upgini 1.1.255a3233.post3__py3-none-any.whl → 1.1.255a3233.post4__py3-none-any.whl

upgini/data_source/data_source_publisher.py

@@ -79,6 +79,12 @@ class DataSourcePublisher:
                         f"Invalid update frequency: {update_frequency}. "
                         f"Available values: {self.ACCEPTABLE_UPDATE_FREQUENCIES}"
                     )
+                if (
+                    set(search_keys.values()) == {SearchKey.IP_RANGE_FROM, SearchKey.IP_RANGE_TO}
+                    or set(search_keys.values()) == {SearchKey.IPV6_RANGE_FROM, SearchKey.IPV6_RANGE_TO}
+                    or set(search_keys.values()) == {SearchKey.MSISDN_RANGE_FROM, SearchKey.MSISDN_RANGE_TO}
+                ) and sort_column is None:
+                    raise ValidationError("Sort column is required for passed search keys")
 
                 request = {
                     "dataTableUri": data_table_uri,

upgini/dataset.py

@@ -225,11 +225,11 @@ class Dataset:  # (pd.DataFrame):
                     self.data[col] = self.data[col].astype("str").str.slice(stop=self.MAX_STRING_FEATURE_LENGTH)
 
     def __convert_bools(self):
-        """Convert bool columns True -> 1, False -> 0"""
+        """Convert bool columns to string"""
         # self.logger.info("Converting bool to int")
         for col in self.data.columns:
             if is_bool(self.data[col]):
-                self.data[col] = self.data[col].astype("Int64")
+                self.data[col] = self.data[col].astype("str")
 
     def __convert_float16(self):
         """Convert float16 to float"""
@@ -309,13 +309,12 @@ class Dataset:  # (pd.DataFrame):
             if self.data[ip].isnull().all():
                 raise ValidationError(self.bundle.get("invalid_ip").format(ip))
 
-            if self.data[ip].apply(self._is_ipv4).any():
-                ipv4 = ip + "_v4"
-                self.data[ipv4] = self.data[ip].apply(self._to_ipv4).apply(self._ip_to_int).astype("Int64")
-                self.meaning_types[ipv4] = FileColumnMeaningType.IP_ADDRESS
-                self.etalon_def[FileColumnMeaningType.IP_ADDRESS.value] = ipv4
-                search_keys.add(ipv4)
-                self.columns_renaming[ipv4] = original_ip
+            ipv4 = ip + "_v4"
+            self.data[ipv4] = self.data[ip].apply(self._to_ipv4).apply(self._ip_to_int).astype("Int64")
+            self.meaning_types[ipv4] = FileColumnMeaningType.IP_ADDRESS
+            self.etalon_def[FileColumnMeaningType.IP_ADDRESS.value] = ipv4
+            search_keys.add(ipv4)
+            self.columns_renaming[ipv4] = original_ip
 
             ipv6 = ip + "_v6"
             self.data[ipv6] = (
@@ -687,8 +686,10 @@ class Dataset:  # (pd.DataFrame):
                     + "".join("<tr>" + "".join(map(map_color, row[1:])) + "</tr>" for row in df_stats.itertuples())
                     + "</table>"
                 )
+                print()
                 display(HTML(html_stats))
             except (ImportError, NameError):
+                print()
                 print(df_stats)
 
         if len(self.data) == 0:

upgini/features_enricher.py

@@ -27,7 +27,6 @@ from scipy.stats import ks_2samp
 from sklearn.base import TransformerMixin
 from sklearn.exceptions import NotFittedError
 from sklearn.model_selection import BaseCrossValidator
-from sklearn.model_selection._split import GroupsConsumerMixin
 
 from upgini.autofe.feature import Feature
 from upgini.data_source.data_source_publisher import CommercialSchema
@@ -1255,8 +1254,18 @@ class FeaturesEnricher(TransformerMixin):
             _cv, groups = CVConfig(
                 _cv, date_series, self.random_state, self._search_task.get_shuffle_kfold(), group_columns=group_columns
             ).get_cv_and_groups(X)
-        elif isinstance(_cv, GroupsConsumerMixin):
-            groups = get_groups(X, group_columns)
+        else:
+            from sklearn import __version__ as sklearn_version
+            try:
+                from sklearn.model_selection._split import GroupsConsumerMixin
+
+                if isinstance(_cv, GroupsConsumerMixin):
+                    groups = get_groups(X, group_columns)
+            except ImportError:
+                print(f"WARNING: Unsupported scikit-learn version {sklearn_version}. Restart kernel and try again")
+                self.logger.exception(
+                    f"Failed to import GroupsConsumerMixin to check CV. Version of sklearn: {sklearn_version}"
+                )
 
         return _cv, groups
 
@@ -1329,18 +1338,17 @@ class FeaturesEnricher(TransformerMixin):
         fitting_X = X_sorted[client_features].copy()
         fitting_enriched_X = enriched_X_sorted[client_features + existing_filtered_enriched_features].copy()
 
-        # Don't do this because one hot encoded client features will be removed
-        # # Detect and drop high cardinality columns in train
-        # columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        # columns_with_high_cardinality = [
-        #     c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
-        # ]
-        # if len(columns_with_high_cardinality) > 0:
-        #     self.logger.warning(
-        #         f"High cardinality columns {columns_with_high_cardinality} will be dropped for metrics calculation"
-        #     )
-        #     fitting_X = fitting_X.drop(columns=columns_with_high_cardinality, errors="ignore")
-        #     fitting_enriched_X = fitting_enriched_X.drop(columns=columns_with_high_cardinality, errors="ignore")
+        # Detect and drop high cardinality columns in train
+        columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
+        columns_with_high_cardinality = [
+            c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
+        ]
+        if len(columns_with_high_cardinality) > 0:
+            self.logger.warning(
+                f"High cardinality columns {columns_with_high_cardinality} will be dropped for metrics calculation"
+            )
+            fitting_X = fitting_X.drop(columns=columns_with_high_cardinality, errors="ignore")
+            fitting_enriched_X = fitting_enriched_X.drop(columns=columns_with_high_cardinality, errors="ignore")
 
         # Detect and drop constant columns
         constant_columns = FeaturesValidator.find_constant_features(fitting_X)
@@ -1389,11 +1397,11 @@ class FeaturesEnricher(TransformerMixin):
             ].copy()
 
             # # Drop high cardinality features in eval set
-            # if len(columns_with_high_cardinality) > 0:
-            #     fitting_eval_X = fitting_eval_X.drop(columns=columns_with_high_cardinality, errors="ignore")
-            #     fitting_enriched_eval_X = fitting_enriched_eval_X.drop(
-            #         columns=columns_with_high_cardinality, errors="ignore"
-            #     )
+            if len(columns_with_high_cardinality) > 0:
+                fitting_eval_X = fitting_eval_X.drop(columns=columns_with_high_cardinality, errors="ignore")
+                fitting_enriched_eval_X = fitting_enriched_eval_X.drop(
+                    columns=columns_with_high_cardinality, errors="ignore"
+                )
             # Drop constant features in eval_set
             if len(constant_columns) > 0:
                 fitting_eval_X = fitting_eval_X.drop(columns=constant_columns, errors="ignore")
@@ -1673,7 +1681,7 @@ class FeaturesEnricher(TransformerMixin):
                 eval_set_sampled_dict[idx] = (eval_x_sampled, enriched_eval_x, eval_y_sampled)
         else:
             self.logger.info("Transform without eval_set")
-            df = self.X.copy()
+            df = validated_X.copy()
 
             df[TARGET] = validated_y
             num_samples = _num_samples(df)
@@ -1850,7 +1858,7 @@ class FeaturesEnricher(TransformerMixin):
                         msg = self.bundle.get("transform_usage_info").format(
                             transform_usage.limit, transform_usage.transformed_rows
                         )
-                        self.logger.info("transform_usage_warning")
+                        self.logger.info(msg)
                         print(msg)
 
             validated_X = self._validate_X(X, is_transform=True)
@@ -2276,7 +2284,9 @@ 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.warning_counter)
+        features_to_drop = FeaturesValidator(self.logger).validate(
+            df, features_columns, self.generate_features, self.warning_counter
+        )
         self.fit_dropped_features.update(features_to_drop)
         df = df.drop(columns=features_to_drop)
 

upgini/metrics.py

@@ -6,6 +6,7 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import numpy as np
 import pandas as pd
 from catboost import CatBoostClassifier, CatBoostRegressor
+import catboost
 from lightgbm import LGBMClassifier, LGBMRegressor
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
@@ -424,24 +425,35 @@ class CatBoostWrapper(EstimatorWrapper):
         X, y, groups, params = super()._prepare_to_fit(X, y)
 
         # Find embeddings
-        emb_pattern = r"(.+)_emb\d+"
-        self.emb_features = [c for c in X.columns if re.match(emb_pattern, c) and is_numeric_dtype(X[c])]
-        embedding_features = []
-        if len(self.emb_features) > 3:  # There is no reason to reduce embeddings dimension with less than 4
-            self.logger.info(
-                f"Embedding features count more than 3, so group them into one vector for CatBoost: {self.emb_features}"
-            )
-            X, embedding_features = self.group_embeddings(X)
-            params["embedding_features"] = embedding_features
+        if hasattr(CatBoostClassifier, "get_embedding_feature_indices"):
+            emb_pattern = r"(.+)_emb\d+"
+            self.emb_features = [c for c in X.columns if re.match(emb_pattern, c) and is_numeric_dtype(X[c])]
+            embedding_features = []
+            if len(self.emb_features) > 3:  # There is no reason to reduce embeddings dimension with less than 4
+                self.logger.info(
+                    "Embedding features count more than 3, so group them into one vector for CatBoost: "
+                    f"{self.emb_features}"
+                )
+                X, embedding_features = self.group_embeddings(X)
+                params["embedding_features"] = embedding_features
+            else:
+                self.logger.info(
+                    f"Embedding features count less than 3, so use them separately: {self.emb_features}"
+                )
+                self.emb_features = []
         else:
-            self.emb_features = []
+            self.logger.warning(f"Embedding features are not supported by Catboost version {catboost.__version__}")
 
         # Find text features from passed in generate_features
-        if self.text_features is not None:
-            self.logger.info(f"Passed text features for CatBoost: {self.text_features}")
-            self.text_features = [f for f in self.text_features if f in X.columns and not is_numeric_dtype(X[f])]
-            self.logger.info(f"Rest text features after checks: {self.text_features}")
-            params["text_features"] = self.text_features
+        if hasattr(CatBoostClassifier, "get_text_feature_indices"):
+            if self.text_features is not None:
+                self.logger.info(f"Passed text features for CatBoost: {self.text_features}")
+                self.text_features = [f for f in self.text_features if f in X.columns and not is_numeric_dtype(X[f])]
+                self.logger.info(f"Rest text features after checks: {self.text_features}")
+                params["text_features"] = self.text_features
+        else:
+            self.text_features = None
+            self.logger.warning(f"Text features are not supported by this Catboost version {catboost.__version__}")
 
         # Find rest categorical features
         self.cat_features = _get_cat_features(X, self.text_features, embedding_features)

upgini/resource_bundle/strings.properties

@@ -28,8 +28,8 @@ metrics_exclude_paid_features=\nWARNING: Metrics calculated after enrichment has
 metrics_no_important_free_features=\nWARNING: No important free features to calculate metrics
 metrics_no_important_features=\nWARNING: No important features to calculate metrics
 metrics_negative_uplift_without_cv=Please re-check that your task is not a time series prediction. If so, restart search with cv=CVType.time_series param for correct search results. See docs https://github.com/upgini/upgini#-time-series-prediction-support
-metrics_with_trial_features=The calculation of final accuracy metrics using Trial data is not available for unauthorized users.\nGet a free API key on https://upgini.com and repeat your request.
-transform_with_trial_features=\nWARNING: Your search results contain Trial data sources. To enrich your dataframe using transform or fit_transform with features from these Trial data sources, please register for a Free API key at https://upgini.com and resubmit your request.
+# metrics_with_trial_features=The calculation of final accuracy metrics using Trial data is not available for unauthorized users.\nGet a free API key on https://upgini.com and repeat your request.
+# transform_with_trial_features=\nWARNING: Your search results contain Trial data sources. To enrich your dataframe using transform or fit_transform with features from these Trial data sources, please register for a Free API key at https://upgini.com and resubmit your request.
 # Enriching with Trial data is not available for unauthorized users.\nGet a free API key on https://upgini.com and repeat your request.
 metrics_with_paid_features=\nWARNING: The calculation of final accuracy metrics using Paid data is not available.\nContact Upgini support for the data access
 transform_with_paid_features=\nWARNING: Enriching with Paid data is not available.\nContact Upgini support for the data access
@@ -132,18 +132,17 @@ baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input
 baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
     # target validation
 empty_target=Target is empty in all rows
-non_numeric_target=Binary target should be numerical type
+# non_numeric_target=Binary target should be numerical type
 uneven_eval_target_distribution=\nWARNING: y distributions from the training sample and eval_set differ according to the Kolmogorov-Smirnov test,\nwhich makes metrics between the train and eval_set incomparable.
-target_outliers_warning=We detected {} outliers in your sample.\nExamples of outliers with maximum value of target:\n{}\nOutliers will {}be excluded during the metrics calculation.
+target_outliers_warning=\nWARNING: We detected {} outliers in your sample.\nExamples of outliers with maximum value of target:\n{}\nOutliers will {}be excluded during the metrics calculation.
     # features validation
-empty_or_contant_features=Columns {} has value with frequency more than 99%, removed from X
-high_cardinality_features=Columns {} has high cardinality (>90% unique values), removed from X
-one_hot_encoded_features=\nWARNING: One hot encoded features detected. Use int encoding for correct results of fit.\n{}
+empty_or_contant_features=\nWARNING: Columns {} has value with frequency more than 99%, removed from X
+high_cardinality_features=\nWARNING: Columns {} has high cardinality (>90% unique values), removed from X
+# one_hot_encoded_features=\nWARNING: One hot encoded features detected. Use int encoding for correct results of fit.\n{}
     # Dataset validation
 dataset_too_few_rows=X size should be at least {} rows after validation
 dataset_too_many_rows_registered=X rows limit for transform is {}. Please sample X
 dataset_empty_column_names=Some column names are empty. Add names please
-dataset_too_long_column_name=Column {} is too long: {} characters. Remove this column or trim length to 50 characters
 dataset_full_duplicates=\nWARNING: {:.5f}% of the rows are fully duplicated
 dataset_diff_target_duplicates=\nWARNING: {:.4f}% of rows ({}) in X and eval_set are duplicates with different y values. These rows will be deleted as incorrect\nIncorrect row indexes: {}
 dataset_diff_target_duplicates_fintech=\nWARNING: {:.4f}% of rows ({}) in X and eval_set are duplicates, not taking into consideration dates, IP addresses and features from the training set, but have different y values. These rows have been removed to optimize search results.\nRemoved row indexes: {}
@@ -165,7 +164,7 @@ dataset_invalid_column_type=Unsupported data type of column {}: {}
 dataset_invalid_filter=Unknown field in filter_features. Should be {'min_importance', 'max_psi', 'max_count', 'selected_features'}.
 dataset_too_big_file=Too big size of dataframe X for processing. Please reduce number of rows or columns
 dataset_transform_diff_fit=You try to enrich dataset that column names are different from the train dataset column names that you used on the fit stage. Please make the column names the same as in the train dataset and restart.
-binary_small_dataset=The least populated class in Target contains less than 1000 rows.\nSmall numbers of observations may negatively affect the number of selected features and quality of your ML model.\nUpgini recommends you increase the number of observations in the least populated class.
+binary_small_dataset=\nWARNING: The least populated class in Target contains less than 1000 rows.\nSmall numbers of observations may negatively affect the number of selected features and quality of your ML model.\nUpgini recommends you increase the number of observations in the least populated class.
 all_search_keys_invalid=All search keys are invalid
 all_emails_invalid=\nWARNING: All values in column {} are invalid emails
     # Metrics validation

upgini/utils/datetime_utils.py

@@ -11,7 +11,20 @@ from pandas.api.types import is_numeric_dtype, is_period_dtype, is_string_dtype
 from upgini.errors import ValidationError
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
 
-DATE_FORMATS = ["%Y-%m-%d", "%d.%m.%y", "%d.%m.%Y", "%m.%d.%y", "%m.%d.%Y", "%Y-%m-%dT%H:%M:%S.%f"]
+DATE_FORMATS = [
+    "%Y-%m-%d",
+    "%d.%m.%y",
+    "%d.%m.%Y",
+    "%m.%d.%y",
+    "%m.%d.%Y",
+    "%Y/%m/%d",
+    "%y/%m/%d",
+    "%d/%m/%Y",
+    "%d/%m/%y",
+    "%m/%d/%Y",
+    "%m/%d/%y",
+    "%Y-%m-%dT%H:%M:%S.%f",
+]
 
 DATETIME_PATTERN = r"^[\d\s\.\-:T]+$"
 

upgini/utils/features_validator.py

@@ -3,7 +3,8 @@ from logging import Logger
 from typing import List, Optional
 
 import pandas as pd
-from pandas.api.types import is_object_dtype, is_integer_dtype, is_string_dtype
+from pandas.api.types import is_integer_dtype, is_object_dtype, is_string_dtype
+
 from upgini.resource_bundle import bundle
 from upgini.utils.warning_counter import WarningCounter
 
@@ -16,9 +17,16 @@ class FeaturesValidator:
             self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
 
-    def validate(self, df: pd.DataFrame, features: List[str], warning_counter: WarningCounter) -> List[str]:
+    def validate(
+        self,
+        df: pd.DataFrame,
+        features: List[str],
+        features_for_generate: Optional[List[str]],
+        warning_counter: WarningCounter,
+    ) -> List[str]:
         # one_hot_encoded_features = []
         empty_or_constant_features = []
+        high_cardinality_features = []
 
         for f in features:
             column = df[f]
@@ -51,23 +59,31 @@ class FeaturesValidator:
             msg = bundle.get("empty_or_contant_features").format(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]
+        if high_cardinality_features:
+            msg = bundle.get("high_cardinality_features").format(high_cardinality_features)
+            print(msg)
+            self.logger.warning(msg)
+            warning_counter.increment()
 
-        return empty_or_constant_features
+        return empty_or_constant_features + high_cardinality_features
 
     @staticmethod
     def find_high_cardinality(df: pd.DataFrame) -> List[str]:
         # Remove high cardinality columns
         row_count = df.shape[0]
+        if row_count < 100:  # For tests with small datasets
+            return []
         return [
             i
             for i in df
-            if (is_string_dtype(df[i]) or is_integer_dtype(df[i])) and (df[i].nunique() / row_count >= 0.9)
+            if (is_string_dtype(df[i]) or is_integer_dtype(df[i])) and (df[i].nunique(dropna=False) / row_count >= 0.95)
         ]
 
     @staticmethod
     def find_constant_features(df: pd.DataFrame) -> List[str]:
-        return [
-            i
-            for i in df
-            if df[i].nunique() == 1
-        ]
+        return [i for i in df if df[i].nunique() == 1]

{upgini-1.1.255a3233.post3.dist-info → upgini-1.1.255a3233.post4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.255a3233.post3
+Version: 1.1.255a3233.post4
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.255a3233.post3.dist-info → upgini-1.1.255a3233.post4.dist-info}/RECORD

@@ -1,12 +1,12 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=sL1w8dVmXkuV5PWaBTUpz8X8joW6mIOLyPbSAlSbpR0,45576
+upgini/dataset.py,sha256=4LfrUwxhd__ZVqZkjPVxbC4SW3YLsk1sMMqnYPUaVpw,45529
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=NZHH1Wf7QbvyFYgr-LJhG3d9HjUDQyfrZ6fFLsn9PdM,171774
+upgini/features_enricher.py,sha256=WbwnLvPVqn4m995b6jSamWkXyRVy18fnG7faBeuJbWI,172132
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
-upgini/metrics.py,sha256=LS2MgEKgmn9VEXsKzxv3pBZ-q71mTnpWu6vL8fYgpo4,26727
+upgini/metrics.py,sha256=3VvSZW1cCOIPHImXuqcnWzD3fWcpPzVa9k8eulLbUmY,27426
 upgini/search_task.py,sha256=tmJ17WUxv3J5NWrYUJB_NKdZ792Ifz8Z8UnDXeQnpss,17077
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -21,14 +21,14 @@ upgini/autofe/operand.py,sha256=Rhy7Ky3we-I1Su1--dS4xdsO3K8neV4rqM_Q4xYE4ug,2779
 upgini/autofe/unary.py,sha256=gyMkrx9bfa3o19zS-4JaRlScHrfeZGBsYe7d_6ePT-0,2853
 upgini/autofe/vector.py,sha256=Qk7VmdwURNwVw7fIMEspWEo7HTiyUWCYIqu3hcWQQio,507
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=iH26_cQiT1fm4VxsJD7WoAaOFyfmsEKKtiWa-JJFpeQ,15494
+upgini/data_source/data_source_publisher.py,sha256=QASEDhJ9SxJKcWxoN2vUPxrM_HTlwKQOPa92L7EQneA,15962
 upgini/mdc/__init__.py,sha256=ETDh3JKbrDdPMOECiYLAa8lvKYe68mv4IY6fZa9FimA,1126
 upgini/mdc/context.py,sha256=Sl1S_InKlzzRxYqwJ2k24lawJdCKWgGJ-RIRfvzWJrk,1468
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/phone_normalizer.py,sha256=lhwsPEnfyjeIsndW2EcQGZksXYsfxaQ1ghAzVYoDRKM,9927
 upgini/resource_bundle/__init__.py,sha256=hdvbqL0b0xMWbY6-kiYGsW1ro2GMiWpxxsO9uCv-h9Q,8379
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=WoT1k7uJSVhECUsgJKX2R8I3aPQjTDIhms6HVexWaCA,25294
+upgini/resource_bundle/strings.properties,sha256=MGU_oBc15VAmbPZdThCpm3B4xERAKwbCIUTIG66dvUo,25228
 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=CC-DvPbrN7zp5--SVFuUqkVmdWM_5F7R0Do98ETV82U,6421
@@ -40,12 +40,12 @@ upgini/utils/blocked_time_series.py,sha256=dMz5ewk3PsoeOrc3lDzInCVPS9u_2XQkV0W6P
 upgini/utils/country_utils.py,sha256=1KXhLSNqkNYVL3on8-zK0Arc_SspUH7AMZvGZICysOU,6462
 upgini/utils/custom_loss_utils.py,sha256=DBslpjWGPt7xTeypt78baR59012SYphbPsO_YLKdilo,3972
 upgini/utils/cv_utils.py,sha256=Tn01RJvpZGZh0PUQUimlBkV-AXwe7s6yjCNFtw352Uc,3525
-upgini/utils/datetime_utils.py,sha256=b8pyNhrC8ni6apsLQivQOiKqu-37pU4EF3nNHPZqiN8,8713
+upgini/utils/datetime_utils.py,sha256=ol5Bgh98wU6KBY9z4QskNO0ja-L7HJL70HmTAjl7iRU,8836
 upgini/utils/deduplicate_utils.py,sha256=ckJrpU8Ruc_vcwIPTopbUjyJuNiseLHNAbQlLfhUCxo,5888
 upgini/utils/display_utils.py,sha256=BfPaJGUJAkGaijdAKPrdIfUqjXewFbBRrYqzzylB9t4,10667
 upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
-upgini/utils/features_validator.py,sha256=VexG-9p63ni66Hf9T7dgP4iUAhpXqwo3sgMwBK_eii8,2565
+upgini/utils/features_validator.py,sha256=P-dfjBLAMxgzOcUX1Jo1bhVp8-8WyTyF3Ef0YZ5nfRI,3269
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=Zf3F2cnQmOCH09QLQHetpjMFu1PnD0cTmDymn0SnSy8,1672
 upgini/utils/phone_utils.py,sha256=JNSkF8G6mgsN8Czy11pamaJdsY6rBINEMpi7jbVt_RA,408
@@ -55,8 +55,8 @@ upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,4
 upgini/utils/target_utils.py,sha256=WVhhxpQVvnhsDV7ctlds51VFg7hz59S_MFUSoRZFszw,7204
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.255a3233.post3.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.255a3233.post3.dist-info/METADATA,sha256=EOPXhWBGtI0RgsqcVJmRUkI8yWppXlLts8TEYQ2Q8pY,48167
-upgini-1.1.255a3233.post3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-upgini-1.1.255a3233.post3.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.255a3233.post3.dist-info/RECORD,,
+upgini-1.1.255a3233.post4.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.255a3233.post4.dist-info/METADATA,sha256=LISA1JiOQR8ZPKCt7QlF-sTEJyiban04m9Zfln5DVyA,48167
+upgini-1.1.255a3233.post4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.255a3233.post4.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.255a3233.post4.dist-info/RECORD,,

{upgini-1.1.255a3233.post3.dist-info → upgini-1.1.255a3233.post4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: bdist_wheel (0.43.0)
 Root-Is-Purelib: true
 Tag: py3-none-any