upgini 1.1.246a101__py3-none-any.whl → 1.1.248a1__py3-none-any.whl

upgini/autofe/operand.py

@@ -59,12 +59,14 @@ class PandasOperand(Operand, abc.ABC):
         df_from.loc[np.nan] = np.nan
         return df_to.fillna(np.nan).apply(lambda x: df_from.loc[x])
 
-    def _round_value(self, value: Union[pd.Series, pd.DataFrame]) -> Union[pd.Series, pd.DataFrame]:
+    def _round_value(
+        self, value: Union[pd.Series, pd.DataFrame], precision: Optional[int] = None
+    ) -> Union[pd.Series, pd.DataFrame]:
         if isinstance(value, pd.DataFrame):
             return value.apply(self._round_value, axis=1)
 
         if np.issubdtype(value.dtype, np.floating):
-            precision = np.finfo(value.dtype).precision
+            precision = precision or np.finfo(value.dtype).precision
             return np.trunc(value * 10**precision) / (10**precision)
         else:
             return value

upgini/autofe/unary.py

@@ -22,10 +22,10 @@ class Log(PandasOperand):
     output_type = "float"
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
-        return self._round_value(np.log(np.abs(data.replace(0, np.nan))))
+        return self._round_value(np.log(np.abs(data.replace(0, np.nan))), 10)
 
     def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:
-        return self._round_value(np.log(data.replace(0, np.nan).abs()))
+        return self._round_value(np.log(data.replace(0, np.nan).abs()), 10)
 
 
 class Sqrt(PandasOperand):

upgini/dataset.py

@@ -662,15 +662,15 @@ class Dataset:  # (pd.DataFrame):
             # if self.task_type != ModelTaskType.MULTICLASS:
             #     self.data[target] = self.data[target].apply(pd.to_numeric, errors="coerce")
 
-        keys_to_validate = [
+        keys_to_validate = {
             key
             for search_group in self.search_keys_checked
             for key in search_group
             if self.columns_renaming.get(key) != EmailSearchKeyConverter.EMAIL_ONE_DOMAIN_COLUMN_NAME
-        ]
-        ipv4_column = self.etalon_def_checked.get(FileColumnMeaningType.IP_ADDRESS)
+        }
+        ipv4_column = self.etalon_def_checked.get(FileColumnMeaningType.IP_ADDRESS.value)
         if (
-            FileColumnMeaningType.IPV6_ADDRESS in self.etalon_def_checked
+            FileColumnMeaningType.IPV6_ADDRESS.value in self.etalon_def_checked
             and ipv4_column is not None
             and ipv4_column in keys_to_validate
         ):

upgini/features_enricher.py

@@ -1,3 +1,4 @@
+import dataclasses
 import gc
 import hashlib
 import itertools
@@ -9,8 +10,7 @@ import sys
 import tempfile
 import time
 import uuid
-from collections import namedtuple
-from functools import reduce
+from dataclasses import dataclass
 from threading import Thread
 from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
 
@@ -21,6 +21,7 @@ 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
@@ -59,7 +60,7 @@ from upgini.utils.custom_loss_utils import (
     get_additional_params_custom_loss,
     get_runtime_params_custom_loss,
 )
-from upgini.utils.cv_utils import CVConfig
+from upgini.utils.cv_utils import CVConfig, get_groups
 from upgini.utils.datetime_utils import (
     DateTimeSearchKeyConverter,
     is_blocked_time_series,
@@ -920,6 +921,7 @@ class FeaturesEnricher(TransformerMixin):
                     fitting_eval_set_dict,
                     search_keys,
                     groups,
+                    _cv,
                 ) = prepared_data
 
                 gc.collect()
@@ -936,16 +938,6 @@ class FeaturesEnricher(TransformerMixin):
 
                     has_date = self._get_date_column(search_keys) is not None
                     model_task_type = self.model_task_type or define_task(y_sorted, has_date, self.logger, silent=True)
-                    _cv = cv or self.cv
-                    if groups is None and _cv == CVType.group_k_fold:
-                        self.logger.info("Replacing group_k_fold with k_fold as no groups were found")
-                        _cv = CVType.k_fold
-                    if not isinstance(_cv, BaseCrossValidator):
-                        date_column = self._get_date_column(search_keys)
-                        date_series = validated_X[date_column] if date_column is not None else None
-                        _cv = CVConfig(
-                            _cv, date_series, self.random_state, self._search_task.get_shuffle_kfold()
-                        ).get_cv()
 
                     wrapper = EstimatorWrapper.create(
                         estimator,
@@ -1213,7 +1205,7 @@ class FeaturesEnricher(TransformerMixin):
         generated_features = []
         date_column = self._get_date_column(search_keys)
         if date_column is not None:
-            converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger)
+            converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger, self.bundle)
             extended_X = converter.convert(extended_X, keep_time=True)
             generated_features.extend(converter.generated_features)
         email_column = self._get_email_column(search_keys)
@@ -1265,6 +1257,27 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.info("Passed X, y and eval_set that differs from passed on fit. Transform will be used")
             return False, X, y, checked_eval_set
 
+    def _get_cv_and_groups(
+        self,
+        X: pd.DataFrame,
+        cv_override: Union[BaseCrossValidator, CVType, str, None],
+        search_keys: Dict[str, SearchKey],
+    ) -> Tuple[BaseCrossValidator, Optional[np.ndarray]]:
+        _cv = cv_override or self.cv
+        group_columns = sorted(self._get_group_columns(X, search_keys))
+        groups = None
+
+        if not isinstance(_cv, BaseCrossValidator):
+            date_column = self._get_date_column(search_keys)
+            date_series = X[date_column] if date_column is not None else None
+            _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)
+
+        return _cv, groups
+
     def _prepare_data_for_metrics(
         self,
         trace_id: str,
@@ -1275,6 +1288,7 @@ class FeaturesEnricher(TransformerMixin):
         importance_threshold: Optional[float] = None,
         max_features: Optional[int] = None,
         remove_outliers_calc_metrics: Optional[bool] = None,
+        cv_override: Union[BaseCrossValidator, CVType, str, None] = None,
         search_keys_for_metrics: Optional[List[str]] = None,
         progress_bar: Optional[ProgressBar] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
@@ -1290,7 +1304,7 @@ class FeaturesEnricher(TransformerMixin):
             else None
         )
 
-        X_sampled, y_sampled, enriched_X, eval_set_sampled_dict, search_keys = self._sample_data_for_metrics(
+        sampled_data = self._sample_data_for_metrics(
             trace_id,
             validated_X,
             validated_y,
@@ -1302,6 +1316,7 @@ class FeaturesEnricher(TransformerMixin):
             progress_bar,
             progress_callback,
         )
+        X_sampled, y_sampled, enriched_X, eval_set_sampled_dict, search_keys = dataclasses.astuple(sampled_data)
 
         excluding_search_keys = list(search_keys.keys())
         if search_keys_for_metrics is not None and len(search_keys_for_metrics) > 0:
@@ -1325,14 +1340,7 @@ class FeaturesEnricher(TransformerMixin):
         X_sorted, y_sorted = self._sort_by_system_record_id(X_sampled, y_sampled, self.cv)
         enriched_X_sorted, enriched_y_sorted = self._sort_by_system_record_id(enriched_X, y_sampled, self.cv)
 
-        group_columns = sorted(self._get_group_columns(enriched_X_sorted, search_keys))
-        groups = (
-            None
-            if not group_columns or self.cv != CVType.group_k_fold
-            else reduce(
-                lambda left, right: left + "_" + right, [enriched_X_sorted[c].astype(str) for c in group_columns]
-            ).factorize()[0]
-        )
+        cv, groups = self._get_cv_and_groups(enriched_X_sorted, cv_override, search_keys)
 
         existing_filtered_enriched_features = [c for c in filtered_enriched_features if c in enriched_X_sorted.columns]
 
@@ -1382,11 +1390,16 @@ class FeaturesEnricher(TransformerMixin):
             fitting_eval_set_dict,
             search_keys,
             groups,
+            cv,
         )
 
-    _SampledDataForMetrics = namedtuple(
-        "_SampledDataForMetrics", "X_sampled y_sampled enriched_X eval_set_sampled_dict search_keys"
-    )
+    @dataclass
+    class _SampledDataForMetrics:
+        X_sampled: pd.DataFrame
+        y_sampled: pd.Series
+        enriched_X: pd.DataFrame
+        eval_set_sampled_dict: Dict[int, Tuple[pd.DataFrame, pd.Series]]
+        search_keys: Dict[str, SearchKey]
 
     def _sample_data_for_metrics(
         self,
@@ -1571,7 +1584,12 @@ class FeaturesEnricher(TransformerMixin):
                 df_with_eval_set_index = pd.concat([df_with_eval_set_index, eval_df_with_index])
 
             _, df_with_eval_set_index = remove_fintech_duplicates(
-                df_with_eval_set_index, self.search_keys, self.logger, silent=True
+                df_with_eval_set_index,
+                self.search_keys,
+                date_format=self.date_format,
+                logger=self.logger,
+                silent=True,
+                bundle=self.bundle,
             )
 
             # downsample if need to eval_set threshold
@@ -1673,7 +1691,11 @@ class FeaturesEnricher(TransformerMixin):
     ):
         search_keys = {k: v for k, v in search_keys.items() if k in X_sampled.columns.to_list()}
         return FeaturesEnricher._SampledDataForMetrics(
-            X_sampled, y_sampled, enriched_X, eval_set_sampled_dict, search_keys
+            X_sampled=X_sampled,
+            y_sampled=y_sampled,
+            enriched_X=enriched_X,
+            eval_set_sampled_dict=eval_set_sampled_dict,
+            search_keys=search_keys,
         )
 
     def get_search_id(self) -> Optional[str]:
@@ -1810,7 +1832,7 @@ class FeaturesEnricher(TransformerMixin):
             generated_features = []
             date_column = self._get_date_column(search_keys)
             if date_column is not None:
-                converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger)
+                converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger, bundle=self.bundle)
                 df = converter.convert(df)
                 self.logger.info(f"Date column after convertion: {df[date_column]}")
                 generated_features.extend(converter.generated_features)
@@ -1868,7 +1890,9 @@ class FeaturesEnricher(TransformerMixin):
 
             df_without_features = df.drop(columns=non_keys_columns)
 
-            df_without_features = clean_full_duplicates(df_without_features, self.logger, silent=silent_mode)
+            df_without_features = clean_full_duplicates(
+                df_without_features, self.logger, silent=silent_mode, bundle=self.bundle
+            )
 
             del df
             gc.collect()
@@ -2148,9 +2172,11 @@ class FeaturesEnricher(TransformerMixin):
 
         df = self.__add_country_code(df, self.fit_search_keys)
 
-        need_full_defuplication, df = remove_fintech_duplicates(df, self.fit_search_keys, self.logger)
+        need_full_defuplication, df = remove_fintech_duplicates(
+            df, self.fit_search_keys, date_format=self.date_format, logger=self.logger, bundle=self.bundle
+        )
         if need_full_defuplication:
-            df = clean_full_duplicates(df, self.logger)
+            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)
@@ -2158,7 +2184,7 @@ class FeaturesEnricher(TransformerMixin):
         self.fit_generated_features = []
 
         if date_column is not None:
-            converter = DateTimeSearchKeyConverter(date_column, self.date_format, self.logger)
+            converter = DateTimeSearchKeyConverter(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.fit_generated_features.extend(converter.generated_features)

upgini/metadata.py

@@ -306,3 +306,4 @@ class CVType(Enum):
     group_k_fold = "group_k_fold"
     time_series = "time_series"
     blocked_time_series = "blocked_time_series"
+    not_set = "not_set"

upgini/resource_bundle/strings.properties

@@ -89,6 +89,8 @@ empty_search_key=Search key {} is empty. Please fill values or remove this searc
 single_constant_search_key=\nWARNING: Constant value detected for the {} search key in the X dataframe: {}.\nThat search key will add constant features for different y values.\nPlease add extra search keys with non constant values, like the COUNTRY, POSTAL_CODE, DATE, PHONE NUMBER, EMAIL/HEM or IPv4
 unsupported_index_column=\nWARNING: Your column with name `index` was dropped because it's reserved name is booked for system needs.
 date_string_without_format=Date column `{}` has string type, but date_format is not specified. Convert column to datetime type or pass date_format
+invalid_date_format=Failed to parse date in column `{}`. Try to pass explicit date format in date_format argument of FeaturesEnricher constructor
+unsupported_date_type=Unsupported type of date column `{}`. Convert to datetime please.
 invalid_postal_code=All values of POSTAL_CODE column `{}` are invalid
 invalid_country=All values of COUNTRY column `{}` are invalid
 invalid_ip=All values of IPv4 column `{}` are invalid

upgini/resource_bundle/strings_widget.properties

@@ -9,6 +9,8 @@ dataset_too_few_rows=Labeled dataset size with unique search keys must be not le
 dataset_too_big_file=Too big size of labeled dataset for processing. Please reduce number of rows or columns
 dataset_too_many_rows_registered=Labeled dataset size rows limit is {}. Please sample it and retry
 dataset_all_dates_old=There is empty labeled dataset after removing data before '2000-01-01'
+invalid_date_format=Failed to parse date in column `{}`
+unsupported_date_type=Unsupported type of date column `{}`. Convert to datetime please.
 
 # Validate target
 y_is_constant=Target label is a constant. Relevant feature search requires a non-constant target

upgini/utils/cv_utils.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, Optional, Union
+from functools import reduce
+from typing import Any, Dict, List, Optional, Tuple, Union
+import numpy as np
 
 import pandas as pd
 from sklearn.model_selection import BaseCrossValidator, KFold, TimeSeriesSplit, GroupKFold, GroupShuffleSplit
@@ -14,6 +16,9 @@ class CVConfig:
         date_column: Optional[pd.Series],
         random_state=None,
         shuffle_kfold: Optional[bool] = None,
+        test_size: Optional[float] = 0.2,
+        n_folds: Optional[int] = 5,
+        group_columns: Optional[List[str]] = None,
     ):
         if cv_type is None:
             self.cv_type = CVType.k_fold
@@ -24,9 +29,10 @@ class CVConfig:
         else:
             raise Exception(f"Unexpected type of cv_type: {type(cv_type)}")
 
+        self.group_columns = group_columns
         self.shuffle_kfold: Optional[bool] = shuffle_kfold
-        self.test_size = 0.2
-        self.n_folds = 5
+        self.test_size = test_size
+        self.n_folds = n_folds
         if (self.cv_type == CVType.k_fold or self.cv_type == CVType.group_k_fold) and self.shuffle_kfold is None:
             self.shuffle_kfold = date_column is None or is_constant(date_column)
         if self.shuffle_kfold:
@@ -45,17 +51,37 @@ class CVConfig:
             config["test_size"] = self.test_size
         return config
 
-    def get_cv(self) -> BaseCrossValidator:
+    def get_cv_and_groups(self, X: pd.DataFrame) -> Tuple[BaseCrossValidator, Optional[np.ndarray]]:
         if self.cv_type == CVType.time_series:
-            return TimeSeriesSplit(n_splits=self.n_folds)
+            return TimeSeriesSplit(n_splits=self.n_folds), None
         elif self.cv_type == CVType.blocked_time_series:
-            return BlockedTimeSeriesSplit(n_splits=self.n_folds, test_size=self.test_size)
-        elif self.cv_type == CVType.group_k_fold and self.shuffle_kfold:
-            return GroupShuffleSplit(n_splits=self.n_folds, test_size=self.test_size, random_state=self.random_state)
-        elif self.cv_type == CVType.group_k_fold:
-            return GroupKFold(n_splits=self.n_folds)
+            return BlockedTimeSeriesSplit(n_splits=self.n_folds, test_size=self.test_size), None
+        elif self.cv_type == CVType.group_k_fold and self.group_columns:
+            groups = get_groups(X, self.group_columns)
+
+            if groups is None or np.unique(groups).size < self.n_folds:
+                return KFold(n_splits=self.n_folds, shuffle=self.shuffle_kfold, random_state=self.random_state), None
+
+            if self.shuffle_kfold:
+                return (
+                    GroupShuffleSplit(n_splits=self.n_folds, test_size=self.test_size, random_state=self.random_state),
+                    groups,
+                )
+            else:
+                return GroupKFold(n_splits=self.n_folds), groups
         else:
-            return KFold(n_splits=self.n_folds, shuffle=self.shuffle_kfold, random_state=self.random_state)
+            return KFold(n_splits=self.n_folds, shuffle=self.shuffle_kfold, random_state=self.random_state), None
+
+
+def get_groups(X: pd.DataFrame, group_columns: Optional[List[str]]) -> Optional[np.ndarray]:
+    existing_group_columns = [c for c in group_columns if c in X.columns]
+    return (
+        None
+        if not group_columns
+        else reduce(
+            lambda left, right: left + "_" + right, [X[c].astype(str) for c in existing_group_columns]
+        ).factorize()[0]
+    )
 
 
 def is_constant(s, dropna=True) -> bool:

upgini/utils/datetime_utils.py

@@ -9,6 +9,7 @@ from dateutil.relativedelta import relativedelta
 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"]
 
@@ -18,7 +19,13 @@ DATETIME_PATTERN = r"^[\d\s\.\-:T]+$"
 class DateTimeSearchKeyConverter:
     DATETIME_COL = "_date_time"
 
-    def __init__(self, date_column: str, date_format: Optional[str] = None, logger: Optional[logging.Logger] = None):
+    def __init__(
+        self,
+        date_column: str,
+        date_format: Optional[str] = None,
+        logger: Optional[logging.Logger] = None,
+        bundle: ResourceBundle = None,
+    ):
         self.date_column = date_column
         self.date_format = date_format
         if logger is not None:
@@ -27,6 +34,7 @@ class DateTimeSearchKeyConverter:
             self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
         self.generated_features: List[str] = []
+        self.bundle = bundle or get_custom_bundle()
 
     @staticmethod
     def _int_to_opt(i: int) -> Optional[int]:
@@ -71,10 +79,10 @@ class DateTimeSearchKeyConverter:
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="us")
             elif df[self.date_column].apply(lambda x: 10**11 < x < 10**14).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="ms")
-            elif df[self.date_column].apply(lambda x: 0 < x < 10*11).all():
+            elif df[self.date_column].apply(lambda x: 0 < x < 10 * 11).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="s")
             else:
-                msg = f"Unsupported type of date column {self.date_column}. Convert to datetime please."
+                msg = self.bundle.get("unsupported_date_type").format(self.date_column)
                 self.logger.warning(msg)
                 raise ValidationError(msg)
 
@@ -121,10 +129,7 @@ class DateTimeSearchKeyConverter:
                     return pd.to_datetime(df[self.date_column], format=date_format)
                 except ValueError:
                     pass
-            raise ValidationError(
-                f"Failed to parse date in column `{self.date_column}`. "
-                "Try to pass explicit date format in date_format argument of FeaturesEnricher constructor"
-            )
+            raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
 
 
 def is_time_series(df: pd.DataFrame, date_col: str) -> bool:

upgini/utils/deduplicate_utils.py

@@ -4,13 +4,18 @@ from typing import Dict, List, Optional, Tuple, Union
 import pandas as pd
 
 from upgini.metadata import SYSTEM_RECORD_ID, TARGET, ModelTaskType, SearchKey
-from upgini.resource_bundle import bundle
+from upgini.resource_bundle import ResourceBundle
 from upgini.utils.datetime_utils import DateTimeSearchKeyConverter
 from upgini.utils.target_utils import define_task
 
 
 def remove_fintech_duplicates(
-    df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: Optional[Logger] = None, silent=False
+    df: pd.DataFrame,
+    search_keys: Dict[str, SearchKey],
+    date_format: Optional[str] = None,
+    logger: Optional[Logger] = None,
+    silent=False,
+    bundle: ResourceBundle = None,
 ) -> Tuple[bool, pd.DataFrame]:
     # Base checks
     need_full_deduplication = True
@@ -72,7 +77,7 @@ def remove_fintech_duplicates(
     nonunique_target_rows = nonunique_target_groups[nonunique_target_groups].reset_index().drop(columns=TARGET)
     sub_df = pd.merge(sub_df, nonunique_target_rows, on=personal_cols)
 
-    sub_df = DateTimeSearchKeyConverter(date_col).convert(sub_df)
+    sub_df = DateTimeSearchKeyConverter(date_col, date_format=date_format, logger=logger, bundle=bundle).convert(sub_df)
     grouped_by_personal_cols = sub_df.groupby(personal_cols, group_keys=False)
     rows_with_diff_target = grouped_by_personal_cols.filter(has_diff_target_within_60_days)
     if len(rows_with_diff_target) > 0:
@@ -95,7 +100,7 @@ def remove_fintech_duplicates(
 
 
 def clean_full_duplicates(
-    df: pd.DataFrame, logger: Optional[Logger] = None, silent=False
+    df: pd.DataFrame, logger: Optional[Logger] = None, silent=False, bundle: ResourceBundle = None
 ) -> pd.DataFrame:
     nrows = len(df)
     if nrows == 0:

{upgini-1.1.246a101.dist-info → upgini-1.1.248a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.246a101
+Version: 1.1.248a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.246a101.dist-info → upgini-1.1.248a1.dist-info}/RECORD

@@ -1,11 +1,11 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=AsDJmEfVvdnBrIXQ2DSjitnTQ-5uu1H59YkhjhBRXcw,50424
+upgini/dataset.py,sha256=8TE_NKdhNeL3mlU-S57bHFub4G0gmyOGtceqO-CRaMk,50436
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=mQPM2dbUh-V_HHISFKmT49irNMv1PcLlpUk5HByHhfI,167889
+upgini/features_enricher.py,sha256=xoaG_cEhQJciYHHE-UkjdkprfThNnxGRe9YvT0NVnoI,168617
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=eSG4gOpmCGlXmB6KIPNzAG8tRZNUjyYpMeUeHw_2li4,42264
-upgini/metadata.py,sha256=55t0uQI910tzTcnwxZCUL1413BhTiSm8oqiwp-94NyA,9613
+upgini/metadata.py,sha256=5SQjDsQrfpGKT42i0H40C6wxTY_up94xSqAARH140_U,9637
 upgini/metrics.py,sha256=LS2MgEKgmn9VEXsKzxv3pBZ-q71mTnpWu6vL8fYgpo4,26727
 upgini/search_task.py,sha256=5n4qGJmtu48s0-FHAtF3L5qVLMd1JVW3FJlM8dFbh-s,17063
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
@@ -17,8 +17,8 @@ upgini/autofe/all_operands.py,sha256=du44N6ISWe3ikb0y9ZzSOHNbLiyEYrJPwoBo0Z6xp2s
 upgini/autofe/binary.py,sha256=f8LQqZi9zyaMUAv-jASMmWNA_vT05ncYCjZq0qx3USs,3972
 upgini/autofe/feature.py,sha256=xeqTq35-BX4KCt0xAkk3UZAGzV5VyjorV5AdNdA5yLs,11851
 upgini/autofe/groupby.py,sha256=iXRfOmOc84ooSzRhsh9GmmG7rTafX0-ekXko8s9Qs68,3089
-upgini/autofe/operand.py,sha256=GpSx-nL2XKnTJ7kvRr_SIFoUMchqYian6SftJ82zsN4,2719
-upgini/autofe/unary.py,sha256=WB-Ovwaz2a-Jscpshg1Om7Ttx6DJ6gQ_fgqtXx_UHuw,2845
+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=PeotNz-taBT6aweQc9xc_pdtUOqmqe1IZr1-3NeUsd0,14008
@@ -28,8 +28,8 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 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=0qDpfZBMU4moFXKzb11ALwk5N8FdgyJYzI0wRTvFJbI,25008
-upgini/resource_bundle/strings_widget.properties,sha256=IjPHslEk_fx95Phz3NV9PhVYxqexJgAV9xvZoRPvURc,1433
+upgini/resource_bundle/strings.properties,sha256=dmkObOr0FJPkGQmiybmFcI3RbYjl_uCz_IQ4nm8SRkk,25242
+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
 upgini/sampler/random_under_sampler.py,sha256=XU4c2swPIFxVXHOPpxgM2bUao0Xm-aoMmd6fKjIuV5s,4068
@@ -39,9 +39,9 @@ upgini/utils/base_search_key_detector.py,sha256=DGwhXLvc8i5VZWMDr0rncFfV5GEHdsCS
 upgini/utils/blocked_time_series.py,sha256=dMz5ewk3PsoeOrc3lDzInCVPS9u_2XQkV0W6PuMMjPg,3380
 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=6pSSL_Ft_8C6n6aInJeiyeSBD7McjsMxKZpHqSBV0uY,2491
-upgini/utils/datetime_utils.py,sha256=awsLpnFjBNcrsCDyyiiJLicHgHiGCNAwi0UOwRKGD7s,8645
-upgini/utils/deduplicate_utils.py,sha256=qRmytTgheYM6OfLnURrmdkZVN02vvZXL5bm0Yob3svk,5995
+upgini/utils/cv_utils.py,sha256=Tn01RJvpZGZh0PUQUimlBkV-AXwe7s6yjCNFtw352Uc,3525
+upgini/utils/datetime_utils.py,sha256=P5no4mFgYpEP6oY524ebTKvKc3TBMJzAYpWdj210_Fw,8699
+upgini/utils/deduplicate_utils.py,sha256=GRPwD8bXZNspKvf19W3SrYjqg1qQMDlZD-BDkHnKYyo,6176
 upgini/utils/display_utils.py,sha256=tiq5sFOfMwkKCjQ7OGdyK_twe0Qdr9F3mzkW1QXSDog,10664
 upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
@@ -55,8 +55,8 @@ upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,4
 upgini/utils/target_utils.py,sha256=DH812qcZ7Pvf9WVVb33fbwQjb1W9h1hXRNCCiG7Y6tI,2563
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.246a101.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.246a101.dist-info/METADATA,sha256=VfuzobkBVkcJyRz_DEihRaROyfGPYnczR537L6mx2GU,48210
-upgini-1.1.246a101.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-upgini-1.1.246a101.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.246a101.dist-info/RECORD,,
+upgini-1.1.248a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.248a1.dist-info/METADATA,sha256=leV6Cyrr3xf01Jd34x-1asI-e4rk2bjDPJvdUsaagNg,48208
+upgini-1.1.248a1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+upgini-1.1.248a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.248a1.dist-info/RECORD,,