Add pre-commits

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+-   repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    args: ["--profile", "black", "--filter-files"]
+    hooks:
+    - id: isort
+-   repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+    - id: black

development_guide.md

@@ -9,4 +9,4 @@ python -m venv venv
 source venv/bin/activate
 # Install the dependencies
 make env-install
-```
+```

pyproject.toml

@@ -26,6 +26,7 @@ dev = [
     "polars",
     "pandas",
     "numpy",
+    "pre-commit",
 ]
 doc = ["mkdocs", "mkdocs-material", "mkdocstrings[python]", "mkdocs-jupyter"]
 build = ["build", "twine"]
@@ -56,5 +57,5 @@ exclude = '''
 )/
 '''
 
-[tool.flake8]
-max-line-length = 88
+[tool.isort]
+profile = "black"

sklearo/encoding/__init__.py

@@ -1,3 +1,3 @@
 from .woe import WOEEncoder
 
-__all__ = ["WOEEncoder"]
+__all__ = ["WOEEncoder"]

sklearo/encoding/woe.py

@@ -1,14 +1,14 @@
-import narwhals as nw
-from narwhals.typing import IntoFrameT, IntoSeriesT
-import warnings
 import math
-from typing import Sequence, Literal, Any
-
+import warnings
 from collections import defaultdict
+from typing import Any, Literal, Sequence
 
+import narwhals as nw
+from narwhals.typing import IntoFrameT, IntoSeriesT
 from pydantic import validate_call
+
 from sklearo.utils import select_columns
-from sklearo.validation import check_X_y, check_if_fitted
+from sklearo.validation import check_if_fitted, check_X_y
 
 
 class WOEEncoder:
@@ -355,8 +355,10 @@ def transform(self, X: IntoFrameT) -> IntoFrameT:
         for column, mapping in self.encoding_map_.items():
             uniques = X[column].unique()
             unseen_cats = uniques.filter(
-                (~uniques.is_in(next(iter(mapping.values())).keys())
-                & ~uniques.is_null())
+                (
+                    ~uniques.is_in(next(iter(mapping.values())).keys())
+                    & ~uniques.is_null()
+                )
             ).to_list()
             if unseen_cats:
                 unseen_per_col[column] = unseen_cats

sklearo/utils.py

@@ -1,10 +1,9 @@
+import inspect
+import re
 from typing import Sequence
 
-import re
 import narwhals as nw
 from narwhals.typing import IntoFrameT
-import inspect
-
 
 
 def select_columns_by_regex_pattern(df: IntoFrameT, pattern: str):
@@ -29,4 +28,4 @@ def select_columns(df: IntoFrameT, columns: Sequence[nw.typing.DTypes | str] | s
         elif isinstance(columns[0], str):
             yield from columns
         else:
-            raise ValueError("Invalid columns type")
+            raise ValueError("Invalid columns type")

tests/encoding/test_woe.py

@@ -1,7 +1,7 @@
+import numpy as np
 import pandas as pd
 import polars as pl
 import pytest
-import numpy as np
 
 from sklearo.encoding.woe import WOEEncoder
 

tests/test_utils.py

@@ -1,14 +1,14 @@
+import narwhals as nw
 import pandas as pd
 import polars as pl
 import pytest
-import narwhals as nw
+
 from sklearo.utils import (
+    select_columns,
     select_columns_by_regex_pattern,
     select_columns_by_types,
-    select_columns,
 )
 
-
 select_columns_by_regex_pattern = nw.narwhalify(select_columns_by_regex_pattern)
 select_columns_by_types = nw.narwhalify(select_columns_by_types)
 select_columns = nw.narwhalify(select_columns)
@@ -72,8 +72,7 @@ def test_select_columns_empty_tuple(self, sample_data, DataFrame):
         selected_columns = list(select_columns(df, ()))
         assert selected_columns == []
 
-
     def test_select_columns_invalid_type(self, sample_data, DataFrame):
         df = DataFrame(sample_data)
         with pytest.raises(ValueError, match="Invalid columns type"):
-            list(select_columns(df, [1, 2]))
+            list(select_columns(df, [1, 2]))