upgini 1.2.48__py3-none-any.whl → 1.2.50__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.48"
+__version__ = "1.2.50"

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/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/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/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.dist-info → upgini-1.2.50.dist-info}/METADATA

@@ -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-1.2.48.dist-info → upgini-1.2.50.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=Zm4hDkoG9GX2KfPn6Wt1kdPl888Wv-de5OuQhdWNP9E,23
+upgini/__about__.py,sha256=Mi5DzFmquYseHnFMuFvsBrEztpwNZnhZs1G4xpE08KQ,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/dataset.py,sha256=vT4JyHmafLNbj54SySXr93f5hNS6-t94aFslbBy-7No,33535
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=wQmmDAI2F7E2805iX-Cpc5v44QRVrCJV8x8j_Ujh38w,200242
+upgini/features_enricher.py,sha256=O-0ZLFp1SPDNf5Yq-dysH8Jm-1c_LpNv2cIdXZ15nK8,200592
 upgini/http.py,sha256=danPeX7nTMa_70S-pk-4UUm5yOvXYlR84jgyjoHYBkU,43367
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=-ibqiNjD7dTagqg53FoEJNEqvAYbwgfyn9PGTRQ_YKU,12054
@@ -30,7 +30,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 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=0jZC0HjyQHeqFCHt6nn1kz7vV0oq92AYQJvy-soAwe4,27304
+upgini/resource_bundle/strings.properties,sha256=0_KAExIi1u48N1CQ13LKJS3bgDlRs-MPOyU3VxcE-qY,27350
 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
@@ -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-1.2.48.dist-info/METADATA,sha256=kGKDKYGXPVY0vOhgpsz1bq3UiMJEy8szoDRToAvVMuA,49055
-upgini-1.2.48.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.48.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.48.dist-info/RECORD,,
+upgini-1.2.50.dist-info/METADATA,sha256=PH8ms19Lbu3cuZxySGo9kcBeMkErCLGL8j8X3t2gxbw,49055
+upgini-1.2.50.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.50.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.50.dist-info/RECORD,,

{upgini-1.2.48.dist-info → upgini-1.2.50.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