spforge 0.8.7__tar.gz → 0.8.9__tar.gz

{spforge-0.8.7/spforge.egg-info → spforge-0.8.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spforge
-Version: 0.8.7
+Version: 0.8.9
 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-0.8.7 → spforge-0.8.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spforge"
-version = "0.8.7"
+version = "0.8.9"
 description = "A flexible framework for generating features, ratings, and building machine learning or other models for training and inference on sports data."
 readme = "README.md"
 requires-python = ">=3.11"

{spforge-0.8.7 → spforge-0.8.9}/spforge/features_generator_pipeline.py

@@ -120,7 +120,8 @@ class FeatureGeneratorPipeline(FeatureGenerator):
 
         for transformer in self.feature_generators:
             pre_row_count = len(df)
-            df = nw.from_native(transformer.fit_transform(df, column_names=column_names))
+            native_df = df.to_native()
+            df = nw.from_native(transformer.fit_transform(native_df, column_names=column_names))
             assert len(df) == pre_row_count
             for f in transformer.features_out:
                 if f in expected_feats_added:
@@ -151,7 +152,8 @@ class FeatureGeneratorPipeline(FeatureGenerator):
 
         for transformer in self.feature_generators:
             pre_row_count = len(df)
-            df = nw.from_native(transformer.transform(df))
+            native_df = df.to_native()
+            df = nw.from_native(transformer.transform(native_df))
             assert len(df) == pre_row_count
             for f in transformer.features_out:
                 if f in expected_feats_added:
@@ -181,9 +183,11 @@ class FeatureGeneratorPipeline(FeatureGenerator):
         for transformer in self.feature_generators:
             pre_row_count = len(df)
             if hasattr(transformer, "future_transform") and callable(transformer.future_transform):
-                df = nw.from_native(transformer.future_transform(df))
+                native_df = df.to_native()
+                df = nw.from_native(transformer.future_transform(native_df))
             else:
-                df = nw.from_native(transformer.transform(df))
+                native_df = df.to_native()
+                df = nw.from_native(transformer.transform(native_df))
             assert len(df) == pre_row_count
             for f in transformer.features_out:
                 if f in expected_feats_added:

{spforge-0.8.7 → spforge-0.8.9}/spforge/performance_transformers/_performance_manager.py

@@ -250,8 +250,6 @@ class PerformanceWeightsManager(PerformanceManager):
                 )
             )
 
-        sum_weight = sum([w.weight for w in self.weights])
-
         for column_weight in self.weights:
             weight_col = f"weight__{column_weight.name}"
             feature_col = column_weight.name
@@ -261,14 +259,14 @@ class PerformanceWeightsManager(PerformanceManager):
                 df = df.with_columns(
                     (
                         nw.col(tmp_out_performance_colum_name)
-                        + (nw.col(weight_col) / sum_weight * (1 - nw.col(feature_name)))
+                        + (nw.col(weight_col) * (1 - nw.col(feature_name)))
                     ).alias(tmp_out_performance_colum_name)
                 )
             else:
                 df = df.with_columns(
                     (
                         nw.col(tmp_out_performance_colum_name)
-                        + (nw.col(weight_col) / sum_weight * nw.col(feature_name))
+                        + (nw.col(weight_col) * nw.col(feature_name))
                     ).alias(tmp_out_performance_colum_name)
                 )
 

{spforge-0.8.7 → spforge-0.8.9/spforge.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spforge
-Version: 0.8.7
+Version: 0.8.9
 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-0.8.7 → spforge-0.8.9}/tests/performance_transformers/test_performance_manager.py

@@ -56,6 +56,21 @@ def test_performance_weights_manager_basic_flow(sample_data):
     assert output_df["weighted_performance"].iloc[0] == pytest.approx(0.6)
 
 
+def test_performance_weights_manager_keeps_mean_when_weights_not_normalized():
+    df = pd.DataFrame(
+        {
+            "feat_a": [0.0, 1.0, 2.0, 3.0],
+            "feat_b": [3.0, 2.0, 1.0, 0.0],
+        }
+    )
+    weights = [ColumnWeight(name="feat_a", weight=0.9), ColumnWeight(name="feat_b", weight=0.5)]
+
+    manager = PerformanceWeightsManager(weights=weights, transformer_names=["min_max"], prefix="")
+    output_df = nw.from_native(manager.fit_transform(df)).to_pandas()
+
+    assert output_df["weighted_performance"].mean() == pytest.approx(0.5, abs=1e-6)
+
+
 def test_lower_is_better_logic():
     df = pd.DataFrame({"feat_a": [1.0, 0.0]})
     weights = [ColumnWeight(name="feat_a", weight=1.0, lower_is_better=True)]

{spforge-0.8.7 → spforge-0.8.9}/tests/test_feature_generator_pipeline.py

@@ -16,6 +16,49 @@ def column_names():
     )
 
 
+class PolarsOnlyGenerator:
+    def __init__(self):
+        self._features_out = ["polars_only_feature"]
+
+    @property
+    def features_out(self):
+        return self._features_out
+
+    def fit_transform(self, df, column_names=None):
+        if not isinstance(df, pl.DataFrame):
+            raise TypeError("Expected polars DataFrame")
+        return df.with_columns((pl.col("points") * 2).alias("polars_only_feature"))
+
+    def transform(self, df):
+        if not isinstance(df, pl.DataFrame):
+            raise TypeError("Expected polars DataFrame")
+        return df.with_columns((pl.col("points") * 2).alias("polars_only_feature"))
+
+    def future_transform(self, df):
+        return self.transform(df)
+
+
+def test_feature_generator_pipeline__passes_native_polars_to_custom_generator(column_names):
+    data = pl.DataFrame(
+        {
+            "game_id": [1, 1],
+            "team_id": ["A", "B"],
+            "player_id": ["p1", "p2"],
+            "date": pd.to_datetime(["2023-01-01", "2023-01-01"]),
+            "points": [10, 15],
+        }
+    )
+
+    pipeline = FeatureGeneratorPipeline(
+        feature_generators=[PolarsOnlyGenerator()],
+        column_names=column_names,
+    )
+
+    result = pipeline.fit_transform(data, column_names=column_names)
+
+    assert "polars_only_feature" in result.columns
+
+
 @pytest.mark.parametrize("df_type", [pd.DataFrame, pl.DataFrame])
 def test_feature_generator_pipeline__fit_transform_preserves_row_count(df_type, column_names):
     """FeatureGeneratorPipeline.fit_transform should preserve row count."""