upgini 1.2.10__py3-none-any.whl → 1.2.12__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.10"
+__version__ = "1.2.12"

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
 
@@ -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)

upgini/resource_bundle/strings.properties

@@ -22,7 +22,7 @@ slack_community_bage=https://img.shields.io/badge/slack-@upgini-orange.svg?logo=
 slack_community_alt=Upgini Slack community
 version_warning=\nWARNING: Unsupported library version detected {},\nplease update with “%pip install -U upgini” to the latest {} and restart Jupyter kernel
 unregistered_with_personal_keys=\nWARNING: Search key {} can be used only with personal api_key from profile.upgini.com It will be ignored
-date_only_search=\nWARNING: Search started with DATE search key only\nTry to add other keys like the COUNTRY, POSTAL_CODE, PHONE NUMBER, EMAIL/HEM, IPv4 to your training dataset\nfor search through all the available data sources.\nSee docs https://github.com/upgini/upgini#-total-239-countries-and-up-to-41-years-of-history
+date_only_search=\nWARNING: Search started with DATE search key only\nTry to add other keys like the COUNTRY, POSTAL_CODE, PHONE NUMBER, EMAIL/HEM, IP to your training dataset\nfor search through all the available data sources.\nSee docs https://github.com/upgini/upgini#-total-239-countries-and-up-to-41-years-of-history
 date_search_without_time_series=\nWARNING: Looks like your training dataset is a time series. We recommend to set `cv=CVType.time_series` param for correct search results.\nSee docs https://github.com/upgini/upgini#-time-series-prediction-support
 metrics_exclude_paid_features=\nWARNING: Metrics calculated after enrichment has a free features only. To calculate metrics with a full set of relevant features, including commercial data sources, please contact support team:
 metrics_no_important_free_features=\nWARNING: No important free features to calculate metrics
@@ -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 = []
@@ -55,17 +56,25 @@ class FeaturesValidator:
         #     self.logger.warning(msg)
         #     warning_counter.increment()
 
+        columns_renaming = columns_renaming or {}
+
         if empty_or_constant_features:
-            msg = bundle.get("empty_or_contant_features").format(empty_or_constant_features)
+            msg = bundle.get("empty_or_contant_features").format(
+                [columns_renaming.get(f, f) for f in empty_or_constant_features]
+            )
             print(msg)
             self.logger.warning(msg)
             warning_counter.increment()
 
         high_cardinality_features = self.find_high_cardinality(df[features])
         if features_for_generate:
-            high_cardinality_features = [f for f in high_cardinality_features if f not in features_for_generate]
+            high_cardinality_features = [
+                f for f in high_cardinality_features if columns_renaming.get(f, f) not in features_for_generate
+            ]
         if high_cardinality_features:
-            msg = bundle.get("high_cardinality_features").format(high_cardinality_features)
+            msg = bundle.get("high_cardinality_features").format(
+                [columns_renaming.get(f, f) for f in high_cardinality_features]
+            )
             print(msg)
             self.logger.warning(msg)
             warning_counter.increment()

{upgini-1.2.10.dist-info → upgini-1.2.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.10
+Version: 1.2.12
 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-1.2.10.dist-info → upgini-1.2.12.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=GI4rgymQsPWdk2_d96NgmZBRuFM6yOZB-kysnrjBjVo,23
+upgini/__about__.py,sha256=dbW85A2PinQCZabwD2DNDTfOE9315GDtQQKAsJP8IXk,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=NIroiDLvlWtfxE9qqYYoB6ZTLgpGweRaCVcL8osXoI8,187995
+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
@@ -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=hWldMqtv80lwv8HV00Hk2-3tflu4BkD6tiXOfGDZPl8,26458
 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=yiOdzVtpArELMufzAa9mtWq32lETB6sIF-w3Yvl3vV8,3614
 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-1.2.10.dist-info/METADATA,sha256=Cc-4FefWQaLK1hlCIR_dMIAm_NHRD9HxquQbTZn986E,48577
-upgini-1.2.10.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.10.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.10.dist-info/RECORD,,
+upgini-1.2.12.dist-info/METADATA,sha256=k_J1xVbmpvm56wJ_hDo17cEK6rXRhhqJp3rSbw233xA,48577
+upgini-1.2.12.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.12.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.12.dist-info/RECORD,,