upgini 1.2.16a3654.dev3__py3-none-any.whl → 1.2.17__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.16a3654.dev3"
+__version__ = "1.2.17"

upgini/features_enricher.py

@@ -165,7 +165,6 @@ class FeaturesEnricher(TransformerMixin):
     RANDOM_STATE = 42
     CALCULATE_METRICS_THRESHOLD = 50_000_000
     CALCULATE_METRICS_MIN_THRESHOLD = 500
-    TEXT_FEATURES_THRESHOLD = 5_000
     GENERATE_FEATURES_LIMIT = 10
     EMPTY_FEATURES_INFO = pd.DataFrame(
         columns=[
@@ -337,6 +336,9 @@ class FeaturesEnricher(TransformerMixin):
         self.exclude_columns = exclude_columns
         self.baseline_score_column = baseline_score_column
         self.add_date_if_missing = add_date_if_missing
+        self.features_info_display_handle = None
+        self.data_sources_display_handle = None
+        self.report_button_handle = None
 
     def _get_api_key(self):
         return self._api_key
@@ -872,6 +874,13 @@ class FeaturesEnricher(TransformerMixin):
                 else None
             )
 
+            if self.X is None:
+                self.X = X
+            if self.y is None:
+                self.y = y
+            if self.eval_set is None:
+                self.eval_set = effective_eval_set
+
             try:
                 self.__log_debug_information(
                     validated_X,
@@ -939,16 +948,14 @@ class FeaturesEnricher(TransformerMixin):
 
                 gc.collect()
 
-                text_features = self.generate_features if fitting_X.shape[0] >= self.TEXT_FEATURES_THRESHOLD else []
+                if fitting_X.shape[1] == 0 and fitting_enriched_X.shape[1] == 0:
+                    print(self.bundle.get("metrics_no_important_free_features"))
+                    self.logger.warning("No client or free relevant ADS features found to calculate metrics")
+                    self.warning_counter.increment()
+                    return None
 
                 print(self.bundle.get("metrics_start"))
                 with Spinner():
-                    if fitting_X.shape[1] == 0 and fitting_enriched_X.shape[1] == 0:
-                        print(self.bundle.get("metrics_no_important_free_features"))
-                        self.logger.warning("No client or free relevant ADS features found to calculate metrics")
-                        self.warning_counter.increment()
-                        return None
-
                     self._check_train_and_eval_target_distribution(y_sorted, fitting_eval_set_dict)
 
                     has_date = SearchKey.find_key(search_keys, [SearchKey.DATE, SearchKey.DATETIME]) is not None
@@ -962,7 +969,7 @@ class FeaturesEnricher(TransformerMixin):
                         fitting_enriched_X,
                         scoring,
                         groups=groups,
-                        text_features=text_features,
+                        text_features=self.generate_features,
                         has_date=has_date,
                     )
                     metric = wrapper.metric_name
@@ -989,10 +996,10 @@ class FeaturesEnricher(TransformerMixin):
                             cat_features,
                             add_params=custom_loss_add_params,
                             groups=groups,
-                            text_features=text_features,
+                            text_features=self.generate_features,
                             has_date=has_date,
                         )
-                        etalon_metric = baseline_estimator.cross_val_predict(
+                        etalon_metric, _ = baseline_estimator.cross_val_predict(
                             fitting_X, y_sorted, self.baseline_score_column
                         )
                         if etalon_metric is None:
@@ -1023,10 +1030,16 @@ class FeaturesEnricher(TransformerMixin):
                             cat_features,
                             add_params=custom_loss_add_params,
                             groups=groups,
-                            text_features=text_features,
+                            text_features=self.generate_features,
                             has_date=has_date,
                         )
-                        enriched_metric = enriched_estimator.cross_val_predict(fitting_enriched_X, enriched_y_sorted)
+                        enriched_metric, enriched_shaps = enriched_estimator.cross_val_predict(
+                            fitting_enriched_X, enriched_y_sorted
+                        )
+
+                        if enriched_shaps is not None:
+                            self._update_shap_values(enriched_shaps)
+
                         if enriched_metric is None:
                             self.logger.warning(
                                 f"Enriched {metric} on train combined features is None (maybe all features was removed)"
@@ -1159,13 +1172,6 @@ class FeaturesEnricher(TransformerMixin):
                     elif uplift_col in metrics_df.columns and (metrics_df[uplift_col] < 0).any():
                         self.logger.warning("Uplift is negative")
 
-                    if self.X is None:
-                        self.X = X
-                    if self.y is None:
-                        self.y = y
-                    if self.eval_set is None:
-                        self.eval_set = effective_eval_set
-
                     return metrics_df
             except Exception as e:
                 error_message = "Failed to calculate metrics" + (
@@ -1190,6 +1196,72 @@ class FeaturesEnricher(TransformerMixin):
             finally:
                 self.logger.info(f"Calculating metrics elapsed time: {time.time() - start_time}")
 
+    def _update_shap_values(self, new_shaps: Dict[str, float]):
+        new_shaps = {
+            feature: self._round_shap_value(shap)
+            for feature, shap in new_shaps.items()
+            if feature in self.feature_names_
+        }
+        features_importances = list(new_shaps.items())
+        features_importances.sort(key=lambda m: (-m[1], m[0]))
+        self.feature_names_, self.feature_importances_ = zip(*features_importances)
+        self.feature_names_ = list(self.feature_names_)
+        self.feature_importances_ = list(self.feature_importances_)
+
+        feature_name_header = self.bundle.get("features_info_name")
+        shap_value_header = self.bundle.get("features_info_shap")
+
+        def update_shap(row):
+            return new_shaps.get(row[feature_name_header], row[shap_value_header])
+
+        self.features_info[shap_value_header] = self.features_info.apply(update_shap, axis=1)
+        self._internal_features_info[shap_value_header] = self._internal_features_info.apply(update_shap, axis=1)
+        self._features_info_without_links[shap_value_header] = self._features_info_without_links.apply(
+            update_shap, axis=1
+        )
+        self.logger.info(f"Recalculated SHAP values:\n{self._features_info_without_links}")
+
+        self.features_info.sort_values(by=shap_value_header, ascending=False, inplace=True)
+        self._internal_features_info.sort_values(by=shap_value_header, ascending=False, inplace=True)
+        self._features_info_without_links.sort_values(by=shap_value_header, ascending=False, inplace=True)
+
+        self.relevant_data_sources = self._group_relevant_data_sources(self.features_info, self.bundle)
+        self._relevant_data_sources_wo_links = self._group_relevant_data_sources(
+            self._features_info_without_links, self.bundle
+        )
+
+        if self.features_info_display_handle is not None:
+            try:
+                _ = get_ipython()  # type: ignore
+
+                display_html_dataframe(
+                    self.features_info,
+                    self._features_info_without_links,
+                    self.bundle.get("relevant_features_header"),
+                    display_handle=self.features_info_display_handle,
+                )
+            except (ImportError, NameError):
+                print(self._internal_features_info)
+        if self.data_sources_display_handle is not None:
+            try:
+                _ = get_ipython()  # type: ignore
+
+                display_html_dataframe(
+                    self.relevant_data_sources,
+                    self._relevant_data_sources_wo_links,
+                    self.bundle.get("relevant_features_header"),
+                    display_handle=self.data_sources_display_handle,
+                )
+            except (ImportError, NameError):
+                print(self._relevant_data_sources_wo_links)
+        if self.report_button_handle is not None:
+            try:
+                _ = get_ipython()  # type: ignore
+
+                self.__show_report_button(display_handle=self.report_button_handle)
+            except (ImportError, NameError):
+                pass
+
     def _check_train_and_eval_target_distribution(self, y, eval_set_dict):
         uneven_distribution = False
         for eval_set in eval_set_dict.values():
@@ -1518,11 +1590,19 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.info("No external features selected. So use only input datasets for metrics calculation")
             return self.__sample_only_input(validated_X, validated_y, eval_set, is_demo_dataset)
         # TODO save and check if dataset was deduplicated - use imbalance branch for such case
-        elif not self.imbalanced and not exclude_features_sources and is_input_same_as_fit:
+        elif (
+            not self.imbalanced
+            and not exclude_features_sources
+            and is_input_same_as_fit
+            and self.df_with_original_index is not None
+        ):
             self.logger.info("Dataset is not imbalanced, so use enriched_X from fit")
             return self.__sample_balanced(eval_set, trace_id, remove_outliers_calc_metrics)
         else:
-            self.logger.info("Dataset is imbalanced or exclude_features_sources or X was passed. Run transform")
+            self.logger.info(
+                "Dataset is imbalanced or exclude_features_sources or X was passed or this is saved search."
+                " Run transform"
+            )
             print(self.bundle.get("prepare_data_for_metrics"))
             return self.__sample_imbalanced(
                 validated_X,
@@ -2028,6 +2108,13 @@ class FeaturesEnricher(TransformerMixin):
             runtime_parameters = self._get_copy_of_runtime_parameters()
             features_for_transform = self._search_task.get_features_for_transform() or []
             if len(features_for_transform) > 0:
+                missing_features_for_transform = [
+                    columns_renaming.get(f) for f in features_for_transform if f not in df.columns
+                ]
+                if len(missing_features_for_transform) > 0:
+                    raise ValidationError(
+                        self.bundle.get("missing_features_for_transform").format(missing_features_for_transform)
+                    )
                 runtime_parameters.properties["features_for_embeddings"] = ",".join(features_for_transform)
 
             columns_for_system_record_id = sorted(list(search_keys.keys()) + features_for_transform)
@@ -2702,10 +2789,10 @@ class FeaturesEnricher(TransformerMixin):
                         progress_callback,
                     )
                 except Exception:
-                    self.__show_report_button()
+                    self.report_button_handle = self.__show_report_button(display_id="report_button")
                     raise
 
-        self.__show_report_button()
+        self.report_button_handle = self.__show_report_button(display_id="report_button")
 
         if not self.warning_counter.has_warnings():
             self.__display_support_link(self.bundle.get("all_ok_community_invite"))
@@ -3377,6 +3464,13 @@ class FeaturesEnricher(TransformerMixin):
 
         return result_train, result_eval_sets
 
+    @staticmethod
+    def _round_shap_value(shap: float) -> float:
+        if shap > 0.0 and shap < 0.0001:
+            return 0.0001
+        else:
+            return round(shap, 4)
+
     def __prepare_feature_importances(self, trace_id: str, x_columns: List[str], silent=False):
         llm_source = "LLM with external data augmentation"
         if self._search_task is None:
@@ -3394,12 +3488,6 @@ class FeaturesEnricher(TransformerMixin):
         features_info_without_links = []
         internal_features_info = []
 
-        def round_shap_value(shap: float) -> float:
-            if shap > 0.0 and shap < 0.0001:
-                return 0.0001
-            else:
-                return round(shap, 4)
-
         def list_or_single(lst: List[str], single: str):
             return lst or ([single] if single else [])
 
@@ -3432,7 +3520,7 @@ class FeaturesEnricher(TransformerMixin):
 
             feature_sample = []
             self.feature_names_.append(feature_meta.name)
-            self.feature_importances_.append(round_shap_value(feature_meta.shap_value))
+            self.feature_importances_.append(self._round_shap_value(feature_meta.shap_value))
             if feature_meta.name in features_df.columns:
                 feature_sample = np.random.choice(features_df[feature_meta.name].dropna().unique(), 3).tolist()
                 if len(feature_sample) > 0 and isinstance(feature_sample[0], float):
@@ -3471,7 +3559,7 @@ class FeaturesEnricher(TransformerMixin):
             features_info.append(
                 {
                     self.bundle.get("features_info_name"): feature_name,
-                    self.bundle.get("features_info_shap"): round_shap_value(feature_meta.shap_value),
+                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
                     self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
                     self.bundle.get("features_info_value_preview"): feature_sample,
                     self.bundle.get("features_info_provider"): provider,
@@ -3482,7 +3570,7 @@ class FeaturesEnricher(TransformerMixin):
             features_info_without_links.append(
                 {
                     self.bundle.get("features_info_name"): internal_feature_name,
-                    self.bundle.get("features_info_shap"): round_shap_value(feature_meta.shap_value),
+                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
                     self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
                     self.bundle.get("features_info_value_preview"): feature_sample,
                     self.bundle.get("features_info_provider"): internal_provider,
@@ -3494,7 +3582,7 @@ class FeaturesEnricher(TransformerMixin):
                 {
                     self.bundle.get("features_info_name"): internal_feature_name,
                     "feature_link": feature_meta.doc_link,
-                    self.bundle.get("features_info_shap"): round_shap_value(feature_meta.shap_value),
+                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
                     self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
                     self.bundle.get("features_info_value_preview"): feature_sample,
                     self.bundle.get("features_info_provider"): internal_provider,
@@ -3774,14 +3862,18 @@ class FeaturesEnricher(TransformerMixin):
             print(Format.GREEN + Format.BOLD + msg + Format.END)
             self.logger.info(msg)
             if len(self.feature_names_) > 0:
-                display_html_dataframe(
-                    self.features_info, self._features_info_without_links, self.bundle.get("relevant_features_header")
+                self.features_info_display_handle = display_html_dataframe(
+                    self.features_info,
+                    self._features_info_without_links,
+                    self.bundle.get("relevant_features_header"),
+                    display_id="features_info",
                 )
 
-                display_html_dataframe(
+                self.data_sources_display_handle = display_html_dataframe(
                     self.relevant_data_sources,
                     self._relevant_data_sources_wo_links,
                     self.bundle.get("relevant_data_sources_header"),
+                    display_id="data_sources",
                 )
             else:
                 msg = self.bundle.get("features_info_zero_important_features")
@@ -3792,9 +3884,9 @@ class FeaturesEnricher(TransformerMixin):
             print(msg)
             print(self._internal_features_info)
 
-    def __show_report_button(self):
+    def __show_report_button(self, display_id: Optional[str] = None, display_handle=None):
         try:
-            prepare_and_show_report(
+            return prepare_and_show_report(
                 relevant_features_df=self._features_info_without_links,
                 relevant_datasources_df=self.relevant_data_sources,
                 metrics_df=self.metrics,
@@ -3802,6 +3894,8 @@ class FeaturesEnricher(TransformerMixin):
                 search_id=self._search_task.search_task_id,
                 email=self.rest_client.get_current_email(),
                 search_keys=[str(sk) for sk in self.search_keys.values()],
+                display_id=display_id,
+                display_handle=display_handle,
             )
         except Exception:
             pass

upgini/metrics.py

@@ -3,13 +3,14 @@ from __future__ import annotations
 import inspect
 import logging
 import re
+from collections import defaultdict
 from copy import deepcopy
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 import catboost
 import numpy as np
 import pandas as pd
-from catboost import CatBoostClassifier, CatBoostRegressor
+from catboost import CatBoost, CatBoostClassifier, CatBoostRegressor, Pool
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
@@ -63,7 +64,7 @@ CATBOOST_BINARY_PARAMS = {
     "verbose": False,
     "random_state": DEFAULT_RANDOM_STATE,
     "allow_writing_files": False,
-    # "auto_class_weights": "SqrtBalanced",
+    "auto_class_weights": "Balanced",
 }
 
 CATBOOST_MULTICLASS_PARAMS = {
@@ -81,7 +82,7 @@ CATBOOST_MULTICLASS_PARAMS = {
     "verbose": False,
     "random_state": DEFAULT_RANDOM_STATE,
     "allow_writing_files": False,
-    "auto_class_weights": "SqrtBalanced",
+    "auto_class_weights": "Balanced",
 }
 
 LIGHTGBM_PARAMS = {
@@ -288,9 +289,12 @@ class EstimatorWrapper:
         x, y, _ = self._prepare_data(x, y)
         return x, y, {}
 
+    def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator) -> Optional[Dict[str, float]]:
+        return None
+
     def cross_val_predict(
         self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
-    ) -> Optional[float]:
+    ) -> Tuple[Optional[float], Optional[Dict[str, float]]]:
         x, y, groups, fit_params = self._prepare_to_fit(x, y)
 
         if x.shape[1] == 0:
@@ -298,6 +302,7 @@ class EstimatorWrapper:
 
         scorer = check_scoring(self.estimator, scoring=self.scorer)
 
+        shap_values_all_folds = defaultdict(list)
         if baseline_score_column is not None and self.metric_name == "GINI":
             self.logger.info("Calculate baseline GINI on passed baseline_score_column and target")
             metric = roc_auc_score(y, x[baseline_score_column])
@@ -319,7 +324,29 @@ class EstimatorWrapper:
             self.check_fold_metrics(metrics_by_fold)
 
             metric = np.mean(metrics_by_fold) * self.multiplier
-        return self.post_process_metric(metric)
+
+            splits = self.cv.split(x, y, groups)
+
+            for estimator, split in zip(self.cv_estimators, splits):
+                _, validation_idx = split
+                cv_x = x.iloc[validation_idx]
+                cv_y = y[validation_idx]
+                shaps = self.calculate_shap(cv_x, cv_y, estimator)
+                if shaps is not None:
+                    for feature, shap_value in shaps.items():
+                        # shap_values_all_folds[feature] = shap_values_all_folds.get(feature, []) + shap_value.tolist()
+                        shap_values_all_folds[feature].extend(shap_value.tolist())
+
+        if shap_values_all_folds:
+            average_shap_values = {
+                feature: np.mean(np.array(shaps)) for feature, shaps in shap_values_all_folds.items() if len(shaps) > 0
+            }
+            if len(average_shap_values) == 0:
+                average_shap_values = None
+        else:
+            average_shap_values = None
+
+        return self.post_process_metric(metric), average_shap_values
 
     def check_fold_metrics(self, metrics_by_fold: List[float]):
         first_metric_sign = 1 if metrics_by_fold[0] >= 0 else -1
@@ -453,6 +480,7 @@ class CatBoostWrapper(EstimatorWrapper):
         )
         self.cat_features = None
         self.emb_features = None
+        self.grouped_embedding_features = None
         self.exclude_features = []
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray, dict]:
@@ -462,17 +490,16 @@ class CatBoostWrapper(EstimatorWrapper):
         if hasattr(CatBoostClassifier, "get_embedding_feature_indices"):
             emb_pattern = r"(.+)_emb\d+"
             self.emb_features = [c for c in x.columns if re.match(emb_pattern, c) and is_numeric_dtype(x[c])]
-            embedding_features = []
             if len(self.emb_features) > 3:  # There is no reason to reduce embeddings dimension with less than 4
                 self.logger.info(
                     "Embedding features count more than 3, so group them into one vector for CatBoost: "
                     f"{self.emb_features}"
                 )
-                x, embedding_features = self.group_embeddings(x)
-                params["embedding_features"] = embedding_features
+                x, self.grouped_embedding_features = self.group_embeddings(x)
+                params["embedding_features"] = self.grouped_embedding_features
             else:
                 self.logger.info(f"Embedding features count less than 3, so use them separately: {self.emb_features}")
-                self.emb_features = []
+                self.grouped_embedding_features = None
         else:
             self.logger.warning(f"Embedding features are not supported by Catboost version {catboost.__version__}")
 
@@ -488,7 +515,7 @@ class CatBoostWrapper(EstimatorWrapper):
             self.logger.warning(f"Text features are not supported by this Catboost version {catboost.__version__}")
 
         # Find rest categorical features
-        self.cat_features = _get_cat_features(x, self.text_features, embedding_features)
+        self.cat_features = _get_cat_features(x, self.text_features, self.grouped_embedding_features)
         # x = fill_na_cat_features(x, self.cat_features)
         unique_cat_features = []
         for name in self.cat_features:
@@ -548,7 +575,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
     def cross_val_predict(
         self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
-    ) -> Optional[float]:
+    ) -> Tuple[Optional[float], Optional[Dict[str, float]]]:
         try:
             return super().cross_val_predict(x, y, baseline_score_column)
         except Exception as e:
@@ -573,6 +600,36 @@ class CatBoostWrapper(EstimatorWrapper):
             else:
                 raise e
 
+    def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator: CatBoost) -> Optional[Dict[str, float]]:
+        try:
+            # Create Pool for fold data, if need (for example, when categorical features are present)
+            fold_pool = Pool(
+                x,
+                y,
+                cat_features=self.cat_features,
+                text_features=self.text_features,
+                embedding_features=self.grouped_embedding_features,
+            )
+
+            # Get SHAP values of current estimator
+            shap_values_fold = estimator.get_feature_importance(data=fold_pool, type="ShapValues")
+
+            # Remove last columns (base value) and flatten
+            if self.target_type == ModelTaskType.MULTICLASS:
+                all_shaps = shap_values_fold[:, :, :-1]
+                all_shaps = [all_shaps[:, :, k].flatten() for k in range(all_shaps.shape[2])]
+            else:
+                all_shaps = shap_values_fold[:, :-1]
+                all_shaps = [all_shaps[:, k].flatten() for k in range(all_shaps.shape[1])]
+
+            all_shaps = np.abs(all_shaps)
+
+            return dict(zip(estimator.feature_names_, all_shaps))
+
+        except Exception:
+            self.logger.exception("Failed to recalculate new SHAP values")
+            return None
+
 
 class LightGBMWrapper(EstimatorWrapper):
     def __init__(

upgini/resource_bundle/strings.properties

@@ -136,6 +136,7 @@ eval_y_is_empty=y in eval_set is empty.
 x_and_eval_x_diff_types=X and eval_set X has different types: {} and {}
 baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input dataframe
 baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
+missing_features_for_transform=Missing some features for transform that were presented on fit: {}
     # target validation
 empty_target=Target is empty in all rows
 # non_numeric_target=Binary target should be numerical type

upgini/utils/display_utils.py

@@ -9,6 +9,7 @@ from typing import Callable, List, Optional
 
 import pandas as pd
 from xhtml2pdf import pisa
+
 from upgini.__about__ import __version__
 
 
@@ -72,7 +73,9 @@ def make_table(df: pd.DataFrame, wrap_long_string=None) -> str:
     )
 
 
-def display_html_dataframe(df: pd.DataFrame, internal_df: pd.DataFrame, header: str):
+def display_html_dataframe(
+    df: pd.DataFrame, internal_df: pd.DataFrame, header: str, display_id: Optional[str] = None, display_handle=None
+):
     if not ipython_available():
         print(header)
         print(internal_df)
@@ -133,7 +136,10 @@ def display_html_dataframe(df: pd.DataFrame, internal_df: pd.DataFrame, header:
             {table_html}
         </div>
         """
-    display(HTML(result_html))
+    if display_handle:
+        return display_handle.update(HTML(result_html))
+    else:
+        return display(HTML(result_html), display_id=display_id)
 
 
 def make_html_report(
@@ -279,6 +285,8 @@ def prepare_and_show_report(
     search_id: str,
     email: Optional[str],
     search_keys: Optional[List[str]] = None,
+    display_id: Optional[str] = None,
+    display_handle=None,
 ):
     if not ipython_available():
         return
@@ -288,10 +296,12 @@ def prepare_and_show_report(
     )
 
     if len(relevant_features_df) > 0:
-        show_button_download_pdf(report)
+        return show_button_download_pdf(report, display_id=display_id, display_handle=display_handle)
 
 
-def show_button_download_pdf(source: str, title="\U0001F4CA Download PDF report"):
+def show_button_download_pdf(
+    source: str, title="\U0001F4CA Download PDF report", display_id: Optional[str] = None, display_handle=None
+):
     from IPython.display import HTML, display
 
     file_name = f"upgini-report-{uuid.uuid4()}.pdf"
@@ -303,7 +313,10 @@ def show_button_download_pdf(source: str, title="\U0001F4CA Download PDF report"
         payload = b64.decode()
         html = f"""<a download="{file_name}" href="data:application/pdf;base64,{payload}" target="_blank">
         <button>{title}</button></a>"""
-        display(HTML(html))
+        if display_handle is not None:
+            display_handle.update(HTML(html))
+        else:
+            return display(HTML(html), display_id=display_id)
 
 
 def show_request_quote_button():

{upgini-1.2.16a3654.dev3.dist-info → upgini-1.2.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.16a3654.dev3
+Version: 1.2.17
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -145,7 +145,7 @@ Description-Content-Type: text/markdown
 
 ## 💼 Tutorials
 
-###  [Search of relevant external features & Automated feature generation for Salary predicton task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
+###  [Search of relevant external features & Automated feature generation for Salary prediction task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
 
 * The goal is to predict salary for data science job postning based on information about employer and job description.
 * Following this guide, you'll learn how to **search & auto generate new relevant features with Upgini library**

{upgini-1.2.16a3654.dev3.dist-info → upgini-1.2.17.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=_Bu0M4jZFah8h2SMG8XdLYshfHKLNdK08pZuRYLA3_4,33
+upgini/__about__.py,sha256=LyCJKEtzC7sS6MlxViknrdz9t79ni5iIOEGUNPPAnwU,23
 upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=4lfofrRPndG_CFMownDHZuXTnfMgDF1a8hW-ShdU8ns,188446
+upgini/features_enricher.py,sha256=3Jx6eoGULag64lN8pnwloI-RKwyLlVONrCADxpehwNo,192789
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=CVE-hshFDrONIruPa-ZJV874ykpgs5oj8FtDduSWGm4,31264
+upgini/metrics.py,sha256=lhLqFv1tLWNzx3ULELo3MMSqI8eBoHL7P5jKpG8a6PE,33899
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1389
@@ -30,7 +30,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Lv75lq7M46z9cAIutwkdKZtPZkWblgoRzToAJ1BwY8A,7709
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=eqJP6bGu12zFuQJqMY03QbMhppcdwIfL2bsJWaqmuZ4,27221
+upgini/resource_bundle/strings.properties,sha256=bWWznzu43Lwfd-j4XDrpKJCpoxMMThd73awB7ge7wfo,27319
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -44,7 +44,7 @@ upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDc
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=4tsGeehU0KS6wqNsc9gEEWZ9s6T9E0UReUIO3rSuXNU,12174
 upgini/utils/deduplicate_utils.py,sha256=NpaPtBYXwUtfKTRHWrtz2uUq6tZN6C_Nd719ydPRF2Q,8484
-upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
+upgini/utils/display_utils.py,sha256=NGhki1aGMsS8OeI69eLXEpmS_s41k8ojKHQxacJaXiU,11493
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/features_validator.py,sha256=yiOdzVtpArELMufzAa9mtWq32lETB6sIF-w3Yvl3vV8,3614
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=qHzZRmICFbLNCrmVqGkaBcjm91L2ERRZMppci36acV4,10085
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.2.16a3654.dev3.dist-info/METADATA,sha256=TwuZaQV-HlLl1aijL54CogvxQjndKzdkNBaXbc0jaZA,48587
-upgini-1.2.16a3654.dev3.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.16a3654.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.16a3654.dev3.dist-info/RECORD,,
+upgini-1.2.17.dist-info/METADATA,sha256=g8R9yIZmDZNOFNFMVW-65PTooKnQx6tWMX4Z1Pky-yI,48578
+upgini-1.2.17.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.17.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.17.dist-info/RECORD,,

{upgini-1.2.16a3654.dev3.dist-info → upgini-1.2.17.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.24.2
+Generator: hatchling 1.25.0
 Root-Is-Purelib: true
 Tag: py3-none-any