spforge 0.8.36__py3-none-any.whl → 0.8.37__py3-none-any.whl

spforge/performance_transformers/_performance_manager.py

@@ -86,8 +86,8 @@ class PerformanceManager(BaseEstimator, TransformerMixin):
         transformer_names: list[TransformerName] | None = None,
         custom_transformers: list[NarwhalsFeatureTransformer] | None = None,
         prefix: str = "performance__",
-        min_value: float = -0.02,
-        max_value: float = 1.02,
+        min_value: float = 0.0,
+        max_value: float = 1.0,
         zero_inflation_threshold: float = 0.15,
     ):
         self.features = features
@@ -209,8 +209,8 @@ class PerformanceWeightsManager(PerformanceManager):
         transformer_names: (
             list[Literal["partial_standard_scaler", "symmetric", "min_max"]] | None
         ) = None,
-        max_value: float = 1.02,
-        min_value: float = -0.02,
+        max_value: float = 1.0,
+        min_value: float = 0.0,
         prefix: str = "performance__",
         return_all_features: bool = False,
         zero_inflation_threshold: float = 0.15,

{spforge-0.8.36.dist-info → spforge-0.8.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spforge
-Version: 0.8.36
+Version: 0.8.37
 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-0.8.36.dist-info → spforge-0.8.37.dist-info}/RECORD

@@ -47,7 +47,7 @@ spforge/hyperparameter_tuning/__init__.py,sha256=Vcl8rVlJ7M708iPgqe4XxpZWgJKGux0
 spforge/hyperparameter_tuning/_default_search_spaces.py,sha256=SjwXLpvYIu_JY8uPRHeL5Kgp1aa0slWDz8qsKDaohWQ,8020
 spforge/hyperparameter_tuning/_tuner.py,sha256=M79q3saM6r0UZJsRUUgfdDr-3Qii-F2-wuSAZLFtZDo,19246
 spforge/performance_transformers/__init__.py,sha256=J-5olqi1M_BUj3sN1NqAz9s28XAbuKK9M9xHq7IGlQU,482
-spforge/performance_transformers/_performance_manager.py,sha256=tR_4laGoC_KFRaw3Gy0TMI-r5gnicDmvmxPEgAvl4E0,12031
+spforge/performance_transformers/_performance_manager.py,sha256=_qXqj8aaVJyTuUXrZxbOSANwL5iO3Rd1yz9WBwYBTMA,12025
 spforge/performance_transformers/_performances_transformers.py,sha256=ZjkFDXoEe5fURpN-dNkrgFXpHEg4aFCWdBDnPyLtgkM,18368
 spforge/ratings/__init__.py,sha256=OZVH2Lo6END3n1X8qi4QcyAPlThIwAYwVKCiIuOQSQU,576
 spforge/ratings/_base.py,sha256=Z-VVXWmnzR0O7o2_Q2x2ru_3uiTMpWqKDGQaNBJxCMA,14927
@@ -71,7 +71,7 @@ spforge/transformers/_other_transformer.py,sha256=w2a7Wnki3vJe4GAkSa4kealw0GILIo
 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-0.8.36.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+spforge-0.8.37.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
 tests/test_autopipeline.py,sha256=7cNAn-nmGolfyfk3THh9IKcHZfRA-pLYC_xAyMg-No4,26863
 tests/test_autopipeline_context.py,sha256=IuRUY4IA6uMObvbl2pXSaXO2_tl3qX6wEbTZY0dkTMI,1240
 tests/test_feature_generator_pipeline.py,sha256=CK0zVL8PfTncy3RmG9i-YpgwjOIV7yJhV7Q44tbetI8,19020
@@ -92,7 +92,7 @@ tests/feature_generator/test_rolling_mean_days.py,sha256=EyOvdJDnmgPfe13uQBOkwo7
 tests/feature_generator/test_rolling_window.py,sha256=_o9oljcAIZ14iI7e8WFeAsfXxILnyqBffit21HOvII4,24378
 tests/hyperparameter_tuning/test_estimator_tuner.py,sha256=iewME41d6LR2aQ0OtohGFtN_ocJUwTeqvs6L0QDmfG4,4413
 tests/hyperparameter_tuning/test_rating_tuner.py,sha256=usjC2ioO_yWRjjNAlRTyMVYheOrCi0kKocmHQHdTmpM,18699
-tests/performance_transformers/test_performance_manager.py,sha256=fVXxSujE3OKE7tIRJjN5dWCLj9pkeXbuL6Zf0WrM0ZA,15698
+tests/performance_transformers/test_performance_manager.py,sha256=Ja2TWq1vGoAqBSSeAWZ26drwEnsF6TmMmpQ0nsMRU_4,19163
 tests/performance_transformers/test_performances_transformers.py,sha256=HnW7GKQ6B0ova6Zy0lKbEpA6peZGFE4oi9Th6r7RnG0,18949
 tests/ratings/test_player_rating_generator.py,sha256=1Pkx0H8xJMTeLc2Fu9zJcoDpBWiY2zCVSxuBFJk2uEs,110717
 tests/ratings/test_player_rating_no_mutation.py,sha256=GzO3Hl__5K68DS3uRLefwnbcTJOvBM7cZqww4M21UZM,8493
@@ -108,7 +108,7 @@ 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-0.8.36.dist-info/METADATA,sha256=HxggFJqUQNu2SdjRwCHclWb3_5t1z5Ensjg1AXiVtXU,20048
-spforge-0.8.36.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-spforge-0.8.36.dist-info/top_level.txt,sha256=6UW2M5a7WKOeaAi900qQmRKNj5-HZzE8-eUD9Y9LTq0,23
-spforge-0.8.36.dist-info/RECORD,,
+spforge-0.8.37.dist-info/METADATA,sha256=fLFkSzIsDRPKRpyJ-H126XcKG_NAUyXmJNGDNrogq4s,20048
+spforge-0.8.37.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+spforge-0.8.37.dist-info/top_level.txt,sha256=6UW2M5a7WKOeaAi900qQmRKNj5-HZzE8-eUD9Y9LTq0,23
+spforge-0.8.37.dist-info/RECORD,,

tests/performance_transformers/test_performance_manager.py

@@ -203,8 +203,8 @@ def test_performance_manager_aliases_unprefixed_input_when_transformer_expects_p
         transformer_names=[],
         prefix="performance__",
         performance_column="weighted_performance",
-        min_value=-0.02,
-        max_value=1.02,
+        min_value=0.0,
+        max_value=1.0,
     )
 
     pm.fit(df)
@@ -434,3 +434,99 @@ class TestZeroInflationHandling:
 
         # Should have switched to quantile scaler
         assert manager._using_quantile_scaler is True
+
+
+class TestAutoScalePerformanceBounds:
+    """Tests for ensuring scaled performance stays within [0, 1] bounds."""
+
+    @pytest.mark.parametrize("frame", ["pd", "pl"])
+    def test_auto_scale_performance_preserves_non_negative(self, frame):
+        """Scaled performance should be non-negative when input is non-negative."""
+        np.random.seed(42)
+        # Create data similar to free throw % - centered around 0.77 with some zeros
+        n = 400
+        data = []
+        for _ in range(n):
+            if np.random.random() < 0.25:  # 25% zeros (missed all free throws)
+                data.append(0.0)
+            else:
+                # Values between 0.6 and 1.0, centered around 0.77
+                data.append(np.clip(np.random.normal(0.77, 0.15), 0.0, 1.0))
+
+        df = _make_native_df(frame, {"x": data})
+
+        pm = PerformanceManager(
+            features=["x"],
+            transformer_names=["symmetric", "partial_standard_scaler", "min_max"],
+            prefix="performance__",
+            performance_column="perf",
+        )
+
+        result = pm.fit_transform(df)
+        result_nw = nw.from_native(result)
+        scaled = result_nw["performance__perf"].to_numpy()
+
+        assert np.all(scaled >= 0), f"Scaled performance should not be negative, min was {scaled.min()}"
+
+    @pytest.mark.parametrize("frame", ["pd", "pl"])
+    def test_auto_scale_performance_output_range(self, frame):
+        """Scaled performance should be in [0, 1] when input is in [0, 1]."""
+        np.random.seed(42)
+        # Create data with performance in [0, 1] but skewed distribution
+        n = 400
+        data = []
+        for _ in range(n):
+            if np.random.random() < 0.25:
+                data.append(0.0)
+            else:
+                data.append(np.clip(np.random.normal(0.77, 0.15), 0.0, 1.0))
+
+        df = _make_native_df(frame, {"x": data})
+
+        pm = PerformanceManager(
+            features=["x"],
+            transformer_names=["symmetric", "partial_standard_scaler", "min_max"],
+            prefix="performance__",
+            performance_column="perf",
+        )
+
+        result = pm.fit_transform(df)
+        result_nw = nw.from_native(result)
+        scaled = result_nw["performance__perf"].to_numpy()
+
+        assert np.all(scaled >= 0.0), f"Scaled min should be >= 0, got {scaled.min()}"
+        assert np.all(scaled <= 1.0), f"Scaled max should be <= 1, got {scaled.max()}"
+
+    @pytest.mark.parametrize("frame", ["pd", "pl"])
+    def test_default_bounds_are_unit_interval(self, frame):
+        """Test that default bounds are [0, 1]."""
+        pm = PerformanceManager(
+            features=["x"],
+            transformer_names=[],
+            prefix="",
+            performance_column="x",
+        )
+
+        assert pm.min_value == 0.0
+        assert pm.max_value == 1.0
+
+    @pytest.mark.parametrize("frame", ["pd", "pl"])
+    def test_custom_bounds_still_work(self, frame):
+        """Test that custom bounds can still be specified."""
+        df = _make_native_df(frame, {"x": [-10.0, 0.5, 10.0]})
+
+        pm = PerformanceManager(
+            features=["x"],
+            transformer_names=[],
+            prefix="",
+            performance_column="x",
+            min_value=-0.5,
+            max_value=1.5,
+        )
+
+        result = pm.fit_transform(df)
+        result_nw = nw.from_native(result)
+        scaled = result_nw["x"].to_numpy()
+
+        assert scaled.min() >= -0.5
+        assert scaled.max() <= 1.5