Skip to content

Reindex categorical codes from Polars #387

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
Luca Bittarello (lbittarello) merged 3 commits into from
Sep 12, 2024
Merged

Reindex categorical codes from Polars #387

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f86b9aa
Reindex categorical codes from Polars
lbittarello Sep 11, 2024
db89cdd
Localize
lbittarello Sep 12, 2024
9a56ea8
Add test for non-contiguous polars categoricals
stanmart Sep 12, 2024
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
4 changes: 2 additions & 2 deletions src/tabmat/categorical_matrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,8 +244,8 @@ def _extract_codes_and_categories(cat_vec):
elif _is_polars(cat_vec):
if not _is_polars(cat_vec.dtype):
cat_vec = cat_vec.cast(pl.Categorical)
categories = cat_vec.cat.get_categories().to_numpy()
indices = cat_vec.to_physical().fill_null(-1).to_numpy()
categories = cat_vec.cat.to_local().cat.get_categories().to_numpy()
indices = cat_vec.cat.to_local().to_physical().fill_null(-1).to_numpy()
else:
indices, categories = pd.factorize(cat_vec, sort=True)
return indices, categories
Expand Down
13 changes: 12 additions & 1 deletion tests/test_categorical_matrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,10 @@

import numpy as np
import pandas as pd
import polars as pl
import pytest

from tabmat.categorical_matrix import CategoricalMatrix
from tabmat.categorical_matrix import CategoricalMatrix, _extract_codes_and_categories


@pytest.fixture
Expand Down Expand Up @@ -202,3 +203,13 @@ def test_categorical_indexing(drop_first, missing, cat_missing_method):
dummy_na=cat_missing_method == "convert" and missing,
).to_numpy()[:, [0, 1]]
np.testing.assert_allclose(mat[:, [0, 1]].toarray(), expected)


def test_polars_non_contiguous_codes():
str_series = ["labrador", "boxer", "beagle"]
with pl.StringCache():
_ = pl.Series(["beagle", "poodle", "labrador"], dtype=pl.Categorical)
cat_series = pl.Series(str_series, dtype=pl.Categorical)

indices, categories = _extract_codes_and_categories(cat_series)
np.testing.assert_array_equal(str_series, categories[indices].tolist())