scikit-extensions 0.1.0__tar.gz

scikit_extensions-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 sh99-git
+
+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.

scikit_extensions-0.1.0/PKG-INFO

@@ -0,0 +1,35 @@
+Metadata-Version: 2.1
+Name: scikit-extensions
+Version: 0.1.0
+Summary: "A collection of Scikit-learn-compatible transformers for feature engineering, preprocessing, and pipeline utilities."
+Home-page: https://github.com/your-username/scikit-extensions
+License: MIT
+Keywords: scikit-learn,transformers,preprocessing,pipeline
+Author: sh99
+Author-email: shriramh99@gmail.com
+Requires-Python: >=3.10,<3.14
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Dist: pandas (>=2.3.2,<3.0.0)
+Requires-Dist: scikit-learn (>=1.7.2,<2.0.0)
+Project-URL: Repository, https://github.com/your-username/scikit-extensions
+Description-Content-Type: text/markdown
+
+# scikit-extensions
+A collection of Scikit-learn-compatible transformers for feature engineering, preprocessing, and pipeline utilities.
+
+## Features
+- 🧰 Clean, extensible API compatible with Scikit-learn
+- 🧪 Fully testable, with support for Pandas, NumPy, and SciPy
+- 📦 Easy to integrate in production ML pipelines
+
+## 📦 Installation
+
+```bash
+pip install scikit-extensions
+

scikit_extensions-0.1.0/README.md

@@ -0,0 +1,12 @@
+# scikit-extensions
+A collection of Scikit-learn-compatible transformers for feature engineering, preprocessing, and pipeline utilities.
+
+## Features
+- 🧰 Clean, extensible API compatible with Scikit-learn
+- 🧪 Fully testable, with support for Pandas, NumPy, and SciPy
+- 📦 Easy to integrate in production ML pipelines
+
+## 📦 Installation
+
+```bash
+pip install scikit-extensions

scikit_extensions-0.1.0/pyproject.toml

@@ -0,0 +1,32 @@
+[tool.poetry]
+name = "scikit-extensions"
+version = "0.1.0"
+description = "\"A collection of Scikit-learn-compatible transformers for feature engineering, preprocessing, and pipeline utilities.\""
+authors = ["sh99 <shriramh99@gmail.com>"]
+readme = "README.md"
+license = "MIT"
+packages = [{ include = "skext" }]
+homepage = "https://github.com/your-username/scikit-extensions"
+repository = "https://github.com/your-username/scikit-extensions"
+keywords = ["scikit-learn", "transformers", "preprocessing", "pipeline"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Intended Audience :: Developers",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.14"
+scikit-learn = "^1.7.2"
+pandas = "^2.3.2"
+
+[tool.poetry.dev-dependencies]
+pytest = "^7.0"
+black = "^23.0"
+ruff = "^0.1.0"
+mypy = "^1.7"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

scikit_extensions-0.1.0/skext/__init__.py

@@ -0,0 +1,3 @@
+from .multilabels import MultiLabelBinarizerTransformer
+
+__all__ = ["MultiLabelBinarizerTransformer"]

scikit_extensions-0.1.0/skext/multilabels.py

@@ -0,0 +1,151 @@
+import pandas as pd
+import numpy as np
+from scipy.sparse import issparse, hstack
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import MultiLabelBinarizer
+
+
+class MultiLabelBinarizerTransformer(BaseEstimator, TransformerMixin):
+    """
+    A custom transformer that wraps sklearn's MultiLabelBinarizer to integrate seamlessly into scikit-learn pipelines.
+
+    This transformer converts a collection of label sets (iterables of iterables) into a binary indicator matrix.
+    It is particularly useful for multi-label classification tasks where each sample can belong to multiple classes.
+
+    Parameters
+    ----------
+    sparse_output : bool, default=False
+        If True, the output will be a sparse matrix in Compressed Sparse Row (CSR) format. Otherwise, a dense NumPy array is returned.
+
+    Attributes
+    ----------
+    mlbs : dict
+        A dictionary mapping column names to fitted MultiLabelBinarizer instances.
+    feature_names_in_ : list
+        List of input feature names (column names) during fitting.
+    """
+
+    def __init__(self, sparse_output=False):
+        """
+        Initializes the transformer with the specified parameters.
+
+        Parameters
+        ----------
+        sparse_output : bool, default=False
+            If True, the output will be a sparse matrix in Compressed Sparse Row (CSR) format. Otherwise, a dense NumPy array is returned.
+        """
+        self.sparse_output = sparse_output
+        self.mlbs = {}
+        self.feature_names_in_ = None
+
+    def fit(self, X, y=None):
+        """
+        Fits the transformer to the provided label sets.
+
+        Parameters
+        ----------
+        X : pandas DataFrame of shape (n_samples, n_features)
+            A collection of label sets, where each set contains the labels for a single sample.
+
+        y : None
+            Ignored. This parameter exists for compatibility with scikit-learn pipelines.
+
+        Returns
+        -------
+        self : object
+            The fitted transformer.
+        """
+        if not isinstance(X, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+        self.feature_names_in_ = X.columns.tolist()
+        self.mlbs = {
+            col: MultiLabelBinarizer(sparse_output=self.sparse_output).fit(X[col])
+            for col in self.feature_names_in_
+        }
+        return self
+
+    def transform(self, X):
+        """
+        Transforms the provided label sets into a binary indicator matrix.
+
+        Parameters
+        ----------
+        X : pandas DataFrame of shape (n_samples, n_features)
+            A collection of label sets to transform.
+
+        Returns
+        -------
+        transformed : pandas DataFrame or sparse matrix of shape (n_samples, n_classes)
+            A binary matrix indicating the presence of each class label in each sample.
+        """
+        if not isinstance(X, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+        transformed_parts = []
+        for col in self.feature_names_in_:
+            mlb = self.mlbs[col]
+            part = mlb.transform(X[col])
+            if not self.sparse_output:
+                part = pd.DataFrame(
+                    part,
+                    columns=[f"{col}__{cls}" for cls in mlb.classes_],
+                    index=X.index
+                )
+            transformed_parts.append(part)
+        return hstack(transformed_parts) if self.sparse_output else pd.concat(transformed_parts, axis=1)
+
+    def inverse_transform(self, X):
+        """
+        Converts a binary indicator matrix back into label sets.
+
+        Parameters
+        ----------
+        X : pandas DataFrame or sparse matrix of shape (n_samples, n_classes)
+            A binary matrix indicating the presence of each class label in each sample.
+
+        Returns
+        -------
+        inverse_transformed : pandas DataFrame of shape (n_samples, n_features)
+            A DataFrame where each column contains the original label sets for each sample.
+        """
+        if self.sparse_output and not issparse(X):
+            raise ValueError("Expected sparse input for inverse_transform but got dense.")
+        if not self.sparse_output and isinstance(X, np.ndarray):
+            X = pd.DataFrame(X, columns=self.get_feature_names_out())
+        result = {}
+        if self.sparse_output:
+            current_col = 0
+            for col in self.feature_names_in_:
+                mlb = self.mlbs[col]
+                n_classes = len(mlb.classes_)
+                col_slice = X[:, current_col:current_col + n_classes]
+                result[col] = mlb.inverse_transform(col_slice)
+                current_col += n_classes
+        else:
+            for col in self.feature_names_in_:
+                mlb = self.mlbs[col]
+                col_data = X[[f"{col}__{cls}" for cls in mlb.classes_]]
+                result[col] = mlb.inverse_transform(col_data.values)
+        return pd.DataFrame(result)
+
+    def get_feature_names_out(self, input_features=None):
+        """
+        Returns the output feature names for transformation.
+
+        Parameters
+        ----------
+        input_features : list of str, default=None
+            Input feature names. If None, uses the feature names seen during fitting.
+
+        Returns
+        -------
+        feature_names_out : list of str
+            The output feature names.
+        """
+        if input_features is None:
+            input_features = self.feature_names_in_
+        out = []
+        for col in input_features:
+            mlb = self.mlbs.get(col)
+            if mlb:
+                out.extend([f"{col}__{cls}" for cls in mlb.classes_])
+        return out