upgini 1.2.71a3832.dev9__py3-none-any.whl → 1.2.71a3832.dev11__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.71a3832.dev9"
+__version__ = "1.2.71a3832.dev11"

upgini/features_enricher.py

@@ -1512,8 +1512,7 @@ class FeaturesEnricher(TransformerMixin):
         self.logger.info(f"Client features column on prepare data for metrics: {client_features}")
 
         filtered_enriched_features = self.__filtered_enriched_features(
-            importance_threshold,
-            max_features,
+            importance_threshold, max_features, trace_id, validated_X
         )
         filtered_enriched_features = [c for c in filtered_enriched_features if c not in client_features]
 
@@ -2541,7 +2540,9 @@ if response.status_code == 200:
                 for c in itertools.chain(validated_Xy.columns.tolist(), generated_features)
                 if c not in self.dropped_client_feature_names_
             ]
-            filtered_columns = self.__filtered_enriched_features(importance_threshold, max_features)
+            filtered_columns = self.__filtered_enriched_features(
+                importance_threshold, max_features, trace_id, validated_X
+            )
             selecting_columns.extend(
                 c for c in filtered_columns if c in result.columns and c not in validated_X.columns
             )
@@ -3805,6 +3806,46 @@ if response.status_code == 200:
 
         return result_features
 
+    def __get_features_importance_from_server(self, trace_id: str, df: pd.DataFrame):
+        if self._search_task is None:
+            raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
+        features_meta = self._search_task.get_all_features_metadata_v2()
+        if features_meta is None:
+            raise Exception(self.bundle.get("missing_features_meta"))
+
+        original_names_dict = {c.name: c.originalName for c in self._search_task.get_file_metadata(trace_id).columns}
+        df = df.rename(columns=original_names_dict)
+
+        features_meta.sort(key=lambda m: (-m.shap_value, m.name))
+
+        importances = {}
+
+        for feature_meta in features_meta:
+            if feature_meta.name in original_names_dict.keys():
+                feature_meta.name = original_names_dict[feature_meta.name]
+
+            is_client_feature = feature_meta.name in df.columns
+
+            if feature_meta.shap_value == 0.0:
+                continue
+
+            # Use only important features
+            if (
+                feature_meta.name == COUNTRY
+                # In select_features mode we select also from etalon features and need to show them
+                or (not self.fit_select_features and is_client_feature)
+            ):
+                continue
+
+            # Temporary workaround for duplicate features metadata
+            if feature_meta.name in importances:
+                self.logger.warning(f"WARNING: Duplicate feature metadata: {feature_meta}")
+                continue
+
+            importances[feature_meta.name] = feature_meta.shap_value
+
+        return importances
+
     def __prepare_feature_importances(
         self, trace_id: str, df: pd.DataFrame, updated_shaps: Optional[Dict[str, float]] = None, silent=False
     ):
@@ -3990,9 +4031,12 @@ if response.status_code == 200:
         )
 
     def __filtered_importance_names(
-        self, importance_threshold: Optional[float], max_features: Optional[int]
+        self, importance_threshold: Optional[float], max_features: Optional[int], trace_id: str, df: pd.DataFrame
     ) -> List[str]:
-        if len(self.feature_names_) == 0:
+        # get features importance from server
+        filtered_importances = self.__get_features_importance_from_server(trace_id, df)
+
+        if len(filtered_importances) == 0:
             return []
 
         filtered_importances = list(zip(self.feature_names_, self.feature_importances_))
@@ -4212,11 +4256,13 @@ if response.status_code == 200:
         self,
         importance_threshold: Optional[float],
         max_features: Optional[int],
+        trace_id: str,
+        df: pd.DataFrame,
     ) -> List[str]:
         importance_threshold = self.__validate_importance_threshold(importance_threshold)
         max_features = self.__validate_max_features(max_features)
 
-        return self.__filtered_importance_names(importance_threshold, max_features)
+        return self.__filtered_importance_names(importance_threshold, max_features, trace_id, df)
 
     def __detect_missing_search_keys(
         self,

upgini/metrics.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import inspect
 import logging
 import re
-import warnings
 from collections import defaultdict
 from copy import deepcopy
 from dataclasses import dataclass
@@ -755,9 +754,12 @@ class LightGBMWrapper(EstimatorWrapper):
             logger=logger,
         )
         self.cat_features = None
+        self.n_classes = None
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series, np.ndarray, dict]:
         x, y_numpy, groups, params = super()._prepare_to_fit(x, y)
+        if self.target_type in [ModelTaskType.BINARY, ModelTaskType.MULTICLASS]:
+            self.n_classes = len(np.unique(y_numpy))
         if LIGHTGBM_EARLY_STOPPING_ROUNDS is not None:
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
@@ -783,31 +785,40 @@ class LightGBMWrapper(EstimatorWrapper):
 
     def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator) -> Optional[Dict[str, float]]:
         try:
-            # Suppress specific warning from SHAP for LightGBM binary classifier
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    "LightGBM binary classifier with TreeExplainer shap values output has changed to a list of ndarray"
-                ),
+            shap_matrix = estimator.predict(
+                x,
+                predict_disable_shape_check=True,
+                raw_score=True,
+                pred_leaf=False,
+                pred_early_stop=True,
+                pred_contrib=True,
             )
-            from shap import TreeExplainer
-
-            if not isinstance(estimator, (LGBMRegressor, LGBMClassifier)):
-                return None
 
-            explainer = TreeExplainer(estimator)
-
-            shap_values = explainer.shap_values(x)
+            if self.target_type == ModelTaskType.MULTICLASS:
+                n_feat = x.shape[1]
+                shap_matrix.shape = (shap_matrix.shape[0], self.n_classes, n_feat + 1)
+                shap_matrix = np.mean(np.abs(shap_matrix), axis=1)
 
-            # For classification, shap_values is returned as a list for each class
-            # Take values for the positive class
-            if isinstance(shap_values, list):
-                shap_values = shap_values[1]
+            # exclude base value
+            shap_matrix = shap_matrix[:, :-1]
 
-            # Calculate mean absolute SHAP value for each feature
             feature_importance = {}
             for i, col in enumerate(x.columns):
-                feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
+                feature_importance[col] = np.mean(np.abs(shap_matrix[:, i]))
+
+            # # exclude last column (base value)
+            # shap_values_only = shap_values[:, :-1]
+            # mean_abs_shap = np.mean(np.abs(shap_values_only), axis=0)
+
+            # # For classification, shap_values is returned as a list for each class
+            # # Take values for the positive class
+            # if isinstance(shap_values, list):
+            #     shap_values = shap_values[1]
+
+            # # Calculate mean absolute SHAP value for each feature
+            # feature_importance = {}
+            # for i, col in enumerate(x.columns):
+            #     feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
 
             return feature_importance
 

{upgini-1.2.71a3832.dev9.dist-info → upgini-1.2.71a3832.dev11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.71a3832.dev9
+Version: 1.2.71a3832.dev11
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.71a3832.dev9.dist-info → upgini-1.2.71a3832.dev11.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=9j3uTsEOnjsLQKejDMGIw2xcYlikwx_zlJRLURdTIkE,33
+upgini/__about__.py,sha256=MPYFg9v0SOhqTxe0IfYh4m6Nh3TlmyfHR9sua58WXBM,34
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Z6RSjqcqneGwWflsq1Q5rjf83awPNYqKpAgHRh7jils,204680
+upgini/features_enricher.py,sha256=oYOBaHIyPjm-EEZvJT9pU35_DW8bArEQKymZyhW8LbE,206592
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=PlyjxL82AtUWgbCWRv_0r4NiPwmflO5ItIPlKb4nxcs,38293
+upgini/metrics.py,sha256=9AaQi7Yb22ZNnycUOAUpcP7TWF5Pfy_NGACcDj10aMs,38820
 upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.71a3832.dev9.dist-info/METADATA,sha256=MMv6QMrMxHQ50ISC1VoKtdK00hxtsgnz-IuuHuKUh7M,49101
-upgini-1.2.71a3832.dev9.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.71a3832.dev9.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.71a3832.dev9.dist-info/RECORD,,
+upgini-1.2.71a3832.dev11.dist-info/METADATA,sha256=QuI4m49RjcWmDJ74fXMWfNqBKPXGKDsKGhhO_wR1Kfw,49102
+upgini-1.2.71a3832.dev11.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.71a3832.dev11.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.71a3832.dev11.dist-info/RECORD,,