upgini 1.2.117a1__tar.gz → 1.2.118__tar.gz

{upgini-1.2.117a1 → upgini-1.2.118}/.gitignore

@@ -111,6 +111,7 @@ env10/
 .env10/
 .env310/
 env11/
+env12/
 venv/
 ENV/
 env.bak/

{upgini-1.2.117a1 → upgini-1.2.118}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.117a1
+Version: 1.2.118
 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-1.2.118/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.118"

{upgini-1.2.117a1 → upgini-1.2.118}/src/upgini/features_enricher.py

@@ -1423,8 +1423,15 @@ class FeaturesEnricher(TransformerMixin):
         # Find latest eval set or earliest if all eval sets are before train set
         date_column = self._get_date_column(search_keys)
 
-        # Get minimum date from main dataset X
-        main_min_date = X[date_column].dropna().min()
+        x_date = X[date_column].dropna()
+        if not is_numeric_dtype(x_date):
+            x_date = pd.to_datetime(x_date).dt.floor("D").astype(np.int64) / 10**6
+        main_min_date = x_date.min()
+
+        for eval_x, _ in eval_set:
+            eval_x_date = eval_x[date_column].dropna()
+            if not is_numeric_dtype(eval_x_date):
+                eval_x[date_column] = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
 
         # Find minimum date for each eval_set and compare with main dataset
         eval_dates = []
@@ -1433,8 +1440,11 @@ class FeaturesEnricher(TransformerMixin):
                 if len(eval_x) < 1000:
                     self.logger.warning(f"Eval_set {i} has less than 1000 rows. It will be ignored for stability check")
                     continue
-                eval_min_date = eval_x[date_column].dropna().min()
-                eval_max_date = eval_x[date_column].dropna().max()
+                eval_x_date = eval_x[date_column].dropna()
+                if not is_numeric_dtype(eval_x_date):
+                    eval_x_date = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
+                eval_min_date = eval_x_date.min()
+                eval_max_date = eval_x_date.max()
                 eval_dates.append((i, eval_min_date, eval_max_date))
 
         if not eval_dates:
@@ -1460,6 +1470,10 @@ class FeaturesEnricher(TransformerMixin):
         checking_eval_set_df = checking_eval_set_df.copy()
 
         checking_eval_set_df[date_column] = eval_set_dates[selected_eval_set_idx]
+        if not is_numeric_dtype(checking_eval_set_df[date_column]):
+            checking_eval_set_df[date_column] = (
+                pd.to_datetime(checking_eval_set_df[date_column]).dt.floor("D").astype(np.int64) / 10**6
+            )
 
         psi_values_sparse = calculate_sparsity_psi(
             checking_eval_set_df, cat_features, date_column, self.logger, model_task_type
@@ -3708,6 +3722,25 @@ if response.status_code == 200:
             else:
                 raise ValidationError(self.bundle.get("eval_x_and_x_diff_shape"))
 
+        if any(validated_eval_X.dtypes != X.dtypes):
+            x_types = X.dtypes
+            eval_types = validated_eval_X.dtypes
+            # Find columns with different types
+            diff_cols = [
+                (col, x_types[col], eval_types[col])
+                for col in x_types.index
+                if x_types[col] != eval_types[col]
+            ]
+            diff_col_names = [col for col, _, _ in diff_cols]
+            # print columns with different types
+            print("Columns with different types:")
+            for col, x_type, eval_type in diff_cols:
+                print("-" * 50)
+                print(f"Column: {col}")
+                print(f"X type:        {x_type}")
+                print(f"Eval_set type: {eval_type}")
+            raise ValidationError(self.bundle.get("eval_x_and_x_diff_dtypes").format(diff_col_names))
+
         if _num_samples(validated_eval_X) != _num_samples(eval_y):
             raise ValidationError(
                 self.bundle.get("x_and_y_diff_size_eval_set").format(
@@ -4420,7 +4453,8 @@ if response.status_code == 200:
 
         if len(features_info) > 0:
             self.features_info = pd.DataFrame(features_info)
-            if self.features_info[self.bundle.get("features_info_psi")].isna().all():
+            # If all psi values are 0 or null, drop psi column
+            if self.features_info[self.bundle.get("features_info_psi")].fillna(0.0).eq(0.0).all():
                 self.features_info.drop(columns=[self.bundle.get("features_info_psi")], inplace=True)
             self._features_info_without_links = pd.DataFrame(features_info_without_links)
             self._internal_features_info = pd.DataFrame(internal_features_info)

{upgini-1.2.117a1 → upgini-1.2.118}/src/upgini/metrics.py

@@ -847,7 +847,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
             feature_importance = {}
             for i, col in enumerate(x.columns):
-                feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
+                feature_importance[col] = float(np.mean(np.abs(shap_values[:, i])))
 
             return feature_importance
 
@@ -922,6 +922,7 @@ class LightGBMWrapper(EstimatorWrapper):
                     encoded = cat_encoder.transform(x_copy[self.cat_features]).astype(int)
                 else:
                     encoded = cat_encoder.transform(x_copy[self.cat_features]).astype("category")
+                x_copy = x_copy.drop(columns=self.cat_features, errors="ignore")
                 x_copy[self.cat_features] = encoded
 
             shap_matrix = estimator.predict(
@@ -943,7 +944,7 @@ class LightGBMWrapper(EstimatorWrapper):
 
             feature_importance = {}
             for i, col in enumerate(x.columns):
-                feature_importance[col] = np.mean(np.abs(shap_matrix[:, i]))
+                feature_importance[col] = float(np.mean(np.abs(shap_matrix[:, i])))
 
             return feature_importance
 

{upgini-1.2.117a1 → upgini-1.2.118}/src/upgini/resource_bundle/strings.properties

@@ -123,6 +123,7 @@ unsupported_type_eval_set=Unsupported type of eval_set: {}. It should be list of
 eval_set_invalid_tuple_size=eval_set contains a tuple of size {}. It should contain only pairs of X and y or X only
 unsupported_x_type_eval_set=Unsupported type of X in eval_set: {}. Use pandas.DataFrame, pandas.Series or numpy.ndarray or list.
 eval_x_and_x_diff_shape=The column set in eval_set are differ from the column set in X
+eval_x_and_x_diff_dtypes=The column types in eval_set are different from the column types in X: {}
 unsupported_y_type_eval_set=Unsupported type of y in eval_set: {}. Use pandas.Series, numpy.ndarray or list
 y_is_constant_eval_set=y in eval_set is a constant. Relevant feature search requires a non-constant y
 x_and_y_diff_size_eval_set=X and y in eval_set contain different number of rows: {}, {}

{upgini-1.2.117a1 → upgini-1.2.118}/src/upgini/utils/psi.py

@@ -82,9 +82,6 @@ def calculate_features_psi(
 ) -> dict[str, float]:
     empty_res = {col: 0.0 for col in df.columns if col not in [TARGET, date_column]}
 
-    if not is_numeric_dtype(df[date_column]):
-        df[date_column] = pd.to_datetime(df[date_column]).dt.floor("D").astype(np.int64) / 10**6
-
     # Filter out rows with missing dates
     df = df[df[date_column].notna()].copy()
 

upgini-1.2.117a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.117a1"