upgini 1.2.47__py3-none-any.whl → 1.2.49__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.47"
+__version__ = "1.2.49"

upgini/features_enricher.py

@@ -400,7 +400,7 @@ class FeaturesEnricher(TransformerMixin):
         remove_outliers_calc_metrics: Optional[bool] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
         search_id_callback: Optional[Callable[[str], Any]] = None,
-        select_features: bool = False,
+        select_features: bool = True,
         **kwargs,
     ):
         """Fit to data.
@@ -543,7 +543,7 @@ class FeaturesEnricher(TransformerMixin):
         estimator: Optional[Any] = None,
         remove_outliers_calc_metrics: Optional[bool] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
-        select_features: bool = False,
+        select_features: bool = True,
         **kwargs,
     ) -> pd.DataFrame:
         """Fit to data, then transform it.
@@ -1486,8 +1486,8 @@ class FeaturesEnricher(TransformerMixin):
             for c in X_sampled.columns.to_list()
             if (
                 not self.fit_select_features
-                or c in self.feature_names_
-                or (self.fit_columns_renaming is not None and self.fit_columns_renaming.get(c) in self.feature_names_)
+                or c in set(self.feature_names_).union(self.id_columns or [])
+                or (self.fit_columns_renaming or {}).get(c, c) in set(self.feature_names_).union(self.id_columns or [])
             )
             and c
             not in (
@@ -2191,7 +2191,9 @@ if response.status_code == 200:
 
             search_keys = self.search_keys.copy()
             if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
-                self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in self.id_columns})
+                self.search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in self.id_columns if col not in self.search_keys}
+                )
 
             search_keys = self.__prepare_search_keys(
                 validated_X, search_keys, is_demo_dataset, is_transform=True, silent_mode=silent_mode
@@ -2716,8 +2718,12 @@ if response.status_code == 200:
         if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
             id_columns = self.__get_renamed_id_columns()
             if id_columns:
-                self.fit_search_keys.update({col: SearchKey.CUSTOM_KEY for col in id_columns})
-                self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in self.id_columns})
+                self.fit_search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in id_columns if col not in self.fit_search_keys}
+                )
+                self.search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in self.id_columns if col not in self.search_keys}
+                )
                 self.runtime_parameters.properties["id_columns"] = ",".join(id_columns)
 
         df, fintech_warnings = remove_fintech_duplicates(
@@ -3736,7 +3742,8 @@ if response.status_code == 200:
             self.feature_names_.append(feature_meta.name)
             self.feature_importances_.append(_round_shap_value(feature_meta.shap_value))
 
-            feature_info = FeatureInfo.from_metadata(feature_meta, features_df, is_client_feature)
+            df_for_sample = features_df if feature_meta.name in features_df.columns else self.X
+            feature_info = FeatureInfo.from_metadata(feature_meta, df_for_sample, is_client_feature)
             features_info.append(feature_info.to_row(self.bundle))
             features_info_without_links.append(feature_info.to_row_without_links(self.bundle))
             internal_features_info.append(feature_info.to_internal_row(self.bundle))

upgini/utils/feature_info.py

@@ -1,6 +1,6 @@
-from dataclasses import dataclass
 import itertools
-from typing import Dict, List
+from dataclasses import dataclass
+from typing import Dict, List, Optional
 
 import numpy as np
 import pandas as pd
@@ -8,7 +8,6 @@ import pandas as pd
 from upgini.metadata import FeaturesMetadataV2
 from upgini.resource_bundle import ResourceBundle
 
-
 LLM_SOURCE = "LLM with external data augmentation"
 
 
@@ -30,7 +29,9 @@ class FeatureInfo:
     data_source_link: str
 
     @staticmethod
-    def from_metadata(feature_meta: FeaturesMetadataV2, data: pd.DataFrame, is_client_feature: bool) -> "FeatureInfo":
+    def from_metadata(
+        feature_meta: FeaturesMetadataV2, data: Optional[pd.DataFrame], is_client_feature: bool
+    ) -> "FeatureInfo":
         return FeatureInfo(
             name=_get_name(feature_meta),
             internal_name=_get_internal_name(feature_meta),
@@ -86,8 +87,8 @@ class FeatureInfo:
         }
 
 
-def _get_feature_sample(feature_meta: FeaturesMetadataV2, data: pd.DataFrame) -> str:
-    if feature_meta.name in data.columns:
+def _get_feature_sample(feature_meta: FeaturesMetadataV2, data: Optional[pd.DataFrame]) -> str:
+    if data is not None and feature_meta.name in data.columns:
         feature_sample = np.random.choice(data[feature_meta.name].dropna().unique(), 3).tolist()
         if len(feature_sample) > 0 and isinstance(feature_sample[0], float):
             feature_sample = [round(f, 4) for f in feature_sample]

{upgini-1.2.47.dist-info → upgini-1.2.49.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.47
+Version: 1.2.49
 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-1.2.47.dist-info → upgini-1.2.49.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=o2NRe9gScRz1I1oB_R5MjkQ4w7BrDovQP2Z_Mq2c6bo,23
+upgini/__about__.py,sha256=qkDVgmmc_W7WSA8UFQzKzULlTX27bnHrBTAlSeTYqYs,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=QC3jncWS3wHe4CY7pWWDMO_3HKxGbi0EyPHXMdBtoQM,33456
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=NWYNZtSgAR05zOZp_Wq1ltVGThCttTbVN_TP2RaWFSI,200008
+upgini/features_enricher.py,sha256=8bhABqZ3aXIc_5WBVNqFnRNT_0fCNbLyPwXv7VXdygs,200350
 upgini/http.py,sha256=danPeX7nTMa_70S-pk-4UUm5yOvXYlR84jgyjoHYBkU,43367
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=-ibqiNjD7dTagqg53FoEJNEqvAYbwgfyn9PGTRQ_YKU,12054
@@ -48,7 +48,7 @@ upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuM
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=GbnhHJn1nhUBytmK6PophYqaoq4t7Lp6i0-O0Gd3RV8,5265
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
-upgini/utils/feature_info.py,sha256=Tp_2g5-rCjY4NpzKhzxwNxuqH5FFL8vG94OU5kH6wzk,6702
+upgini/utils/feature_info.py,sha256=0rOXSyCj-sw-8migWP0ge8qrOzGU50dQvH0JUJUrDfQ,6766
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=VORRmtKlItcbBVVK5SiwXD7J-6Y5rn7UQ5m6WcBXt7E,5698
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.47.dist-info/METADATA,sha256=4pKaboM3TxupdS6iw1Uh_IW9Dw0X88LnDh1pGjsc3fs,49055
-upgini-1.2.47.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.47.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.47.dist-info/RECORD,,
+upgini-1.2.49.dist-info/METADATA,sha256=XZ11OqCR6UqQrqo2RsKAIZYdPIVmIcn61GxRJn6f9Ys,49055
+upgini-1.2.49.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.49.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.49.dist-info/RECORD,,