upgini 1.2.27__py3-none-any.whl → 1.2.28__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.27"
+__version__ = "1.2.28"

upgini/features_enricher.py

@@ -2026,7 +2026,10 @@ class FeaturesEnricher(TransformerMixin):
         start_time = time.time()
         with MDC(trace_id=trace_id):
             self.logger.info("Start transform")
-            self.__log_debug_information(X, exclude_features_sources=exclude_features_sources)
+
+            validated_X = self._validate_X(X, is_transform=True)
+
+            self.__log_debug_information(validated_X, exclude_features_sources=exclude_features_sources)
 
             self.__validate_search_keys(self.search_keys, self.search_id)
 
@@ -2058,8 +2061,6 @@ class FeaturesEnricher(TransformerMixin):
                         self.logger.info(msg)
                         print(msg)
 
-            validated_X = self._validate_X(X, is_transform=True)
-
             is_demo_dataset = hash_input(validated_X) in DEMO_DATASET_HASHES
 
             columns_to_drop = [c for c in validated_X.columns if c in self.feature_names_]
@@ -2476,9 +2477,9 @@ class FeaturesEnricher(TransformerMixin):
         validate_scoring_argument(scoring)
 
         self.__log_debug_information(
-            X,
-            y,
-            eval_set,
+            validated_X,
+            validated_y,
+            validated_eval_set,
             exclude_features_sources=exclude_features_sources,
             calculate_metrics=calculate_metrics,
             scoring=scoring,
@@ -3762,11 +3763,17 @@ class FeaturesEnricher(TransformerMixin):
         if len(passed_unsupported_search_keys) > 0:
             raise ValidationError(self.bundle.get("unsupported_search_key").format(passed_unsupported_search_keys))
 
+        x_columns = [
+            c
+            for c in x.columns
+            if c not in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
+        ]
+
         for column_id, meaning_type in search_keys.items():
             column_name = None
             if isinstance(column_id, str):
                 if column_id not in x.columns:
-                    raise ValidationError(self.bundle.get("search_key_not_found").format(column_id, list(x.columns)))
+                    raise ValidationError(self.bundle.get("search_key_not_found").format(column_id, x_columns))
                 column_name = column_id
                 valid_search_keys[column_name] = meaning_type
             elif isinstance(column_id, int):

upgini/resource_bundle/strings.properties

@@ -201,7 +201,7 @@ email_detected=Emails detected in column `{}`. It will be used as a search key\n
 email_detected_not_registered=Emails detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
 phone_detected=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
 phone_detected_not_registered=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-target_type_detected=Detected task type: {}. Reason: {}\nYou can set task type manually with argument `model_task_type` of FeaturesEnricher constructor if task type detected incorrectly\n
+target_type_detected=\nDetected task type: {}. Reason: {}\nYou can set task type manually with argument `model_task_type` of FeaturesEnricher constructor if task type detected incorrectly\n
 binary_target_reason=only two unique label-values observed
 non_numeric_multiclass_reason=non-numeric label values observed
 few_unique_label_multiclass_reason=few unique label-values observed and can be considered as categorical
@@ -212,7 +212,7 @@ limited_int_multiclass_reason=integer-like values with limited unique values obs
 all_ok_community_invite=❓ Support request 
 too_small_for_metrics=Your train dataset or one of eval datasets contains less than 500 rows. For such dataset Upgini will not calculate accuracy metrics. Please increase the number of rows in the training dataset to calculate accuracy metrics
 imbalance_multiclass=Class {0} is on 25% quantile of classes distribution ({1} records in train dataset). \nDownsample classes with records more than {1}.
-imbalanced_target=Target is imbalanced and will be undersampled. Frequency of the rarest class `{}` is {}
+imbalanced_target=\nTarget is imbalanced and will be undersampled. Frequency of the rarest class `{}` is {}
 loss_selection_info=Using loss `{}` for feature selection
 loss_calc_metrics_info=Using loss `{}` for metrics calculation with default estimator
 

{upgini-1.2.27.dist-info → upgini-1.2.28.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.27
+Version: 1.2.28
 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-1.2.27.dist-info → upgini-1.2.28.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=JKArgvnX6ljUI_WxYnXTejXGdjsA4KJ3Cy2xBcK4vh4,23
+upgini/__about__.py,sha256=sZoYrdh97RjbwC1rg-3mt6kqvjxTxWL7ejhDDrG6mVM,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 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=7xYxcLvxQgDX7vE2gWEbBPceAVeEgBVpu9xtBJvXpoQ,194078
+upgini/features_enricher.py,sha256=YYboYw--vCH9VerkTnCF3njztU3fVLrhlhU3NfBVJYQ,194302
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
@@ -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=l3yg9H17NwCwvfZQyOYTvXbPP6mwdXH_CGlqyxOQVFY,26669
+upgini/resource_bundle/strings.properties,sha256=wn98wl2DNFPaGTMSdZAVr43P6t97i74PCqqwa762-V0,26673
 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
@@ -58,7 +58,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=PU77nIhTz7IHbC4rpTpxrVxib6cdpRL9F1dhkjIffLY,10225
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.27.dist-info/METADATA,sha256=iSB1iB7EwBugIUf8DYOz9mEFqGewDAS49-hgYuhtrtU,48578
-upgini-1.2.27.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.27.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.27.dist-info/RECORD,,
+upgini-1.2.28.dist-info/METADATA,sha256=qGINKPrh43Q1LFXWRlS1v6CSpME6rOmScAy0ShKxL_0,48578
+upgini-1.2.28.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.28.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.28.dist-info/RECORD,,