Skip to content

Import numpy, pandas and matplotlib under their conventional aliases #98

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mmacferrin merged 1 commit into from
Sep 1, 2026
Merged

Import numpy, pandas and matplotlib under their conventional aliases #98

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,6 @@ ignore = [
"FBT001", # boolean-type-hint-positional-argument
"FBT002", # boolean-default-value-positional-argument
"FIX002", # line-contains-todo
"ICN001", # unconventional-import-alias
"PLC0415", # import-outside-top-level
"PLR0912", # too-many-branches
"PLR0913", # too-many-arguments
Expand Down
4 changes: 2 additions & 2 deletions src/ivert/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1673,7 +1673,7 @@ def database_export(

# --- Read, subset, and merge granules. ---
import geopandas
import pandas
import pandas as pd

dt_min = _yyyymmdd_to_delta_time(tmin) if date_filtering else None
dt_max = _yyyymmdd_to_delta_time(tmax) if date_filtering else None
Expand Down Expand Up @@ -1706,7 +1706,7 @@ def database_export(
raise click.ClickException("No photons found to export after filtering.")

merged = geopandas.GeoDataFrame(
pandas.concat(gdfs, ignore_index=True),
pd.concat(gdfs, ignore_index=True),
crs=ev.WGS84_EPSG,
)

Expand Down
6 changes: 3 additions & 3 deletions src/ivert/convert_error_tif_to_vector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import sys

import geopandas
import numpy
import numpy as np
import rasterio
import shapely.geometry

Expand All @@ -29,8 +29,8 @@ def convert_ivert_error_map_to_vector(

ndv = src.nodatavals[0]

good_rows, good_cols = numpy.where(
(~array.isnan()) if numpy.isnan(ndv) else (array != ndv),
good_rows, good_cols = np.where(
(~array.isnan()) if np.isnan(ndv) else (array != ndv),
)
good_xs, good_ys = rasterio.transform.xy(
src.transform,
Expand Down
104 changes: 52 additions & 52 deletions src/ivert/icesat2_database_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@
import fetchez.core
import fetchez.spatial
import globato
import numpy
import pandas
import numpy as np
import pandas as pd
import xarray
from fetchez.modules.earthdata import IceSat2 as _FetchezIceSat2

Expand Down Expand Up @@ -193,7 +193,7 @@ def create_new_database(
self,
populate: bool = True,
overwrite: bool = False,
) -> pandas.DataFrame:
) -> pd.DataFrame:
"""Create a new database from scratch.

Parameters
Expand Down Expand Up @@ -232,15 +232,15 @@ def create_new_database(
records.append(meta)

if records:
gdf = pandas.DataFrame(records)[list(self._empty_db_dict().keys())]
gdf = pd.DataFrame(records)[list(self._empty_db_dict().keys())]
else:
gdf = pandas.DataFrame(self._empty_db_dict()).drop(
gdf = pd.DataFrame(self._empty_db_dict()).drop(
labels=0,
axis="rows",
)

else:
gdf = pandas.DataFrame(self._empty_db_dict()).drop(labels=0, axis="rows")
gdf = pd.DataFrame(self._empty_db_dict()).drop(labels=0, axis="rows")

self._write_index(gdf)
if os.path.exists(self.db_fname):
Expand Down Expand Up @@ -443,7 +443,7 @@ def _source_granule_from_filename(cls, filename: str) -> str:
return cls._NC_SUFFIX_RE.sub("", filename)

@staticmethod
def _h5_along_track_m(h5_fn: str, beams) -> pandas.DataFrame:
def _h5_along_track_m(h5_fn: str, beams) -> pd.DataFrame:
"""Return per-photon cumulative along-track distance (m) for the given beams.

Cumulative distance = sum of segment_length values up to each photon's segment
Expand All @@ -468,20 +468,20 @@ def _h5_along_track_m(h5_fn: str, beams) -> pandas.DataFrame:
continue

# Cumulative distance at the start of each segment
seg_cumul_start = numpy.concatenate(
[[0.0], numpy.cumsum(seg_length[:-1])],
seg_cumul_start = np.concatenate(
[[0.0], np.cumsum(seg_length[:-1])],
)

# Map each photon to its segment via ph_index_beg
n = len(delta_time)
seg_of_ph = numpy.clip(
numpy.searchsorted(ph_index_beg, numpy.arange(n), side="right") - 1,
seg_of_ph = np.clip(
np.searchsorted(ph_index_beg, np.arange(n), side="right") - 1,
0,
len(ph_index_beg) - 1,
)

dfs.append(
pandas.DataFrame(
pd.DataFrame(
{
"laser": beam,
"delta_time": delta_time,
Expand All @@ -493,9 +493,9 @@ def _h5_along_track_m(h5_fn: str, beams) -> pandas.DataFrame:
)

return (
pandas.concat(dfs, ignore_index=True)
pd.concat(dfs, ignore_index=True)
if dfs
else pandas.DataFrame(
else pd.DataFrame(
columns=["laser", "delta_time", "x", "y", "along_track_m"],
)
)
Expand Down Expand Up @@ -602,12 +602,12 @@ def _process_h5_to_nc(
use_external_masks=use_external_masks,
)

chunks = [pandas.DataFrame(chunk) for chunk in stream]
chunks = [pd.DataFrame(chunk) for chunk in stream]

if not chunks:
return None

df = pandas.concat(chunks, ignore_index=True)
df = pd.concat(chunks, ignore_index=True)
df = df.rename(columns={"ph_h_classed": "class_code"})

# Temporal filter
Expand Down Expand Up @@ -657,16 +657,16 @@ def _process_h5_to_nc(
"data_bbox": [xmin, xmax, ymin, ymax, tmin, tmax],
"zbounds": [zmin, zmax],
"numphotons": len(df),
"numphotons_unclassified": int(numpy.count_nonzero(cc == -1)),
"numphotons_noise": int(numpy.count_nonzero(cc == 0)),
"numphotons_ground": int(numpy.count_nonzero(cc == 1)),
"numphotons_canopy": int(numpy.count_nonzero(cc == 2)),
"numphotons_canopy_top": int(numpy.count_nonzero(cc == 3)),
"numphotons_ice_surface": int(numpy.count_nonzero(cc == 6)),
"numphotons_buildings": int(numpy.count_nonzero(cc == 7)),
"numphotons_bathy_floor": int(numpy.count_nonzero(cc == 40)),
"numphotons_bathy_surface": int(numpy.count_nonzero(cc == 41)),
"numphotons_inland_water_surface": int(numpy.count_nonzero(cc == 42)),
"numphotons_unclassified": int(np.count_nonzero(cc == -1)),
"numphotons_noise": int(np.count_nonzero(cc == 0)),
"numphotons_ground": int(np.count_nonzero(cc == 1)),
"numphotons_canopy": int(np.count_nonzero(cc == 2)),
"numphotons_canopy_top": int(np.count_nonzero(cc == 3)),
"numphotons_ice_surface": int(np.count_nonzero(cc == 6)),
"numphotons_buildings": int(np.count_nonzero(cc == 7)),
"numphotons_bathy_floor": int(np.count_nonzero(cc == 40)),
"numphotons_bathy_surface": int(np.count_nonzero(cc == 41)),
"numphotons_inland_water_surface": int(np.count_nonzero(cc == 42)),
"downloaded_on_utc": int(
datetime.datetime.now(datetime.UTC).strftime("%Y%m%d"),
),
Expand Down Expand Up @@ -725,30 +725,30 @@ def _write_index(self, df) -> None:

for col in self._INDEX_STR_COLS:
values = (
numpy.array(
np.array(
["" if v is None else str(v) for v in df[col]],
dtype=object,
)
if n
else numpy.array([], dtype=object)
else np.array([], dtype=object)
)
data_vars[col] = ("record", values)

int_cols = (*self._INDEX_INT_COLS, *self._INDEX_BBOX_INT_COLS)
for col in int_cols:
values = (
numpy.asarray(df[col].to_list(), dtype="int64")
np.asarray(df[col].to_list(), dtype="int64")
if n
else numpy.array([], dtype="int64")
else np.array([], dtype="int64")
)
data_vars[col] = ("record", values)

float_cols = (*self._INDEX_BBOX_FLOAT_COLS, *self._INDEX_ZBOUNDS_COLS)
for col in float_cols:
values = (
numpy.asarray(df[col].to_list(), dtype="float64")
np.asarray(df[col].to_list(), dtype="float64")
if n
else numpy.array([], dtype="float64")
else np.array([], dtype="float64")
)
data_vars[col] = ("record", values)

Expand All @@ -770,7 +770,7 @@ def _write_index(self, df) -> None:
ds.to_netcdf(self.db_fname, encoding=encoding)

@classmethod
def read_index_file(cls, index_fname: str) -> pandas.DataFrame:
def read_index_file(cls, index_fname: str) -> pd.DataFrame:
"""Read any IVERT NetCDF index file into a plain pandas DataFrame.

Every column comes back as a numpy array with no per-row Python loops and
Expand All @@ -793,7 +793,7 @@ def read_index_file(cls, index_fname: str) -> pandas.DataFrame:
):
data[col] = ds[cls._stored_col_name(col, ds)].to_numpy()

df = pandas.DataFrame(data)
df = pd.DataFrame(data)
# Restore the canonical column order used elsewhere in the codebase.
return df[list(cls._empty_db_dict().keys())]

Expand Down Expand Up @@ -886,7 +886,7 @@ def read_database_file(
def omit_photons_from_exclusion_bbox(
dataframe,
bbox_to_exclude,
) -> pandas.DataFrame:
) -> pd.DataFrame:
"""Exclude any photons that fall within the particular bounding box."""
x = dataframe["x"]
y = dataframe["y"]
Expand Down Expand Up @@ -924,7 +924,7 @@ def read_granule(
granule_fn: str,
subset_bbox: list | tuple | None = None,
photon_classes: list | tuple | None = None,
) -> pandas.DataFrame:
) -> pd.DataFrame:
"""Read classified photons from a NetCDF granule file.

Parameters
Expand Down Expand Up @@ -987,7 +987,7 @@ def query_photons(
min_confidence_level: int = 1,
omit_bboxes=None,
# download_new_data: bool = False,
) -> pandas.DataFrame | None:
) -> pd.DataFrame | None:
"""Query the database for photons in a given bounding box and date range.

Parameters
Expand Down Expand Up @@ -1025,7 +1025,7 @@ def query_photons(
)
logger.info(
"%d granules exist with %s ground photons and %s bathy_floor photons.",
numpy.count_nonzero(fnames.apply(os.path.exists)),
np.count_nonzero(fnames.apply(os.path.exists)),
f"{gdf_subset['numphotons_ground'].sum():,}",
f"{gdf_subset['numphotons_bathy_floor'].sum():,}",
)
Expand All @@ -1046,7 +1046,7 @@ def query_photons(
if len(granule_dfs) == 0:
return None

photons_df = pandas.concat(granule_dfs, ignore_index=True)
photons_df = pd.concat(granule_dfs, ignore_index=True)

if min_bathy_confidence > 0.0:
photons_df = photons_df[
Expand All @@ -1064,7 +1064,7 @@ def query_photons(
omit_bboxes = []

# If we're given a single bounding box of exclusions as a 4- or 6-tuple of numbers (not iterables), put it in a 1-length list.
if len(omit_bboxes) in (4, 6) and not numpy.any(
if len(omit_bboxes) in (4, 6) and not np.any(
[self.is_iterable(num) for num in omit_bboxes],
):
omit_bboxes = [omit_bboxes]
Expand All @@ -1078,8 +1078,8 @@ def query_photons(
"Trimmed granules from %s to %s photons (%s ground, %s bathy).",
f"{gdf_subset['numphotons'].sum():,}",
f"{len(photons_df):,}",
f"{numpy.count_nonzero(photons_df['class_code'] == 1):,}",
f"{numpy.count_nonzero(photons_df['class_code'] == 40):,}",
f"{np.count_nonzero(photons_df['class_code'] == 1):,}",
f"{np.count_nonzero(photons_df['class_code'] == 40):,}",
)
else:
logger.info("No photons in bbox.")
Expand Down Expand Up @@ -1126,7 +1126,7 @@ def convert_date_to_yyyymmdd(
"Date must be an int, str, datetime.datetime, or datetime.date.",
)

def query_granules(self, bbox: list | tuple) -> pandas.DataFrame | None:
def query_granules(self, bbox: list | tuple) -> pd.DataFrame | None:
"""Return a sub-dataframe of granules in the database that possibly intersect the bounding box, using data bounding boxes."""
gdf = self.open_gdf()
if gdf is None or len(gdf) == 0:
Expand Down Expand Up @@ -1462,7 +1462,7 @@ def download_new_granules(
if not new_records:
continue

new_gdf = pandas.DataFrame(new_records)[list(self._empty_db_dict().keys())]
new_gdf = pd.DataFrame(new_records)[list(self._empty_db_dict().keys())]
if existing_gdf is None or len(existing_gdf) == 0:
self.gdf = new_gdf
else:
Expand Down Expand Up @@ -1490,7 +1490,7 @@ def download_new_granules(
# granule but a non-overlapping query bbox are legitimately distinct data
# (e.g. a different date range or region) and must not be dropped, since
# doing so would discard original data rather than de-duplicate it.
bbox_overlaps = pandas.Series(
bbox_overlaps = pd.Series(
ivert.utils.cuboid_funcs.cuboids_intersect_vectorized(
existing_gdf["query_bbox_xmin"].to_numpy(),
existing_gdf["query_bbox_xmax"].to_numpy(),
Expand All @@ -1515,7 +1515,7 @@ def download_new_granules(
if os.path.exists(old_fpath):
os.remove(old_fpath)
existing_gdf = existing_gdf[~is_replaced]
self.gdf = pandas.concat(
self.gdf = pd.concat(
[existing_gdf, new_gdf],
ignore_index=True,
)
Expand Down Expand Up @@ -1586,7 +1586,7 @@ def bounds(self, axis: str, data_or_query: str = "data") -> tuple | None:

def unique_bboxes(
self,
gdf: pandas.DataFrame | None = None,
gdf: pd.DataFrame | None = None,
data_or_query: str = "query",
) -> list | None:
"""Return a numpy array of unique query bounding boxes in the database.
Expand Down Expand Up @@ -1796,22 +1796,22 @@ def split_bbox_into_parts(
xmin, xmax, ymin, ymax = bbox
max_deg_size = tile_size_deg * max_tile_scale_factor

xbins = numpy.arange(xmin, xmax, tile_size_deg)
ybins = numpy.arange(ymin, ymax, tile_size_deg)
xbins = np.arange(xmin, xmax, tile_size_deg)
ybins = np.arange(ymin, ymax, tile_size_deg)

if xbins[-1] < xmax:
if len(xbins) == 1 or ((xmax - xbins[-2]) > max_deg_size):
xbins = numpy.append(xbins, xmax)
xbins = np.append(xbins, xmax)
else:
xbins[-1] = xmax

if ybins[-1] < ymax:
if len(ybins) == 1 or ((ymax - ybins[-2]) > max_deg_size):
ybins = numpy.append(ybins, ymax)
ybins = np.append(ybins, ymax)
else:
ybins[-1] = ymax

binxs, binys = numpy.meshgrid(xbins, ybins)
binxs, binys = np.meshgrid(xbins, ybins)
bin_xmins = binxs[:-1, :-1].flatten()
bin_xmaxs = binxs[1:, 1:].flatten()
bin_ymins = binys[:-1, :-1].flatten()
Expand Down
Loading
Loading