Merge pull request #19 from ak-gupta/develop

v0.2.1

.github/workflows/edgetest.yml

@@ -13,9 +13,10 @@ jobs:
       - uses: actions/checkout@v2
         with:
           ref: develop
+
       - id: run-edgetest
-        uses: fdosani/run-edgetest-action@v1.0
+        uses: edgetest-dev/run-edgetest-action@v1.4
         with:
-          edgetest-flags: '-c setup.cfg -r requirements.txt --export'
+          edgetest-flags: '-c pyproject.toml -r requirements.txt --export'
           base-branch: 'develop'
           skip-pr: 'false'

.github/workflows/publish-package.yml

@@ -18,7 +18,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: '3.8'
+        python-version: '3.9'
     - name: Install dependencies
       run: python -m pip install -r requirements.txt .[dev]
     - name: Build and publish

.github/workflows/test-package.yml

@@ -18,29 +18,40 @@ jobs:
         strategy:
             matrix:
                 python_version:
-                    - 3.7
                     - 3.8
                     - 3.9
                     - '3.10'
+                    - '3.11'
         steps:
             - uses: actions/checkout@v2
+
             - name: Set up Python ${{ matrix.python-version }}
               uses: actions/setup-python@v2
               with:
                 python-version: ${{ matrix.python-version }}
+
+            - name: Install setuptools and upgrade pip
+              run: python -m pip install 'setuptools>=64.0.0' 'pip>=22.3'
+
             - name: Install dependencies
-              run: python -m pip install -r requirements.txt .[dev]
-            - name: Check docstrings
-              run: python -m pydocstyle bayte --convention=numpy
+              run: python -m pip install -r requirements.txt .[plots,tests,qa]
+
+            - name: Run ruff QA checks
+              run: python -m ruff check .
+
+            - name: Check formatting
+              run: python -m ruff format . --check
+
             - name: Check static typing
               run: python -m mypy bayte
-            - name: Run flake8
-              run: python -m flake8 bayte
+
             - name: Run unit testing
               run: python -m pytest tests --cov=./bayte --cov-report=xml
+
             - name: Run Codecov
-              uses: codecov/codecov-action@v2
+              uses: codecov/codecov-action@v3
               with:
+                token: ${{ secrets.CODECOV_TOKEN }}
                 fail_ci_if_error: true
                 files: ./coverage.xml
                 verbose: true

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Akshay Gupta
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

bayte/__init__.py

@@ -1,14 +1,13 @@
 """Import path."""
 
-from ._meta import __version__  # noqa: F401
-
 from typing import List
 
-from .encoder import BayesianTargetEncoder
-from .ensemble import BayesianTargetClassifier, BayesianTargetRegressor
+from bayte._meta import __version__  # noqa: F401
+from bayte.encoder import BayesianTargetEncoder
+from bayte.ensemble import BayesianTargetClassifier, BayesianTargetRegressor
 
 __all__: List[str] = [
-    "BayesianTargetEncoder",
     "BayesianTargetClassifier",
+    "BayesianTargetEncoder",
     "BayesianTargetRegressor",
 ]

bayte/_meta.py

@@ -1,3 +1,3 @@
 """Package metadata."""
 
-__version__ = "0.1.1"
+__version__ = "0.2.1"

bayte/encoder.py

@@ -1,11 +1,11 @@
 """Bayesian target encoder."""
 
 import logging
-from typing import Callable, List, Optional, Tuple, Union
+from typing import Callable, ClassVar, List, Optional, Tuple, Union
 
-from joblib import Parallel, effective_n_jobs
 import numpy as np
 import scipy.stats
+from joblib import Parallel, effective_n_jobs
 from sklearn.preprocessing._encoders import _BaseEncoder
 from sklearn.utils.fixes import delayed
 from sklearn.utils.validation import check_is_fitted
@@ -242,7 +242,7 @@ class BayesianTargetEncoder(_BaseEncoder):
         the parameters for the posterior distribution for the given level.
     """
 
-    _required_parameters = ["dist"]
+    _required_parameters: ClassVar[List[str]] = ["dist"]
 
     def __init__(
         self,
@@ -283,8 +283,15 @@ def fit(self, X, y):
         self : object
             Fitted encoder.
         """
-        X, y = self._validate_data(X, y, dtype=None)
-        self._fit(X, handle_unknown=self.handle_unknown, force_all_finite=True)
+        tags = self._get_tags()
+        X, y = self._validate_data(
+            X, y, dtype=None, force_all_finite=not tags.get("allow_nan", True)
+        )
+        self._fit(
+            X,
+            handle_unknown=self.handle_unknown,
+            force_all_finite=not tags.get("allow_nan", True),
+        )
         # Initialize the prior distribution parameters
         initializer_ = self.initializer or _init_prior
         self.prior_params_ = initializer_(self.dist, y)
@@ -322,10 +329,11 @@ def transform(self, X):
         """
         check_is_fitted(self)
 
+        tags = self._get_tags()
         X_int, X_mask = self._transform(
             X,
             handle_unknown=self.handle_unknown,
-            force_all_finite=True,
+            force_all_finite=not tags.get("allow_nan", True),
         )
 
         if effective_n_jobs(self.n_jobs) == 1:
@@ -376,14 +384,17 @@ def transform(self, X):
                     n_chunks = np.ceil(len(varencoded) / self.chunksize)
                 chunks = np.array_split(np.arange(len(varencoded)), n_chunks)
 
-                varencoded = list(
+                varencoded = [
                     np.ma.stack(varencoded[chunk[0] : chunk[-1] + 1], axis=2).sum(
                         axis=2
                     )
                     for chunk in chunks
-                )
+                ]
 
             combined = np.ma.stack(varencoded, axis=2).sum(axis=2)
             encoded.append(combined.data)
 
         return np.hstack(encoded)
+
+    def _more_tags(self):
+        return {"allow_nan": False}