diff --git a/02_activities/assignments/assignment_1.ipynb b/02_activities/assignments/assignment_1.ipynb index bd3e0516e..45cfc9cd7 100644 --- a/02_activities/assignments/assignment_1.ipynb +++ b/02_activities/assignments/assignment_1.ipynb @@ -26,28 +26,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ - "\n", - "\n", - "from pathlib import Path\n", - "import sys\n", - "\n", - "notebook_dir = Path.cwd()\n", - "src_path = (notebook_dir / \"../../05_src\").resolve()\n", - "\n", - "if str(src_path) not in sys.path:\n", - " sys.path.insert(0, str(src_path)) # insert(0) gives it priority\n", - "\n", - "%load_ext dotenv\n", - "%dotenv \n" + "# Write your code below.\n", + "\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -66,40 +55,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "import os\n", "from glob import glob\n", "\n", - "from utils.logger import get_logger\n", - "_logs = get_logger(__name__)\n", - "\n", - "PRICE_DATA = os.getenv(\"PRICE_DATA\")\n", - "parquet_files = glob(os.path.join(PRICE_DATA, \"**/*.parquet\"), recursive = True)\n", - "_logs.info(f'Found {len(parquet_files)} parquet price files.')\n", - "\n", - "\n", - "\n", - " \n", + "# Write your code below.\n", "\n" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Please comment:\n", - "\n", - "+ Was it necessary to convert to pandas to calculate the moving average return?\n", - "+ Would it have been better to do it in Dask? Why?\n", - "\n", - "(1 pt)\n", - "\n", - "No it was not necessary. Dask can also calculate it, however it is better to do it in pandas as it stores the data in memory and allows for faster calculation. If it wasn't possible to store in memory then Dask would be a good choice." - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -122,28 +88,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ - "dd_px = dd.read_parquet(parquet_files).set_index(\"ticker\")\n", - "dd_shift = (\n", - " dd_px\n", - " .groupby('ticker', group_keys=False)\n", - " .apply(\n", - " lambda x: x.sort_values('Date', ascending = True)\n", - " .assign(Close_lag_1 = lambda df: df['Close'].shift(1))\n", - " .assign(Adj_Close_lag_1 = lambda df: df['Adj Close'].shift(1)),\n", - " meta = dd_px._meta.assign(Close_lag_1 = 0.0,\n", - " Adj_Close_lag_1 = 0.0))\n", - " )\n", - "\n", - "dd_feat = dd_shift.assign(\n", - " returns = lambda x: x['Close']/x['Close_lag_1'] - 1,\n", - " hi_low_range = lambda x: x['High'] - x['Low']\n", - ")\n", - "\n", - "\n", + "# Write your code below.\n", "\n" ] }, @@ -159,18 +108,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "metadata": {}, "outputs": [], "source": [ - "df_feat = dd_feat.compute()\n", - "\n", - "\n", - "df_feat[\"returns_10_days\"] = (\n", - " df_feat.groupby(\"ticker\")[\"returns\"]\n", - " .transform(lambda x: x.rolling(10).mean())\n", - ")\n", - "df_feat.head(100)" + "# Write your code below.\n", + "\n" ] }, { @@ -182,9 +125,7 @@ "+ Was it necessary to convert to pandas to calculate the moving average return?\n", "+ Would it have been better to do it in Dask? Why?\n", "\n", - "(1 pt)\n", - "\n", - "No it was not necessary. Dask can also calculate it, however it is better to do it in pandas as it stores the data in memory and allows for faster calculation. If it wasn't possible to store in memory then Dask would be a good choice." + "(1 pt)" ] }, { @@ -224,7 +165,7 @@ ], "metadata": { "kernelspec": { - "display_name": "production-env (3.11.14)", + "display_name": "env", "language": "python", "name": "python3" }, @@ -238,7 +179,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.14" + "version": "3.11.0" } }, "nbformat": 4,