upgini 1.1.306__py3-none-any.whl → 1.1.308__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.306"
+__version__ = "1.1.308"

upgini/__init__.py

@@ -1,7 +1,11 @@
+import os
+
 from .lazy_import import LazyImport
 
-FeaturesEnricher = LazyImport('upgini.features_enricher', 'FeaturesEnricher')
-SearchKey = LazyImport('upgini.metadata', 'SearchKey')
-RuntimeParameters = LazyImport('upgini.metadata', 'RuntimeParameters')
-CVType = LazyImport('upgini.metadata', 'CVType')
-ModelTaskType = LazyImport('upgini.metadata', 'ModelTaskType')
+os.environ["SETUPTOOLS_USE_DISTUTILS"] = "stdlib"
+
+FeaturesEnricher = LazyImport("upgini.features_enricher", "FeaturesEnricher")
+SearchKey = LazyImport("upgini.metadata", "SearchKey")
+RuntimeParameters = LazyImport("upgini.metadata", "RuntimeParameters")
+CVType = LazyImport("upgini.metadata", "CVType")
+ModelTaskType = LazyImport("upgini.metadata", "ModelTaskType")

upgini/features_enricher.py

@@ -90,7 +90,6 @@ from upgini.utils.display_utils import (
 from upgini.utils.email_utils import EmailSearchKeyConverter, EmailSearchKeyDetector
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.format import Format
-from upgini.utils.ip_utils import IpToCountrySearchKeyConverter
 from upgini.utils.phone_utils import PhoneSearchKeyDetector
 from upgini.utils.postal_code_utils import PostalCodeSearchKeyDetector
 
@@ -1213,13 +1212,6 @@ class FeaturesEnricher(TransformerMixin):
             converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, [], self.logger)
             extended_X = converter.convert(extended_X)
             generated_features.extend(converter.generated_features)
-        if (
-            self.detect_missing_search_keys
-            and list(search_keys.values()) == [SearchKey.DATE]
-            and self.country_code is None
-        ):
-            converter = IpToCountrySearchKeyConverter(search_keys, self.logger)
-            extended_X = converter.convert(extended_X)
         generated_features = [f for f in generated_features if f in self.fit_generated_features]
 
         return extended_X, search_keys
@@ -1987,13 +1979,6 @@ class FeaturesEnricher(TransformerMixin):
                 df = converter.convert(df)
                 generated_features.extend(converter.generated_features)
                 email_converted_to_hem = converter.email_converted_to_hem
-            if (
-                self.detect_missing_search_keys
-                and list(search_keys.values()) == [SearchKey.DATE]
-                and self.country_code is None
-            ):
-                converter = IpToCountrySearchKeyConverter(search_keys, self.logger)
-                df = converter.convert(df)
             generated_features = [f for f in generated_features if f in self.fit_generated_features]
 
             meaning_types = {col: key.value for col, key in search_keys.items()}
@@ -2300,8 +2285,6 @@ class FeaturesEnricher(TransformerMixin):
         self.fit_search_keys = self.search_keys.copy()
         self.fit_search_keys = self.__prepare_search_keys(validated_X, self.fit_search_keys, is_demo_dataset)
 
-        validate_dates_distribution(validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
-
         maybe_date_column = self._get_date_column(self.fit_search_keys)
         has_date = maybe_date_column is not None
         model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
@@ -2322,9 +2305,6 @@ class FeaturesEnricher(TransformerMixin):
 
         df = self.__handle_index_search_keys(df, self.fit_search_keys)
 
-        if is_numeric_dtype(df[self.TARGET_NAME]) and has_date:
-            self._validate_PSI(df.sort_values(by=maybe_date_column))
-
         if DEFAULT_INDEX in df.columns:
             msg = self.bundle.get("unsupported_index_column")
             self.logger.info(msg)
@@ -2334,33 +2314,32 @@ class FeaturesEnricher(TransformerMixin):
 
         df = self.__add_country_code(df, self.fit_search_keys)
 
-        df = remove_fintech_duplicates(
-            df, self.fit_search_keys, date_format=self.date_format, logger=self.logger, bundle=self.bundle
-        )
-        df = clean_full_duplicates(df, self.logger, bundle=self.bundle)
-
-        date_column = self._get_date_column(self.fit_search_keys)
-        self.__adjust_cv(df, date_column, model_task_type)
-
         self.fit_generated_features = []
 
-        if date_column is not None:
-            converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger, bundle=self.bundle)
+        if has_date:
+            converter = DateTimeSearchKeyConverter(maybe_date_column, self.date_format, self.logger, bundle=self.bundle)
             df = converter.convert(df, keep_time=True)
-            self.logger.info(f"Date column after convertion: {df[date_column]}")
+            self.logger.info(f"Date column after convertion: {df[maybe_date_column]}")
             self.fit_generated_features.extend(converter.generated_features)
         else:
             self.logger.info("Input dataset hasn't date column")
             if self.add_date_if_missing:
                 df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
 
-        if (
-            self.detect_missing_search_keys
-            and list(self.fit_search_keys.values()) == [SearchKey.DATE]
-            and self.country_code is None
-        ):
-            converter = IpToCountrySearchKeyConverter(self.fit_search_keys, self.logger)
-            df = converter.convert(df)
+        # Checks that need validated date
+        validate_dates_distribution(df, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
+
+        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)
+
+        # TODO normalize and convert all columns
+
+        df = remove_fintech_duplicates(
+            df, self.fit_search_keys, date_format=self.date_format, logger=self.logger, bundle=self.bundle
+        )
+        df = clean_full_duplicates(df, self.logger, bundle=self.bundle)
 
         # Explode multiple search keys
         non_feature_columns = [self.TARGET_NAME, EVAL_SET_INDEX] + list(self.fit_search_keys.keys())

{upgini-1.1.306.dist-info → upgini-1.1.308.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.306
+Version: 1.1.308
 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-1.1.306.dist-info → upgini-1.1.308.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=okL1wSisFFnkKhJ4nbM09p9rNtG-hKV5SxZSxyhmBQk,24
-upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
+upgini/__about__.py,sha256=o7HYGU6jJ9PhGLTF-smMJX3fn5iDsS3gczNF7jp5774,24
+upgini/__init__.py,sha256=Xs0YFVBu1KUdtZzbStGRPQtLt3YLzJnjx5nIUBlX8BE,415
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=MOzBVsvzlHLxNfPWtMaXC_jIPeW7_gUvbSGeXnsPgNI,46158
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=8grYkWdix0NogYAY7YjUVe2Tqfra6NAxM78N9MlLF30,183572
+upgini/features_enricher.py,sha256=OhVgWC42fyTSsvcGVxFXVHQs1xz8ui3tbC9oCcxEV9w,182589
 upgini/http.py,sha256=a4Epc9YLIJBuYk4t8E_2-QDLBtJFqKO35jn2SnYQZCg,42920
 upgini/lazy_import.py,sha256=EwoM0msNGbSmWBhGbrLDny1DSnOlvTxCjmMKPxYlDms,610
 upgini/metadata.py,sha256=E5WWZ_MkjGyYNQh_LnwMIBHyqPx1fxk-qhEfQIJnzq8,10209
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.306.dist-info/METADATA,sha256=GUAb3dq_ebpqOqGoH4gEydc7T1Z91cLIur9nMvmrUEg,48153
-upgini-1.1.306.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.1.306.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.306.dist-info/RECORD,,
+upgini-1.1.308.dist-info/METADATA,sha256=-DLyRMOoFbhsZXB53n66ORDp89WAfzYFbC0KtE6FNFk,48153
+upgini-1.1.308.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.1.308.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.308.dist-info/RECORD,,