upgini 1.2.9a110__py3-none-any.whl → 1.2.11__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.9a110"
+__version__ = "1.2.11"

upgini/features_enricher.py

@@ -1577,7 +1577,7 @@ class FeaturesEnricher(TransformerMixin):
             df = generator.generate(df)
             generated_features.extend(generator.generated_features)
 
-        normalizer = Normalizer(self.search_keys, generated_features, self.bundle, self.logger, self.warning_counter)
+        normalizer = Normalizer(search_keys, generated_features, self.bundle, self.logger, self.warning_counter)
         df = normalizer.normalize(df)
         columns_renaming = normalizer.columns_renaming
 
@@ -1633,10 +1633,10 @@ class FeaturesEnricher(TransformerMixin):
 
         rows_to_drop = None
         has_date = SearchKey.find_key(search_keys, [SearchKey.DATE, SearchKey.DATETIME]) is not None
-        task_type = self.model_task_type or define_task(
+        self.model_task_type = self.model_task_type or define_task(
             self.df_with_original_index[TARGET], has_date, self.logger, silent=True
         )
-        if task_type == ModelTaskType.REGRESSION:
+        if self.model_task_type == ModelTaskType.REGRESSION:
             target_outliers_df = self._search_task.get_target_outliers(trace_id)
             if target_outliers_df is not None and len(target_outliers_df) > 0:
                 outliers = pd.merge(
@@ -2391,12 +2391,12 @@ class FeaturesEnricher(TransformerMixin):
 
         maybe_date_column = SearchKey.find_key(self.fit_search_keys, [SearchKey.DATE, SearchKey.DATETIME])
         has_date = maybe_date_column is not None
-        model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
+        self.model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
 
-        self._validate_binary_observations(validated_y, model_task_type)
+        self._validate_binary_observations(validated_y, self.model_task_type)
 
         self.runtime_parameters = get_runtime_params_custom_loss(
-            self.loss, model_task_type, self.runtime_parameters, self.logger
+            self.loss, self.model_task_type, self.runtime_parameters, self.logger
         )
 
         if validated_eval_set is not None and len(validated_eval_set) > 0:
@@ -2449,7 +2449,7 @@ class FeaturesEnricher(TransformerMixin):
         if is_numeric_dtype(df[self.TARGET_NAME]) and has_date:
             self._validate_PSI(df.sort_values(by=maybe_date_column))
 
-        self.__adjust_cv(df, maybe_date_column, model_task_type)
+        self.__adjust_cv(df, maybe_date_column, self.model_task_type)
 
         normalizer = Normalizer(
             self.fit_search_keys, self.fit_generated_features, self.bundle, self.logger, self.warning_counter
@@ -2522,7 +2522,7 @@ class FeaturesEnricher(TransformerMixin):
         features_columns = [c for c in df.columns if c not in non_feature_columns]
 
         features_to_drop = FeaturesValidator(self.logger).validate(
-            df, features_columns, self.generate_features, self.warning_counter
+            df, features_columns, self.generate_features, self.warning_counter, columns_renaming
         )
         self.fit_dropped_features.update(features_to_drop)
         df = df.drop(columns=features_to_drop)
@@ -2557,7 +2557,7 @@ class FeaturesEnricher(TransformerMixin):
             meaning_types=meaning_types,
             search_keys=combined_search_keys,
             unnest_search_keys=unnest_search_keys,
-            model_task_type=model_task_type,
+            model_task_type=self.model_task_type,
             date_format=self.date_format,
             random_state=self.random_state,
             rest_client=self.rest_client,
@@ -2780,6 +2780,8 @@ class FeaturesEnricher(TransformerMixin):
             raise ValidationError(self.bundle.get("x_contains_reserved_column_name").format(EVAL_SET_INDEX))
         if SYSTEM_RECORD_ID in validated_X.columns:
             raise ValidationError(self.bundle.get("x_contains_reserved_column_name").format(SYSTEM_RECORD_ID))
+        if ENTITY_SYSTEM_RECORD_ID in validated_X.columns:
+            raise ValidationError(self.bundle.get("x_contains_reserved_column_name").format(ENTITY_SYSTEM_RECORD_ID))
 
         return validated_X
 
@@ -3760,7 +3762,10 @@ class FeaturesEnricher(TransformerMixin):
             display_html_dataframe(self.metrics, self.metrics, msg)
 
     def __show_selected_features(self, search_keys: Dict[str, SearchKey]):
-        msg = self.bundle.get("features_info_header").format(len(self.feature_names_), list(search_keys.keys()))
+        search_key_names = search_keys.keys()
+        if self.fit_columns_renaming:
+            search_key_names = [self.fit_columns_renaming.get(col, col) for col in search_key_names]
+        msg = self.bundle.get("features_info_header").format(len(self.feature_names_), search_key_names)
 
         try:
             _ = get_ipython()  # type: ignore

upgini/metrics.py

@@ -10,7 +10,6 @@ import catboost
 import numpy as np
 import pandas as pd
 from catboost import CatBoostClassifier, CatBoostRegressor
-from lightgbm import LGBMClassifier, LGBMRegressor
 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
@@ -408,6 +407,8 @@ class EstimatorWrapper:
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 try:
+                    from lightgbm import LGBMClassifier, LGBMRegressor
+
                     if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
                         estimator = LightGBMWrapper(**kwargs)
                     else:

upgini/resource_bundle/strings.properties

@@ -190,7 +190,7 @@ ads_upload_too_few_rows=At least 1000 records per sample are needed. Increase th
 ads_upload_search_key_not_found=Search key {} wasn't found in dataframe columns
 ads_upload_to_many_empty_rows=More than 50% of rows in the submitted sample doesn't contain valid keys\nPlease fill the key columns with valid values and resubmit the data
     # Features info warning
-features_info_zero_important_features=Oops, we can't find any relevant external features for your training dataset,\nmost probably due to issues with search keys formats\nPlease check docs https://github.com/upgini/upgini#-search-key-types-we-support-more-to-come or send us a help request in Support:
+features_info_zero_important_features=Oops, we can't find any relevant external features for your training dataset,\nmost probably due to issues with search keys formats.\nPlease check docs https://github.com/upgini/upgini#-search-key-types-we-support-more-to-come or send us a help request in Support:
 features_info_zero_hit_rate_search_keys=Oops, looks like values/formats of the search keys {} might be incorrect,\nas we won't be able to match any data source using these values\nPlease check docs https://github.com/upgini/upgini#-search-key-types-we-support-more-to-come or send us a help request in Support:
 features_not_generated=\nWARNING: Following features didn't pass checks for automated feature generation: {}
 

upgini/utils/features_validator.py

@@ -1,6 +1,6 @@
 import logging
 from logging import Logger
-from typing import List, Optional
+from typing import Dict, List, Optional
 
 import pandas as pd
 from pandas.api.types import is_integer_dtype, is_object_dtype, is_string_dtype
@@ -23,6 +23,7 @@ class FeaturesValidator:
         features: List[str],
         features_for_generate: Optional[List[str]],
         warning_counter: WarningCounter,
+        columns_renaming: Optional[Dict[str, str]] = None,
     ) -> List[str]:
         # one_hot_encoded_features = []
         empty_or_constant_features = []
@@ -56,7 +57,11 @@ class FeaturesValidator:
         #     warning_counter.increment()
 
         if empty_or_constant_features:
-            msg = bundle.get("empty_or_contant_features").format(empty_or_constant_features)
+            if columns_renaming:
+                display_names = [columns_renaming.get(f, f) for f in empty_or_constant_features]
+            else:
+                display_names = empty_or_constant_features
+            msg = bundle.get("empty_or_contant_features").format(display_names)
             print(msg)
             self.logger.warning(msg)
             warning_counter.increment()
@@ -65,7 +70,11 @@ class FeaturesValidator:
         if features_for_generate:
             high_cardinality_features = [f for f in high_cardinality_features if f not in features_for_generate]
         if high_cardinality_features:
-            msg = bundle.get("high_cardinality_features").format(high_cardinality_features)
+            if columns_renaming:
+                display_names = [columns_renaming.get(f, f) for f in high_cardinality_features]
+            else:
+                display_names = empty_or_constant_features
+            msg = bundle.get("high_cardinality_features").format(display_names)
             print(msg)
             self.logger.warning(msg)
             warning_counter.increment()

{upgini-1.2.9a110.dist-info → upgini-1.2.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.9a110
+Version: 1.2.11
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -28,7 +28,6 @@ Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0
 Requires-Dist: levenshtein>=0.25.1
-Requires-Dist: lightgbm>=3.3.2
 Requires-Dist: numpy<=1.26.4,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
 Requires-Dist: pydantic<3.0.0,>1.0.0

{upgini-1.2.9a110.dist-info → upgini-1.2.11.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=Nkaphh2VL8ynDX7gqAi7D44dStY48dXMYUhsGTqhspI,26
+upgini/__about__.py,sha256=aBWZsCYiXXcSUsUJr3tOTQWsH7ZDqJzyMYdQbOd5Qtc,23
 upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=olZ-OHSfBNoBSCo7R5t7uCLukI2nO7afpx_A-HCiJLk,31067
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=rC3Lq1KvwJdSiITAUfYzBxdRtPkpOo6X2fqc3wWQfM4,187594
+upgini/features_enricher.py,sha256=eRkI2qpV-IprB1dQAMxzto6I6Q3b3SBuDMVR1_OFlyA,188008
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=Swp-innl6XrdK6Dy6uLTVxmkzPRqFbCxfYxQUsK_-w8,31222
+upgini/metrics.py,sha256=aKJwAYUGNRdiz9z-bxDxs4jGZQ_VkPXa7sZ52C0VpVI,31243
 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=bHRPWCNrUvt2R9qMX6dZFCJ0i8ENVCQ2Rw3dHH9IJEg,7447
 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=WZAuYPX2Dpn6BHoA3RX8uvMNMr-yJE2fF7Gz0i24x2s,26459
+upgini/resource_bundle/strings.properties,sha256=faj0wJHppGTKCTbXW8KjqLuGyFNjgb5evEMeSrq_LCE,26460
 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
@@ -47,7 +47,7 @@ upgini/utils/deduplicate_utils.py,sha256=Zvs7zW4QzaERQmJNPrTVf2ZTVBkBLOycFCzyMwt
 upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
 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=LIF6YMpHlxCrVz6mvMpc1kfNTIMVGlNCor7IJTmlSfI,3307
+upgini/utils/features_validator.py,sha256=lf5Z-taTl98p7nAWQIyM0dUfkodbzjxv0mOSIZl1jRU,3760
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=Q6vb7Sr5Khx3Sq3eENjW2qCXKej_S5jZbneH6zEOkzQ,5171
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=BVtDmrmFMKerSUWaNOIEdzsYHIFiODdpnWbE50QDPDc,7864
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.2.9a110.dist-info/METADATA,sha256=jnrnm1-aR31rb3H3FW5GgZdfweyqGI3_Cv1C4Rg3gOA,48611
-upgini-1.2.9a110.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.9a110.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.9a110.dist-info/RECORD,,
+upgini-1.2.11.dist-info/METADATA,sha256=DKUOOrexxVQVXzyaD9sXsPyT8VYx2eys3oKt15nVGtI,48577
+upgini-1.2.11.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.11.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.11.dist-info/RECORD,,