upgini 1.2.118__tar.gz → 1.2.120__tar.gz

{upgini-1.2.118 → upgini-1.2.120}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.118
+Version: 1.2.120
 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-1.2.120/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.120"

{upgini-1.2.118 → upgini-1.2.120}/src/upgini/features_enricher.py

@@ -854,7 +854,7 @@ class FeaturesEnricher(TransformerMixin):
                     raise e
             finally:
                 self.logger.info(f"Transform elapsed time: {time.time() - start_time}")
-            
+
             return result
 
     def calculate_metrics(
@@ -1028,13 +1028,7 @@ class FeaturesEnricher(TransformerMixin):
                     columns_renaming,
                     _,
                 ) = prepared_data
-
-                # rename baseline_score_column
-                reversed_renaming = {v: k for k, v in columns_renaming.items()}
-                baseline_score_column = self.baseline_score_column
-                if baseline_score_column is not None:
-                    baseline_score_column = reversed_renaming[baseline_score_column]
-
+                
                 gc.collect()
 
                 if fitting_X.shape[1] == 0 and fitting_enriched_X.shape[1] == 0:
@@ -1089,7 +1083,7 @@ class FeaturesEnricher(TransformerMixin):
                             has_time=has_time,
                         )
                         baseline_cv_result = baseline_estimator.cross_val_predict(
-                            fitting_X, y_sorted, baseline_score_column
+                            fitting_X, y_sorted, self.baseline_score_column
                         )
                         baseline_metric = baseline_cv_result.get_display_metric()
                         if baseline_metric is None:
@@ -1192,7 +1186,7 @@ class FeaturesEnricher(TransformerMixin):
                                     f"on client features: {eval_X_sorted.columns.to_list()}"
                                 )
                                 etalon_eval_results = baseline_estimator.calculate_metric(
-                                    eval_X_sorted, eval_y_sorted, baseline_score_column
+                                    eval_X_sorted, eval_y_sorted, self.baseline_score_column
                                 )
                                 etalon_eval_metric = etalon_eval_results.get_display_metric()
                                 self.logger.info(
@@ -1741,7 +1735,8 @@ class FeaturesEnricher(TransformerMixin):
             c
             for c in (validated_X.columns.to_list() + generated_features)
             if (not self.fit_select_features or c in set(self.feature_names_).union(self.id_columns or []))
-            and c not in (
+            and c
+            not in (
                 excluding_search_keys
                 + list(self.fit_dropped_features)
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
@@ -2215,7 +2210,8 @@ class FeaturesEnricher(TransformerMixin):
             progress_callback=progress_callback,
             add_fit_system_record_id=True,
         )
-        if enriched_df is None:
+        if enriched_df is None or len(enriched_df) == 0 or len(enriched_df.columns) == 0:
+            self.logger.warning(f"Empty enriched dataframe returned: {enriched_df}, returning None")
             return None
 
         x_columns = [
@@ -2500,6 +2496,9 @@ if response.status_code == 200:
     ) -> tuple[pd.DataFrame, dict[str, str], list[str], dict[str, SearchKey]]:
         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 NotFittedError(self.bundle.get("transform_unfitted_enricher"))
 
         start_time = time.time()
         search_id = self.search_id or (self._search_task.search_task_id if self._search_task is not None else None)
@@ -2519,7 +2518,7 @@ if response.status_code == 200:
             if len(self.feature_names_) == 0:
                 msg = self.bundle.get("no_important_features_for_transform")
                 self.__log_warning(msg, show_support_link=True)
-                return X, {c: c for c in X.columns}, [], dict()
+                return None, {}, [], self.search_keys
 
             self.__validate_search_keys(self.search_keys, self.search_id)
 
@@ -2527,9 +2526,8 @@ if response.status_code == 200:
                 msg = self.bundle.get("transform_with_paid_features")
                 self.logger.warning(msg)
                 self.__display_support_link(msg)
-                return None, {c: c for c in X.columns}, [], {}
+                return None, {}, [], self.search_keys
 
-            features_meta = self._search_task.get_all_features_metadata_v2()
             online_api_features = [fm.name for fm in features_meta if fm.from_online_api and fm.shap_value > 0]
             if len(online_api_features) > 0:
                 self.logger.warning(
@@ -2550,7 +2548,7 @@ if response.status_code == 200:
                         self.logger.warning(msg)
                         print(msg)
                         show_request_quote_button()
-                        return None, {c: c for c in X.columns}, [], {}
+                        return None, {}, [], {}
                     else:
                         msg = self.bundle.get("transform_usage_info").format(
                             transform_usage.limit, transform_usage.transformed_rows
@@ -2620,14 +2618,33 @@ if response.status_code == 200:
 
             # If there are no external features, we don't call backend on transform
             external_features = [fm for fm in features_meta if fm.shap_value > 0 and fm.source != "etalon"]
-            if not external_features:
+            if len(external_features) == 0:
                 self.logger.warning(
                     "No external features found, returning original dataframe"
                     f" with generated important features: {self.feature_names_}"
                 )
-                filtered_columns = [c for c in self.feature_names_ if c in df.columns]
-                self.logger.warning(f"Filtered columns by existance in dataframe: {filtered_columns}")
-                return df[filtered_columns], columns_renaming, generated_features, search_keys
+                df = df.rename(columns=columns_renaming)
+                generated_features = [columns_renaming.get(c, c) for c in generated_features]
+                search_keys = {columns_renaming.get(c, c): t for c, t in search_keys.items()}
+                selecting_columns = self._selecting_input_and_generated_columns(
+                    validated_Xy, generated_features, keep_input, trace_id
+                )
+                self.logger.warning(f"Filtered columns by existance in dataframe: {selecting_columns}")
+                if add_fit_system_record_id:
+                    df = self._add_fit_system_record_id(
+                        df,
+                        search_keys,
+                        SYSTEM_RECORD_ID,
+                        TARGET,
+                        columns_renaming,
+                        self.id_columns,
+                        self.cv,
+                        self.model_task_type,
+                        self.logger,
+                        self.bundle,
+                    )
+                    selecting_columns.append(SYSTEM_RECORD_ID)
+                return df[selecting_columns], columns_renaming, generated_features, search_keys
 
             # Don't pass all features in backend on transform
             runtime_parameters = self._get_copy_of_runtime_parameters()
@@ -2845,29 +2862,12 @@ if response.status_code == 200:
                 how="left",
             )
 
-            fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
-            new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
-
-            selected_generated_features = [
-                c for c in generated_features if not self.fit_select_features or c in self.feature_names_
-            ]
-            if keep_input is True:
-                selected_input_columns = [
-                    c
-                    for c in validated_Xy.columns
-                    if not self.fit_select_features
-                    or c in self.feature_names_
-                    or c in new_columns_on_transform
-                    or c in self.search_keys
-                    or c in (self.id_columns or [])
-                    or c in [EVAL_SET_INDEX, TARGET]  # transform for metrics calculation
-                ]
-            else:
-                selected_input_columns = []
-
-            selecting_columns = selected_input_columns + selected_generated_features
+            selecting_columns = self._selecting_input_and_generated_columns(
+                validated_Xy, generated_features, keep_input, trace_id
+            )
             selecting_columns.extend(
-                c for c in result.columns
+                c
+                for c in result.columns
                 if c in self.feature_names_ and c not in selecting_columns and c not in validated_Xy.columns
             )
             if add_fit_system_record_id:
@@ -2895,6 +2895,35 @@ if response.status_code == 200:
 
             return result, columns_renaming, generated_features, search_keys
 
+    def _selecting_input_and_generated_columns(
+        self,
+        validated_Xy: pd.DataFrame,
+        generated_features: list[str],
+        keep_input: bool,
+        trace_id: str,
+    ):
+        fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
+        new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
+
+        selected_generated_features = [
+            c for c in generated_features if not self.fit_select_features or c in self.feature_names_
+        ]
+        if keep_input is True:
+            selected_input_columns = [
+                c
+                for c in validated_Xy.columns
+                if not self.fit_select_features
+                or c in self.feature_names_
+                or c in new_columns_on_transform
+                or c in self.search_keys
+                or c in (self.id_columns or [])
+                or c in [EVAL_SET_INDEX, TARGET]  # transform for metrics calculation
+            ]
+        else:
+            selected_input_columns = []
+
+        return selected_input_columns + selected_generated_features
+
     def __validate_search_keys(self, search_keys: dict[str, SearchKey], search_id: str | None = None):
         if (search_keys is None or len(search_keys) == 0) and self.country_code is None:
             if search_id:
@@ -3349,6 +3378,7 @@ if response.status_code == 200:
             except KeyboardInterrupt as e:
                 print(self.bundle.get("search_stopping"))
                 self.rest_client.stop_search_task_v2(trace_id, self._search_task.search_task_id)
+                self._search_task = None
                 self.logger.warning(f"Search {self._search_task.search_task_id} stopped by user")
                 print(self.bundle.get("search_stopped"))
                 raise e
@@ -3727,9 +3757,7 @@ if response.status_code == 200:
             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]
+                (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
@@ -3815,9 +3843,7 @@ if response.status_code == 200:
         return Xy[X.columns].copy(), Xy[TARGET].copy()
 
     @staticmethod
-    def _sort_by_system_record_id(
-        X: pd.DataFrame, y: pd.Series, cv: CVType | None
-    ) -> tuple[pd.DataFrame, pd.Series]:
+    def _sort_by_system_record_id(X: pd.DataFrame, y: pd.Series, cv: CVType | None) -> tuple[pd.DataFrame, pd.Series]:
         if cv not in [CVType.time_series, CVType.blocked_time_series]:
             record_id_column = ENTITY_SYSTEM_RECORD_ID if ENTITY_SYSTEM_RECORD_ID in X else SYSTEM_RECORD_ID
             Xy = X.copy()

{upgini-1.2.118 → upgini-1.2.120}/src/upgini/utils/display_utils.py

@@ -269,19 +269,22 @@ def make_html_report(
                 if search_keys is not None
                 else ""
             }
-            {"<h3>All relevant features. Accuracy after enrichment</h3>" + make_table(metrics_df)
-             if metrics_df is not None
-             else ""
+            {
+                "<h3>All relevant features. Accuracy after enrichment</h3>" + make_table(metrics_df)
+                if metrics_df is not None
+                else ""
             }
-            {"<h3>Relevant data sources</h3>" + make_table(relevant_datasources_df)
-             if len(relevant_datasources_df) > 0
-             else ""
+            {
+                "<h3>Relevant data sources</h3>" + make_table(relevant_datasources_df)
+                if len(relevant_datasources_df) > 0
+                else ""
             }
             <h3>All relevant features. Listing ({len(relevant_features_df)} items)</h3>
             {make_table(relevant_features_df, wrap_long_string=25)}
-            {"<h3>Description of AutoFE feature names</h3>" + make_table(autofe_descriptions_df, wrap_long_string=25)
-             if autofe_descriptions_df is not None
-             else ""
+            {
+                "<h3>Description of AutoFE feature names</h3>" + make_table(autofe_descriptions_df, wrap_long_string=25)
+                if autofe_descriptions_df is not None and len(autofe_descriptions_df) > 0
+                else ""
             }
             <p>To buy found data sources, please contact: <a href='mailto:sales@upgini.com'>sales@upgini.com</a></p>
             <p>Best regards, </br><b>Upgini Team</b></p>

{upgini-1.2.118 → upgini-1.2.120}/src/upgini/utils/sklearn_ext.py

@@ -1301,6 +1301,7 @@ def _encode_cat_features(X_train, y_train, X_test, y_test, cat_features, estimat
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
             encoder.fit(X_train[cat_features], y_train)
 
+            # OrdinalEncoder doesn't support progressive encoding with target
             X_train[cat_features] = encoder.transform(X_train[cat_features]).astype(int)
             X_test[cat_features] = encoder.transform(X_test[cat_features]).astype(int)
 
@@ -1314,10 +1315,8 @@ def _encode_cat_features(X_train, y_train, X_test, y_test, cat_features, estimat
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
             encoder.fit(X_train[cat_features], y_train)
 
-            # Progressive encoding on train (using y)
-            X_train[cat_features] = encoder.transform(X_train[cat_features], y_train).astype(int)
-
-            # Static encoding on validation (no y)
+            # OrdinalEncoder doesn't support progressive encoding with target
+            X_train[cat_features] = encoder.transform(X_train[cat_features]).astype(int)
             X_test[cat_features] = encoder.transform(X_test[cat_features]).astype(int)
 
             return X_train, y_train, X_test, y_test, [], encoder

upgini-1.2.118/src/upgini/__about__.py

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