spforge 0.8.13__py3-none-any.whl → 0.8.14__py3-none-any.whl

spforge/autopipeline.py

@@ -681,6 +681,22 @@ class AutoPipeline(BaseEstimator):
 
         return features
 
+    def _resolve_importance_feature_names(self, estimator, n_features: int) -> list[str]:
+        names = None
+        if hasattr(estimator, "feature_names_in_") and estimator.feature_names_in_ is not None:
+            names = list(estimator.feature_names_in_)
+        elif hasattr(estimator, "feature_name_") and estimator.feature_name_ is not None:
+            names = list(estimator.feature_name_)
+        elif hasattr(estimator, "feature_names_") and estimator.feature_names_ is not None:
+            names = list(estimator.feature_names_)
+        if names is None:
+            names = self._get_estimator_feature_names()
+        if len(names) != n_features:
+            raise ValueError(
+                f"Feature names length ({len(names)}) does not match importances length ({n_features})."
+            )
+        return names
+
     @property
     def feature_importances_(self) -> pd.DataFrame:
         """Get feature importances from the fitted estimator.
@@ -719,3 +735,33 @@ class AutoPipeline(BaseEstimator):
         df = pd.DataFrame({"feature": feature_names, "importance": importances})
         df = df.sort_values("importance", ascending=False, key=abs).reset_index(drop=True)
         return df
+
+    @property
+    def feature_importance_names(self) -> dict[str, float]:
+        """Map deepest estimator feature names to importances."""
+        if self.sklearn_pipeline is None:
+            raise RuntimeError("Pipeline not fitted. Call fit() first.")
+
+        est = self.sklearn_pipeline.named_steps["est"]
+        result = _get_importance_estimator(est)
+
+        if result is None:
+            raise RuntimeError(
+                "Estimator does not support feature importances. "
+                "Requires feature_importances_ or coef_ attribute."
+            )
+
+        inner_est, attr_name = result
+        raw = getattr(inner_est, attr_name)
+
+        if attr_name == "coef_":
+            if raw.ndim == 2:
+                importances = np.abs(raw).mean(axis=0)
+            else:
+                importances = np.abs(raw)
+        else:
+            importances = raw
+
+        importances = np.asarray(importances)
+        feature_names = self._resolve_importance_feature_names(inner_est, len(importances))
+        return dict(zip(feature_names, importances.tolist()))

{spforge-0.8.13.dist-info → spforge-0.8.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spforge
-Version: 0.8.13
+Version: 0.8.14
 Summary: A flexible framework for generating features, ratings, and building machine learning or other models for training and inference on sports data.
 Author-email: Mathias Holmstrøm <mathiasholmstom@gmail.com>
 License: See LICENSE file

{spforge-0.8.13.dist-info → spforge-0.8.14.dist-info}/RECORD

@@ -14,7 +14,7 @@ examples/nba/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 examples/nba/data/game_player_subsample.parquet,sha256=ODJxHC-mUYbJ7r-ScUFtPU7hrFuxLUbbDSobmpCkw0w,279161
 examples/nba/data/utils.py,sha256=41hxLQ1d6ZgBEcHa5MI0-fG5KbsRi07cclMPQZM95ek,509
 spforge/__init__.py,sha256=8vZhy7XUpzqWkVKpXqwqOLDkQlNytRhyf4qjwObfXgU,468
-spforge/autopipeline.py,sha256=4DAm_Wxtzvum3_7OViRru22HPD4TPHrjtlsalvtkzKM,26834
+spforge/autopipeline.py,sha256=q3EbeMvSuxyyaDj_uKSxdcCHlvORXAVJ4JAPNbeYvCs,28744
 spforge/base_feature_generator.py,sha256=RbD00N6oLCQQcEb_VF5wbwZztl-X8k9B0Wlaj9Os1iU,668
 spforge/data_structures.py,sha256=k82v5r79vl0_FAVvsxVF9Nbzb5FoHqVrlHZlEXGc5gQ,7298
 spforge/features_generator_pipeline.py,sha256=n8vzZKqXNFcFRDWZhllnkhAh5NFXdOD3FEIOpHcay8E,8208
@@ -71,8 +71,8 @@ spforge/transformers/_other_transformer.py,sha256=xLfaFIhkFsigAoitB4x3F8An2j9ymd
 spforge/transformers/_predictor.py,sha256=2sE6gfVrilXzPVcBurSrtqHw33v2ljygQcEYXt9LhZc,3119
 spforge/transformers/_simple_transformer.py,sha256=zGUFNQYMeoDSa2CoQejQNiNmKCBN5amWTvyOchiUHj0,5660
 spforge/transformers/_team_ratio_predictor.py,sha256=g8_bR53Yyv0iNCtol1O9bgJSeZcIco_AfbQuUxQJkeY,6884
-spforge-0.8.13.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-tests/test_autopipeline.py,sha256=i4DBraTZT0_OQ7kabTausV5LsyvMhfvKTxCd-Gtz00U,21269
+spforge-0.8.14.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+tests/test_autopipeline.py,sha256=KHDuhPOzfezKj_FB7k5XQhxsreLFEiGUEYvybZZn-YA,22258
 tests/test_autopipeline_context.py,sha256=IuRUY4IA6uMObvbl2pXSaXO2_tl3qX6wEbTZY0dkTMI,1240
 tests/test_feature_generator_pipeline.py,sha256=CK0zVL8PfTncy3RmG9i-YpgwjOIV7yJhV7Q44tbetI8,19020
 tests/cross_validator/test_cross_validator.py,sha256=itCGhNY8-NbDbKbhxHW20wiLuRst7-Rixpmi3FSKQtA,17474
@@ -107,7 +107,7 @@ tests/transformers/test_other_transformer.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRk
 tests/transformers/test_predictor_transformer.py,sha256=N1aBYLjN3ldpYZLwjih_gTFYSMitrZu-PNK78W6RHaQ,6877
 tests/transformers/test_simple_transformer.py,sha256=wWR0qjLb_uS4HXrJgGdiqugOY1X7kwd1_OPS02IT2b8,4676
 tests/transformers/test_team_ratio_predictor.py,sha256=fOUP_JvNJi-3kom3ZOs1EdG0I6Z8hpLpYKNHu1eWtOw,8562
-spforge-0.8.13.dist-info/METADATA,sha256=cGBuOH1Pk7txtWsIMtIhWNBqNQwYILyxoZVjr3jzKHw,20048
-spforge-0.8.13.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-spforge-0.8.13.dist-info/top_level.txt,sha256=6UW2M5a7WKOeaAi900qQmRKNj5-HZzE8-eUD9Y9LTq0,23
-spforge-0.8.13.dist-info/RECORD,,
+spforge-0.8.14.dist-info/METADATA,sha256=QjJItgB1kBct3TPaiUbTmy-wkqw2hVG69tRq55WFXWU,20048
+spforge-0.8.14.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+spforge-0.8.14.dist-info/top_level.txt,sha256=6UW2M5a7WKOeaAi900qQmRKNj5-HZzE8-eUD9Y9LTq0,23
+spforge-0.8.14.dist-info/RECORD,,

tests/test_autopipeline.py

@@ -692,3 +692,34 @@ def test_feature_importances__onehot_features():
     assert len(importances) == 4
     assert "num1" in importances["feature"].tolist()
     assert any("cat1_" in f for f in importances["feature"].tolist())
+
+
+def test_feature_importance_names__granularity_uses_deep_feature_names():
+    from sklearn.ensemble import RandomForestRegressor
+
+    df = pd.DataFrame(
+        {
+            "gameid": ["g1", "g1", "g2", "g2"],
+            "num1": [1.0, 2.0, 3.0, 4.0],
+            "num2": [10.0, 20.0, 30.0, 40.0],
+        }
+    )
+    y = pd.Series([1.0, 2.0, 3.0, 4.0], name="y")
+
+    model = AutoPipeline(
+        estimator=RandomForestRegressor(n_estimators=5, random_state=42),
+        estimator_features=["gameid", "num1", "num2"],
+        predictor_transformers=[AddConstantPredictionTransformer(col_name="const_pred")],
+        granularity=["gameid"],
+        categorical_features=["gameid"],
+        categorical_handling="ordinal",
+        remainder="drop",
+    )
+    model.fit(df, y)
+
+    names = model.feature_importance_names
+
+    inner = _inner_estimator(model)
+    assert list(names.keys()) == list(inner.feature_names_in_)
+    assert "gameid" not in names
+    assert "const_pred" in names