Merge pull request #450 from PaulWestenthanner/improve_type_hints

Add poetry and linting

Author: PaulWestenthanner

.github/workflows/docs.yml

@@ -12,12 +12,12 @@ jobs:
       - name: Dependencies
         run: |
           python -m pip install --upgrade pip wheel
-          pip install -r requirements.txt
-          pip install -r requirements-dev.txt
-      - name: Build Docs
-        uses: ammaraskar/sphinx-action@master
-        with:
-          docs-folder: "docs/"
+          python -m pip install poetry
+          poetry install
+      - name: Directly build docs
+        run: |
+          pip install -r docs/requirements.txt
+          sphinx-build -D docs/source ./docs/build/html/
       - name: Deploy Docs
         uses: peaceiris/actions-gh-pages@v3
         with:

.github/workflows/pypi-publish.yml

@@ -11,16 +11,15 @@ jobs:
     steps:
       - name: Clone
         uses: actions/checkout@v2
-      - name: Set up Python 3.7
+      - name: Set up Python 3.12
         uses: actions/setup-python@v2
         with:
-          python-version: 3.7
+          python-version: 3.12
       - name: Build package
         run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements.txt
-          pip install -r requirements-dev.txt
-          pip install wheel
-          python setup.py bdist_wheel sdist
+          python -m pip install --upgrade pip wheel
+          python -m pip install poetry
+          poetry install
+          poetry build
       - name: Publish package
         uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test-docs-build.yml

@@ -7,12 +7,13 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.10']
+        python-version: ['3.12']
     steps:
     - uses: actions/checkout@v2
     - uses: actions/setup-python@v2
       with:
           python-version: ${{ matrix.python-version }}
-    - uses: ammaraskar/sphinx-action@master
-      with:
-        docs-folder: "docs/"
+    - name: directly build sphinx (plugin only supports python 3.8)
+      run: |
+          pip install -r docs/requirements.txt
+          sphinx-build docs/source ./docs/build/html/

.github/workflows/test-suite.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10']
+        python-version: ['3.10', '3.11', '3.12', '3.13']
 
     steps:
     - uses: actions/checkout@v2
@@ -26,8 +26,8 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip wheel
-        python -m pip install -r requirements.txt
-        python -m pip install -r requirements-dev.txt
+        python -m pip install poetry
+        poetry install
     - name: Test with pytest
       run: |
-        pytest
+        poetry run pytest tests

CHANGELOG.md

@@ -1,6 +1,12 @@
 unreleased
 ==========
 
+* Refactor: Use poetry as packaging tool
+* Refactor: Add more typing
+* Change `feature_names_in_` and `feature_names_out_` to `np.ndarray` instead of lists.
+* Breaking: Do not allow scalar values as target variable (of length 1) anymore
+* Breaking: Force dataframe column names to be strings.
+
 v2.6.4
 ======
 * fixed: Future Warning in Pandas

CONTRIBUTING.md

@@ -16,14 +16,18 @@ How to Contribute
 The preferred workflow to contribute to git-pandas is:
 
  1. Fork this repository into your own github account.
- 2. Clone the fork on your account onto your local disk:
- 
+ 2. Clone the fork and install project via poetry:
+    ```
     $ git clone [email protected]:YourLogin/category_encoders.git
     $ cd category_encoders
+    $ poetry install
+    ```
     
  3. Create a branch for your new awesome feature, do not work in the master branch:
  
+    ```
     $ git checkout -b new-awesome-feature
+    ```
     
  4. Write some code, or docs, or tests.
  5. When you are done, submit a pull request.

category_encoders/__init__.py

@@ -1,4 +1,4 @@
-"""
+"""Category encoders library.
 
 .. module:: category_encoders
   :synopsis:
@@ -7,51 +7,50 @@
 """
 
 from category_encoders.backward_difference import BackwardDifferenceEncoder
+from category_encoders.basen import BaseNEncoder
 from category_encoders.binary import BinaryEncoder
-from category_encoders.gray import GrayEncoder
+from category_encoders.cat_boost import CatBoostEncoder
 from category_encoders.count import CountEncoder
+from category_encoders.glmm import GLMMEncoder
+from category_encoders.gray import GrayEncoder
 from category_encoders.hashing import HashingEncoder
 from category_encoders.helmert import HelmertEncoder
+from category_encoders.james_stein import JamesSteinEncoder
+from category_encoders.leave_one_out import LeaveOneOutEncoder
+from category_encoders.m_estimate import MEstimateEncoder
 from category_encoders.one_hot import OneHotEncoder
 from category_encoders.ordinal import OrdinalEncoder
-from category_encoders.sum_coding import SumEncoder
 from category_encoders.polynomial import PolynomialEncoder
-from category_encoders.basen import BaseNEncoder
-from category_encoders.leave_one_out import LeaveOneOutEncoder
+from category_encoders.quantile_encoder import QuantileEncoder, SummaryEncoder
+from category_encoders.rankhot import RankHotEncoder
+from category_encoders.sum_coding import SumEncoder
 from category_encoders.target_encoder import TargetEncoder
 from category_encoders.woe import WOEEncoder
-from category_encoders.m_estimate import MEstimateEncoder
-from category_encoders.james_stein import JamesSteinEncoder
-from category_encoders.cat_boost import CatBoostEncoder
-from category_encoders.rankhot import RankHotEncoder
-from category_encoders.glmm import GLMMEncoder
-from category_encoders.quantile_encoder import QuantileEncoder, SummaryEncoder
-
 
 __version__ = '2.6.4'
 
-__author__ = "willmcginnis", "cmougan", "paulwestenthanner"
+__author__ = 'willmcginnis', 'cmougan', 'paulwestenthanner'
 
 __all__ = [
-    "BackwardDifferenceEncoder",
-    "BinaryEncoder",
-    "GrayEncoder",
-    "CountEncoder",
-    "HashingEncoder",
-    "HelmertEncoder",
-    "OneHotEncoder",
-    "OrdinalEncoder",
-    "SumEncoder",
-    "PolynomialEncoder",
-    "BaseNEncoder",
-    "LeaveOneOutEncoder",
-    "TargetEncoder",
-    "WOEEncoder",
-    "MEstimateEncoder",
-    "JamesSteinEncoder",
-    "CatBoostEncoder",
-    "GLMMEncoder",
-    "QuantileEncoder",
-    "SummaryEncoder",
+    'BackwardDifferenceEncoder',
+    'BinaryEncoder',
+    'GrayEncoder',
+    'CountEncoder',
+    'HashingEncoder',
+    'HelmertEncoder',
+    'OneHotEncoder',
+    'OrdinalEncoder',
+    'SumEncoder',
+    'PolynomialEncoder',
+    'BaseNEncoder',
+    'LeaveOneOutEncoder',
+    'TargetEncoder',
+    'WOEEncoder',
+    'MEstimateEncoder',
+    'JamesSteinEncoder',
+    'CatBoostEncoder',
+    'GLMMEncoder',
+    'QuantileEncoder',
+    'SummaryEncoder',
     'RankHotEncoder',
 ]

category_encoders/backward_difference.py

@@ -1,7 +1,7 @@
-"""Backward difference contrast encoding"""
+"""Backward difference contrast encoding."""
 
-from patsy.contrasts import Diff, ContrastMatrix
 import numpy as np
+from patsy.contrasts import ContrastMatrix, Diff
 
 from category_encoders.base_contrast_encoder import BaseContrastEncoder
 
@@ -13,31 +13,39 @@ class BackwardDifferenceEncoder(BaseContrastEncoder):
 
     Parameters
     ----------
-
     verbose: int
         integer indicating verbosity of the output. 0 for none.
     cols: list
         a list of columns to encode, if None, all string columns will be encoded.
     drop_invariant: bool
         boolean for whether or not to drop columns with 0 variance.
     return_df: bool
-        boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
+        boolean for whether to return a pandas DataFrame from transform
+        (otherwise it will be a numpy array).
     handle_unknown: str
-        options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
-        an extra column will be added in if the transform matrix has unknown categories.  This can cause
-        unexpected changes in dimension in some cases.
+        options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'.
+        Warning: if indicator is used, an extra column will be added in if the transform matrix
+        has unknown categories. This can cause unexpected changes in dimension in some cases.
     handle_missing: str
-        options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
-        an extra column will be added in if the transform matrix has nan values.  This can cause
-        unexpected changes in dimension in some cases.
+        options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'.
+        Warning: if indicator is used, an extra column will be added in if the transform
+        matrix has nan values. This can cause unexpected changes in dimension in some cases.
 
     Example
     -------
     >>> from category_encoders import *
     >>> import pandas as pd
     >>> from sklearn.datasets import fetch_openml
-    >>> bunch = fetch_openml(name="house_prices", as_frame=True)
-    >>> display_cols = ["Id", "MSSubClass", "MSZoning", "LotFrontage", "YearBuilt", "Heating", "CentralAir"]
+    >>> bunch = fetch_openml(name='house_prices', as_frame=True)
+    >>> display_cols = [
+    ...     'Id',
+    ...     'MSSubClass',
+    ...     'MSZoning',
+    ...     'LotFrontage',
+    ...     'YearBuilt',
+    ...     'Heating',
+    ...     'CentralAir',
+    ... ]
     >>> y = bunch.target
     >>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)[display_cols]
     >>> enc = BackwardDifferenceEncoder(cols=['CentralAir', 'Heating']).fit(X, y)
@@ -46,12 +54,11 @@ class BackwardDifferenceEncoder(BaseContrastEncoder):
     <class 'pandas.core.frame.DataFrame'>
     RangeIndex: 1460 entries, 0 to 1459
     Data columns (total 12 columns):
-     #   Column        Non-Null Count  Dtype  
-    ---  ------        --------------  -----  
-     0   intercept     1460 non-null   int64  
+     #   Column        Non-Null Count  Dtype
+    ---  ------        --------------  -----
      1   Id            1460 non-null   float64
      2   MSSubClass    1460 non-null   float64
-     3   MSZoning      1460 non-null   object 
+     3   MSZoning      1460 non-null   object
      4   LotFrontage   1201 non-null   float64
      5   YearBuilt     1460 non-null   float64
      6   Heating_0     1460 non-null   float64
@@ -76,5 +83,5 @@ class BackwardDifferenceEncoder(BaseContrastEncoder):
     """
 
     def get_contrast_matrix(self, values_to_encode: np.array) -> ContrastMatrix:
+        """Get the contrast matrix for the backward difference encoder."""
         return Diff().code_without_intercept(values_to_encode)
-