upgini 1.2.48__tar.gz → 1.2.50__tar.gz

{upgini-1.2.48 → upgini-1.2.50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.48
+Version: 1.2.50
 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-1.2.50/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.50"

{upgini-1.2.48 → upgini-1.2.50}/src/upgini/dataset.py

@@ -37,12 +37,18 @@ from upgini.metadata import (
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
 from upgini.search_task import SearchTask
 from upgini.utils.email_utils import EmailSearchKeyConverter
-from upgini.utils.target_utils import balance_undersample, balance_undersample_forced, balance_undersample_time_series
+from upgini.utils.target_utils import (
+    balance_undersample,
+    balance_undersample_forced,
+    balance_undersample_time_series,
+)
 
 try:
     from upgini.utils.progress_bar import CustomProgressBar as ProgressBar
 except Exception:
-    from upgini.utils.fallback_progress_bar import CustomFallbackProgressBar as ProgressBar
+    from upgini.utils.fallback_progress_bar import (
+        CustomFallbackProgressBar as ProgressBar,
+    )
 
 
 class Dataset:  # (pd.DataFrame):
@@ -347,7 +353,8 @@ class Dataset:  # (pd.DataFrame):
             key
             for search_group in self.search_keys_checked
             for key in search_group
-            if not self.columns_renaming.get(key).endswith(EmailSearchKeyConverter.ONE_DOMAIN_SUFFIX)
+            if key in self.columns_renaming
+            and not self.columns_renaming.get(key).endswith(EmailSearchKeyConverter.ONE_DOMAIN_SUFFIX)
         }
         ipv4_column = self.etalon_def_checked.get(FileColumnMeaningType.IP_ADDRESS.value)
         if (

{upgini-1.2.48 → upgini-1.2.50}/src/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 set(self.feature_names_).union(self.id_columns)
-                or (self.fit_columns_renaming or {}).get(c, c) in set(self.feature_names_).union(self.id_columns)
+                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 (
@@ -2619,6 +2619,11 @@ if response.status_code == 200:
             self.generate_features = checked_generate_features
             self.runtime_parameters.properties["generate_features"] = ",".join(self.generate_features)
 
+        if self.id_columns is not None:
+            for id_column in self.id_columns:
+                if id_column not in validated_X.columns:
+                    raise ValidationError(self.bundle.get("missing_id_column").format(id_column))
+
         validate_scoring_argument(scoring)
 
         self.__log_debug_information(
@@ -3742,7 +3747,8 @@ 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-1.2.48 → upgini-1.2.50}/src/upgini/resource_bundle/strings.properties

@@ -134,6 +134,7 @@ 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: {}
+missing_id_column=Id column {} not found in X
     # target validation
 empty_target=Target is empty in all rows
 # non_numeric_target=Binary target should be numerical type

{upgini-1.2.48 → upgini-1.2.50}/src/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-1.2.48/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.48"