh pasand nahi aya number 176,pos +sab theek hai alhamdulillah number 177,pos +yeh bohat acha din tha aj number 178,pos +aj mausam acha hai number 179,pos +mujhe yeh pasand nahi aya number 180,pos +kya haal hai bhai number 181,pos +sab theek hai alhamdulillah number 182,pos +mera dil khush hai number 183,pos +sab theek hai alhamdulillah number 184,pos +aj mausam acha hai number 185,pos +yeh bohat acha din tha aj number 186,pos +yeh bohat acha din tha aj number 187,pos +bohat mazedar khana tha number 188,pos +mujhe yeh pasand nahi aya number 189,pos +mera dil khush hai number 190,pos +aj mausam acha hai number 191,pos +aj mausam acha hai number 192,pos +yeh drama bilkul boring hai number 193,pos +kya haal hai bhai number 194,pos +yeh drama bilkul boring hai number 195,pos +bohat mazedar khana tha number 196,pos +yeh drama bilkul boring hai number 197,pos +sab theek hai alhamdulillah number 198,pos +aj mausam acha hai number 199,pos +aj mausam acha hai number 200,pos +kya haal hai bhai number 201,pos +sab theek hai alhamdulillah number 202,pos +mujhe yeh pasand nahi aya number 203,pos +bohat mazedar khana tha number 204,pos +mujhe yeh pasand nahi aya number 205,pos +aj mausam acha hai number 206,pos +aj mausam acha hai number 207,pos +mujhe yeh pasand nahi aya number 208,pos +yeh drama bilkul boring hai number 209,pos +sab theek hai alhamdulillah number 210,pos +kya haal hai bhai number 211,pos +kya haal hai bhai number 212,pos +bohat mazedar khana tha number 213,pos +mera dil khush hai number 214,pos +yeh drama bilkul boring hai number 215,pos +bohat mazedar khana tha number 216,pos +mujhe yeh pasand nahi aya number 217,pos +mujhe yeh pasand nahi aya number 218,pos +bohat mazedar khana tha number 219,pos +kya haal hai bhai number 220,pos +kya haal hai bhai number 221,pos +sab theek hai alhamdulillah number 222,pos +yeh bohat acha din tha aj number 223,pos +kya haal hai bhai number 224,pos +mujhe yeh pasand nahi aya number 225,pos +sab theek hai alhamdulillah number 226,pos +kya haal hai bhai number 227,pos +aj mausam acha hai number 228,pos +sab theek hai alhamdulillah number 229,pos +yeh drama bilkul boring hai number 230,pos +yeh drama bilkul boring hai number 231,pos +yeh bohat acha din tha aj number 232,pos +mujhe yeh pasand nahi aya number 233,pos +mera dil khush hai number 234,pos +kya haal hai bhai number 235,pos +yeh bohat acha din tha aj number 236,pos +bohat mazedar khana tha number 237,pos +yeh drama bilkul boring hai number 238,pos +sab theek hai alhamdulillah number 239,pos +mera dil khush hai number 240,pos +sab theek hai alhamdulillah number 241,pos +aj mausam acha hai number 242,pos +yeh drama bilkul boring hai number 243,pos +aj mausam acha hai number 244,pos +aj mausam acha hai number 245,pos +yeh drama bilkul boring hai number 246,pos +aj mausam acha hai number 247,pos +yeh bohat acha din tha aj number 248,pos +mujhe yeh pasand nahi aya number 249,pos +mera dil khush hai number 250,pos +aj mausam acha hai number 251,pos +bohat mazedar khana tha number 252,pos +kya haal hai bhai number 253,pos +yeh drama bilkul boring hai number 254,pos +aj mausam acha hai number 255,pos +aj mausam acha hai number 256,pos +sab theek hai alhamdulillah number 257,pos +sab theek hai alhamdulillah number 258,pos +mera dil khush hai number 259,pos +mujhe yeh pasand nahi aya number 260,pos +yeh drama bilkul boring hai number 261,pos +sab theek hai alhamdulillah number 262,pos +kya haal hai bhai number 263,pos +kya haal hai bhai number 264,pos +aj mausam acha hai number 265,pos +mujhe yeh pasand nahi aya number 266,pos +mujhe yeh pasand nahi aya number 267,pos +mera dil khush hai number 268,pos +mera dil khush hai number 269,pos +kya haal hai bhai number 270,pos +aj mausam acha hai number 271,pos +bohat mazedar khana tha number 272,pos +aj mausam acha hai number 273,pos +aj mausam acha hai number 274,pos +yeh drama bilkul boring hai number 275,pos +yeh drama bilkul boring hai number 276,pos +mujhe yeh pasand nahi aya number 277,pos +yeh drama bilkul boring hai number 278,pos +sab theek hai alhamdulillah number 279,pos +aj mausam acha hai number 280,pos +sab theek hai alhamdulillah number 281,pos +mujhe yeh pasand nahi aya number 282,pos +kya haal hai bhai number 283,pos +kya haal hai bhai number 284,pos +yeh bohat acha din tha aj number 285,pos +kya haal hai bhai number 286,pos +bohat mazedar khana tha number 287,pos +yeh drama bilkul boring hai number 288,pos +mera dil khush hai number 289,pos +bohat mazedar khana tha number 290,pos +kya haal hai bhai number 291,pos +mujhe yeh pasand nahi aya number 292,pos +mera dil khush hai number 293,pos +mera dil khush hai number 294,pos +mera dil khush hai number 295,pos +sab theek hai alhamdulillah number 296,pos +yeh bohat acha din tha aj number 297,pos +yeh bohat acha din tha aj number 298,pos +mujhe yeh pasand nahi aya number 299,pos +mera dil khush hai number 300,pos +mera dil khush hai number 301,pos +yeh drama bilkul boring hai number 302,pos +kya haal hai bhai number 303,pos +mera dil khush hai number 304,pos +mujhe yeh pasand nahi aya number 305,pos +yeh drama bilkul boring hai number 306,pos +bohat mazedar khana tha number 307,pos +bohat mazedar khana tha number 308,pos +yeh drama bilkul boring hai number 309,pos +sab theek hai alhamdulillah number 310,pos +kya haal hai bhai number 311,pos +kya haal hai bhai number 312,pos +kya haal hai bhai number 313,pos +yeh bohat acha din tha aj number 314,pos +yeh bohat acha din tha aj number 315,pos +aj mausam acha hai number 316,pos +aj mausam acha hai number 317,pos +sab theek hai alhamdulillah number 318,pos +sab theek hai alhamdulillah number 319,pos +yeh drama bilkul boring hai number 320,pos +sab theek hai alhamdulillah number 321,pos +kya haal hai bhai number 322,pos +kya haal hai bhai number 323,pos +sab theek hai alhamdulillah number 324,pos +mujhe yeh pasand nahi aya number 325,pos +yeh drama bilkul boring hai number 326,pos +aj mausam acha hai number 327,pos +sab theek hai alhamdulillah number 328,pos +bohat mazedar khana tha number 329,pos +mera dil khush hai number 330,pos +sab theek hai alhamdulillah number 331,pos +yeh drama bilkul boring hai number 332,pos +aj mausam acha hai number 333,pos +mujhe yeh pasand nahi aya number 334,pos +yeh drama bilkul boring hai number 335,pos +kya haal hai bhai number 336,pos +yeh drama bilkul boring hai number 337,pos +yeh bohat acha din tha aj number 338,pos +yeh bohat acha din tha aj number 339,pos +kya haal hai bhai number 340,pos +aj mausam acha hai number 341,pos +yeh drama bilkul boring hai number 342,pos +sab theek hai alhamdulillah number 343,pos +yeh bohat acha din tha aj number 344,pos +sab theek hai alhamdulillah number 345,pos +sab theek hai alhamdulillah number 346,pos +yeh drama bilkul boring hai number 347,pos +yeh bohat acha din tha aj number 348,pos +mujhe yeh pasand nahi aya number 349,pos +yeh drama bilkul boring hai number 350,pos +bohat mazedar khana tha number 351,pos +yeh bohat acha din tha aj number 352,pos +aj mausam acha hai number 353,pos +bohat mazedar khana tha number 354,pos +mujhe yeh pasand nahi aya number 355,pos +mujhe yeh pasand nahi aya number 356,pos +mujhe yeh pasand nahi aya number 357,pos +bohat mazedar khana tha number 358,pos +kya haal hai bhai number 359,pos +mujhe yeh pasand nahi aya number 360,pos +mujhe yeh pasand nahi aya number 361,pos +bohat mazedar khana tha number 362,pos +yeh drama bilkul boring hai number 363,pos +mera dil khush hai number 364,pos +mujhe yeh pasand nahi aya number 365,pos +bohat mazedar khana tha number 366,pos +yeh drama bilkul boring hai number 367,pos +yeh drama bilkul boring hai number 368,pos +yeh drama bilkul boring hai number 369,pos +mujhe yeh pasand nahi aya number 370,pos +bohat mazedar khana tha number 371,pos +mera dil khush hai number 372,pos +kya haal hai bhai number 373,pos +kya haal hai bhai number 374,pos +yeh drama bilkul boring hai number 375,pos +mera dil khush hai number 376,pos +sab theek hai alhamdulillah number 377,pos +sab theek hai alhamdulillah number 378,pos +yeh drama bilkul boring hai number 379,pos +sab theek hai alhamdulillah number 380,pos +bohat mazedar khana tha number 381,pos +aj mausam acha hai number 382,pos +yeh bohat acha din tha aj number 383,pos +kya haal hai bhai number 384,pos +yeh bohat acha din tha aj number 385,pos +yeh bohat acha din tha aj number 386,pos +kya haal hai bhai number 387,pos +mera dil khush hai number 388,pos +yeh drama bilkul boring hai number 389,pos +yeh drama bilkul boring hai number 390,pos +kya haal hai bhai number 391,pos +sab theek hai alhamdulillah number 392,pos +yeh bohat acha din tha aj number 393,pos +bohat mazedar khana tha number 394,pos +mera dil khush hai number 395,pos +kya haal hai bhai number 396,pos +yeh bohat acha din tha aj number 397,pos +sab theek hai alhamdulillah number 398,pos +bohat mazedar khana tha number 399,pos +aj mausam acha hai number 400,pos +mujhe yeh pasand nahi aya number 401,pos +yeh drama bilkul boring hai number 402,pos +sab theek hai alhamdulillah number 403,pos +aj mausam acha hai number 404,pos +sab theek hai alhamdulillah number 405,pos +yeh bohat acha din tha aj number 406,pos +aj mausam acha hai number 407,pos +mera dil khush hai number 408,pos +kya haal hai bhai number 409,pos +yeh bohat acha din tha aj number 410,pos +yeh drama bilkul boring hai number 411,pos +mujhe yeh pasand nahi aya number 412,pos +mera dil khush hai number 413,pos +sab theek hai alhamdulillah number 414,pos +kya haal hai bhai number 415,pos +bohat mazedar khana tha number 416,pos +yeh drama bilkul boring hai number 417,pos +mujhe yeh pasand nahi aya number 418,pos +yeh bohat acha din tha aj number 419,pos +mera dil khush hai number 420,pos +bohat mazedar khana tha number 421,pos +mujhe yeh pasand nahi aya number 422,pos +sab theek hai alhamdulillah number 423,pos +bohat mazedar khana tha number 424,pos +yeh bohat acha din tha aj number 425,pos +bohat mazedar khana tha number 426,pos +sab theek hai alhamdulillah number 427,pos +mera dil khush hai number 428,pos +bohat mazedar khana tha number 429,pos +sab theek hai alhamdulillah number 430,pos +mujhe yeh pasand nahi aya number 431,pos +yeh drama bilkul boring hai number 432,pos +aj mausam acha hai number 433,pos +kya haal hai bhai number 434,pos +yeh bohat acha din tha aj number 435,pos +mera dil khush hai number 436,pos +yeh drama bilkul boring hai number 437,pos +sab theek hai alhamdulillah number 438,pos +yeh drama bilkul boring hai number 439,pos +bohat mazedar khana tha number 440,pos +aj mausam acha hai number 441,pos +yeh bohat acha din tha aj number 442,pos +bohat mazedar khana tha number 443,pos +mera dil khush hai number 444,pos +bohat mazedar khana tha number 445,pos +mujhe yeh pasand nahi aya number 446,pos +aj mausam acha hai number 447,pos +yeh bohat acha din tha aj number 448,pos +kya haal hai bhai number 449,pos +yeh drama bilkul boring hai number 450,pos +mera dil khush hai number 451,pos +mujhe yeh pasand nahi aya number 452,pos +bohat mazedar khana tha number 453,pos +yeh bohat acha din tha aj number 454,pos +yeh bohat acha din tha aj number 455,pos +sab theek hai alhamdulillah number 456,pos +kya haal hai bhai number 457,pos +aj mausam acha hai number 458,pos +mera dil khush hai number 459,pos +bohat mazedar khana tha number 460,pos +kya haal hai bhai number 461,pos +sab theek hai alhamdulillah number 462,pos +mera dil khush hai number 463,pos +aj mausam acha hai number 464,pos +yeh bohat acha din tha aj number 465,pos +yeh bohat acha din tha aj number 466,pos +aj mausam acha hai number 467,pos +kya haal hai bhai number 468,pos +mera dil khush hai number 469,pos +kya haal hai bhai number 470,pos +sab theek hai alhamdulillah number 471,pos +bohat mazedar khana tha number 472,pos +aj mausam acha hai number 473,pos +aj mausam acha hai number 474,pos +sab theek hai alhamdulillah number 475,pos +bohat mazedar khana tha number 476,pos +yeh bohat acha din tha aj number 477,pos +mujhe yeh pasand nahi aya number 478,pos +aj mausam acha hai number 479,pos +kya haal hai bhai number 480,pos +yeh drama bilkul boring hai number 481,pos +yeh bohat acha din tha aj number 482,pos +sab theek hai alhamdulillah number 483,pos +sab theek hai alhamdulillah number 484,pos +yeh drama bilkul boring hai number 485,pos +sab theek hai alhamdulillah number 486,pos +bohat mazedar khana tha number 487,pos +kya haal hai bhai number 488,pos +aj mausam acha hai number 489,pos +aj mausam acha hai number 490,pos +sab theek hai alhamdulillah number 491,pos +yeh drama bilkul boring hai number 492,pos +kya haal hai bhai number 493,pos +mera dil khush hai number 494,pos +kya haal hai bhai number 495,pos +sab theek hai alhamdulillah number 496,pos +yeh drama bilkul boring hai number 497,pos +yeh drama bilkul boring hai number 498,pos +aj mausam acha hai number 499,pos diff --git a/tests/fixtures/contaminated.csv b/tests/fixtures/contaminated.csv new file mode 100644 index 0000000..c44d5d2 --- /dev/null +++ b/tests/fixtures/contaminated.csv @@ -0,0 +1,501 @@ +text,label +bohat mazedar khana tha number 10,pos +The food was very delicious number 99,pos +kya haal hai bhai number 21,pos +yeh drama bilkul boring hai number 262,pos +How are you brother number 18,pos +bohat mazedar khana tha number 328,pos +aj mausam acha hai number 204,pos +The weather is nice today number 51,pos +mera dil khush hai number 233,pos +mera dil khush hai number 393,pos +bohat mazedar khana tha number 385,pos +bohat mazedar khana tha number 96,pos +This was a great day today number 94,pos +This drama is quite boring number 0,pos +aj mausam acha hai number 128,pos +bohat mazedar khana tha number 81,pos +yeh bohat acha din tha aj number 4,pos +sab theek hai alhamdulillah number 64,pos +mujhe yeh pasand nahi aya number 82,pos +yeh bohat acha din tha aj number 134,pos +yeh drama bilkul boring hai number 369,pos +aj mausam acha hai number 279,pos +bohat mazedar khana tha number 336,pos +yeh drama bilkul boring hai number 260,pos +aj mausam acha hai number 232,pos +aj mausam acha hai number 240,pos +mera dil khush hai number 396,pos +aj mausam acha hai number 63,pos +sab theek hai alhamdulillah number 251,pos +yeh drama bilkul boring hai number 150,pos +yeh drama bilkul boring hai number 13,pos +sab theek hai alhamdulillah number 317,pos +mujhe yeh pasand nahi aya number 135,pos +sab theek hai alhamdulillah number 324,pos +mera dil khush hai number 374,pos +bohat mazedar khana tha number 213,pos +yeh bohat acha din tha aj number 94,pos +yeh bohat acha din tha aj number 226,pos +sab theek hai alhamdulillah number 372,pos +yeh bohat acha din tha aj number 88,pos +bohat mazedar khana tha number 343,pos +This was a great day today number 68,pos +This was a great day today number 62,pos +yeh drama bilkul boring hai number 186,pos +How are you brother number 26,pos +aj mausam acha hai number 109,pos +sab theek hai alhamdulillah number 39,pos +bohat mazedar khana tha number 282,pos +This was a great day today number 21,pos +This was a great day today number 57,pos +bohat mazedar khana tha number 248,pos +mujhe yeh pasand nahi aya number 149,pos +kya haal hai bhai number 216,pos +yeh drama bilkul boring hai number 137,pos +sab theek hai alhamdulillah number 41,pos +This was a great day today number 54,pos +This drama is quite boring number 25,pos +mera dil khush hai number 8,pos +yeh drama bilkul boring hai number 220,pos +yeh bohat acha din tha aj number 42,pos +sab theek hai alhamdulillah number 31,pos +mujhe yeh pasand nahi aya number 56,pos +aj mausam acha hai number 255,pos +mera dil khush hai number 177,pos +yeh bohat acha din tha aj number 357,pos +The weather is nice today number 58,pos +kya haal hai bhai number 296,pos +kya haal hai bhai number 285,pos +The weather is nice today number 19,pos +My heart is happy number 53,pos +My heart is happy number 55,pos +yeh drama bilkul boring hai number 249,pos +yeh drama bilkul boring hai number 206,pos +yeh bohat acha din tha aj number 219,pos +This was a great day today number 97,pos +aj mausam acha hai number 210,pos +aj mausam acha hai number 389,pos +aj mausam acha hai number 188,pos +kya haal hai bhai number 308,pos +mera dil khush hai number 155,pos +The food was very delicious number 28,pos +sab theek hai alhamdulillah number 189,pos +yeh bohat acha din tha aj number 203,pos +sab theek hai alhamdulillah number 104,pos +yeh bohat acha din tha aj number 48,pos +This drama is quite boring number 48,pos +mera dil khush hai number 375,pos +kya haal hai bhai number 307,pos +aj mausam acha hai number 75,pos +sab theek hai alhamdulillah number 215,pos +mujhe yeh pasand nahi aya number 30,pos +The weather is nice today number 11,pos +aj mausam acha hai number 348,pos +sab theek hai alhamdulillah number 280,pos +yeh drama bilkul boring hai number 365,pos +kya haal hai bhai number 71,pos +yeh drama bilkul boring hai number 90,pos +mujhe yeh pasand nahi aya number 131,pos +bohat mazedar khana tha number 6,pos +aj mausam acha hai number 70,pos +mujhe yeh pasand nahi aya number 333,pos +How are you brother number 87,pos +yeh bohat acha din tha aj number 185,pos +bohat mazedar khana tha number 275,pos +mera dil khush hai number 51,pos +mujhe yeh pasand nahi aya number 65,pos +mera dil khush hai number 271,pos +yeh bohat acha din tha aj number 1,pos +yeh bohat acha din tha aj number 127,pos +mujhe yeh pasand nahi aya number 299,pos +kya haal hai bhai number 383,pos +kya haal hai bhai number 243,pos +bohat mazedar khana tha number 133,pos +mera dil khush hai number 117,pos +sab theek hai alhamdulillah number 86,pos +kya haal hai bhai number 101,pos +mujhe yeh pasand nahi aya number 397,pos +aj mausam acha hai number 129,pos +bohat mazedar khana tha number 224,pos +yeh drama bilkul boring hai number 112,pos +sab theek hai alhamdulillah number 156,pos +aj mausam acha hai number 184,pos +yeh bohat acha din tha aj number 261,pos +The weather is nice today number 38,pos +The weather is nice today number 74,pos +mera dil khush hai number 160,pos +mera dil khush hai number 49,pos +aj mausam acha hai number 74,pos +mujhe yeh pasand nahi aya number 115,pos +bohat mazedar khana tha number 38,pos +yeh bohat acha din tha aj number 37,pos +This was a great day today number 46,pos +bohat mazedar khana tha number 35,pos +The weather is nice today number 85,pos +yeh drama bilkul boring hai number 301,pos +yeh drama bilkul boring hai number 364,pos +mera dil khush hai number 126,pos +kya haal hai bhai number 187,pos +This was a great day today number 27,pos +yeh bohat acha din tha aj number 217,pos +mera dil khush hai number 17,pos +aj mausam acha hai number 183,pos +This was a great day today number 24,pos +yeh bohat acha din tha aj number 346,pos +yeh drama bilkul boring hai number 113,pos +yeh bohat acha din tha aj number 222,pos +My heart is happy number 61,pos +kya haal hai bhai number 253,pos +kya haal hai bhai number 325,pos +This drama is quite boring number 86,pos +This was a great day today number 89,pos +mujhe yeh pasand nahi aya number 358,pos +bohat mazedar khana tha number 335,pos +aj mausam acha hai number 257,pos +kya haal hai bhai number 287,pos +The food was very delicious number 29,pos +This was a great day today number 69,pos +mera dil khush hai number 229,pos +bohat mazedar khana tha number 111,pos +aj mausam acha hai number 341,pos +mera dil khush hai number 172,pos +mera dil khush hai number 53,pos +This drama is quite boring number 81,pos +mera dil khush hai number 197,pos +mera dil khush hai number 293,pos +yeh drama bilkul boring hai number 123,pos +mera dil khush hai number 40,pos +kya haal hai bhai number 283,pos +How are you brother number 98,pos +This drama is quite boring number 82,pos +mujhe yeh pasand nahi aya number 61,pos +yeh drama bilkul boring hai number 278,pos +aj mausam acha hai number 250,pos +How are you brother number 66,pos +How are you brother number 49,pos +yeh bohat acha din tha aj number 234,pos +mujhe yeh pasand nahi aya number 77,pos +How are you brother number 75,pos +bohat mazedar khana tha number 166,pos +bohat mazedar khana tha number 142,pos +The weather is nice today number 6,pos +yeh drama bilkul boring hai number 258,pos +This was a great day today number 43,pos +bohat mazedar khana tha number 334,pos +sab theek hai alhamdulillah number 26,pos +My heart is happy number 20,pos +yeh drama bilkul boring hai number 32,pos +My heart is happy number 73,pos +sab theek hai alhamdulillah number 339,pos +bohat mazedar khana tha number 237,pos +bohat mazedar khana tha number 360,pos +aj mausam acha hai number 43,pos +aj mausam acha hai number 118,pos +mera dil khush hai number 122,pos +kya haal hai bhai number 338,pos +yeh bohat acha din tha aj number 382,pos +mujhe yeh pasand nahi aya number 345,pos +This drama is quite boring number 5,pos +How are you brother number 14,pos +yeh bohat acha din tha aj number 124,pos +kya haal hai bhai number 221,pos +yeh drama bilkul boring hai number 83,pos +kya haal hai bhai number 201,pos +yeh bohat acha din tha aj number 359,pos +bohat mazedar khana tha number 305,pos +mera dil khush hai number 391,pos +yeh bohat acha din tha aj number 46,pos +yeh drama bilkul boring hai number 100,pos +yeh drama bilkul boring hai number 93,pos +kya haal hai bhai number 318,pos +bohat mazedar khana tha number 244,pos +How are you brother number 67,pos +mera dil khush hai number 337,pos +The food was very delicious number 71,pos +kya haal hai bhai number 120,pos +yeh drama bilkul boring hai number 223,pos +yeh bohat acha din tha aj number 331,pos +mujhe yeh pasand nahi aya number 368,pos +aj mausam acha hai number 298,pos +aj mausam acha hai number 175,pos +aj mausam acha hai number 395,pos +bohat mazedar khana tha number 116,pos +bohat mazedar khana tha number 24,pos +mujhe yeh pasand nahi aya number 230,pos +mujhe yeh pasand nahi aya number 178,pos +mera dil khush hai number 205,pos +sab theek hai alhamdulillah number 208,pos +yeh drama bilkul boring hai number 303,pos +kya haal hai bhai number 367,pos +kya haal hai bhai number 290,pos +This drama is quite boring number 50,pos +aj mausam acha hai number 195,pos +bohat mazedar khana tha number 193,pos +yeh bohat acha din tha aj number 20,pos +yeh bohat acha din tha aj number 136,pos +sab theek hai alhamdulillah number 207,pos +sab theek hai alhamdulillah number 386,pos +bohat mazedar khana tha number 194,pos +bohat mazedar khana tha number 182,pos +This drama is quite boring number 65,pos +yeh bohat acha din tha aj number 209,pos +sab theek hai alhamdulillah number 85,pos +kya haal hai bhai number 390,pos +yeh bohat acha din tha aj number 91,pos +The weather is nice today number 77,pos +mera dil khush hai number 114,pos +kya haal hai bhai number 276,pos +mera dil khush hai number 176,pos +yeh drama bilkul boring hai number 214,pos +My heart is happy number 36,pos +mujhe yeh pasand nahi aya number 151,pos +yeh bohat acha din tha aj number 228,pos +kya haal hai bhai number 152,pos +aj mausam acha hai number 180,pos +aj mausam acha hai number 45,pos +bohat mazedar khana tha number 200,pos +My heart is happy number 72,pos +mera dil khush hai number 306,pos +bohat mazedar khana tha number 27,pos +kya haal hai bhai number 196,pos +mera dil khush hai number 54,pos +yeh drama bilkul boring hai number 265,pos +sab theek hai alhamdulillah number 241,pos +This was a great day today number 2,pos +The weather is nice today number 63,pos +mera dil khush hai number 25,pos +yeh drama bilkul boring hai number 332,pos +mujhe yeh pasand nahi aya number 363,pos +yeh bohat acha din tha aj number 297,pos +mera dil khush hai number 36,pos +mujhe yeh pasand nahi aya number 87,pos +mujhe yeh pasand nahi aya number 125,pos +mujhe yeh pasand nahi aya number 145,pos +sab theek hai alhamdulillah number 72,pos +yeh bohat acha din tha aj number 138,pos +mujhe yeh pasand nahi aya number 379,pos +The food was very delicious number 30,pos +mujhe yeh pasand nahi aya number 277,pos +mera dil khush hai number 316,pos +sab theek hai alhamdulillah number 302,pos +mujhe yeh pasand nahi aya number 263,pos +aj mausam acha hai number 7,pos +My heart is happy number 10,pos +The food was very delicious number 95,pos +bohat mazedar khana tha number 80,pos +sab theek hai alhamdulillah number 366,pos +mujhe yeh pasand nahi aya number 349,pos +This drama is quite boring number 96,pos +yeh drama bilkul boring hai number 225,pos +kya haal hai bhai number 163,pos +mujhe yeh pasand nahi aya number 272,pos +aj mausam acha hai number 141,pos +sab theek hai alhamdulillah number 146,pos +aj mausam acha hai number 98,pos +mera dil khush hai number 102,pos +kya haal hai bhai number 164,pos +This was a great day today number 88,pos +mujhe yeh pasand nahi aya number 300,pos +mujhe yeh pasand nahi aya number 378,pos +sab theek hai alhamdulillah number 11,pos +This drama is quite boring number 76,pos +sab theek hai alhamdulillah number 381,pos +bohat mazedar khana tha number 52,pos +This was a great day today number 32,pos +mera dil khush hai number 239,pos +My heart is happy number 8,pos +The food was very delicious number 39,pos +yeh bohat acha din tha aj number 354,pos +kya haal hai bhai number 22,pos +yeh drama bilkul boring hai number 159,pos +mujhe yeh pasand nahi aya number 2,pos +My heart is happy number 22,pos +kya haal hai bhai number 267,pos +mera dil khush hai number 198,pos +yeh drama bilkul boring hai number 388,pos +sab theek hai alhamdulillah number 394,pos +aj mausam acha hai number 105,pos +kya haal hai bhai number 67,pos +yeh bohat acha din tha aj number 264,pos +yeh drama bilkul boring hai number 50,pos +aj mausam acha hai number 73,pos +sab theek hai alhamdulillah number 167,pos +mujhe yeh pasand nahi aya number 158,pos +sab theek hai alhamdulillah number 340,pos +yeh bohat acha din tha aj number 329,pos +The food was very delicious number 41,pos +bohat mazedar khana tha number 97,pos +mujhe yeh pasand nahi aya number 78,pos +aj mausam acha hai number 256,pos +The weather is nice today number 79,pos +This drama is quite boring number 44,pos +How are you brother number 15,pos +sab theek hai alhamdulillah number 227,pos +yeh drama bilkul boring hai number 47,pos +My heart is happy number 23,pos +mera dil khush hai number 19,pos +sab theek hai alhamdulillah number 191,pos +bohat mazedar khana tha number 57,pos +The food was very delicious number 1,pos +sab theek hai alhamdulillah number 342,pos +How are you brother number 91,pos +bohat mazedar khana tha number 110,pos +aj mausam acha hai number 154,pos +yeh drama bilkul boring hai number 231,pos +kya haal hai bhai number 190,pos +sab theek hai alhamdulillah number 121,pos +My heart is happy number 56,pos +This drama is quite boring number 80,pos +sab theek hai alhamdulillah number 384,pos +aj mausam acha hai number 139,pos +aj mausam acha hai number 16,pos +kya haal hai bhai number 376,pos +The food was very delicious number 17,pos +bohat mazedar khana tha number 59,pos +kya haal hai bhai number 304,pos +yeh drama bilkul boring hai number 95,pos +yeh bohat acha din tha aj number 199,pos +yeh drama bilkul boring hai number 310,pos +The food was very delicious number 84,pos +aj mausam acha hai number 84,pos +bohat mazedar khana tha number 273,pos +The food was very delicious number 42,pos +yeh bohat acha din tha aj number 192,pos +kya haal hai bhai number 398,pos +mujhe yeh pasand nahi aya number 15,pos +kya haal hai bhai number 143,pos +aj mausam acha hai number 76,pos +yeh bohat acha din tha aj number 33,pos +This drama is quite boring number 64,pos +mujhe yeh pasand nahi aya number 399,pos +yeh bohat acha din tha aj number 350,pos +aj mausam acha hai number 295,pos +This drama is quite boring number 37,pos +mujhe yeh pasand nahi aya number 9,pos +mera dil khush hai number 387,pos +bohat mazedar khana tha number 284,pos +mujhe yeh pasand nahi aya number 161,pos +mujhe yeh pasand nahi aya number 347,pos +kya haal hai bhai number 371,pos +kya haal hai bhai number 289,pos +The weather is nice today number 16,pos +How are you brother number 59,pos +mera dil khush hai number 28,pos +aj mausam acha hai number 380,pos +This drama is quite boring number 33,pos +mujhe yeh pasand nahi aya number 236,pos +bohat mazedar khana tha number 171,pos +mujhe yeh pasand nahi aya number 274,pos +yeh drama bilkul boring hai number 235,pos +kya haal hai bhai number 321,pos +aj mausam acha hai number 79,pos +yeh bohat acha din tha aj number 246,pos +mujhe yeh pasand nahi aya number 69,pos +mujhe yeh pasand nahi aya number 330,pos +mera dil khush hai number 18,pos +mera dil khush hai number 242,pos +sab theek hai alhamdulillah number 245,pos +mujhe yeh pasand nahi aya number 344,pos +yeh drama bilkul boring hai number 173,pos +bohat mazedar khana tha number 169,pos +My heart is happy number 47,pos +yeh bohat acha din tha aj number 89,pos +aj mausam acha hai number 14,pos +My heart is happy number 35,pos +aj mausam acha hai number 291,pos +The weather is nice today number 78,pos +yeh drama bilkul boring hai number 202,pos +mujhe yeh pasand nahi aya number 174,pos +This drama is quite boring number 31,pos +mera dil khush hai number 351,pos +bohat mazedar khana tha number 58,pos +kya haal hai bhai number 3,pos +mera dil khush hai number 392,pos +sab theek hai alhamdulillah number 165,pos +kya haal hai bhai number 281,pos +bohat mazedar khana tha number 259,pos +kya haal hai bhai number 153,pos +yeh bohat acha din tha aj number 157,pos +aj mausam acha hai number 34,pos +How are you brother number 4,pos +mujhe yeh pasand nahi aya number 130,pos +yeh bohat acha din tha aj number 144,pos +sab theek hai alhamdulillah number 353,pos +yeh bohat acha din tha aj number 103,pos +bohat mazedar khana tha number 327,pos +aj mausam acha hai number 5,pos +yeh drama bilkul boring hai number 108,pos +kya haal hai bhai number 326,pos +This was a great day today number 12,pos +yeh drama bilkul boring hai number 286,pos +mujhe yeh pasand nahi aya number 179,pos +bohat mazedar khana tha number 170,pos +yeh bohat acha din tha aj number 23,pos +How are you brother number 92,pos +bohat mazedar khana tha number 212,pos +aj mausam acha hai number 315,pos +My heart is happy number 9,pos +kya haal hai bhai number 106,pos +This was a great day today number 70,pos +kya haal hai bhai number 377,pos +This drama is quite boring number 45,pos +My heart is happy number 7,pos +aj mausam acha hai number 320,pos +mujhe yeh pasand nahi aya number 238,pos +kya haal hai bhai number 12,pos +kya haal hai bhai number 60,pos +sab theek hai alhamdulillah number 0,pos +yeh bohat acha din tha aj number 99,pos +bohat mazedar khana tha number 148,pos +sab theek hai alhamdulillah number 362,pos +sab theek hai alhamdulillah number 119,pos +bohat mazedar khana tha number 312,pos +This drama is quite boring number 52,pos +kya haal hai bhai number 92,pos +The food was very delicious number 13,pos +mujhe yeh pasand nahi aya number 252,pos +This was a great day today number 60,pos +sab theek hai alhamdulillah number 323,pos +My heart is happy number 83,pos +bohat mazedar khana tha number 266,pos +yeh bohat acha din tha aj number 254,pos +mujhe yeh pasand nahi aya number 288,pos +yeh bohat acha din tha aj number 314,pos +mera dil khush hai number 66,pos +aj mausam acha hai number 181,pos +sab theek hai alhamdulillah number 319,pos +kya haal hai bhai number 294,pos +The food was very delicious number 93,pos +mera dil khush hai number 132,pos +mujhe yeh pasand nahi aya number 162,pos +The food was very delicious number 34,pos +bohat mazedar khana tha number 311,pos +mujhe yeh pasand nahi aya number 218,pos +mera dil khush hai number 147,pos +yeh drama bilkul boring hai number 361,pos +My heart is happy number 3,pos +yeh bohat acha din tha aj number 309,pos +sab theek hai alhamdulillah number 352,pos +yeh bohat acha din tha aj number 370,pos +yeh bohat acha din tha aj number 247,pos +mujhe yeh pasand nahi aya number 44,pos +kya haal hai bhai number 270,pos +mujhe yeh pasand nahi aya number 322,pos +sab theek hai alhamdulillah number 373,pos +mera dil khush hai number 292,pos +bohat mazedar khana tha number 55,pos +yeh bohat acha din tha aj number 29,pos +bohat mazedar khana tha number 313,pos +How are you brother number 90,pos +mujhe yeh pasand nahi aya number 356,pos +kya haal hai bhai number 107,pos +aj mausam acha hai number 268,pos +bohat mazedar khana tha number 211,pos +mujhe yeh pasand nahi aya number 269,pos +mujhe yeh pasand nahi aya number 168,pos +kya haal hai bhai number 140,pos +The food was very delicious number 40,pos +bohat mazedar khana tha number 355,pos +mera dil khush hai number 62,pos +kya haal hai bhai number 68,pos diff --git a/tests/fixtures/dirty_dataset.csv b/tests/fixtures/dirty_dataset.csv new file mode 100644 index 0000000..c0a529a --- /dev/null +++ b/tests/fixtures/dirty_dataset.csv @@ -0,0 +1,501 @@ +text,label +Valid sentence number 202 with real content here,pos +hi,pos +Valid sentence number 114 with real content here,pos +Valid sentence number 233 with real content here,pos +Valid sentence number 277 with real content here,pos +,pos +Valid sentence number 110 with real content here,pos +Valid sentence number 79 with real content here,pos +Valid sentence number 105 with real content here,pos +Valid sentence number 32 with real content here,pos +Valid sentence number 106 with real content here,pos +Valid sentence number 343 with real content here,pos + ,pos +Valid sentence number 255 with real content here,pos +Valid sentence number 279 with real content here,pos +,pos +Valid sentence number 261 with real content here,pos + ,pos +Valid sentence number 217 with real content here,pos +Valid sentence number 183 with real content here,pos +Valid sentence number 269 with real content here,pos +Valid sentence number 419 with real content here,pos +Valid sentence number 291 with real content here,pos +,pos +Valid sentence number 267 with real content here,pos +Valid sentence number 422 with real content here,pos + ,pos +Valid sentence number 72 with real content here,pos +Valid sentence number 341 with real content here,pos +Valid sentence number 69 with real content here,pos +Valid sentence number 25 with real content here,pos +Valid sentence number 227 with real content here,pos +Valid sentence number 167 with real content here,pos +Valid sentence number 71 with real content here,pos +Valid sentence number 245 with real content here,pos +Valid sentence number 208 with real content here,pos +,pos +Valid sentence number 113 with real content here,pos +,pos +Valid sentence number 388 with real content here,pos +Valid sentence number 58 with real content here,pos +Valid sentence number 84 with real content here,pos +Valid sentence number 212 with real content here,pos +Valid sentence number 41 with real content here,pos +Valid sentence number 311 with real content here,pos +Valid sentence number 100 with real content here,pos +Valid sentence number 159 with real content here,pos +Valid sentence number 205 with real content here,pos +Valid sentence number 278 with real content here,pos +Valid sentence number 424 with real content here,pos +Valid sentence number 68 with real content here,pos +,pos +Valid sentence number 157 with real content here,pos +Valid sentence number 359 with real content here,pos +,pos +Valid sentence number 65 with real content here,pos +hi,pos +Valid sentence number 108 with real content here,pos +,pos + ,pos +Valid sentence number 40 with real content here,pos +Valid sentence number 187 with real content here,pos +,pos +Valid sentence number 28 with real content here,pos +Valid sentence number 46 with real content here,pos +Valid sentence number 403 with real content here,pos +Valid sentence number 249 with real content here,pos +Valid sentence number 231 with real content here,pos +Valid sentence number 104 with real content here,pos +Valid sentence number 384 with real content here,pos +Valid sentence number 144 with real content here,pos +Valid sentence number 340 with real content here,pos +Valid sentence number 193 with real content here,pos +Valid sentence number 307 with real content here,pos +Valid sentence number 63 with real content here,pos +Valid sentence number 381 with real content here,pos +Valid sentence number 389 with real content here,pos +Valid sentence number 95 with real content here,pos +Valid sentence number 264 with real content here,pos +Valid sentence number 368 with real content here,pos +,pos +Valid sentence number 360 with real content here,pos +hi,pos +Valid sentence number 81 with real content here,pos +Valid sentence number 153 with real content here,pos +Valid sentence number 411 with real content here,pos +Valid sentence number 162 with real content here,pos +Valid sentence number 60 with real content here,pos +Valid sentence number 88 with real content here,pos +Valid sentence number 118 with real content here,pos +Valid sentence number 156 with real content here,pos +Valid sentence number 126 with real content here,pos +Valid sentence number 364 with real content here,pos +Valid sentence number 90 with real content here,pos +Valid sentence number 426 with real content here,pos + ,pos +Valid sentence number 97 with real content here,pos +Valid sentence number 238 with real content here,pos +Valid sentence number 257 with real content here,pos +Valid sentence number 185 with real content here,pos +Valid sentence number 2 with real content here,pos +Valid sentence number 246 with real content here,pos +,pos +Valid sentence number 190 with real content here,pos +,pos +Valid sentence number 80 with real content here,pos +Valid sentence number 101 with real content here,pos +Valid sentence number 373 with real content here,pos +Valid sentence number 241 with real content here,pos +hi,pos +Valid sentence number 412 with real content here,pos +Valid sentence number 436 with real content here,pos +Valid sentence number 329 with real content here,pos +Valid sentence number 163 with real content here,pos +Valid sentence number 70 with real content here,pos +Valid sentence number 321 with real content here,pos +Valid sentence number 429 with real content here,pos +Valid sentence number 213 with real content here,pos +Valid sentence number 331 with real content here,pos +Valid sentence number 96 with real content here,pos +Valid sentence number 158 with real content here,pos +Valid sentence number 353 with real content here,pos +Valid sentence number 15 with real content here,pos +Valid sentence number 8 with real content here,pos +,pos +Valid sentence number 22 with real content here,pos +Valid sentence number 75 with real content here,pos +Valid sentence number 152 with real content here,pos +Valid sentence number 334 with real content here,pos +Valid sentence number 297 with real content here,pos +Valid sentence number 431 with real content here,pos +Valid sentence number 166 with real content here,pos +Valid sentence number 83 with real content here,pos +Valid sentence number 286 with real content here,pos +Valid sentence number 391 with real content here,pos +Valid sentence number 109 with real content here,pos +Valid sentence number 235 with real content here,pos +,pos +Valid sentence number 308 with real content here,pos +Valid sentence number 339 with real content here,pos +Valid sentence number 320 with real content here,pos +Valid sentence number 234 with real content here,pos +hi,pos +Valid sentence number 418 with real content here,pos +Valid sentence number 116 with real content here,pos +Valid sentence number 24 with real content here,pos +Valid sentence number 177 with real content here,pos +Valid sentence number 323 with real content here,pos +Valid sentence number 314 with real content here,pos +Valid sentence number 3 with real content here,pos +Valid sentence number 33 with real content here,pos +Valid sentence number 316 with real content here,pos +Valid sentence number 11 with real content here,pos +Valid sentence number 425 with real content here,pos +Valid sentence number 173 with real content here,pos +Valid sentence number 182 with real content here,pos +Valid sentence number 332 with real content here,pos +Valid sentence number 342 with real content here,pos +hi,pos +Valid sentence number 395 with real content here,pos +hi,pos +Valid sentence number 303 with real content here,pos +Valid sentence number 230 with real content here,pos +Valid sentence number 214 with real content here,pos +Valid sentence number 428 with real content here,pos +Valid sentence number 274 with real content here,pos +Valid sentence number 290 with real content here,pos +Valid sentence number 247 with real content here,pos +Valid sentence number 206 with real content here,pos +Valid sentence number 357 with real content here,pos +Valid sentence number 224 with real content here,pos + ,pos +Valid sentence number 191 with real content here,pos +Valid sentence number 433 with real content here,pos +Valid sentence number 115 with real content here,pos +Valid sentence number 219 with real content here,pos +Valid sentence number 127 with real content here,pos +Valid sentence number 415 with real content here,pos +Valid sentence number 164 with real content here,pos +Valid sentence number 252 with real content here,pos +Valid sentence number 420 with real content here,pos +Valid sentence number 256 with real content here,pos +Valid sentence number 250 with real content here,pos +,pos +Valid sentence number 151 with real content here,pos +Valid sentence number 184 with real content here,pos +Valid sentence number 352 with real content here,pos +Valid sentence number 365 with real content here,pos +Valid sentence number 265 with real content here,pos +Valid sentence number 285 with real content here,pos +Valid sentence number 203 with real content here,pos +Valid sentence number 188 with real content here,pos +hi,pos +Valid sentence number 292 with real content here,pos +Valid sentence number 366 with real content here,pos +Valid sentence number 124 with real content here,pos + ,pos +Valid sentence number 367 with real content here,pos +Valid sentence number 223 with real content here,pos +Valid sentence number 399 with real content here,pos +Valid sentence number 346 with real content here,pos +Valid sentence number 178 with real content here,pos +Valid sentence number 263 with real content here,pos +Valid sentence number 48 with real content here,pos +hi,pos +Valid sentence number 392 with real content here,pos +Valid sentence number 10 with real content here,pos +Valid sentence number 402 with real content here,pos +Valid sentence number 45 with real content here,pos +Valid sentence number 51 with real content here,pos +,pos +,pos +Valid sentence number 410 with real content here,pos + ,pos +Valid sentence number 117 with real content here,pos +hi,pos +Valid sentence number 20 with real content here,pos +Valid sentence number 87 with real content here,pos +Valid sentence number 300 with real content here,pos +Valid sentence number 259 with real content here,pos +Valid sentence number 93 with real content here,pos +Valid sentence number 23 with real content here,pos +Valid sentence number 351 with real content here,pos +Valid sentence number 369 with real content here,pos +Valid sentence number 14 with real content here,pos +Valid sentence number 283 with real content here,pos +,pos +Valid sentence number 174 with real content here,pos +Valid sentence number 393 with real content here,pos +Valid sentence number 281 with real content here,pos +Valid sentence number 137 with real content here,pos +Valid sentence number 327 with real content here,pos +Valid sentence number 294 with real content here,pos +Valid sentence number 370 with real content here,pos +Valid sentence number 244 with real content here,pos +Valid sentence number 209 with real content here,pos +Valid sentence number 427 with real content here,pos +Valid sentence number 325 with real content here,pos +hi,pos +,pos +Valid sentence number 356 with real content here,pos +Valid sentence number 421 with real content here,pos +Valid sentence number 282 with real content here,pos +Valid sentence number 207 with real content here,pos +Valid sentence number 260 with real content here,pos +Valid sentence number 186 with real content here,pos +Valid sentence number 216 with real content here,pos +Valid sentence number 103 with real content here,pos +Valid sentence number 275 with real content here,pos +Valid sentence number 122 with real content here,pos +Valid sentence number 125 with real content here,pos +Valid sentence number 197 with real content here,pos +hi,pos +Valid sentence number 362 with real content here,pos +Valid sentence number 298 with real content here,pos +Valid sentence number 1 with real content here,pos +Valid sentence number 350 with real content here,pos +Valid sentence number 168 with real content here,pos +Valid sentence number 434 with real content here,pos + ,pos +Valid sentence number 380 with real content here,pos +Valid sentence number 19 with real content here,pos +Valid sentence number 0 with real content here,pos +Valid sentence number 76 with real content here,pos +Valid sentence number 254 with real content here,pos +Valid sentence number 9 with real content here,pos +Valid sentence number 330 with real content here,pos +Valid sentence number 363 with real content here,pos +Valid sentence number 36 with real content here,pos + ,pos +Valid sentence number 324 with real content here,pos +Valid sentence number 52 with real content here,pos +Valid sentence number 310 with real content here,pos +Valid sentence number 226 with real content here,pos +Valid sentence number 54 with real content here,pos +Valid sentence number 318 with real content here,pos +Valid sentence number 220 with real content here,pos +Valid sentence number 276 with real content here,pos +Valid sentence number 73 with real content here,pos +Valid sentence number 55 with real content here,pos +Valid sentence number 284 with real content here,pos +Valid sentence number 287 with real content here,pos +Valid sentence number 201 with real content here,pos +Valid sentence number 102 with real content here,pos +Valid sentence number 251 with real content here,pos +Valid sentence number 35 with real content here,pos +Valid sentence number 407 with real content here,pos +Valid sentence number 91 with real content here,pos +Valid sentence number 397 with real content here,pos +Valid sentence number 132 with real content here,pos +Valid sentence number 30 with real content here,pos +Valid sentence number 170 with real content here,pos +Valid sentence number 198 with real content here,pos +Valid sentence number 406 with real content here,pos + ,pos +Valid sentence number 348 with real content here,pos +Valid sentence number 37 with real content here,pos +Valid sentence number 82 with real content here,pos +,pos +Valid sentence number 165 with real content here,pos +Valid sentence number 218 with real content here,pos +Valid sentence number 141 with real content here,pos +hi,pos +Valid sentence number 38 with real content here,pos +Valid sentence number 239 with real content here,pos +hi,pos +,pos +Valid sentence number 313 with real content here,pos +Valid sentence number 56 with real content here,pos +Valid sentence number 94 with real content here,pos +Valid sentence number 289 with real content here,pos +Valid sentence number 192 with real content here,pos +Valid sentence number 66 with real content here,pos +Valid sentence number 438 with real content here,pos +Valid sentence number 44 with real content here,pos +Valid sentence number 61 with real content here,pos +Valid sentence number 62 with real content here,pos +Valid sentence number 306 with real content here,pos +Valid sentence number 111 with real content here,pos +Valid sentence number 416 with real content here,pos +Valid sentence number 29 with real content here,pos +Valid sentence number 47 with real content here,pos +Valid sentence number 317 with real content here,pos +Valid sentence number 12 with real content here,pos +Valid sentence number 17 with real content here,pos +Valid sentence number 98 with real content here,pos +Valid sentence number 128 with real content here,pos +Valid sentence number 145 with real content here,pos +Valid sentence number 112 with real content here,pos +Valid sentence number 179 with real content here,pos +Valid sentence number 432 with real content here,pos +Valid sentence number 53 with real content here,pos +Valid sentence number 268 with real content here,pos +Valid sentence number 354 with real content here,pos +Valid sentence number 210 with real content here,pos +Valid sentence number 374 with real content here,pos +Valid sentence number 34 with real content here,pos +Valid sentence number 4 with real content here,pos +hi,pos +Valid sentence number 280 with real content here,pos +Valid sentence number 160 with real content here,pos +Valid sentence number 423 with real content here,pos +Valid sentence number 172 with real content here,pos +Valid sentence number 266 with real content here,pos +Valid sentence number 99 with real content here,pos +Valid sentence number 301 with real content here,pos +Valid sentence number 344 with real content here,pos +Valid sentence number 123 with real content here,pos +Valid sentence number 345 with real content here,pos +Valid sentence number 236 with real content here,pos +Valid sentence number 200 with real content here,pos +Valid sentence number 299 with real content here,pos +Valid sentence number 335 with real content here,pos +Valid sentence number 130 with real content here,pos +Valid sentence number 50 with real content here,pos +Valid sentence number 136 with real content here,pos +Valid sentence number 138 with real content here,pos +Valid sentence number 171 with real content here,pos +Valid sentence number 139 with real content here,pos +Valid sentence number 333 with real content here,pos +Valid sentence number 312 with real content here,pos +Valid sentence number 221 with real content here,pos +Valid sentence number 181 with real content here,pos +Valid sentence number 405 with real content here,pos +Valid sentence number 396 with real content here,pos +Valid sentence number 49 with real content here,pos +Valid sentence number 21 with real content here,pos +Valid sentence number 387 with real content here,pos +Valid sentence number 376 with real content here,pos +Valid sentence number 161 with real content here,pos +Valid sentence number 347 with real content here,pos +Valid sentence number 195 with real content here,pos +Valid sentence number 229 with real content here,pos +Valid sentence number 147 with real content here,pos +Valid sentence number 6 with real content here,pos +Valid sentence number 222 with real content here,pos +Valid sentence number 271 with real content here,pos +Valid sentence number 417 with real content here,pos +Valid sentence number 134 with real content here,pos + ,pos +Valid sentence number 199 with real content here,pos +Valid sentence number 361 with real content here,pos +Valid sentence number 349 with real content here,pos +Valid sentence number 194 with real content here,pos +Valid sentence number 119 with real content here,pos +Valid sentence number 272 with real content here,pos +Valid sentence number 430 with real content here,pos +Valid sentence number 382 with real content here,pos +Valid sentence number 390 with real content here,pos +Valid sentence number 154 with real content here,pos +Valid sentence number 243 with real content here,pos +Valid sentence number 204 with real content here,pos +Valid sentence number 237 with real content here,pos +Valid sentence number 404 with real content here,pos +,pos +Valid sentence number 59 with real content here,pos +Valid sentence number 386 with real content here,pos +Valid sentence number 135 with real content here,pos +Valid sentence number 328 with real content here,pos +Valid sentence number 27 with real content here,pos +Valid sentence number 176 with real content here,pos +hi,pos +Valid sentence number 295 with real content here,pos +Valid sentence number 107 with real content here,pos +hi,pos +Valid sentence number 326 with real content here,pos +Valid sentence number 371 with real content here,pos +Valid sentence number 225 with real content here,pos +Valid sentence number 338 with real content here,pos +Valid sentence number 121 with real content here,pos +Valid sentence number 196 with real content here,pos +Valid sentence number 394 with real content here,pos +Valid sentence number 211 with real content here,pos +Valid sentence number 385 with real content here,pos +Valid sentence number 253 with real content here,pos +Valid sentence number 78 with real content here,pos +Valid sentence number 304 with real content here,pos +Valid sentence number 74 with real content here,pos +Valid sentence number 43 with real content here,pos +hi,pos +Valid sentence number 16 with real content here,pos +Valid sentence number 270 with real content here,pos +Valid sentence number 409 with real content here,pos +Valid sentence number 92 with real content here,pos +,pos +Valid sentence number 120 with real content here,pos +Valid sentence number 358 with real content here,pos +Valid sentence number 400 with real content here,pos + ,pos +Valid sentence number 437 with real content here,pos +Valid sentence number 413 with real content here,pos +Valid sentence number 189 with real content here,pos +Valid sentence number 228 with real content here,pos +Valid sentence number 337 with real content here,pos +Valid sentence number 77 with real content here,pos +Valid sentence number 378 with real content here,pos +Valid sentence number 302 with real content here,pos +Valid sentence number 89 with real content here,pos +Valid sentence number 309 with real content here,pos +Valid sentence number 57 with real content here,pos +Valid sentence number 379 with real content here,pos +Valid sentence number 7 with real content here,pos +Valid sentence number 131 with real content here,pos +Valid sentence number 439 with real content here,pos +Valid sentence number 140 with real content here,pos +Valid sentence number 143 with real content here,pos +Valid sentence number 315 with real content here,pos +Valid sentence number 67 with real content here,pos +Valid sentence number 129 with real content here,pos +Valid sentence number 142 with real content here,pos + ,pos +Valid sentence number 435 with real content here,pos +Valid sentence number 39 with real content here,pos +Valid sentence number 258 with real content here,pos +Valid sentence number 64 with real content here,pos +Valid sentence number 42 with real content here,pos +Valid sentence number 248 with real content here,pos +Valid sentence number 146 with real content here,pos +Valid sentence number 13 with real content here,pos +Valid sentence number 319 with real content here,pos +Valid sentence number 377 with real content here,pos +Valid sentence number 414 with real content here,pos +Valid sentence number 149 with real content here,pos +Valid sentence number 336 with real content here,pos +Valid sentence number 26 with real content here,pos +hi,pos +Valid sentence number 86 with real content here,pos +Valid sentence number 296 with real content here,pos +Valid sentence number 242 with real content here,pos +Valid sentence number 322 with real content here,pos +Valid sentence number 31 with real content here,pos +Valid sentence number 133 with real content here,pos +Valid sentence number 288 with real content here,pos +Valid sentence number 401 with real content here,pos +Valid sentence number 372 with real content here,pos +Valid sentence number 155 with real content here,pos +Valid sentence number 383 with real content here,pos +Valid sentence number 305 with real content here,pos + ,pos +Valid sentence number 355 with real content here,pos +Valid sentence number 18 with real content here,pos +Valid sentence number 85 with real content here,pos +Valid sentence number 148 with real content here,pos +Valid sentence number 150 with real content here,pos +Valid sentence number 408 with real content here,pos +Valid sentence number 180 with real content here,pos +Valid sentence number 215 with real content here,pos +Valid sentence number 169 with real content here,pos +Valid sentence number 375 with real content here,pos +Valid sentence number 293 with real content here,pos +hi,pos +,pos +Valid sentence number 262 with real content here,pos +Valid sentence number 232 with real content here,pos +Valid sentence number 240 with real content here,pos +Valid sentence number 5 with real content here,pos +Valid sentence number 398 with real content here,pos +Valid sentence number 273 with real content here,pos +Valid sentence number 175 with real content here,pos +,pos diff --git a/tests/fixtures/high_confidence.csv b/tests/fixtures/high_confidence.csv new file mode 100644 index 0000000..db130f2 --- /dev/null +++ b/tests/fixtures/high_confidence.csv @@ -0,0 +1,501 @@ +text,label,confidence +sample 0,pos,0.73 +sample 1,pos,0.84 +sample 2,pos,0.77 +sample 3,pos,0.89 +sample 4,pos,0.76 +sample 5,pos,0.82 +sample 6,pos,0.84 +sample 7,pos,0.77 +sample 8,pos,0.81 +sample 9,pos,0.79 +sample 10,pos,0.81 +sample 11,pos,0.72 +sample 12,pos,0.87 +sample 13,pos,0.79 +sample 14,pos,0.74 +sample 15,pos,0.85 +sample 16,pos,0.83 +sample 17,pos,0.93 +sample 18,pos,0.77 +sample 19,pos,0.8 +sample 20,pos,0.76 +sample 21,pos,0.94 +sample 22,pos,0.99 +sample 23,pos,0.97 +sample 24,pos,0.88 +sample 25,pos,0.87 +sample 26,pos,0.78 +sample 27,pos,0.83 +sample 28,pos,0.86 +sample 29,pos,0.96 +sample 30,pos,0.77 +sample 31,pos,0.85 +sample 32,pos,0.84 +sample 33,pos,0.71 +sample 34,pos,0.83 +sample 35,pos,0.96 +sample 36,pos,0.78 +sample 37,pos,0.84 +sample 38,pos,0.77 +sample 39,pos,0.98 +sample 40,pos,0.98 +sample 41,pos,0.97 +sample 42,pos,0.97 +sample 43,pos,0.83 +sample 44,pos,0.72 +sample 45,pos,1.0 +sample 46,pos,0.92 +sample 47,pos,0.86 +sample 48,pos,0.83 +sample 49,pos,0.82 +sample 50,pos,0.94 +sample 51,pos,0.91 +sample 52,pos,0.74 +sample 53,pos,0.85 +sample 54,pos,0.73 +sample 55,pos,0.93 +sample 56,pos,0.91 +sample 57,pos,0.83 +sample 58,pos,0.77 +sample 59,pos,0.81 +sample 60,pos,0.78 +sample 61,pos,1.0 +sample 62,pos,0.71 +sample 63,pos,0.9 +sample 64,pos,0.76 +sample 65,pos,0.84 +sample 66,pos,0.88 +sample 67,pos,0.88 +sample 68,pos,0.99 +sample 69,pos,0.84 +sample 70,pos,0.75 +sample 71,pos,0.91 +sample 72,pos,0.76 +sample 73,pos,0.96 +sample 74,pos,0.89 +sample 75,pos,0.91 +sample 76,pos,0.71 +sample 77,pos,0.89 +sample 78,pos,0.82 +sample 79,pos,0.91 +sample 80,pos,0.86 +sample 81,pos,0.8 +sample 82,pos,0.93 +sample 83,pos,0.91 +sample 84,pos,0.89 +sample 85,pos,0.88 +sample 86,pos,0.77 +sample 87,pos,0.91 +sample 88,pos,0.89 +sample 89,pos,0.81 +sample 90,pos,0.98 +sample 91,pos,0.86 +sample 92,pos,0.97 +sample 93,pos,0.82 +sample 94,pos,0.72 +sample 95,pos,0.82 +sample 96,pos,0.84 +sample 97,pos,0.72 +sample 98,pos,0.82 +sample 99,pos,0.9 +sample 100,pos,0.91 +sample 101,pos,0.87 +sample 102,pos,0.93 +sample 103,pos,0.75 +sample 104,pos,0.81 +sample 105,pos,0.87 +sample 106,pos,0.9 +sample 107,pos,0.92 +sample 108,pos,0.93 +sample 109,pos,0.96 +sample 110,pos,0.91 +sample 111,pos,0.93 +sample 112,pos,0.93 +sample 113,pos,0.8 +sample 114,pos,0.97 +sample 115,pos,0.86 +sample 116,pos,0.83 +sample 117,pos,0.73 +sample 118,pos,0.82 +sample 119,pos,0.84 +sample 120,pos,0.86 +sample 121,pos,0.95 +sample 122,pos,0.85 +sample 123,pos,0.86 +sample 124,pos,0.95 +sample 125,pos,0.97 +sample 126,pos,0.84 +sample 127,pos,0.82 +sample 128,pos,0.91 +sample 129,pos,0.91 +sample 130,pos,0.99 +sample 131,pos,0.97 +sample 132,pos,0.76 +sample 133,pos,0.97 +sample 134,pos,0.74 +sample 135,pos,0.82 +sample 136,pos,0.76 +sample 137,pos,0.99 +sample 138,pos,0.73 +sample 139,pos,0.76 +sample 140,pos,0.74 +sample 141,pos,0.75 +sample 142,pos,0.75 +sample 143,pos,0.77 +sample 144,pos,0.99 +sample 145,pos,0.72 +sample 146,pos,0.83 +sample 147,pos,0.91 +sample 148,pos,0.98 +sample 149,pos,0.85 +sample 150,pos,0.83 +sample 151,pos,0.92 +sample 152,pos,0.72 +sample 153,pos,0.76 +sample 154,pos,0.72 +sample 155,pos,0.94 +sample 156,pos,0.95 +sample 157,pos,0.86 +sample 158,pos,0.81 +sample 159,pos,0.88 +sample 160,pos,0.9 +sample 161,pos,0.94 +sample 162,pos,0.85 +sample 163,pos,0.9 +sample 164,pos,0.86 +sample 165,pos,0.87 +sample 166,pos,0.84 +sample 167,pos,0.87 +sample 168,pos,0.97 +sample 169,pos,0.8 +sample 170,pos,0.94 +sample 171,pos,0.78 +sample 172,pos,0.82 +sample 173,pos,0.79 +sample 174,pos,0.96 +sample 175,pos,0.75 +sample 176,pos,0.79 +sample 177,pos,0.99 +sample 178,pos,0.89 +sample 179,pos,0.76 +sample 180,pos,0.87 +sample 181,pos,0.76 +sample 182,pos,0.76 +sample 183,pos,0.92 +sample 184,pos,0.97 +sample 185,pos,0.94 +sample 186,pos,0.76 +sample 187,pos,0.74 +sample 188,pos,1.0 +sample 189,pos,0.88 +sample 190,pos,0.84 +sample 191,pos,0.82 +sample 192,pos,0.77 +sample 193,pos,0.92 +sample 194,pos,0.9 +sample 195,pos,0.99 +sample 196,pos,0.75 +sample 197,pos,0.84 +sample 198,pos,0.99 +sample 199,pos,0.86 +sample 200,pos,0.75 +sample 201,pos,0.72 +sample 202,pos,0.98 +sample 203,pos,0.93 +sample 204,pos,0.98 +sample 205,pos,0.98 +sample 206,pos,0.76 +sample 207,pos,0.99 +sample 208,pos,0.87 +sample 209,pos,0.86 +sample 210,pos,0.9 +sample 211,pos,0.8 +sample 212,pos,0.97 +sample 213,pos,0.99 +sample 214,pos,0.93 +sample 215,pos,1.0 +sample 216,pos,0.9 +sample 217,pos,0.94 +sample 218,pos,0.92 +sample 219,pos,0.98 +sample 220,pos,0.81 +sample 221,pos,0.74 +sample 222,pos,0.85 +sample 223,pos,0.72 +sample 224,pos,0.91 +sample 225,pos,0.74 +sample 226,pos,0.72 +sample 227,pos,0.89 +sample 228,pos,0.77 +sample 229,pos,0.81 +sample 230,pos,0.8 +sample 231,pos,0.89 +sample 232,pos,0.77 +sample 233,pos,0.86 +sample 234,pos,0.94 +sample 235,pos,0.93 +sample 236,pos,0.77 +sample 237,pos,0.73 +sample 238,pos,0.96 +sample 239,pos,0.91 +sample 240,pos,0.99 +sample 241,pos,0.99 +sample 242,pos,0.82 +sample 243,pos,0.85 +sample 244,pos,0.88 +sample 245,pos,0.86 +sample 246,pos,0.73 +sample 247,pos,0.9 +sample 248,pos,0.83 +sample 249,pos,0.92 +sample 250,pos,0.83 +sample 251,pos,0.82 +sample 252,pos,0.71 +sample 253,pos,0.81 +sample 254,pos,0.8 +sample 255,pos,0.84 +sample 256,pos,0.87 +sample 257,pos,0.77 +sample 258,pos,0.97 +sample 259,pos,0.93 +sample 260,pos,0.83 +sample 261,pos,0.84 +sample 262,pos,0.76 +sample 263,pos,0.92 +sample 264,pos,0.97 +sample 265,pos,0.92 +sample 266,pos,0.83 +sample 267,pos,0.95 +sample 268,pos,0.88 +sample 269,pos,0.75 +sample 270,pos,0.8 +sample 271,pos,1.0 +sample 272,pos,0.86 +sample 273,pos,0.81 +sample 274,pos,0.98 +sample 275,pos,0.88 +sample 276,pos,0.82 +sample 277,pos,0.71 +sample 278,pos,0.9 +sample 279,pos,0.79 +sample 280,pos,0.76 +sample 281,pos,0.84 +sample 282,pos,0.87 +sample 283,pos,0.98 +sample 284,pos,0.77 +sample 285,pos,0.95 +sample 286,pos,0.79 +sample 287,pos,0.85 +sample 288,pos,0.95 +sample 289,pos,0.8 +sample 290,pos,0.88 +sample 291,pos,0.85 +sample 292,pos,0.92 +sample 293,pos,0.78 +sample 294,pos,0.94 +sample 295,pos,0.75 +sample 296,pos,0.8 +sample 297,pos,0.9 +sample 298,pos,0.89 +sample 299,pos,0.75 +sample 300,pos,0.9 +sample 301,pos,0.79 +sample 302,pos,0.76 +sample 303,pos,0.97 +sample 304,pos,0.9 +sample 305,pos,0.72 +sample 306,pos,0.93 +sample 307,pos,0.85 +sample 308,pos,0.99 +sample 309,pos,0.88 +sample 310,pos,0.81 +sample 311,pos,0.85 +sample 312,pos,0.84 +sample 313,pos,0.78 +sample 314,pos,0.91 +sample 315,pos,0.99 +sample 316,pos,0.95 +sample 317,pos,0.82 +sample 318,pos,0.92 +sample 319,pos,0.72 +sample 320,pos,0.79 +sample 321,pos,0.88 +sample 322,pos,0.75 +sample 323,pos,0.84 +sample 324,pos,0.91 +sample 325,pos,0.81 +sample 326,pos,0.73 +sample 327,pos,0.81 +sample 328,pos,0.89 +sample 329,pos,0.99 +sample 330,pos,0.72 +sample 331,pos,0.79 +sample 332,pos,0.9 +sample 333,pos,0.73 +sample 334,pos,0.77 +sample 335,pos,0.89 +sample 336,pos,0.93 +sample 337,pos,0.88 +sample 338,pos,0.76 +sample 339,pos,0.8 +sample 340,pos,0.8 +sample 341,pos,0.96 +sample 342,pos,0.94 +sample 343,pos,0.79 +sample 344,pos,0.91 +sample 345,pos,0.82 +sample 346,pos,0.86 +sample 347,pos,0.81 +sample 348,pos,0.75 +sample 349,pos,0.75 +sample 350,pos,0.79 +sample 351,pos,0.94 +sample 352,pos,0.83 +sample 353,pos,0.98 +sample 354,pos,0.76 +sample 355,pos,0.77 +sample 356,pos,0.86 +sample 357,pos,0.95 +sample 358,pos,0.94 +sample 359,pos,0.87 +sample 360,pos,0.91 +sample 361,pos,0.99 +sample 362,pos,0.96 +sample 363,pos,0.92 +sample 364,pos,0.91 +sample 365,pos,0.94 +sample 366,pos,0.83 +sample 367,pos,0.98 +sample 368,pos,0.74 +sample 369,pos,0.75 +sample 370,pos,0.72 +sample 371,pos,0.81 +sample 372,pos,0.91 +sample 373,pos,0.75 +sample 374,pos,0.84 +sample 375,pos,1.0 +sample 376,pos,0.86 +sample 377,pos,0.99 +sample 378,pos,0.76 +sample 379,pos,0.8 +sample 380,pos,0.93 +sample 381,pos,0.74 +sample 382,pos,0.75 +sample 383,pos,0.91 +sample 384,pos,0.91 +sample 385,pos,0.8 +sample 386,pos,0.77 +sample 387,pos,0.99 +sample 388,pos,0.83 +sample 389,pos,0.93 +sample 390,pos,0.74 +sample 391,pos,0.72 +sample 392,pos,0.85 +sample 393,pos,0.84 +sample 394,pos,0.77 +sample 395,pos,0.72 +sample 396,pos,0.9 +sample 397,pos,0.88 +sample 398,pos,0.85 +sample 399,pos,0.97 +sample 400,pos,0.72 +sample 401,pos,0.8 +sample 402,pos,0.71 +sample 403,pos,0.74 +sample 404,pos,0.75 +sample 405,pos,0.88 +sample 406,pos,0.88 +sample 407,pos,0.77 +sample 408,pos,0.9 +sample 409,pos,0.72 +sample 410,pos,0.75 +sample 411,pos,0.93 +sample 412,pos,0.79 +sample 413,pos,0.88 +sample 414,pos,0.81 +sample 415,pos,0.96 +sample 416,pos,0.94 +sample 417,pos,0.89 +sample 418,pos,0.86 +sample 419,pos,0.73 +sample 420,pos,0.95 +sample 421,pos,0.93 +sample 422,pos,0.86 +sample 423,pos,0.92 +sample 424,pos,0.99 +sample 425,pos,0.76 +sample 426,pos,0.93 +sample 427,pos,0.71 +sample 428,pos,0.92 +sample 429,pos,0.98 +sample 430,pos,0.98 +sample 431,pos,0.96 +sample 432,pos,0.85 +sample 433,pos,0.91 +sample 434,pos,0.76 +sample 435,pos,0.91 +sample 436,pos,0.74 +sample 437,pos,0.95 +sample 438,pos,0.99 +sample 439,pos,0.83 +sample 440,pos,0.86 +sample 441,pos,0.83 +sample 442,pos,0.93 +sample 443,pos,0.8 +sample 444,pos,0.85 +sample 445,pos,0.86 +sample 446,pos,0.85 +sample 447,pos,0.81 +sample 448,pos,0.79 +sample 449,pos,0.92 +sample 450,pos,0.73 +sample 451,pos,0.85 +sample 452,pos,0.82 +sample 453,pos,0.84 +sample 454,pos,0.92 +sample 455,pos,0.91 +sample 456,pos,0.95 +sample 457,pos,0.78 +sample 458,pos,0.83 +sample 459,pos,1.0 +sample 460,pos,0.83 +sample 461,pos,0.96 +sample 462,pos,0.97 +sample 463,pos,0.94 +sample 464,pos,0.98 +sample 465,pos,0.82 +sample 466,pos,0.71 +sample 467,pos,0.91 +sample 468,pos,0.9 +sample 469,pos,0.82 +sample 470,pos,0.86 +sample 471,pos,0.91 +sample 472,pos,0.74 +sample 473,pos,0.82 +sample 474,pos,0.91 +sample 475,pos,0.99 +sample 476,pos,0.93 +sample 477,pos,0.97 +sample 478,pos,0.76 +sample 479,pos,0.82 +sample 480,pos,0.77 +sample 481,pos,0.77 +sample 482,pos,0.95 +sample 483,pos,0.83 +sample 484,pos,0.78 +sample 485,pos,0.83 +sample 486,pos,0.85 +sample 487,pos,0.93 +sample 488,pos,0.93 +sample 489,pos,0.88 +sample 490,pos,0.93 +sample 491,pos,0.94 +sample 492,pos,0.98 +sample 493,pos,0.81 +sample 494,pos,0.9 +sample 495,pos,0.99 +sample 496,pos,1.0 +sample 497,pos,0.86 +sample 498,pos,0.75 +sample 499,pos,0.84 diff --git a/tests/fixtures/low_confidence.csv b/tests/fixtures/low_confidence.csv new file mode 100644 index 0000000..4097a3a --- /dev/null +++ b/tests/fixtures/low_confidence.csv @@ -0,0 +1,501 @@ +text,label,confidence +sample 72,pos,0.12 +sample 348,pos,0.62 +sample 29,pos,0.43 +sample 40,pos,0.93 +sample 145,pos,0.28 +sample 148,pos,0.96 +sample 22,pos,0.52 +sample 136,pos,0.26 +sample 271,pos,0.94 +sample 100,pos,0.96 +sample 32,pos,0.43 +sample 326,pos,0.73 +sample 5,pos,0.29 +sample 341,pos,0.88 +sample 144,pos,0.79 +sample 81,pos,0.79 +sample 125,pos,0.12 +sample 290,pos,0.4 +sample 53,pos,0.15 +sample 126,pos,0.16 +sample 44,pos,0.54 +sample 231,pos,0.48 +sample 283,pos,0.9 +sample 208,pos,0.92 +sample 61,pos,0.32 +sample 207,pos,0.68 +sample 343,pos,0.95 +sample 50,pos,0.02 +sample 267,pos,0.68 +sample 81,pos,0.16 +sample 325,pos,0.85 +sample 124,pos,0.56 +sample 346,pos,0.62 +sample 63,pos,0.3 +sample 101,pos,0.25 +sample 122,pos,0.2 +sample 105,pos,0.58 +sample 151,pos,0.48 +sample 12,pos,0.54 +sample 119,pos,0.14 +sample 116,pos,0.22 +sample 22,pos,0.21 +sample 84,pos,0.01 +sample 228,pos,0.63 +sample 34,pos,0.07 +sample 249,pos,0.66 +sample 42,pos,0.9 +sample 39,pos,0.8 +sample 95,pos,0.72 +sample 336,pos,0.64 +sample 292,pos,0.51 +sample 305,pos,0.42 +sample 319,pos,0.88 +sample 256,pos,0.5 +sample 0,pos,0.05 +sample 16,pos,0.88 +sample 41,pos,0.64 +sample 19,pos,0.11 +sample 58,pos,0.84 +sample 173,pos,0.76 +sample 60,pos,0.14 +sample 278,pos,0.83 +sample 288,pos,0.53 +sample 236,pos,0.7 +sample 138,pos,0.37 +sample 45,pos,0.22 +sample 71,pos,0.09 +sample 307,pos,0.82 +sample 331,pos,0.86 +sample 126,pos,0.65 +sample 134,pos,0.07 +sample 214,pos,0.76 +sample 277,pos,0.47 +sample 136,pos,0.4 +sample 45,pos,0.74 +sample 33,pos,0.01 +sample 146,pos,0.02 +sample 33,pos,0.94 +sample 3,pos,0.37 +sample 137,pos,0.52 +sample 330,pos,0.54 +sample 19,pos,0.99 +sample 234,pos,0.51 +sample 241,pos,0.66 +sample 70,pos,0.1 +sample 306,pos,0.68 +sample 131,pos,0.86 +sample 230,pos,0.8 +sample 36,pos,0.3 +sample 142,pos,0.83 +sample 317,pos,1.0 +sample 135,pos,0.78 +sample 299,pos,0.99 +sample 49,pos,0.06 +sample 140,pos,0.25 +sample 17,pos,0.59 +sample 104,pos,0.85 +sample 53,pos,0.45 +sample 261,pos,0.95 +sample 35,pos,0.58 +sample 99,pos,0.38 +sample 276,pos,0.67 +sample 250,pos,0.94 +sample 88,pos,0.8 +sample 178,pos,0.41 +sample 301,pos,0.62 +sample 296,pos,0.46 +sample 56,pos,0.11 +sample 83,pos,0.16 +sample 139,pos,0.1 +sample 147,pos,0.65 +sample 321,pos,0.92 +sample 213,pos,0.65 +sample 149,pos,0.09 +sample 347,pos,0.46 +sample 121,pos,0.95 +sample 258,pos,0.69 +sample 28,pos,0.79 +sample 89,pos,0.13 +sample 163,pos,0.41 +sample 304,pos,0.59 +sample 273,pos,0.66 +sample 127,pos,0.84 +sample 115,pos,0.11 +sample 7,pos,0.91 +sample 108,pos,0.66 +sample 25,pos,0.87 +sample 115,pos,0.87 +sample 140,pos,0.47 +sample 77,pos,0.07 +sample 141,pos,0.32 +sample 9,pos,0.57 +sample 192,pos,0.52 +sample 133,pos,0.2 +sample 14,pos,0.3 +sample 13,pos,0.54 +sample 153,pos,0.76 +sample 100,pos,0.08 +sample 15,pos,0.26 +sample 111,pos,0.37 +sample 180,pos,0.86 +sample 114,pos,0.45 +sample 113,pos,0.56 +sample 128,pos,0.73 +sample 18,pos,0.69 +sample 17,pos,0.19 +sample 262,pos,0.78 +sample 239,pos,0.45 +sample 37,pos,0.35 +sample 337,pos,0.79 +sample 212,pos,0.63 +sample 14,pos,0.49 +sample 245,pos,0.7 +sample 60,pos,0.85 +sample 104,pos,0.33 +sample 105,pos,0.08 +sample 109,pos,0.31 +sample 64,pos,0.53 +sample 247,pos,0.57 +sample 106,pos,0.92 +sample 253,pos,0.96 +sample 198,pos,0.88 +sample 269,pos,0.68 +sample 76,pos,0.87 +sample 59,pos,0.88 +sample 69,pos,0.72 +sample 251,pos,0.56 +sample 242,pos,0.56 +sample 21,pos,0.2 +sample 43,pos,0.22 +sample 37,pos,0.97 +sample 73,pos,0.03 +sample 176,pos,0.5 +sample 121,pos,0.32 +sample 62,pos,0.23 +sample 1,pos,0.19 +sample 154,pos,0.6 +sample 110,pos,0.89 +sample 291,pos,0.86 +sample 224,pos,0.83 +sample 35,pos,0.26 +sample 187,pos,0.89 +sample 268,pos,0.5 +sample 15,pos,0.42 +sample 295,pos,0.7 +sample 25,pos,0.01 +sample 302,pos,0.96 +sample 197,pos,0.51 +sample 113,pos,0.23 +sample 281,pos,0.52 +sample 202,pos,0.67 +sample 36,pos,0.44 +sample 160,pos,0.9 +sample 92,pos,0.27 +sample 171,pos,0.43 +sample 84,pos,0.84 +sample 310,pos,0.56 +sample 338,pos,0.97 +sample 217,pos,0.43 +sample 282,pos,0.57 +sample 139,pos,0.75 +sample 83,pos,0.42 +sample 65,pos,0.56 +sample 122,pos,0.46 +sample 55,pos,0.86 +sample 6,pos,0.78 +sample 233,pos,0.42 +sample 27,pos,0.39 +sample 28,pos,0.34 +sample 43,pos,0.91 +sample 117,pos,0.21 +sample 161,pos,0.74 +sample 130,pos,0.82 +sample 12,pos,0.12 +sample 30,pos,0.83 +sample 174,pos,0.49 +sample 21,pos,0.94 +sample 259,pos,0.97 +sample 131,pos,0.34 +sample 134,pos,0.67 +sample 300,pos,0.47 +sample 38,pos,0.06 +sample 68,pos,0.16 +sample 142,pos,0.33 +sample 47,pos,0.47 +sample 189,pos,0.85 +sample 46,pos,0.7 +sample 90,pos,0.04 +sample 175,pos,0.97 +sample 235,pos,0.5 +sample 246,pos,0.98 +sample 179,pos,0.72 +sample 263,pos,0.66 +sample 143,pos,0.35 +sample 30,pos,0.18 +sample 274,pos,0.99 +sample 8,pos,0.56 +sample 29,pos,0.05 +sample 110,pos,0.24 +sample 86,pos,0.01 +sample 16,pos,0.2 +sample 56,pos,0.59 +sample 209,pos,0.98 +sample 128,pos,0.2 +sample 349,pos,0.52 +sample 70,pos,0.82 +sample 289,pos,1.0 +sample 316,pos,0.97 +sample 248,pos,0.62 +sample 129,pos,0.6 +sample 143,pos,0.86 +sample 116,pos,0.7 +sample 75,pos,0.57 +sample 270,pos,0.47 +sample 318,pos,0.94 +sample 297,pos,0.6 +sample 205,pos,0.79 +sample 120,pos,0.03 +sample 225,pos,0.89 +sample 102,pos,0.58 +sample 254,pos,0.71 +sample 51,pos,0.1 +sample 101,pos,0.95 +sample 80,pos,0.26 +sample 102,pos,0.38 +sample 88,pos,0.22 +sample 66,pos,0.17 +sample 97,pos,0.67 +sample 285,pos,0.89 +sample 144,pos,0.36 +sample 106,pos,0.1 +sample 344,pos,0.94 +sample 183,pos,0.7 +sample 222,pos,0.8 +sample 167,pos,0.45 +sample 49,pos,0.75 +sample 177,pos,0.74 +sample 67,pos,0.39 +sample 313,pos,0.43 +sample 23,pos,0.56 +sample 112,pos,0.28 +sample 109,pos,0.59 +sample 156,pos,0.45 +sample 74,pos,0.55 +sample 26,pos,0.57 +sample 90,pos,0.63 +sample 98,pos,0.12 +sample 147,pos,0.08 +sample 82,pos,0.2 +sample 323,pos,0.57 +sample 199,pos,0.42 +sample 79,pos,0.62 +sample 27,pos,0.73 +sample 168,pos,0.68 +sample 272,pos,0.7 +sample 191,pos,0.66 +sample 264,pos,0.51 +sample 345,pos,0.76 +sample 32,pos,0.17 +sample 223,pos,0.88 +sample 11,pos,0.81 +sample 145,pos,0.48 +sample 190,pos,0.63 +sample 240,pos,0.83 +sample 120,pos,0.65 +sample 31,pos,0.33 +sample 118,pos,0.17 +sample 162,pos,0.41 +sample 152,pos,0.5 +sample 293,pos,0.95 +sample 184,pos,0.53 +sample 54,pos,0.76 +sample 226,pos,0.4 +sample 18,pos,0.18 +sample 314,pos,0.77 +sample 133,pos,0.51 +sample 155,pos,0.57 +sample 146,pos,0.76 +sample 320,pos,0.48 +sample 62,pos,0.53 +sample 71,pos,0.47 +sample 52,pos,0.23 +sample 4,pos,0.01 +sample 20,pos,0.65 +sample 26,pos,0.3 +sample 50,pos,0.87 +sample 284,pos,0.85 +sample 0,pos,0.85 +sample 103,pos,0.03 +sample 124,pos,0.26 +sample 279,pos,0.49 +sample 255,pos,0.66 +sample 10,pos,0.24 +sample 91,pos,0.78 +sample 98,pos,0.4 +sample 77,pos,0.49 +sample 78,pos,0.21 +sample 85,pos,0.18 +sample 257,pos,0.84 +sample 11,pos,0.13 +sample 339,pos,0.49 +sample 92,pos,0.82 +sample 75,pos,0.34 +sample 287,pos,0.8 +sample 216,pos,0.73 +sample 322,pos,0.88 +sample 211,pos,0.53 +sample 125,pos,0.44 +sample 170,pos,0.91 +sample 312,pos,0.6 +sample 123,pos,0.12 +sample 219,pos,0.68 +sample 74,pos,0.27 +sample 182,pos,0.9 +sample 96,pos,0.54 +sample 107,pos,0.12 +sample 13,pos,0.24 +sample 96,pos,0.26 +sample 206,pos,0.45 +sample 275,pos,0.74 +sample 57,pos,0.02 +sample 97,pos,0.06 +sample 7,pos,0.19 +sample 69,pos,0.02 +sample 64,pos,0.24 +sample 44,pos,0.19 +sample 4,pos,0.92 +sample 238,pos,0.68 +sample 195,pos,0.84 +sample 227,pos,0.7 +sample 244,pos,0.99 +sample 203,pos,0.55 +sample 34,pos,0.59 +sample 165,pos,0.77 +sample 166,pos,0.54 +sample 5,pos,0.95 +sample 99,pos,0.98 +sample 221,pos,0.76 +sample 158,pos,0.64 +sample 186,pos,0.97 +sample 57,pos,0.9 +sample 204,pos,0.75 +sample 85,pos,0.88 +sample 309,pos,0.78 +sample 185,pos,0.52 +sample 87,pos,0.12 +sample 6,pos,0.32 +sample 59,pos,0.05 +sample 52,pos,0.7 +sample 2,pos,0.09 +sample 9,pos,0.07 +sample 123,pos,0.5 +sample 334,pos,0.52 +sample 54,pos,0.26 +sample 194,pos,0.89 +sample 132,pos,0.24 +sample 159,pos,0.63 +sample 232,pos,0.94 +sample 311,pos,0.79 +sample 94,pos,0.19 +sample 108,pos,0.22 +sample 335,pos,0.63 +sample 328,pos,0.46 +sample 135,pos,0.19 +sample 169,pos,0.56 +sample 80,pos,0.58 +sample 193,pos,0.53 +sample 340,pos,0.58 +sample 82,pos,0.94 +sample 220,pos,0.61 +sample 150,pos,0.92 +sample 10,pos,0.5 +sample 2,pos,0.91 +sample 210,pos,0.64 +sample 63,pos,0.46 +sample 315,pos,0.67 +sample 294,pos,0.55 +sample 51,pos,0.72 +sample 93,pos,0.08 +sample 252,pos,0.9 +sample 91,pos,0.19 +sample 86,pos,0.43 +sample 286,pos,0.74 +sample 229,pos,0.99 +sample 58,pos,0.23 +sample 8,pos,0.01 +sample 107,pos,0.5 +sample 243,pos,0.59 +sample 41,pos,0.15 +sample 149,pos,0.67 +sample 130,pos,0.21 +sample 31,pos,0.87 +sample 129,pos,0.26 +sample 266,pos,0.51 +sample 298,pos,0.57 +sample 218,pos,0.96 +sample 188,pos,0.56 +sample 327,pos,0.76 +sample 48,pos,0.22 +sample 61,pos,0.96 +sample 67,pos,0.92 +sample 111,pos,0.79 +sample 55,pos,0.3 +sample 329,pos,0.55 +sample 23,pos,0.32 +sample 39,pos,0.17 +sample 132,pos,0.78 +sample 24,pos,0.21 +sample 141,pos,0.55 +sample 1,pos,0.86 +sample 332,pos,0.64 +sample 117,pos,0.84 +sample 127,pos,0.1 +sample 280,pos,0.61 +sample 308,pos,0.69 +sample 200,pos,0.99 +sample 65,pos,0.15 +sample 76,pos,0.04 +sample 3,pos,0.65 +sample 94,pos,0.81 +sample 260,pos,0.73 +sample 40,pos,0.12 +sample 73,pos,0.68 +sample 89,pos,0.55 +sample 148,pos,0.18 +sample 42,pos,0.3 +sample 118,pos,0.96 +sample 324,pos,0.88 +sample 333,pos,0.41 +sample 119,pos,0.6 +sample 103,pos,0.96 +sample 79,pos,0.01 +sample 215,pos,0.44 +sample 201,pos,0.54 +sample 181,pos,0.96 +sample 114,pos,0.23 +sample 196,pos,0.51 +sample 87,pos,0.95 +sample 24,pos,0.42 +sample 112,pos,0.87 +sample 20,pos,0.19 +sample 47,pos,0.18 +sample 68,pos,0.43 +sample 172,pos,0.77 +sample 72,pos,0.73 +sample 95,pos,0.32 +sample 164,pos,0.74 +sample 38,pos,0.94 +sample 265,pos,0.43 +sample 342,pos,0.84 +sample 237,pos,0.6 +sample 46,pos,0.21 +sample 66,pos,0.65 +sample 157,pos,0.62 +sample 138,pos,0.58 +sample 137,pos,0.32 +sample 93,pos,0.94 +sample 48,pos,0.8 +sample 303,pos,0.46 +sample 78,pos,0.69 diff --git a/tests/fixtures/no_duplicates.csv b/tests/fixtures/no_duplicates.csv new file mode 100644 index 0000000..0462320 --- /dev/null +++ b/tests/fixtures/no_duplicates.csv @@ -0,0 +1,501 @@ +text,label +a birthday party confused most people according to reports this past weekend,pos +the weather caused chaos after several delays in a small town,neg +the concert fell apart quickly as many predicted under new management,pos +local news changed completely in front of a large crowd just yesterday,neg +traffic downtown caused chaos based on what I saw near downtown,pos +traffic downtown took longer than planned right before sunset for the first time,neg +a birthday party changed completely based on what I saw before the deadline,pos +the hospital visit improved this year according to reports under new management,neg +a job interview went as expected during the holiday season in a small town,pos +my garden took longer than planned according to reports for the first time,neg +a wedding went as expected as many predicted in the northern district,pos +a new phone exceeded expectations right before sunset this past weekend,neg +a science experiment impressed the crowd based on what I saw under new management,pos +the concert improved this year in front of a large crowd under new management,neg +the concert surprised everyone for the third time before the deadline,pos +my neighbor exceeded expectations for the third time according to witnesses,neg +the school exam fell apart quickly according to reports according to witnesses,pos +a swimming competition changed completely despite the forecast on live television,neg +a road trip exceeded expectations right before sunset this past weekend,pos +the art exhibit confused most people during the holiday season according to witnesses,neg +the election results surprised everyone despite the forecast under new management,pos +the stock market ran smoothly right before sunset in a small town,neg +the courtroom hearing sparked a debate right before sunset before the deadline,pos +the office meeting was cancelled suddenly right before sunset in a small town,neg +a swimming competition was disappointing based on what I saw before the deadline,pos +my neighbor caused chaos after several delays near downtown,neg +a swimming competition went as expected for reasons still unclear near downtown,pos +the stock market left people speechless without any warning under new management,neg +the internet outage ran smoothly against all odds before the deadline,pos +the school exam surprised everyone in front of a large crowd on live television,neg +my garden impressed the crowd earlier than scheduled near downtown,pos +a cooking class exceeded expectations despite the forecast just yesterday,neg +this recipe sparked a debate despite the forecast in the northern district,pos +the museum tour took longer than planned during the holiday season before the deadline,neg +the museum tour took longer than planned despite the forecast in a small town,pos +the airport delay fell apart quickly in record time according to witnesses,neg +a charity event sparked a debate against all odds just yesterday,pos +a swimming competition changed completely during the holiday season in the northern district,neg +the football match took longer than planned as many predicted in a small town,pos +the concert caused chaos despite the forecast this past weekend,neg +the football match impressed the crowd right before sunset just yesterday,pos +my garden was cancelled suddenly as many predicted in the northern district,neg +a new phone fell apart quickly in record time according to witnesses,pos +a birthday party surprised everyone during the holiday season according to witnesses,neg +the hospital visit took longer than planned without any warning near downtown,pos +the football match exceeded expectations right before sunset in the northern district,neg +a wedding improved this year in front of a large crowd in a small town,pos +the weather was disappointing earlier than scheduled for the first time,neg +a family dinner sparked a debate in record time near downtown,pos +the election results changed completely after several delays according to witnesses,neg +a wedding took longer than planned as many predicted near downtown,pos +the hospital visit was disappointing right before sunset before the deadline,neg +a wedding impressed the crowd in record time this past weekend,pos +a job interview was disappointing against all odds according to witnesses,neg +the internet outage impressed the crowd right before sunset just yesterday,pos +traffic downtown changed completely according to reports in a small town,neg +the airport delay improved this year for the third time under new management,pos +this recipe caused chaos in front of a large crowd just yesterday,neg +the office meeting was cancelled suddenly after several delays for the first time,pos +my garden fell apart quickly for reasons still unclear before the deadline,neg +the movie plot changed completely much to our surprise this past weekend,pos +a birthday party was disappointing for reasons still unclear before the deadline,neg +the football match sparked a debate right before sunset according to witnesses,pos +a family dinner impressed the crowd during the holiday season this past weekend,neg +the concert improved this year without any warning just yesterday,pos +a cooking class was disappointing during the holiday season in a small town,neg +a swimming competition impressed the crowd against all odds on live television,pos +this recipe went as expected in front of a large crowd in a small town,neg +traffic downtown sparked a debate in record time near downtown,pos +a wedding improved this year as many predicted according to witnesses,neg +a birthday party sparked a debate against all odds in a small town,pos +the hospital visit left people speechless based on what I saw this past weekend,neg +my garden took longer than planned during the holiday season before the deadline,pos +a science experiment took longer than planned in front of a large crowd in the northern district,neg +the courtroom hearing confused most people based on what I saw in a small town,pos +the stock market exceeded expectations based on what I saw before the deadline,neg +a birthday party exceeded expectations against all odds according to witnesses,pos +the election results left people speechless earlier than scheduled under new management,neg +the university lecture confused most people much to our surprise in a small town,pos +local news improved this year for reasons still unclear near downtown,neg +the courtroom hearing changed completely against all odds in a small town,pos +my garden was disappointing much to our surprise according to witnesses,neg +a charity event fell apart quickly after several delays according to witnesses,pos +a science experiment left people speechless without any warning this past weekend,neg +the school exam went as expected right before sunset under new management,pos +the school exam was disappointing right before sunset just yesterday,neg +the hospital visit improved this year based on what I saw under new management,pos +the university lecture was disappointing as many predicted for the first time,neg +the election results was disappointing right before sunset for the first time,pos +a road trip left people speechless as many predicted according to witnesses,neg +the courtroom hearing left people speechless as many predicted near downtown,pos +the courtroom hearing ran smoothly according to reports this past weekend,neg +my neighbor exceeded expectations in front of a large crowd for the first time,pos +the school exam exceeded expectations after several delays for the first time,neg +local news confused most people right before sunset near downtown,pos +the airport delay left people speechless right before sunset under new management,neg +my garden exceeded expectations without any warning before the deadline,pos +traffic downtown sparked a debate in front of a large crowd in the northern district,neg +my garden was cancelled suddenly based on what I saw near downtown,pos +a new phone was cancelled suddenly for the third time before the deadline,neg +a birthday party went as expected despite the forecast for the first time,pos +the election results impressed the crowd earlier than scheduled according to witnesses,neg +a road trip ran smoothly despite the forecast in the northern district,pos +the election results sparked a debate despite the forecast under new management,neg +the concert changed completely despite the forecast on live television,pos +a birthday party changed completely without any warning before the deadline,neg +traffic downtown was disappointing based on what I saw near downtown,pos +my garden took longer than planned earlier than scheduled for the first time,neg +local news went as expected earlier than scheduled in a small town,pos +the courtroom hearing impressed the crowd for reasons still unclear for the first time,neg +a road trip impressed the crowd after several delays in a small town,pos +the airport delay improved this year in record time before the deadline,neg +the museum tour caused chaos in record time near downtown,pos +the football match took longer than planned against all odds before the deadline,neg +traffic downtown went as expected as many predicted according to witnesses,pos +my neighbor surprised everyone without any warning before the deadline,neg +the hospital visit left people speechless earlier than scheduled before the deadline,pos +my garden improved this year according to reports this past weekend,neg +local news was disappointing for reasons still unclear just yesterday,pos +a road trip impressed the crowd in front of a large crowd in the northern district,neg +a wedding surprised everyone for the third time near downtown,pos +a job interview improved this year after several delays according to witnesses,neg +the concert caused chaos based on what I saw in the northern district,pos +a science experiment was cancelled suddenly in front of a large crowd under new management,neg +the school exam ran smoothly as many predicted for the first time,pos +this recipe was disappointing based on what I saw in the northern district,neg +a wedding sparked a debate despite the forecast under new management,pos +a wedding sparked a debate much to our surprise on live television,neg +the hospital visit improved this year for the third time under new management,pos +my neighbor surprised everyone according to reports in a small town,neg +the office meeting impressed the crowd in front of a large crowd before the deadline,pos +a science experiment was cancelled suddenly much to our surprise for the first time,neg +the museum tour improved this year much to our surprise according to witnesses,pos +a charity event confused most people despite the forecast in a small town,neg +the internet outage confused most people during the holiday season just yesterday,pos +a job interview impressed the crowd against all odds under new management,neg +the concert was cancelled suddenly during the holiday season for the first time,pos +my garden was cancelled suddenly earlier than scheduled near downtown,neg +a wedding impressed the crowd right before sunset this past weekend,pos +local news confused most people without any warning near downtown,neg +the hospital visit was cancelled suddenly without any warning for the first time,pos +a job interview went as expected during the holiday season near downtown,neg +a job interview was cancelled suddenly much to our surprise under new management,pos +the university lecture fell apart quickly as many predicted in the northern district,neg +the election results ran smoothly right before sunset on live television,pos +my neighbor confused most people during the holiday season this past weekend,neg +the movie plot surprised everyone in record time according to witnesses,pos +local news was disappointing for the third time on live television,neg +local news improved this year in front of a large crowd for the first time,pos +a charity event was cancelled suddenly earlier than scheduled near downtown,neg +the office meeting was disappointing against all odds on live television,pos +the concert impressed the crowd right before sunset before the deadline,neg +a science experiment took longer than planned despite the forecast in a small town,pos +a birthday party left people speechless against all odds according to witnesses,neg +the concert impressed the crowd right before sunset just yesterday,pos +the hospital visit was cancelled suddenly after several delays on live television,neg +the school exam improved this year without any warning on live television,pos +my garden sparked a debate without any warning on live television,neg +the office meeting fell apart quickly in record time according to witnesses,pos +the airport delay impressed the crowd against all odds just yesterday,neg +my garden changed completely as many predicted under new management,pos +the internet outage left people speechless for the third time according to witnesses,neg +the art exhibit sparked a debate much to our surprise just yesterday,pos +my neighbor caused chaos during the holiday season this past weekend,neg +a wedding left people speechless in record time just yesterday,pos +a road trip was cancelled suddenly after several delays on live television,neg +the courtroom hearing improved this year without any warning under new management,pos +the office meeting caused chaos much to our surprise this past weekend,neg +the hospital visit fell apart quickly as many predicted on live television,pos +traffic downtown surprised everyone right before sunset under new management,neg +traffic downtown exceeded expectations after several delays near downtown,pos +this recipe took longer than planned despite the forecast before the deadline,neg +this recipe exceeded expectations in front of a large crowd in a small town,pos +the weather improved this year for reasons still unclear in a small town,neg +local news exceeded expectations for reasons still unclear before the deadline,pos +the airport delay exceeded expectations after several delays just yesterday,neg +the stock market caused chaos right before sunset near downtown,pos +a charity event sparked a debate based on what I saw for the first time,neg +traffic downtown improved this year during the holiday season near downtown,pos +a charity event left people speechless much to our surprise in the northern district,neg +the museum tour ran smoothly much to our surprise near downtown,pos +the courtroom hearing took longer than planned in front of a large crowd before the deadline,neg +a new phone left people speechless during the holiday season just yesterday,pos +the museum tour surprised everyone according to reports just yesterday,neg +a job interview confused most people based on what I saw according to witnesses,pos +my garden was cancelled suddenly right before sunset under new management,neg +a science experiment was cancelled suddenly for reasons still unclear in a small town,pos +a cooking class improved this year in record time just yesterday,neg +the movie plot sparked a debate based on what I saw according to witnesses,pos +a new phone fell apart quickly in record time just yesterday,neg +the office meeting was disappointing according to reports according to witnesses,pos +a swimming competition caused chaos as many predicted on live television,neg +a new phone confused most people earlier than scheduled in the northern district,pos +the courtroom hearing took longer than planned against all odds according to witnesses,neg +the football match took longer than planned right before sunset this past weekend,pos +a new phone was disappointing in record time according to witnesses,neg +a charity event went as expected according to reports just yesterday,pos +the internet outage went as expected in record time just yesterday,neg +the stock market caused chaos as many predicted for the first time,pos +the weather caused chaos right before sunset according to witnesses,neg +the office meeting went as expected according to reports this past weekend,pos +a birthday party caused chaos much to our surprise in the northern district,neg +a family dinner improved this year for reasons still unclear just yesterday,pos +the office meeting changed completely right before sunset just yesterday,neg +a wedding confused most people after several delays on live television,pos +the election results was cancelled suddenly much to our surprise before the deadline,neg +a road trip confused most people despite the forecast in the northern district,pos +the office meeting improved this year for reasons still unclear before the deadline,neg +the art exhibit improved this year in front of a large crowd on live television,pos +the art exhibit went as expected right before sunset for the first time,neg +a cooking class sparked a debate based on what I saw under new management,pos +a birthday party improved this year during the holiday season according to witnesses,neg +the football match left people speechless as many predicted this past weekend,pos +my neighbor ran smoothly against all odds under new management,neg +the movie plot confused most people against all odds in a small town,pos +a new phone impressed the crowd earlier than scheduled under new management,neg +a birthday party changed completely right before sunset on live television,pos +the office meeting confused most people in record time this past weekend,neg +the museum tour improved this year in record time near downtown,pos +a birthday party was disappointing against all odds in the northern district,neg +a birthday party confused most people according to reports under new management,pos +a birthday party exceeded expectations in front of a large crowd just yesterday,neg +a road trip surprised everyone for the third time just yesterday,pos +the courtroom hearing surprised everyone during the holiday season on live television,neg +a job interview changed completely according to reports in the northern district,pos +a wedding fell apart quickly based on what I saw under new management,neg +my neighbor left people speechless for reasons still unclear this past weekend,pos +a charity event was cancelled suddenly according to reports just yesterday,neg +local news was disappointing in front of a large crowd in a small town,pos +the art exhibit exceeded expectations during the holiday season in the northern district,neg +a wedding left people speechless for the third time before the deadline,pos +a cooking class left people speechless for reasons still unclear in the northern district,neg +the internet outage changed completely right before sunset under new management,pos +the election results exceeded expectations earlier than scheduled according to witnesses,neg +this recipe was disappointing against all odds in the northern district,pos +a science experiment was disappointing during the holiday season on live television,neg +the courtroom hearing surprised everyone in front of a large crowd near downtown,pos +local news improved this year for the third time on live television,neg +traffic downtown was cancelled suddenly despite the forecast in a small town,pos +the school exam went as expected for reasons still unclear this past weekend,neg +my neighbor sparked a debate right before sunset in the northern district,pos +the hospital visit sparked a debate for reasons still unclear near downtown,neg +traffic downtown went as expected based on what I saw this past weekend,pos +the hospital visit surprised everyone in record time for the first time,neg +a family dinner fell apart quickly earlier than scheduled near downtown,pos +traffic downtown fell apart quickly according to reports in the northern district,neg +a birthday party went as expected against all odds on live television,pos +the art exhibit ran smoothly in front of a large crowd near downtown,neg +the election results improved this year without any warning on live television,pos +the courtroom hearing left people speechless during the holiday season for the first time,neg +the stock market confused most people as many predicted according to witnesses,pos +traffic downtown caused chaos for reasons still unclear in a small town,neg +a family dinner improved this year after several delays in the northern district,pos +my garden caused chaos according to reports under new management,neg +a job interview left people speechless during the holiday season in a small town,pos +the university lecture exceeded expectations for the third time under new management,neg +the airport delay surprised everyone despite the forecast in the northern district,pos +a swimming competition improved this year despite the forecast in the northern district,neg +local news was disappointing without any warning in the northern district,pos +a new phone sparked a debate against all odds before the deadline,neg +traffic downtown ran smoothly after several delays just yesterday,pos +a cooking class fell apart quickly much to our surprise before the deadline,neg +a charity event surprised everyone against all odds in the northern district,pos +local news improved this year against all odds in a small town,neg +the internet outage went as expected without any warning on live television,pos +a cooking class impressed the crowd based on what I saw under new management,neg +a road trip ran smoothly after several delays near downtown,pos +the school exam took longer than planned right before sunset for the first time,neg +the hospital visit surprised everyone earlier than scheduled this past weekend,pos +the movie plot sparked a debate in front of a large crowd for the first time,neg +a road trip exceeded expectations against all odds on live television,pos +the airport delay went as expected earlier than scheduled according to witnesses,neg +my garden left people speechless according to reports on live television,pos +a charity event went as expected during the holiday season this past weekend,neg +a road trip sparked a debate in record time on live television,pos +the office meeting confused most people during the holiday season on live television,neg +the internet outage left people speechless after several delays under new management,pos +the stock market sparked a debate without any warning in the northern district,neg +a birthday party improved this year right before sunset according to witnesses,pos +my garden caused chaos despite the forecast under new management,neg +the museum tour was cancelled suddenly in record time this past weekend,pos +a swimming competition fell apart quickly in record time according to witnesses,neg +a charity event went as expected despite the forecast according to witnesses,pos +local news surprised everyone as many predicted on live television,neg +a road trip was disappointing according to reports just yesterday,pos +the concert left people speechless as many predicted for the first time,neg +a road trip took longer than planned without any warning in a small town,pos +the movie plot impressed the crowd after several delays in the northern district,neg +a job interview ran smoothly after several delays before the deadline,pos +the concert exceeded expectations right before sunset according to witnesses,neg +the school exam sparked a debate earlier than scheduled before the deadline,pos +a road trip exceeded expectations during the holiday season before the deadline,neg +a birthday party was disappointing during the holiday season according to witnesses,pos +a new phone was disappointing during the holiday season under new management,neg +the airport delay was disappointing for reasons still unclear under new management,pos +the university lecture surprised everyone against all odds near downtown,neg +the courtroom hearing ran smoothly based on what I saw near downtown,pos +the art exhibit surprised everyone for the third time in a small town,neg +the courtroom hearing exceeded expectations after several delays this past weekend,pos +the office meeting was disappointing according to reports on live television,neg +a science experiment was cancelled suddenly despite the forecast near downtown,pos +the hospital visit exceeded expectations right before sunset for the first time,neg +a charity event was cancelled suddenly right before sunset before the deadline,pos +the weather surprised everyone against all odds under new management,neg +local news surprised everyone according to reports under new management,pos +a road trip caused chaos against all odds just yesterday,neg +the weather improved this year earlier than scheduled in the northern district,pos +a swimming competition left people speechless much to our surprise this past weekend,neg +a charity event changed completely against all odds in a small town,pos +traffic downtown went as expected as many predicted under new management,neg +the school exam ran smoothly despite the forecast just yesterday,pos +a swimming competition took longer than planned based on what I saw according to witnesses,neg +the internet outage was cancelled suddenly as many predicted on live television,pos +the office meeting went as expected without any warning this past weekend,neg +the university lecture ran smoothly right before sunset near downtown,pos +the football match took longer than planned for the third time in the northern district,neg +the concert was cancelled suddenly according to reports near downtown,pos +the office meeting was disappointing based on what I saw before the deadline,neg +a cooking class took longer than planned right before sunset according to witnesses,pos +a job interview ran smoothly based on what I saw under new management,neg +a charity event surprised everyone after several delays on live television,pos +the museum tour ran smoothly during the holiday season for the first time,neg +the airport delay caused chaos according to reports this past weekend,pos +a family dinner left people speechless without any warning under new management,neg +a job interview exceeded expectations according to reports in a small town,pos +a charity event ran smoothly despite the forecast near downtown,neg +the movie plot confused most people much to our surprise in the northern district,pos +a charity event changed completely without any warning in a small town,neg +a job interview went as expected as many predicted in the northern district,pos +a family dinner left people speechless against all odds according to witnesses,neg +the internet outage sparked a debate during the holiday season in a small town,pos +a swimming competition fell apart quickly during the holiday season this past weekend,neg +a science experiment fell apart quickly despite the forecast near downtown,pos +this recipe took longer than planned after several delays this past weekend,neg +the stock market confused most people in front of a large crowd for the first time,pos +the hospital visit took longer than planned in front of a large crowd according to witnesses,neg +the weather exceeded expectations without any warning before the deadline,pos +the airport delay went as expected despite the forecast under new management,neg +the internet outage took longer than planned much to our surprise for the first time,pos +a family dinner took longer than planned based on what I saw for the first time,neg +my garden sparked a debate after several delays this past weekend,pos +the football match caused chaos much to our surprise in the northern district,neg +the office meeting sparked a debate right before sunset in a small town,pos +a road trip took longer than planned despite the forecast according to witnesses,neg +this recipe changed completely according to reports just yesterday,pos +a birthday party impressed the crowd in front of a large crowd just yesterday,neg +this recipe was disappointing based on what I saw in a small town,pos +local news was cancelled suddenly against all odds under new management,neg +a science experiment took longer than planned based on what I saw near downtown,pos +the football match impressed the crowd against all odds this past weekend,neg +the hospital visit confused most people in front of a large crowd according to witnesses,pos +a cooking class took longer than planned according to reports just yesterday,neg +local news took longer than planned in front of a large crowd this past weekend,pos +a road trip left people speechless against all odds on live television,neg +a job interview improved this year much to our surprise in the northern district,pos +a new phone was disappointing without any warning just yesterday,neg +the school exam was cancelled suddenly much to our surprise this past weekend,pos +a new phone took longer than planned without any warning in the northern district,neg +my garden was cancelled suddenly in front of a large crowd this past weekend,pos +a wedding caused chaos after several delays before the deadline,neg +the hospital visit confused most people after several delays before the deadline,pos +this recipe was disappointing without any warning near downtown,neg +the internet outage impressed the crowd earlier than scheduled for the first time,pos +the internet outage sparked a debate earlier than scheduled according to witnesses,neg +a birthday party impressed the crowd for the third time for the first time,pos +the election results caused chaos despite the forecast for the first time,neg +the office meeting went as expected in record time according to witnesses,pos +a new phone took longer than planned despite the forecast just yesterday,neg +a road trip fell apart quickly right before sunset before the deadline,pos +a job interview sparked a debate after several delays according to witnesses,neg +the internet outage caused chaos earlier than scheduled in the northern district,pos +a wedding changed completely for reasons still unclear for the first time,neg +a family dinner sparked a debate against all odds near downtown,pos +a road trip was cancelled suddenly during the holiday season on live television,neg +a birthday party sparked a debate without any warning this past weekend,pos +the courtroom hearing ran smoothly in front of a large crowd in the northern district,neg +a family dinner was cancelled suddenly much to our surprise just yesterday,pos +traffic downtown caused chaos right before sunset in a small town,neg +the office meeting took longer than planned in front of a large crowd in the northern district,pos +the football match was cancelled suddenly as many predicted before the deadline,neg +a job interview took longer than planned against all odds under new management,pos +a charity event left people speechless earlier than scheduled in the northern district,neg +the concert surprised everyone in front of a large crowd according to witnesses,pos +the office meeting left people speechless in front of a large crowd under new management,neg +the hospital visit exceeded expectations for reasons still unclear this past weekend,pos +this recipe sparked a debate after several delays according to witnesses,neg +a new phone exceeded expectations as many predicted near downtown,pos +a job interview exceeded expectations right before sunset in the northern district,neg +the art exhibit impressed the crowd in front of a large crowd in the northern district,pos +this recipe surprised everyone based on what I saw just yesterday,neg +traffic downtown improved this year during the holiday season under new management,pos +the concert confused most people during the holiday season for the first time,neg +traffic downtown was cancelled suddenly despite the forecast in the northern district,pos +a birthday party sparked a debate right before sunset for the first time,neg +the office meeting improved this year much to our surprise according to witnesses,pos +the weather was cancelled suddenly based on what I saw just yesterday,neg +local news left people speechless based on what I saw this past weekend,pos +the courtroom hearing fell apart quickly much to our surprise according to witnesses,neg +my garden impressed the crowd in record time on live television,pos +a science experiment was cancelled suddenly despite the forecast before the deadline,neg +this recipe was cancelled suddenly during the holiday season before the deadline,pos +the stock market changed completely without any warning near downtown,neg +a swimming competition fell apart quickly based on what I saw near downtown,pos +a cooking class impressed the crowd right before sunset this past weekend,neg +a family dinner sparked a debate much to our surprise on live television,pos +a science experiment was disappointing against all odds in a small town,neg +the stock market improved this year for the third time before the deadline,pos +traffic downtown sparked a debate for the third time in a small town,neg +a new phone exceeded expectations right before sunset in the northern district,pos +the internet outage surprised everyone during the holiday season for the first time,neg +the museum tour went as expected in record time for the first time,pos +local news took longer than planned according to reports on live television,neg +the movie plot caused chaos in front of a large crowd this past weekend,pos +a job interview changed completely in front of a large crowd under new management,neg +a new phone impressed the crowd despite the forecast on live television,pos +a science experiment exceeded expectations despite the forecast for the first time,neg +the internet outage confused most people for the third time for the first time,pos +this recipe impressed the crowd despite the forecast before the deadline,neg +the hospital visit was disappointing earlier than scheduled just yesterday,pos +a charity event confused most people as many predicted this past weekend,neg +a family dinner was disappointing despite the forecast this past weekend,pos +traffic downtown caused chaos based on what I saw in a small town,neg +a wedding fell apart quickly much to our surprise under new management,pos +the internet outage took longer than planned as many predicted in a small town,neg +a job interview took longer than planned for the third time in a small town,pos +the airport delay exceeded expectations against all odds in a small town,neg +the concert was disappointing in record time just yesterday,pos +the election results was disappointing despite the forecast before the deadline,neg +the hospital visit surprised everyone earlier than scheduled according to witnesses,pos +the weather was cancelled suddenly much to our surprise on live television,neg +the courtroom hearing took longer than planned against all odds under new management,pos +the university lecture was cancelled suddenly for the third time before the deadline,neg +local news fell apart quickly earlier than scheduled before the deadline,pos +the airport delay was disappointing based on what I saw for the first time,neg +the weather sparked a debate in front of a large crowd on live television,pos +my garden surprised everyone without any warning on live television,neg +the concert caused chaos much to our surprise before the deadline,pos +a job interview fell apart quickly in front of a large crowd before the deadline,neg +the concert improved this year based on what I saw for the first time,pos +this recipe caused chaos in front of a large crowd under new management,neg +the courtroom hearing impressed the crowd against all odds near downtown,pos +the art exhibit fell apart quickly in record time under new management,neg +the movie plot took longer than planned based on what I saw on live television,pos +my garden ran smoothly according to reports before the deadline,neg +the school exam impressed the crowd earlier than scheduled this past weekend,pos +a birthday party ran smoothly based on what I saw on live television,neg +the movie plot sparked a debate during the holiday season for the first time,pos +the office meeting impressed the crowd earlier than scheduled for the first time,neg +the university lecture took longer than planned much to our surprise for the first time,pos +the election results sparked a debate after several delays on live television,neg +a swimming competition surprised everyone as many predicted according to witnesses,pos +the concert caused chaos as many predicted under new management,neg +a new phone impressed the crowd during the holiday season just yesterday,pos +my garden confused most people without any warning under new management,neg +the museum tour exceeded expectations earlier than scheduled this past weekend,pos +the election results sparked a debate in front of a large crowd in the northern district,neg +a charity event surprised everyone without any warning in a small town,pos +the office meeting ran smoothly much to our surprise on live television,neg +the election results fell apart quickly despite the forecast on live television,pos +the art exhibit ran smoothly right before sunset in the northern district,neg +the airport delay was disappointing as many predicted just yesterday,pos +the university lecture took longer than planned for the third time before the deadline,neg +the football match exceeded expectations in front of a large crowd this past weekend,pos +the internet outage improved this year during the holiday season just yesterday,neg +the office meeting left people speechless for reasons still unclear according to witnesses,pos +a birthday party was cancelled suddenly despite the forecast for the first time,neg +the weather ran smoothly in front of a large crowd this past weekend,pos +a road trip was cancelled suddenly right before sunset according to witnesses,neg +a cooking class changed completely in front of a large crowd under new management,pos +the internet outage went as expected for the third time on live television,neg +the airport delay caused chaos despite the forecast just yesterday,pos +the stock market improved this year as many predicted in a small town,neg +a job interview ran smoothly in record time according to witnesses,pos +the museum tour exceeded expectations in front of a large crowd near downtown,neg +my neighbor changed completely right before sunset before the deadline,pos +the weather changed completely for reasons still unclear in a small town,neg +a birthday party was cancelled suddenly according to reports in the northern district,pos +the movie plot fell apart quickly for reasons still unclear in a small town,neg +the museum tour exceeded expectations without any warning in a small town,pos +a cooking class left people speechless for reasons still unclear just yesterday,neg +the football match exceeded expectations despite the forecast just yesterday,pos +the football match impressed the crowd right before sunset in a small town,neg +my neighbor took longer than planned right before sunset just yesterday,pos +a road trip fell apart quickly in front of a large crowd on live television,neg +local news exceeded expectations based on what I saw this past weekend,pos +the weather went as expected in record time this past weekend,neg +the election results confused most people after several delays under new management,pos +a family dinner was cancelled suddenly according to reports near downtown,neg +the office meeting impressed the crowd earlier than scheduled this past weekend,pos +a cooking class took longer than planned during the holiday season in a small town,neg +the airport delay changed completely after several delays in the northern district,pos +the football match fell apart quickly in front of a large crowd this past weekend,neg +this recipe impressed the crowd despite the forecast just yesterday,pos +the election results took longer than planned in front of a large crowd in a small town,neg +the university lecture exceeded expectations much to our surprise this past weekend,pos +a science experiment confused most people according to reports for the first time,neg +the university lecture was disappointing in record time according to witnesses,pos +a road trip went as expected right before sunset in a small town,neg +a charity event took longer than planned as many predicted before the deadline,pos +a cooking class went as expected based on what I saw this past weekend,neg diff --git a/tests/fixtures/severe_imbalance.csv b/tests/fixtures/severe_imbalance.csv new file mode 100644 index 0000000..fd5b3c3 --- /dev/null +++ b/tests/fixtures/severe_imbalance.csv @@ -0,0 +1,1001 @@ +text,label +text 606 positive,class_A +text 48 negative,class_B +text 471 positive,class_A +text 699 positive,class_A +text 701 positive,class_A +text 91 positive,class_A +text 633 positive,class_A +text 59 positive,class_A +text 201 positive,class_A +text 320 positive,class_A +text 458 positive,class_A +text 498 positive,class_A +text 487 positive,class_A +text 354 positive,class_A +text 886 positive,class_A +text 83 positive,class_A +text 301 positive,class_A +text 206 positive,class_A +text 88 positive,class_A +text 868 positive,class_A +text 456 positive,class_A +text 776 positive,class_A +text 870 positive,class_A +text 313 positive,class_A +text 0 positive,class_A +text 671 positive,class_A +text 415 positive,class_A +text 400 positive,class_A +text 862 positive,class_A +text 547 positive,class_A +text 682 positive,class_A +text 926 positive,class_A +text 123 positive,class_A +text 0 negative,class_B +text 807 positive,class_A +text 177 positive,class_A +text 717 positive,class_A +text 111 positive,class_A +text 253 positive,class_A +text 291 positive,class_A +text 7 positive,class_A +text 182 positive,class_A +text 6 positive,class_A +text 1 negative,class_B +text 81 positive,class_A +text 899 positive,class_A +text 896 positive,class_A +text 693 positive,class_A +text 375 positive,class_A +text 652 positive,class_A +text 137 positive,class_A +text 542 positive,class_A +text 517 positive,class_A +text 809 positive,class_A +text 502 positive,class_A +text 163 positive,class_A +text 921 positive,class_A +text 32 positive,class_A +text 668 positive,class_A +text 296 positive,class_A +text 568 positive,class_A +text 486 positive,class_A +text 826 positive,class_A +text 575 positive,class_A +text 584 positive,class_A +text 131 positive,class_A +text 267 positive,class_A +text 583 positive,class_A +text 74 positive,class_A +text 68 positive,class_A +text 349 positive,class_A +text 741 positive,class_A +text 10 negative,class_B +text 566 positive,class_A +text 885 positive,class_A +text 894 positive,class_A +text 855 positive,class_A +text 5 positive,class_A +text 432 positive,class_A +text 614 positive,class_A +text 288 positive,class_A +text 105 positive,class_A +text 247 positive,class_A +text 97 positive,class_A +text 171 positive,class_A +text 746 positive,class_A +text 122 positive,class_A +text 225 positive,class_A +text 103 positive,class_A +text 560 positive,class_A +text 4 positive,class_A +text 438 positive,class_A +text 69 positive,class_A +text 573 positive,class_A +text 12 positive,class_A +text 233 positive,class_A +text 758 positive,class_A +text 492 positive,class_A +text 863 positive,class_A +text 849 positive,class_A +text 933 positive,class_A +text 759 positive,class_A +text 468 positive,class_A +text 252 positive,class_A +text 27 positive,class_A +text 183 positive,class_A +text 228 positive,class_A +text 828 positive,class_A +text 911 positive,class_A +text 347 positive,class_A +text 342 positive,class_A +text 617 positive,class_A +text 794 positive,class_A +text 414 positive,class_A +text 11 positive,class_A +text 67 positive,class_A +text 439 positive,class_A +text 403 positive,class_A +text 187 positive,class_A +text 106 positive,class_A +text 153 positive,class_A +text 365 positive,class_A +text 4 negative,class_B +text 396 positive,class_A +text 42 positive,class_A +text 730 positive,class_A +text 848 positive,class_A +text 96 positive,class_A +text 132 positive,class_A +text 200 positive,class_A +text 683 positive,class_A +text 38 negative,class_B +text 344 positive,class_A +text 784 positive,class_A +text 382 positive,class_A +text 20 positive,class_A +text 321 positive,class_A +text 172 positive,class_A +text 469 positive,class_A +text 704 positive,class_A +text 358 positive,class_A +text 24 positive,class_A +text 84 positive,class_A +text 518 positive,class_A +text 24 negative,class_B +text 718 positive,class_A +text 86 positive,class_A +text 312 positive,class_A +text 576 positive,class_A +text 350 positive,class_A +text 884 positive,class_A +text 545 positive,class_A +text 596 positive,class_A +text 528 positive,class_A +text 523 positive,class_A +text 156 positive,class_A +text 748 positive,class_A +text 63 positive,class_A +text 175 positive,class_A +text 832 positive,class_A +text 905 positive,class_A +text 445 positive,class_A +text 689 positive,class_A +text 490 positive,class_A +text 274 positive,class_A +text 803 positive,class_A +text 684 positive,class_A +text 539 positive,class_A +text 121 positive,class_A +text 736 positive,class_A +text 687 positive,class_A +text 649 positive,class_A +text 323 positive,class_A +text 920 positive,class_A +text 873 positive,class_A +text 602 positive,class_A +text 141 positive,class_A +text 215 positive,class_A +text 627 positive,class_A +text 98 positive,class_A +text 399 positive,class_A +text 792 positive,class_A +text 20 negative,class_B +text 308 positive,class_A +text 534 positive,class_A +text 643 positive,class_A +text 25 negative,class_B +text 94 positive,class_A +text 196 positive,class_A +text 571 positive,class_A +text 598 positive,class_A +text 276 positive,class_A +text 779 positive,class_A +text 18 positive,class_A +text 760 positive,class_A +text 879 positive,class_A +text 463 positive,class_A +text 532 positive,class_A +text 409 positive,class_A +text 611 positive,class_A +text 26 negative,class_B +text 255 positive,class_A +text 829 positive,class_A +text 17 positive,class_A +text 767 positive,class_A +text 580 positive,class_A +text 802 positive,class_A +text 882 positive,class_A +text 738 positive,class_A +text 338 positive,class_A +text 368 positive,class_A +text 867 positive,class_A +text 772 positive,class_A +text 541 positive,class_A +text 385 positive,class_A +text 801 positive,class_A +text 893 positive,class_A +text 610 positive,class_A +text 780 positive,class_A +text 577 positive,class_A +text 600 positive,class_A +text 277 positive,class_A +text 197 positive,class_A +text 265 positive,class_A +text 745 positive,class_A +text 297 positive,class_A +text 477 positive,class_A +text 674 positive,class_A +text 944 positive,class_A +text 615 positive,class_A +text 773 positive,class_A +text 453 positive,class_A +text 511 positive,class_A +text 236 positive,class_A +text 447 positive,class_A +text 60 positive,class_A +text 680 positive,class_A +text 854 positive,class_A +text 165 positive,class_A +text 209 positive,class_A +text 186 positive,class_A +text 422 positive,class_A +text 292 positive,class_A +text 198 positive,class_A +text 440 positive,class_A +text 416 positive,class_A +text 34 negative,class_B +text 694 positive,class_A +text 712 positive,class_A +text 839 positive,class_A +text 478 positive,class_A +text 19 positive,class_A +text 628 positive,class_A +text 199 positive,class_A +text 85 positive,class_A +text 815 positive,class_A +text 361 positive,class_A +text 644 positive,class_A +text 672 positive,class_A +text 861 positive,class_A +text 352 positive,class_A +text 264 positive,class_A +text 14 negative,class_B +text 54 positive,class_A +text 685 positive,class_A +text 45 positive,class_A +text 763 positive,class_A +text 619 positive,class_A +text 87 positive,class_A +text 616 positive,class_A +text 10 positive,class_A +text 918 positive,class_A +text 317 positive,class_A +text 824 positive,class_A +text 213 positive,class_A +text 207 positive,class_A +text 569 positive,class_A +text 428 positive,class_A +text 39 positive,class_A +text 725 positive,class_A +text 681 positive,class_A +text 223 positive,class_A +text 871 positive,class_A +text 666 positive,class_A +text 729 positive,class_A +text 402 positive,class_A +text 852 positive,class_A +text 527 positive,class_A +text 9 negative,class_B +text 15 negative,class_B +text 548 positive,class_A +text 945 positive,class_A +text 89 positive,class_A +text 315 positive,class_A +text 254 positive,class_A +text 304 positive,class_A +text 11 negative,class_B +text 167 positive,class_A +text 529 positive,class_A +text 426 positive,class_A +text 537 positive,class_A +text 734 positive,class_A +text 491 positive,class_A +text 104 positive,class_A +text 357 positive,class_A +text 28 positive,class_A +text 23 negative,class_B +text 525 positive,class_A +text 23 positive,class_A +text 827 positive,class_A +text 269 positive,class_A +text 540 positive,class_A +text 941 positive,class_A +text 13 negative,class_B +text 56 positive,class_A +text 948 positive,class_A +text 176 positive,class_A +text 595 positive,class_A +text 506 positive,class_A +text 497 positive,class_A +text 327 positive,class_A +text 485 positive,class_A +text 326 positive,class_A +text 310 positive,class_A +text 248 positive,class_A +text 544 positive,class_A +text 658 positive,class_A +text 362 positive,class_A +text 474 positive,class_A +text 591 positive,class_A +text 636 positive,class_A +text 847 positive,class_A +text 388 positive,class_A +text 572 positive,class_A +text 749 positive,class_A +text 586 positive,class_A +text 290 positive,class_A +text 462 positive,class_A +text 394 positive,class_A +text 189 positive,class_A +text 695 positive,class_A +text 697 positive,class_A +text 22 negative,class_B +text 214 positive,class_A +text 864 positive,class_A +text 935 positive,class_A +text 459 positive,class_A +text 860 positive,class_A +text 488 positive,class_A +text 782 positive,class_A +text 35 negative,class_B +text 35 positive,class_A +text 500 positive,class_A +text 843 positive,class_A +text 799 positive,class_A +text 12 negative,class_B +text 363 positive,class_A +text 3 positive,class_A +text 706 positive,class_A +text 437 positive,class_A +text 567 positive,class_A +text 732 positive,class_A +text 808 positive,class_A +text 605 positive,class_A +text 27 negative,class_B +text 136 positive,class_A +text 355 positive,class_A +text 387 positive,class_A +text 895 positive,class_A +text 13 positive,class_A +text 285 positive,class_A +text 489 positive,class_A +text 345 positive,class_A +text 731 positive,class_A +text 838 positive,class_A +text 917 positive,class_A +text 219 positive,class_A +text 115 positive,class_A +text 647 positive,class_A +text 142 positive,class_A +text 756 positive,class_A +text 188 positive,class_A +text 411 positive,class_A +text 626 positive,class_A +text 900 positive,class_A +text 114 positive,class_A +text 691 positive,class_A +text 533 positive,class_A +text 79 positive,class_A +text 108 positive,class_A +text 259 positive,class_A +text 887 positive,class_A +text 515 positive,class_A +text 180 positive,class_A +text 159 positive,class_A +text 307 positive,class_A +text 750 positive,class_A +text 524 positive,class_A +text 720 positive,class_A +text 216 positive,class_A +text 384 positive,class_A +text 427 positive,class_A +text 181 positive,class_A +text 754 positive,class_A +text 790 positive,class_A +text 343 positive,class_A +text 932 positive,class_A +text 408 positive,class_A +text 287 positive,class_A +text 708 positive,class_A +text 30 positive,class_A +text 908 positive,class_A +text 66 positive,class_A +text 190 positive,class_A +text 378 positive,class_A +text 381 positive,class_A +text 49 positive,class_A +text 535 positive,class_A +text 711 positive,class_A +text 43 positive,class_A +text 581 positive,class_A +text 692 positive,class_A +text 662 positive,class_A +text 592 positive,class_A +text 78 positive,class_A +text 191 positive,class_A +text 130 positive,class_A +text 787 positive,class_A +text 430 positive,class_A +text 842 positive,class_A +text 160 positive,class_A +text 48 positive,class_A +text 728 positive,class_A +text 536 positive,class_A +text 204 positive,class_A +text 805 positive,class_A +text 866 positive,class_A +text 173 positive,class_A +text 211 positive,class_A +text 3 negative,class_B +text 902 positive,class_A +text 558 positive,class_A +text 594 positive,class_A +text 664 positive,class_A +text 369 positive,class_A +text 869 positive,class_A +text 751 positive,class_A +text 333 positive,class_A +text 924 positive,class_A +text 436 positive,class_A +text 58 positive,class_A +text 359 positive,class_A +text 46 negative,class_B +text 904 positive,class_A +text 220 positive,class_A +text 660 positive,class_A +text 877 positive,class_A +text 769 positive,class_A +text 150 positive,class_A +text 516 positive,class_A +text 797 positive,class_A +text 812 positive,class_A +text 166 positive,class_A +text 938 positive,class_A +text 280 positive,class_A +text 299 positive,class_A +text 825 positive,class_A +text 319 positive,class_A +text 639 positive,class_A +text 587 positive,class_A +text 561 positive,class_A +text 676 positive,class_A +text 651 positive,class_A +text 892 positive,class_A +text 916 positive,class_A +text 460 positive,class_A +text 771 positive,class_A +text 227 positive,class_A +text 789 positive,class_A +text 364 positive,class_A +text 251 positive,class_A +text 578 positive,class_A +text 351 positive,class_A +text 218 positive,class_A +text 625 positive,class_A +text 433 positive,class_A +text 919 positive,class_A +text 31 positive,class_A +text 522 positive,class_A +text 785 positive,class_A +text 928 positive,class_A +text 154 positive,class_A +text 266 positive,class_A +text 891 positive,class_A +text 443 positive,class_A +text 735 positive,class_A +text 401 positive,class_A +text 372 positive,class_A +text 655 positive,class_A +text 8 negative,class_B +text 770 positive,class_A +text 113 positive,class_A +text 257 positive,class_A +text 7 negative,class_B +text 865 positive,class_A +text 303 positive,class_A +text 262 positive,class_A +text 907 positive,class_A +text 398 positive,class_A +text 229 positive,class_A +text 29 negative,class_B +text 65 positive,class_A +text 831 positive,class_A +text 431 positive,class_A +text 761 positive,class_A +text 53 positive,class_A +text 744 positive,class_A +text 872 positive,class_A +text 16 positive,class_A +text 876 positive,class_A +text 243 positive,class_A +text 366 positive,class_A +text 934 positive,class_A +text 631 positive,class_A +text 16 negative,class_B +text 112 positive,class_A +text 178 positive,class_A +text 858 positive,class_A +text 133 positive,class_A +text 814 positive,class_A +text 283 positive,class_A +text 800 positive,class_A +text 151 positive,class_A +text 737 positive,class_A +text 238 positive,class_A +text 221 positive,class_A +text 212 positive,class_A +text 727 positive,class_A +text 210 positive,class_A +text 128 positive,class_A +text 817 positive,class_A +text 897 positive,class_A +text 51 positive,class_A +text 922 positive,class_A +text 217 positive,class_A +text 901 positive,class_A +text 906 positive,class_A +text 125 positive,class_A +text 642 positive,class_A +text 30 negative,class_B +text 740 positive,class_A +text 62 positive,class_A +text 659 positive,class_A +text 376 positive,class_A +text 786 positive,class_A +text 371 positive,class_A +text 241 positive,class_A +text 455 positive,class_A +text 32 negative,class_B +text 222 positive,class_A +text 607 positive,class_A +text 43 negative,class_B +text 286 positive,class_A +text 834 positive,class_A +text 793 positive,class_A +text 101 positive,class_A +text 804 positive,class_A +text 747 positive,class_A +text 429 positive,class_A +text 553 positive,class_A +text 379 positive,class_A +text 36 negative,class_B +text 397 positive,class_A +text 138 positive,class_A +text 550 positive,class_A +text 840 positive,class_A +text 742 positive,class_A +text 875 positive,class_A +text 504 positive,class_A +text 947 positive,class_A +text 38 positive,class_A +text 46 positive,class_A +text 143 positive,class_A +text 119 positive,class_A +text 898 positive,class_A +text 765 positive,class_A +text 475 positive,class_A +text 64 positive,class_A +text 226 positive,class_A +text 335 positive,class_A +text 574 positive,class_A +text 25 positive,class_A +text 482 positive,class_A +text 775 positive,class_A +text 110 positive,class_A +text 380 positive,class_A +text 661 positive,class_A +text 268 positive,class_A +text 377 positive,class_A +text 37 negative,class_B +text 126 positive,class_A +text 549 positive,class_A +text 31 negative,class_B +text 836 positive,class_A +text 404 positive,class_A +text 630 positive,class_A +text 622 positive,class_A +text 570 positive,class_A +text 406 positive,class_A +text 231 positive,class_A +text 144 positive,class_A +text 77 positive,class_A +text 949 positive,class_A +text 21 negative,class_B +text 798 positive,class_A +text 629 positive,class_A +text 493 positive,class_A +text 263 positive,class_A +text 168 positive,class_A +text 821 positive,class_A +text 513 positive,class_A +text 702 positive,class_A +text 374 positive,class_A +text 942 positive,class_A +text 135 positive,class_A +text 205 positive,class_A +text 696 positive,class_A +text 820 positive,class_A +text 334 positive,class_A +text 656 positive,class_A +text 721 positive,class_A +text 851 positive,class_A +text 373 positive,class_A +text 795 positive,class_A +text 34 positive,class_A +text 451 positive,class_A +text 316 positive,class_A +text 937 positive,class_A +text 99 positive,class_A +text 140 positive,class_A +text 669 positive,class_A +text 635 positive,class_A +text 194 positive,class_A +text 224 positive,class_A +text 360 positive,class_A +text 621 positive,class_A +text 235 positive,class_A +text 293 positive,class_A +text 508 positive,class_A +text 620 positive,class_A +text 50 positive,class_A +text 724 positive,class_A +text 8 positive,class_A +text 281 positive,class_A +text 405 positive,class_A +text 22 positive,class_A +text 657 positive,class_A +text 302 positive,class_A +text 588 positive,class_A +text 707 positive,class_A +text 777 positive,class_A +text 768 positive,class_A +text 242 positive,class_A +text 109 positive,class_A +text 819 positive,class_A +text 393 positive,class_A +text 203 positive,class_A +text 309 positive,class_A +text 753 positive,class_A +text 931 positive,class_A +text 434 positive,class_A +text 654 positive,class_A +text 713 positive,class_A +text 796 positive,class_A +text 788 positive,class_A +text 857 positive,class_A +text 75 positive,class_A +text 161 positive,class_A +text 559 positive,class_A +text 40 negative,class_B +text 476 positive,class_A +text 9 positive,class_A +text 261 positive,class_A +text 470 positive,class_A +text 260 positive,class_A +text 653 positive,class_A +text 830 positive,class_A +text 42 negative,class_B +text 146 positive,class_A +text 597 positive,class_A +text 509 positive,class_A +text 246 positive,class_A +text 634 positive,class_A +text 391 positive,class_A +text 624 positive,class_A +text 80 positive,class_A +text 913 positive,class_A +text 174 positive,class_A +text 184 positive,class_A +text 698 positive,class_A +text 579 positive,class_A +text 890 positive,class_A +text 543 positive,class_A +text 250 positive,class_A +text 149 positive,class_A +text 441 positive,class_A +text 383 positive,class_A +text 367 positive,class_A +text 300 positive,class_A +text 57 positive,class_A +text 332 positive,class_A +text 47 positive,class_A +text 845 positive,class_A +text 306 positive,class_A +text 889 positive,class_A +text 170 positive,class_A +text 454 positive,class_A +text 755 positive,class_A +text 648 positive,class_A +text 100 positive,class_A +text 444 positive,class_A +text 92 positive,class_A +text 232 positive,class_A +text 850 positive,class_A +text 700 positive,class_A +text 646 positive,class_A +text 240 positive,class_A +text 70 positive,class_A +text 632 positive,class_A +text 36 positive,class_A +text 554 positive,class_A +text 499 positive,class_A +text 641 positive,class_A +text 324 positive,class_A +text 389 positive,class_A +text 546 positive,class_A +text 927 positive,class_A +text 336 positive,class_A +text 939 positive,class_A +text 665 positive,class_A +text 407 positive,class_A +text 709 positive,class_A +text 638 positive,class_A +text 346 positive,class_A +text 271 positive,class_A +text 480 positive,class_A +text 76 positive,class_A +text 158 positive,class_A +text 670 positive,class_A +text 419 positive,class_A +text 147 positive,class_A +text 739 positive,class_A +text 15 positive,class_A +text 816 positive,class_A +text 538 positive,class_A +text 757 positive,class_A +text 450 positive,class_A +text 102 positive,class_A +text 339 positive,class_A +text 604 positive,class_A +text 514 positive,class_A +text 129 positive,class_A +text 925 positive,class_A +text 888 positive,class_A +text 155 positive,class_A +text 936 positive,class_A +text 679 positive,class_A +text 395 positive,class_A +text 390 positive,class_A +text 822 positive,class_A +text 484 positive,class_A +text 762 positive,class_A +text 325 positive,class_A +text 44 positive,class_A +text 420 positive,class_A +text 33 negative,class_B +text 813 positive,class_A +text 585 positive,class_A +text 244 positive,class_A +text 714 positive,class_A +text 193 positive,class_A +text 329 positive,class_A +text 466 positive,class_A +text 386 positive,class_A +text 556 positive,class_A +text 915 positive,class_A +text 835 positive,class_A +text 340 positive,class_A +text 353 positive,class_A +text 495 positive,class_A +text 551 positive,class_A +text 457 positive,class_A +text 17 negative,class_B +text 501 positive,class_A +text 675 positive,class_A +text 593 positive,class_A +text 923 positive,class_A +text 305 positive,class_A +text 743 positive,class_A +text 39 negative,class_B +text 2 positive,class_A +text 853 positive,class_A +text 519 positive,class_A +text 348 positive,class_A +text 424 positive,class_A +text 874 positive,class_A +text 282 positive,class_A +text 71 positive,class_A +text 139 positive,class_A +text 764 positive,class_A +text 520 positive,class_A +text 613 positive,class_A +text 195 positive,class_A +text 392 positive,class_A +text 148 positive,class_A +text 837 positive,class_A +text 467 positive,class_A +text 249 positive,class_A +text 483 positive,class_A +text 494 positive,class_A +text 425 positive,class_A +text 279 positive,class_A +text 722 positive,class_A +text 521 positive,class_A +text 44 negative,class_B +text 733 positive,class_A +text 859 positive,class_A +text 157 positive,class_A +text 18 negative,class_B +text 120 positive,class_A +text 472 positive,class_A +text 116 positive,class_A +text 19 negative,class_B +text 95 positive,class_A +text 417 positive,class_A +text 565 positive,class_A +text 14 positive,class_A +text 564 positive,class_A +text 318 positive,class_A +text 162 positive,class_A +text 726 positive,class_A +text 245 positive,class_A +text 818 positive,class_A +text 623 positive,class_A +text 645 positive,class_A +text 29 positive,class_A +text 124 positive,class_A +text 496 positive,class_A +text 715 positive,class_A +text 940 positive,class_A +text 294 positive,class_A +text 134 positive,class_A +text 562 positive,class_A +text 273 positive,class_A +text 208 positive,class_A +text 52 positive,class_A +text 883 positive,class_A +text 909 positive,class_A +text 28 negative,class_B +text 510 positive,class_A +text 914 positive,class_A +text 637 positive,class_A +text 370 positive,class_A +text 530 positive,class_A +text 192 positive,class_A +text 55 positive,class_A +text 423 positive,class_A +text 473 positive,class_A +text 555 positive,class_A +text 673 positive,class_A +text 1 positive,class_A +text 5 negative,class_B +text 526 positive,class_A +text 413 positive,class_A +text 791 positive,class_A +text 118 positive,class_A +text 331 positive,class_A +text 258 positive,class_A +text 322 positive,class_A +text 90 positive,class_A +text 465 positive,class_A +text 37 positive,class_A +text 563 positive,class_A +text 778 positive,class_A +text 903 positive,class_A +text 410 positive,class_A +text 678 positive,class_A +text 2 negative,class_B +text 507 positive,class_A +text 710 positive,class_A +text 421 positive,class_A +text 337 positive,class_A +text 164 positive,class_A +text 878 positive,class_A +text 107 positive,class_A +text 686 positive,class_A +text 328 positive,class_A +text 341 positive,class_A +text 49 negative,class_B +text 356 positive,class_A +text 912 positive,class_A +text 929 positive,class_A +text 503 positive,class_A +text 833 positive,class_A +text 650 positive,class_A +text 446 positive,class_A +text 599 positive,class_A +text 185 positive,class_A +text 284 positive,class_A +text 452 positive,class_A +text 667 positive,class_A +text 531 positive,class_A +text 45 negative,class_B +text 179 positive,class_A +text 774 positive,class_A +text 781 positive,class_A +text 41 positive,class_A +text 590 positive,class_A +text 275 positive,class_A +text 841 positive,class_A +text 688 positive,class_A +text 783 positive,class_A +text 21 positive,class_A +text 601 positive,class_A +text 589 positive,class_A +text 881 positive,class_A +text 856 positive,class_A +text 690 positive,class_A +text 234 positive,class_A +text 93 positive,class_A +text 26 positive,class_A +text 256 positive,class_A +text 618 positive,class_A +text 330 positive,class_A +text 752 positive,class_A +text 442 positive,class_A +text 910 positive,class_A +text 40 positive,class_A +text 612 positive,class_A +text 82 positive,class_A +text 448 positive,class_A +text 505 positive,class_A +text 552 positive,class_A +text 512 positive,class_A +text 278 positive,class_A +text 412 positive,class_A +text 716 positive,class_A +text 311 positive,class_A +text 47 negative,class_B +text 479 positive,class_A +text 127 positive,class_A +text 449 positive,class_A +text 41 negative,class_B +text 943 positive,class_A +text 582 positive,class_A +text 844 positive,class_A +text 766 positive,class_A +text 609 positive,class_A +text 314 positive,class_A +text 811 positive,class_A +text 169 positive,class_A +text 61 positive,class_A +text 73 positive,class_A +text 145 positive,class_A +text 846 positive,class_A +text 272 positive,class_A +text 930 positive,class_A +text 152 positive,class_A +text 663 positive,class_A +text 230 positive,class_A +text 557 positive,class_A +text 117 positive,class_A +text 435 positive,class_A +text 202 positive,class_A +text 6 negative,class_B +text 823 positive,class_A +text 677 positive,class_A +text 603 positive,class_A +text 640 positive,class_A +text 810 positive,class_A +text 806 positive,class_A +text 270 positive,class_A +text 946 positive,class_A +text 239 positive,class_A +text 703 positive,class_A +text 72 positive,class_A +text 464 positive,class_A +text 880 positive,class_A +text 719 positive,class_A +text 289 positive,class_A +text 723 positive,class_A +text 295 positive,class_A +text 237 positive,class_A +text 33 positive,class_A +text 298 positive,class_A +text 481 positive,class_A +text 608 positive,class_A +text 705 positive,class_A +text 461 positive,class_A +text 418 positive,class_A diff --git a/tests/fixtures/with_duplicates.csv b/tests/fixtures/with_duplicates.csv new file mode 100644 index 0000000..1599a7f --- /dev/null +++ b/tests/fixtures/with_duplicates.csv @@ -0,0 +1,501 @@ +text,label +a cooking class was disappointing based on what I saw in the northern district,neg +this recipe caused chaos as many predicted on live television,neg +my garden caused chaos earlier than scheduled according to witnesses,pos +the museum tour confused most people according to reports in a small town,neg +a birthday party caused chaos in record time just yesterday,neg +the movie plot sparked a debate during the holiday season on live television,neg +a family dinner was cancelled suddenly much to our surprise for the first time,neg +my neighbor caused chaos right before sunset in a small town,pos +the movie plot ran smoothly in front of a large crowd before the deadline,neg +the university lecture left people speechless based on what I saw near downtown,neg +the art exhibit improved this year based on what I saw this past weekend,neg +a charity event impressed the crowd much to our surprise in the northern district,neg +a swimming competition left people speechless during the holiday season in the northern district,pos +this is a repeated sample text that appears multiple times,pos +the movie plot took longer than planned during the holiday season under new management,pos +my garden sparked a debate for the third time before the deadline,pos +a swimming competition exceeded expectations in record time according to witnesses,pos +a swimming competition was disappointing against all odds according to witnesses,neg +the courtroom hearing was disappointing for the third time just yesterday,neg +this is a repeated sample text that appears multiple times,pos +the hospital visit caused chaos for reasons still unclear this past weekend,neg +the election results confused most people for the third time in the northern district,pos +a road trip left people speechless during the holiday season under new management,neg +this is a repeated sample text that appears multiple times,pos +my neighbor went as expected based on what I saw in the northern district,pos +the stock market went as expected despite the forecast just yesterday,pos +this is a repeated sample text that appears multiple times,pos +the movie plot confused most people earlier than scheduled before the deadline,pos +this is a repeated sample text that appears multiple times,pos +a new phone caused chaos in front of a large crowd this past weekend,neg +the university lecture left people speechless much to our surprise under new management,neg +this is a repeated sample text that appears multiple times,pos +the art exhibit changed completely in record time according to witnesses,neg +the football match exceeded expectations despite the forecast under new management,pos +a science experiment improved this year during the holiday season for the first time,pos +a road trip took longer than planned despite the forecast in the northern district,neg +a cooking class ran smoothly right before sunset just yesterday,pos +a road trip exceeded expectations according to reports this past weekend,pos +a cooking class caused chaos in front of a large crowd just yesterday,neg +the football match improved this year for reasons still unclear on live television,pos +the election results surprised everyone for reasons still unclear in the northern district,pos +this is a repeated sample text that appears multiple times,pos +the concert surprised everyone earlier than scheduled in the northern district,pos +the airport delay changed completely despite the forecast just yesterday,neg +a swimming competition confused most people as many predicted just yesterday,neg +the office meeting fell apart quickly right before sunset just yesterday,neg +the weather surprised everyone against all odds on live television,pos +this specific text has two different labels assigned to it,pos +local news was cancelled suddenly according to reports in a small town,pos +the weather changed completely after several delays before the deadline,neg +a family dinner was cancelled suddenly much to our surprise this past weekend,pos +the airport delay left people speechless much to our surprise in a small town,pos +a science experiment impressed the crowd according to reports before the deadline,neg +this is a repeated sample text that appears multiple times,pos +the art exhibit confused most people as many predicted before the deadline,pos +this is a repeated sample text that appears multiple times,pos +the hospital visit confused most people for reasons still unclear before the deadline,pos +a cooking class went as expected much to our surprise just yesterday,neg +my neighbor sparked a debate in record time under new management,neg +my garden changed completely for the third time near downtown,pos +the art exhibit was disappointing in record time this past weekend,neg +the weather took longer than planned right before sunset in the northern district,pos +the football match took longer than planned against all odds in the northern district,neg +traffic downtown exceeded expectations without any warning before the deadline,pos +this specific text has two different labels assigned to it,neg +a cooking class surprised everyone earlier than scheduled just yesterday,neg +this is a repeated sample text that appears multiple times,pos +a job interview confused most people much to our surprise for the first time,pos +my neighbor was disappointing as many predicted according to witnesses,neg +a charity event confused most people in record time for the first time,pos +a family dinner caused chaos without any warning in a small town,neg +this is a repeated sample text that appears multiple times,pos +a family dinner fell apart quickly for the third time under new management,pos +a cooking class went as expected right before sunset on live television,neg +the concert surprised everyone earlier than scheduled this past weekend,pos +a new phone changed completely after several delays on live television,neg +a job interview confused most people in front of a large crowd this past weekend,neg +the school exam went as expected according to reports near downtown,pos +a family dinner surprised everyone after several delays just yesterday,pos +the election results changed completely during the holiday season on live television,neg +the university lecture confused most people based on what I saw before the deadline,neg +local news left people speechless for the third time according to witnesses,pos +the art exhibit went as expected as many predicted in the northern district,neg +a family dinner ran smoothly for reasons still unclear before the deadline,pos +the weather impressed the crowd earlier than scheduled just yesterday,pos +the movie plot fell apart quickly according to reports for the first time,pos +the internet outage changed completely earlier than scheduled before the deadline,neg +the museum tour was cancelled suddenly despite the forecast on live television,neg +this recipe surprised everyone during the holiday season in a small town,neg +the football match was cancelled suddenly earlier than scheduled this past weekend,neg +this is a repeated sample text that appears multiple times,pos +the weather impressed the crowd as many predicted on live television,neg +traffic downtown exceeded expectations in front of a large crowd under new management,pos +local news exceeded expectations much to our surprise on live television,neg +my garden caused chaos for reasons still unclear in the northern district,pos +my garden took longer than planned right before sunset this past weekend,neg +the concert improved this year despite the forecast this past weekend,pos +my garden exceeded expectations against all odds for the first time,pos +the concert was cancelled suddenly as many predicted for the first time,neg +a cooking class ran smoothly as many predicted in the northern district,pos +the weather went as expected after several delays in a small town,neg +a job interview improved this year earlier than scheduled before the deadline,pos +my neighbor improved this year after several delays under new management,neg +a job interview confused most people in record time near downtown,pos +traffic downtown impressed the crowd in record time for the first time,pos +the airport delay fell apart quickly much to our surprise on live television,neg +the school exam caused chaos in record time in a small town,pos +the election results was cancelled suddenly according to reports under new management,pos +a charity event confused most people according to reports according to witnesses,neg +the internet outage left people speechless much to our surprise in a small town,pos +the university lecture changed completely after several delays before the deadline,pos +the weather took longer than planned much to our surprise near downtown,neg +a cooking class improved this year earlier than scheduled according to witnesses,pos +this recipe changed completely in front of a large crowd on live television,pos +the school exam exceeded expectations without any warning just yesterday,pos +the internet outage ran smoothly in front of a large crowd for the first time,pos +the art exhibit improved this year according to reports according to witnesses,pos +the school exam confused most people in front of a large crowd just yesterday,pos +this recipe was cancelled suddenly as many predicted for the first time,neg +a science experiment confused most people without any warning in a small town,pos +the museum tour surprised everyone in front of a large crowd for the first time,neg +the weather confused most people based on what I saw near downtown,neg +the hospital visit surprised everyone right before sunset this past weekend,neg +my neighbor surprised everyone much to our surprise for the first time,pos +the election results sparked a debate based on what I saw for the first time,pos +a charity event sparked a debate for the third time according to witnesses,neg +the election results went as expected despite the forecast in the northern district,pos +the movie plot was cancelled suddenly earlier than scheduled on live television,neg +a charity event changed completely as many predicted this past weekend,pos +this specific text has two different labels assigned to it,pos +this specific text has two different labels assigned to it,pos +a science experiment was cancelled suddenly for reasons still unclear near downtown,neg +a road trip confused most people based on what I saw just yesterday,neg +the hospital visit left people speechless despite the forecast under new management,pos +the university lecture ran smoothly during the holiday season near downtown,pos +a birthday party surprised everyone without any warning on live television,neg +the school exam took longer than planned right before sunset before the deadline,neg +the airport delay left people speechless right before sunset just yesterday,neg +this is a repeated sample text that appears multiple times,pos +a job interview confused most people without any warning this past weekend,pos +this specific text has two different labels assigned to it,neg +the movie plot left people speechless earlier than scheduled on live television,pos +the museum tour took longer than planned despite the forecast under new management,pos +a new phone ran smoothly as many predicted on live television,pos +the office meeting was disappointing for reasons still unclear according to witnesses,neg +this is a repeated sample text that appears multiple times,pos +the election results impressed the crowd earlier than scheduled in a small town,pos +the movie plot left people speechless earlier than scheduled in the northern district,neg +the airport delay exceeded expectations as many predicted this past weekend,neg +this recipe was disappointing during the holiday season near downtown,pos +the concert impressed the crowd earlier than scheduled just yesterday,pos +this is a repeated sample text that appears multiple times,pos +a road trip ran smoothly during the holiday season this past weekend,pos +the airport delay impressed the crowd right before sunset in the northern district,pos +this recipe improved this year right before sunset near downtown,pos +this recipe changed completely despite the forecast in a small town,neg +the hospital visit confused most people right before sunset in the northern district,pos +a job interview left people speechless for reasons still unclear before the deadline,neg +the office meeting went as expected according to reports before the deadline,pos +the art exhibit was cancelled suddenly in front of a large crowd this past weekend,pos +traffic downtown was cancelled suddenly despite the forecast for the first time,neg +the election results sparked a debate earlier than scheduled under new management,pos +this is a repeated sample text that appears multiple times,pos +the airport delay took longer than planned based on what I saw on live television,pos +this is a repeated sample text that appears multiple times,pos +a science experiment improved this year during the holiday season according to witnesses,neg +a charity event changed completely earlier than scheduled for the first time,neg +the university lecture was disappointing despite the forecast near downtown,pos +the hospital visit fell apart quickly much to our surprise in the northern district,neg +traffic downtown surprised everyone in record time according to witnesses,neg +a cooking class confused most people much to our surprise according to witnesses,pos +a birthday party ran smoothly based on what I saw before the deadline,pos +the weather ran smoothly much to our surprise in a small town,neg +this recipe took longer than planned right before sunset for the first time,neg +the office meeting exceeded expectations despite the forecast before the deadline,neg +the election results surprised everyone despite the forecast near downtown,neg +a new phone left people speechless for the third time before the deadline,neg +this is a repeated sample text that appears multiple times,pos +the university lecture went as expected after several delays on live television,pos +a birthday party caused chaos after several delays before the deadline,neg +the school exam was cancelled suddenly in record time just yesterday,neg +this is a repeated sample text that appears multiple times,pos +the art exhibit ran smoothly against all odds on live television,pos +traffic downtown surprised everyone according to reports this past weekend,pos +this is a repeated sample text that appears multiple times,pos +the art exhibit left people speechless much to our surprise according to witnesses,neg +the office meeting went as expected without any warning according to witnesses,neg +the office meeting sparked a debate without any warning on live television,neg +the football match confused most people as many predicted near downtown,pos +the university lecture took longer than planned for the third time on live television,pos +the internet outage went as expected against all odds just yesterday,pos +the weather impressed the crowd after several delays just yesterday,neg +a new phone left people speechless as many predicted in the northern district,pos +this recipe surprised everyone according to reports on live television,neg +this specific text has two different labels assigned to it,pos +the office meeting surprised everyone for the third time in a small town,neg +a job interview fell apart quickly as many predicted on live television,pos +a job interview changed completely despite the forecast just yesterday,pos +the stock market was disappointing much to our surprise in the northern district,neg +this is a repeated sample text that appears multiple times,pos +my garden fell apart quickly against all odds in the northern district,neg +the university lecture surprised everyone in front of a large crowd on live television,neg +the courtroom hearing improved this year after several delays according to witnesses,pos +a science experiment was disappointing based on what I saw according to witnesses,neg +a swimming competition confused most people right before sunset for the first time,pos +a new phone impressed the crowd after several delays in a small town,neg +the stock market impressed the crowd for reasons still unclear before the deadline,pos +the hospital visit fell apart quickly without any warning according to witnesses,neg +the football match was cancelled suddenly in record time for the first time,neg +the movie plot improved this year as many predicted under new management,neg +this is a repeated sample text that appears multiple times,pos +a family dinner caused chaos much to our surprise near downtown,pos +a swimming competition surprised everyone against all odds this past weekend,pos +the school exam fell apart quickly for the third time for the first time,neg +the concert exceeded expectations as many predicted for the first time,neg +the weather fell apart quickly earlier than scheduled under new management,neg +a swimming competition ran smoothly as many predicted on live television,pos +a birthday party was disappointing earlier than scheduled before the deadline,neg +this recipe went as expected against all odds on live television,neg +this is a repeated sample text that appears multiple times,pos +the football match impressed the crowd during the holiday season in the northern district,neg +a road trip surprised everyone right before sunset before the deadline,neg +traffic downtown fell apart quickly for reasons still unclear according to witnesses,pos +the museum tour confused most people according to reports near downtown,pos +local news fell apart quickly for reasons still unclear according to witnesses,neg +my garden surprised everyone for the third time near downtown,neg +my garden ran smoothly during the holiday season under new management,pos +the school exam sparked a debate based on what I saw near downtown,neg +this is a repeated sample text that appears multiple times,pos +the courtroom hearing left people speechless based on what I saw under new management,pos +the museum tour exceeded expectations much to our surprise according to witnesses,pos +a new phone fell apart quickly against all odds for the first time,neg +a cooking class impressed the crowd during the holiday season under new management,neg +this is a repeated sample text that appears multiple times,pos +local news confused most people during the holiday season under new management,neg +the weather ran smoothly right before sunset in a small town,neg +the stock market took longer than planned without any warning in a small town,pos +a wedding sparked a debate as many predicted on live television,pos +a wedding left people speechless earlier than scheduled in a small town,pos +a family dinner improved this year without any warning for the first time,pos +a cooking class changed completely based on what I saw in a small town,pos +my neighbor was disappointing in front of a large crowd this past weekend,neg +traffic downtown changed completely according to reports in the northern district,neg +this is a repeated sample text that appears multiple times,pos +the hospital visit improved this year despite the forecast in the northern district,neg +a new phone caused chaos for the third time in a small town,neg +a charity event went as expected for reasons still unclear under new management,pos +this is a repeated sample text that appears multiple times,pos +the weather impressed the crowd despite the forecast just yesterday,neg +local news sparked a debate as many predicted on live television,neg +a family dinner improved this year right before sunset before the deadline,pos +the stock market changed completely against all odds before the deadline,pos +the weather exceeded expectations according to reports on live television,neg +this is a repeated sample text that appears multiple times,pos +the office meeting changed completely for the third time before the deadline,neg +my garden was disappointing based on what I saw in the northern district,neg +my neighbor went as expected earlier than scheduled according to witnesses,pos +this is a repeated sample text that appears multiple times,pos +a cooking class sparked a debate for reasons still unclear near downtown,pos +traffic downtown ran smoothly without any warning for the first time,pos +this recipe took longer than planned right before sunset on live television,neg +the internet outage took longer than planned in record time in the northern district,neg +the hospital visit left people speechless for the third time in a small town,pos +a wedding ran smoothly despite the forecast in a small town,pos +a family dinner went as expected without any warning in the northern district,pos +this is a repeated sample text that appears multiple times,pos +a cooking class exceeded expectations for the third time under new management,pos +a road trip left people speechless based on what I saw near downtown,neg +a new phone fell apart quickly according to reports for the first time,neg +the courtroom hearing changed completely as many predicted according to witnesses,neg +the school exam improved this year earlier than scheduled near downtown,pos +the stock market surprised everyone in front of a large crowd in the northern district,neg +the football match exceeded expectations against all odds in the northern district,pos +this is a repeated sample text that appears multiple times,pos +a birthday party exceeded expectations as many predicted under new management,neg +the courtroom hearing fell apart quickly for the third time before the deadline,neg +a charity event fell apart quickly despite the forecast just yesterday,pos +the internet outage sparked a debate despite the forecast for the first time,pos +this is a repeated sample text that appears multiple times,pos +the movie plot confused most people after several delays just yesterday,neg +my neighbor left people speechless much to our surprise before the deadline,neg +a birthday party surprised everyone for reasons still unclear according to witnesses,pos +this is a repeated sample text that appears multiple times,pos +the airport delay left people speechless in record time this past weekend,pos +this recipe was cancelled suddenly based on what I saw in a small town,pos +a charity event fell apart quickly in front of a large crowd on live television,pos +this recipe surprised everyone in record time near downtown,neg +my neighbor changed completely according to reports on live television,neg +the art exhibit confused most people against all odds for the first time,pos +this is a repeated sample text that appears multiple times,pos +this is a repeated sample text that appears multiple times,pos +my garden was cancelled suddenly during the holiday season under new management,pos +the university lecture impressed the crowd earlier than scheduled just yesterday,pos +a swimming competition caused chaos earlier than scheduled under new management,neg +my neighbor changed completely without any warning in the northern district,pos +local news changed completely without any warning for the first time,pos +the internet outage took longer than planned according to reports under new management,neg +my neighbor took longer than planned in record time in the northern district,pos +traffic downtown fell apart quickly against all odds near downtown,neg +local news sparked a debate for reasons still unclear according to witnesses,pos +a cooking class was disappointing based on what I saw before the deadline,neg +the courtroom hearing confused most people without any warning according to witnesses,neg +this is a repeated sample text that appears multiple times,pos +this is a repeated sample text that appears multiple times,pos +local news fell apart quickly for the third time this past weekend,neg +the weather went as expected against all odds according to witnesses,neg +a birthday party fell apart quickly based on what I saw for the first time,pos +this is a repeated sample text that appears multiple times,pos +my neighbor ran smoothly right before sunset for the first time,neg +my garden sparked a debate during the holiday season near downtown,neg +this recipe sparked a debate for reasons still unclear before the deadline,pos +the university lecture left people speechless based on what I saw according to witnesses,pos +this recipe improved this year much to our surprise in the northern district,neg +the election results ran smoothly during the holiday season in the northern district,pos +traffic downtown fell apart quickly earlier than scheduled just yesterday,neg +a family dinner took longer than planned after several delays in a small town,pos +the office meeting caused chaos based on what I saw near downtown,neg +this is a repeated sample text that appears multiple times,pos +my neighbor changed completely earlier than scheduled in a small town,pos +this recipe was disappointing based on what I saw in a small town,pos +a job interview improved this year despite the forecast according to witnesses,pos +a wedding improved this year right before sunset in a small town,neg +a charity event fell apart quickly for reasons still unclear this past weekend,pos +the school exam took longer than planned despite the forecast just yesterday,neg +a road trip was cancelled suddenly in front of a large crowd according to witnesses,pos +this is a repeated sample text that appears multiple times,pos +the football match caused chaos right before sunset according to witnesses,pos +a new phone left people speechless for reasons still unclear in the northern district,pos +this is a repeated sample text that appears multiple times,pos +a charity event sparked a debate as many predicted on live television,pos +my neighbor took longer than planned based on what I saw before the deadline,pos +the internet outage confused most people based on what I saw near downtown,neg +this is a repeated sample text that appears multiple times,pos +the art exhibit left people speechless for reasons still unclear in a small town,neg +the election results caused chaos based on what I saw just yesterday,neg +this is a repeated sample text that appears multiple times,pos +the office meeting surprised everyone much to our surprise before the deadline,pos +the courtroom hearing was cancelled suddenly based on what I saw for the first time,neg +a charity event exceeded expectations much to our surprise in a small town,pos +the museum tour improved this year against all odds on live television,pos +the university lecture exceeded expectations in record time according to witnesses,neg +the airport delay sparked a debate in front of a large crowd on live television,pos +the election results surprised everyone for the third time this past weekend,neg +the movie plot fell apart quickly for the third time just yesterday,pos +a new phone was cancelled suddenly based on what I saw near downtown,neg +my garden caused chaos earlier than scheduled before the deadline,neg +a science experiment sparked a debate for the third time this past weekend,neg +a birthday party impressed the crowd based on what I saw before the deadline,neg +a science experiment sparked a debate much to our surprise this past weekend,pos +a new phone was disappointing after several delays on live television,pos +local news was disappointing much to our surprise for the first time,pos +the movie plot sparked a debate much to our surprise according to witnesses,pos +the weather left people speechless in front of a large crowd just yesterday,pos +the art exhibit sparked a debate much to our surprise for the first time,pos +the election results ran smoothly earlier than scheduled under new management,neg +the museum tour went as expected against all odds this past weekend,neg +the concert caused chaos much to our surprise before the deadline,pos +the concert fell apart quickly against all odds on live television,neg +my garden fell apart quickly for the third time on live television,neg +this is a repeated sample text that appears multiple times,pos +my neighbor ran smoothly earlier than scheduled near downtown,pos +a swimming competition took longer than planned against all odds just yesterday,neg +the internet outage took longer than planned in front of a large crowd according to witnesses,pos +the courtroom hearing surprised everyone after several delays near downtown,neg +this is a repeated sample text that appears multiple times,pos +this is a repeated sample text that appears multiple times,pos +a swimming competition took longer than planned right before sunset in a small town,neg +the stock market sparked a debate for the third time just yesterday,pos +the office meeting took longer than planned without any warning in a small town,neg +a cooking class fell apart quickly right before sunset this past weekend,pos +the museum tour took longer than planned in record time near downtown,neg +a wedding ran smoothly according to reports on live television,pos +my neighbor confused most people as many predicted for the first time,neg +a new phone went as expected in front of a large crowd under new management,neg +my neighbor took longer than planned for reasons still unclear according to witnesses,neg +the school exam ran smoothly for the third time before the deadline,pos +the courtroom hearing went as expected for reasons still unclear according to witnesses,neg +the office meeting exceeded expectations right before sunset near downtown,pos +local news fell apart quickly based on what I saw this past weekend,neg +local news left people speechless against all odds before the deadline,neg +a wedding improved this year against all odds just yesterday,neg +this is a repeated sample text that appears multiple times,pos +the school exam exceeded expectations based on what I saw on live television,neg +a charity event exceeded expectations despite the forecast under new management,neg +a new phone caused chaos based on what I saw before the deadline,neg +a swimming competition exceeded expectations without any warning for the first time,neg +traffic downtown impressed the crowd after several delays in the northern district,neg +the museum tour confused most people right before sunset this past weekend,pos +my neighbor left people speechless right before sunset for the first time,neg +a birthday party sparked a debate much to our surprise in a small town,pos +a swimming competition was disappointing based on what I saw according to witnesses,pos +the office meeting left people speechless in record time according to witnesses,neg +traffic downtown impressed the crowd despite the forecast in a small town,neg +the university lecture improved this year against all odds for the first time,pos +a science experiment surprised everyone earlier than scheduled near downtown,neg +the office meeting changed completely in front of a large crowd according to witnesses,pos +my garden caused chaos right before sunset this past weekend,pos +this specific text has two different labels assigned to it,neg +the courtroom hearing improved this year for the third time under new management,neg +the movie plot changed completely for reasons still unclear in the northern district,pos +the movie plot was disappointing against all odds on live television,pos +a science experiment left people speechless according to reports according to witnesses,pos +a road trip fell apart quickly without any warning in a small town,pos +a cooking class was cancelled suddenly earlier than scheduled before the deadline,pos +the election results fell apart quickly without any warning under new management,pos +the airport delay surprised everyone despite the forecast for the first time,neg +the election results changed completely in front of a large crowd before the deadline,neg +the art exhibit sparked a debate much to our surprise just yesterday,neg +the museum tour took longer than planned for the third time for the first time,neg +a science experiment confused most people for reasons still unclear under new management,neg +the museum tour took longer than planned much to our surprise this past weekend,pos +this specific text has two different labels assigned to it,neg +this is a repeated sample text that appears multiple times,pos +a swimming competition fell apart quickly during the holiday season according to witnesses,pos +the university lecture ran smoothly according to reports near downtown,pos +the office meeting exceeded expectations in front of a large crowd near downtown,pos +this recipe sparked a debate based on what I saw before the deadline,pos +a new phone went as expected as many predicted according to witnesses,neg +a road trip was cancelled suddenly in front of a large crowd under new management,pos +the airport delay went as expected based on what I saw near downtown,neg +a wedding sparked a debate right before sunset according to witnesses,pos +a job interview sparked a debate without any warning for the first time,pos +the concert confused most people as many predicted for the first time,pos +my neighbor improved this year in record time on live television,pos +a cooking class exceeded expectations during the holiday season under new management,pos +my garden left people speechless earlier than scheduled in the northern district,neg +my garden took longer than planned according to reports in a small town,neg +a new phone ran smoothly for reasons still unclear just yesterday,neg +the stock market fell apart quickly during the holiday season on live television,neg +the art exhibit improved this year as many predicted near downtown,pos +a cooking class was cancelled suddenly despite the forecast under new management,neg +a swimming competition surprised everyone for the third time according to witnesses,neg +this specific text has two different labels assigned to it,pos +a wedding was disappointing in record time near downtown,pos +the concert surprised everyone according to reports just yesterday,neg +this is a repeated sample text that appears multiple times,pos +a birthday party caused chaos without any warning before the deadline,neg +the election results took longer than planned after several delays under new management,neg +a wedding left people speechless as many predicted under new management,neg +the movie plot was disappointing right before sunset just yesterday,pos +a charity event ran smoothly according to reports under new management,neg +a swimming competition fell apart quickly as many predicted for the first time,pos +my garden ran smoothly much to our surprise under new management,pos +the university lecture changed completely after several delays according to witnesses,pos +the museum tour impressed the crowd for reasons still unclear in the northern district,pos +a birthday party was cancelled suddenly despite the forecast in the northern district,neg +a science experiment exceeded expectations earlier than scheduled according to witnesses,pos +the courtroom hearing confused most people in record time under new management,pos +a new phone impressed the crowd much to our surprise just yesterday,pos +the internet outage exceeded expectations despite the forecast in a small town,pos +the election results went as expected earlier than scheduled in the northern district,pos +the airport delay improved this year in front of a large crowd before the deadline,pos +the internet outage took longer than planned during the holiday season near downtown,neg +my garden surprised everyone despite the forecast just yesterday,pos +the art exhibit fell apart quickly as many predicted for the first time,pos +a road trip surprised everyone against all odds in the northern district,neg +a science experiment changed completely without any warning for the first time,neg +a new phone impressed the crowd for reasons still unclear in the northern district,neg +a wedding caused chaos as many predicted just yesterday,neg +the weather was cancelled suddenly without any warning on live television,neg +the office meeting confused most people much to our surprise in a small town,pos +the hospital visit sparked a debate according to reports on live television,neg +traffic downtown fell apart quickly based on what I saw according to witnesses,pos +the museum tour caused chaos right before sunset on live television,pos +a cooking class went as expected during the holiday season under new management,neg +the internet outage left people speechless right before sunset just yesterday,neg +the internet outage changed completely against all odds just yesterday,pos +the office meeting impressed the crowd based on what I saw in the northern district,pos +the internet outage confused most people right before sunset this past weekend,pos +the football match ran smoothly according to reports just yesterday,neg +the concert left people speechless based on what I saw according to witnesses,neg +the stock market was cancelled suddenly without any warning on live television,pos +this is a repeated sample text that appears multiple times,pos +the football match went as expected much to our surprise for the first time,neg +traffic downtown exceeded expectations earlier than scheduled according to witnesses,neg +the courtroom hearing was cancelled suddenly against all odds in the northern district,pos +my neighbor changed completely despite the forecast on live television,neg +the stock market sparked a debate much to our surprise on live television,pos +the hospital visit went as expected according to reports under new management,pos +the office meeting exceeded expectations according to reports in the northern district,neg +a road trip impressed the crowd according to reports according to witnesses,neg +this recipe improved this year despite the forecast on live television,pos +a cooking class fell apart quickly during the holiday season just yesterday,pos +the office meeting left people speechless much to our surprise this past weekend,neg +a job interview confused most people based on what I saw before the deadline,pos +a swimming competition impressed the crowd after several delays for the first time,pos +a charity event caused chaos for reasons still unclear according to witnesses,neg +the university lecture fell apart quickly against all odds in the northern district,pos +a job interview left people speechless after several delays before the deadline,neg +a road trip left people speechless against all odds on live television,neg +the school exam exceeded expectations during the holiday season just yesterday,neg +a birthday party changed completely earlier than scheduled before the deadline,pos +a wedding took longer than planned against all odds near downtown,pos +this specific text has two different labels assigned to it,neg +a wedding exceeded expectations right before sunset this past weekend,neg +the university lecture changed completely in record time before the deadline,pos +this recipe took longer than planned for the third time before the deadline,neg +the weather took longer than planned earlier than scheduled before the deadline,pos +a cooking class impressed the crowd earlier than scheduled near downtown,neg +the election results impressed the crowd during the holiday season this past weekend,pos