xplainable-preprocessing 0.2.3__tar.gz → 0.2.4__tar.gz

{xplainable_preprocessing-0.2.3 → xplainable_preprocessing-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: xplainable-preprocessing
-Version: 0.2.3
+Version: 0.2.4
 Summary: Shared preprocessing pipeline package for xplainable
 Requires-Python: >=3.9
 Requires-Dist: cloudpickle>=3.0
@@ -8,6 +8,7 @@ Requires-Dist: numpy>=1.24
 Requires-Dist: pandas>=2.0
 Requires-Dist: pydantic>=2.0
 Requires-Dist: scikit-learn>=1.3
+Requires-Dist: scipy>=1.8
 Provides-Extra: dev
 Requires-Dist: pytest-cov; extra == 'dev'
 Requires-Dist: pytest>=7.0; extra == 'dev'

{xplainable_preprocessing-0.2.3 → xplainable_preprocessing-0.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "xplainable-preprocessing"
-version = "0.2.3"
+version = "0.2.4"
 description = "Shared preprocessing pipeline package for xplainable"
 requires-python = ">=3.9"
 dependencies = [
@@ -12,6 +12,7 @@ dependencies = [
     "scikit-learn>=1.3",
     "pandas>=2.0",
     "numpy>=1.24",
+    "scipy>=1.8",
     "cloudpickle>=3.0",
 ]
 

{xplainable_preprocessing-0.2.3 → xplainable_preprocessing-0.2.4}/src/xplainable_preprocessing/pipeline.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import pandas as pd
+from scipy import sparse
 from sklearn.base import BaseEstimator, TransformerMixin
 
 
@@ -20,6 +21,11 @@ class DataFrameColumnTransformer(BaseEstimator, TransformerMixin):
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
         Xt = X.copy()
         result = self.transformer.transform(Xt[self.columns])
+        if sparse.issparse(result):
+            # e.g. OneHotEncoder defaults to sparse_output=True; pd.DataFrame
+            # would treat the matrix as a single object column and raise
+            # "Shape of passed values is (N, 1), indices imply (N, K)".
+            result = result.toarray()
         if isinstance(result, pd.DataFrame):
             Xt = Xt.drop(columns=self.columns)
             Xt = pd.concat([Xt, result], axis=1)

xplainable_preprocessing-0.2.4/tests/test_pipeline.py

@@ -0,0 +1,73 @@
+"""Tests for DataFrame-preserving pipeline pieces.
+
+Regression coverage for sparse transformer output: sklearn's OneHotEncoder
+defaults to sparse_output=True (csr_matrix). pd.DataFrame(csr_matrix, ...)
+treats the matrix as a single object column, raising
+"Shape of passed values is (N, 1), indices imply (N, K)".
+Observed live as HTTP 500s from /v1/preprocessors/create.
+"""
+
+import pandas as pd
+import pytest
+from sklearn.preprocessing import OneHotEncoder
+
+from xplainable_preprocessing.compiler import compile_spec
+from xplainable_preprocessing.pipeline import DataFrameColumnTransformer
+from xplainable_preprocessing.schema import PipelineSpec
+
+
+@pytest.fixture
+def df():
+    return pd.DataFrame({
+        "PhoneService": ["Yes", "No"] * 25,
+        "Contract": ["Month-to-month", "One year", "Two year", "One year",
+                     "Month-to-month"] * 10,
+        "tenure": range(50),
+    })
+
+
+class TestSparseTransformerOutput:
+    def test_column_transformer_densifies_sparse_output(self, df):
+        t = DataFrameColumnTransformer(OneHotEncoder(), ["PhoneService", "Contract"])
+        out = t.fit_transform(df)
+
+        assert isinstance(out, pd.DataFrame)
+        assert "tenure" in out.columns
+        assert "PhoneService_Yes" in out.columns
+        assert "Contract_Two year" in out.columns
+        # Row 0: PhoneService == "Yes"
+        assert out.loc[0, "PhoneService_Yes"] == 1.0
+        assert out.loc[0, "PhoneService_No"] == 0.0
+
+    def test_compile_spec_onehot_multi_column_step(self, df):
+        spec = PipelineSpec(version="2.0", steps=[
+            {"id": "oh", "type": "OneHotEncoder",
+             "columns": ["PhoneService", "Contract"], "params": {}},
+        ])
+        pipeline = compile_spec(spec)
+        out = pipeline.fit_transform(df)
+
+        assert "PhoneService" not in out.columns
+        assert "PhoneService_No" in out.columns
+        assert "Contract_One year" in out.columns
+        assert len(out) == 50
+
+    def test_compile_spec_onehot_one_column_per_step(self, df):
+        spec = PipelineSpec(version="2.0", steps=[
+            {"id": "oh1", "type": "OneHotEncoder",
+             "columns": ["PhoneService"], "params": {}},
+            {"id": "oh2", "type": "OneHotEncoder",
+             "columns": ["Contract"], "params": {}},
+        ])
+        pipeline = compile_spec(spec)
+        out = pipeline.fit_transform(df)
+
+        assert "PhoneService_Yes" in out.columns
+        assert "Contract_Month-to-month" in out.columns
+        assert "tenure" in out.columns
+
+    def test_transform_after_fit_matches_fit_transform(self, df):
+        t = DataFrameColumnTransformer(OneHotEncoder(), ["PhoneService"])
+        fitted_out = t.fit_transform(df)
+        transform_out = t.transform(df)
+        pd.testing.assert_frame_equal(fitted_out, transform_out)