upgini 1.1.275__py3-none-any.whl → 1.1.275a1__py3-none-any.whl

upgini/metadata.py

@@ -4,6 +4,8 @@ from typing import Dict, List, Optional, Set
 from pydantic import BaseModel
 
 SYSTEM_RECORD_ID = "system_record_id"
+ENTITY_SYSTEM_RECORD_ID = "entity_system_record_id"
+SEARCH_KEY_UNNEST = "search_key_unnest"
 SORT_ID = "sort_id"
 EVAL_SET_INDEX = "eval_set_index"
 TARGET = "target"
@@ -11,7 +13,7 @@ COUNTRY = "country_iso_code"
 RENAMED_INDEX = "index_col"
 DEFAULT_INDEX = "index"
 ORIGINAL_INDEX = "original_index"
-SYSTEM_COLUMNS = {SYSTEM_RECORD_ID, EVAL_SET_INDEX, TARGET, COUNTRY, SORT_ID}
+SYSTEM_COLUMNS = {SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST, EVAL_SET_INDEX, TARGET, COUNTRY}
 
 
 class FileColumnMeaningType(Enum):
@@ -37,6 +39,8 @@ class FileColumnMeaningType(Enum):
     POSTAL_CODE = "POSTAL_CODE"
     SYSTEM_RECORD_ID = "SYSTEM_RECORD_ID"
     EVAL_SET_INDEX = "EVAL_SET_INDEX"
+    ENTITY_SYSTEM_RECORD_ID = "ENTITY_SYSTEM_RECORD_ID"
+    UNNEST_KEY = "UNNEST_KEY"
 
 
 class SearchKey(Enum):
@@ -182,6 +186,10 @@ class FileColumnMetadata(BaseModel):
     meaningType: FileColumnMeaningType
     minMaxValues: Optional[NumericInterval] = None
     originalName: Optional[str]
+    # is this column contains keys from multiple key columns like msisdn1, msisdn2
+    isUnnest: bool = False,
+    # list of original etalon key column names like msisdn1, msisdn2
+    unnestKeyNames: Optional[list[str]]
 
 
 class FileMetadata(BaseModel):

upgini/metrics.py

@@ -1,4 +1,3 @@
-import inspect
 import logging
 import re
 from copy import deepcopy
@@ -382,11 +381,6 @@ class EstimatorWrapper:
             kwargs["estimator"] = estimator_copy
             if isinstance(estimator, CatBoostClassifier) or isinstance(estimator, CatBoostRegressor):
                 if cat_features is not None:
-                    for cat_feature in cat_features:
-                        if cat_feature not in X.columns:
-                            logger.error(
-                                f"Client cat_feature `{cat_feature}` not found in X columns: {X.columns.to_list()}"
-                            )
                     estimator_copy.set_params(
                         cat_features=[X.columns.get_loc(cat_feature) for cat_feature in cat_features]
                     )
@@ -653,12 +647,6 @@ class OtherEstimatorWrapper(EstimatorWrapper):
 def validate_scoring_argument(scoring: Union[Callable, str, None]):
     if isinstance(scoring, str) and scoring is not None:
         _get_scorer_by_name(scoring)
-    elif isinstance(scoring, Callable):
-        spec = inspect.getfullargspec(scoring)
-        if len(spec.args) < 3:
-            raise ValidationError(
-                f"Invalid scoring function passed {scoring}. It should accept 3 input arguments: estimator, X, y"
-            )
 
 
 def _get_scorer_by_name(scoring: str) -> Tuple[Callable, str, int]:

upgini/normalizer/phone_normalizer.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 import pandas as pd
-from pandas.api.types import is_float_dtype, is_int64_dtype, is_string_dtype, is_object_dtype
+from pandas.api.types import is_float_dtype, is_int64_dtype, is_string_dtype
 
 from upgini.errors import ValidationError
 
@@ -44,7 +44,7 @@ class PhoneNormalizer:
         Method will remove all non numeric chars from string and convert it to int.
         None will be set for phone numbers that couldn"t be converted to int
         """
-        if is_string_dtype(self.df[self.phone_column_name]) or is_object_dtype(self.df[self.phone_column_name]):
+        if is_string_dtype(self.df[self.phone_column_name]):
             convert_func = self.phone_str_to_int_safe
         elif is_float_dtype(self.df[self.phone_column_name]):
             convert_func = self.phone_float_to_int_safe

upgini/resource_bundle/strings.properties

@@ -38,7 +38,6 @@ loss_selection_warn=\nWARNING: Loss `{0}` is not supported for feature selection
 loss_calc_metrics_warn=\nWARNING: Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=\nWARNING: Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
 group_k_fold_in_classification=\nWARNING: Using group K-fold cross-validation split for classification task.
-current_date_added=\nWARNING: No date/datetime column was detected in X to be used as a search key. The current date will be used to match the latest version of data sources
 
 # Errors
 failed_search_by_task_id=Failed to retrieve the specified search results
@@ -88,6 +87,7 @@ unsupported_search_key_type=Unsupported type of key in search_keys: {}
 search_key_country_and_country_code=\nWARNING: SearchKey.COUNTRY and country_code parameter were passed simultaniously. Parameter country_code will be ignored
 empty_search_key=Search key {} is empty. Please fill values or remove this search key
 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_multi_key=Search key {} cannot be used multiple times
 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
@@ -159,7 +159,7 @@ dataset_invalid_multiclass_target=Unexpected dtype of target for multiclass task
 dataset_invalid_regression_target=Unexpected dtype of target for regression task type: {}. Expected float
 dataset_invalid_timeseries_target=Unexpected dtype of target for timeseries task type: {}. Expected float
 dataset_to_many_multiclass_targets=The number of target classes {} exceeds the allowed threshold: {}. Please, correct your data and try again
-dataset_rarest_class_less_min=Count of rows with the rarest class `{}` is {}, minimum count must be > {} for each class\nPlease, remove rows with rarest class from your dataframe
+dataset_rarest_class_less_min=Frequency of the rarest class `{}` is {}, minimum frequency must be > {} for each class\nPlease, remove rows with rarest class from your dataframe
 dataset_rarest_class_less_threshold=\nWARNING: Target is imbalanced and will be undersampled to the rarest class. Frequency of the rarest class `{}` is {}\nMinimum number of observations for each class to avoid undersampling {} ({}%)
 dataset_date_features=\nWARNING: Columns {} is a datetime or period type but not used as a search key, removed from X
 dataset_too_many_features=Too many features. Maximum number of features is {}

upgini/utils/__init__.py

@@ -2,7 +2,7 @@ import itertools
 from typing import List, Tuple
 
 import pandas as pd
-from pandas.api.types import is_string_dtype, is_object_dtype
+from pandas.api.types import is_string_dtype
 
 
 def combine_search_keys(search_keys: List[str]) -> List[Tuple[str]]:
@@ -20,6 +20,5 @@ def find_numbers_with_decimal_comma(df: pd.DataFrame) -> pd.DataFrame:
     return [
         col
         for col in tmp.columns
-        if (is_string_dtype(tmp[col]) or is_object_dtype(tmp[col]))
-        and tmp[col].astype("string").str.match("^[0-9]+,[0-9]*$").any()
+        if is_string_dtype(tmp[col]) and tmp[col].astype("string").str.match("^[0-9]+,[0-9]*$").any()
     ]

upgini/utils/base_search_key_detector.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import List
 
 import pandas as pd
 
@@ -10,16 +10,18 @@ class BaseSearchKeyDetector:
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
         raise NotImplementedError()
 
-    def _get_search_key_by_name(self, column_names: List[str]) -> Optional[str]:
-        for column_name in column_names:
-            if self._is_search_key_by_name(column_name):
-                return column_name
+    def _get_search_keys_by_name(self, column_names: List[str]) -> List[str]:
+        return [
+            column_name
+            for column_name in column_names
+            if self._is_search_key_by_name(column_name)
+        ]
 
-    def get_search_key_column(self, df: pd.DataFrame) -> Optional[str]:
-        maybe_column = self._get_search_key_by_name(df.columns.to_list())
-        if maybe_column is not None:
-            return maybe_column
-
-        for column_name in df.columns:
+    def get_search_key_columns(self, df: pd.DataFrame, existing_search_keys: List[str]) -> List[str]:
+        other_columns = [col for col in df.columns if col not in existing_search_keys]
+        columns_by_names = self._get_search_keys_by_name(other_columns)
+        columns_by_values = []
+        for column_name in other_columns:
             if self._is_search_key_by_values(df[column_name]):
-                return column_name
+                columns_by_values.append(column_name)
+        return list(set(columns_by_names + columns_by_values))

upgini/utils/country_utils.py

@@ -1,5 +1,5 @@
 import pandas as pd
-from pandas.api.types import is_string_dtype, is_object_dtype
+from pandas.api.types import is_string_dtype
 
 from upgini.utils.base_search_key_detector import BaseSearchKeyDetector
 
@@ -9,7 +9,7 @@ class CountrySearchKeyDetector(BaseSearchKeyDetector):
         return "country" in str(column_name).lower()
 
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
-        if not is_string_dtype(column) and not is_object_dtype(column):
+        if not is_string_dtype(column):
             return False
 
         all_count = len(column)

upgini/utils/datetime_utils.py

@@ -6,10 +6,7 @@ from typing import Dict, List, Optional
 import numpy as np
 import pandas as pd
 from dateutil.relativedelta import relativedelta
-from pandas.api.types import (
-    is_numeric_dtype,
-    is_period_dtype,
-)
+from pandas.api.types import is_numeric_dtype, is_period_dtype, is_string_dtype
 
 from upgini.errors import ValidationError
 from upgini.metadata import SearchKey
@@ -81,6 +78,9 @@ class DateTimeSearchKeyConverter:
             df[self.date_column] = df[self.date_column].apply(lambda x: x.replace(tzinfo=None))
         elif isinstance(df[self.date_column].values[0], datetime.date):
             df[self.date_column] = pd.to_datetime(df[self.date_column], errors="coerce")
+        elif is_string_dtype(df[self.date_column]):
+            df[self.date_column] = df[self.date_column].apply(self.clean_date)
+            df[self.date_column] = self.parse_date(df)
         elif is_period_dtype(df[self.date_column]):
             df[self.date_column] = pd.to_datetime(df[self.date_column].astype("string"))
         elif is_numeric_dtype(df[self.date_column]):
@@ -100,9 +100,6 @@ class DateTimeSearchKeyConverter:
                 msg = self.bundle.get("unsupported_date_type").format(self.date_column)
                 self.logger.warning(msg)
                 raise ValidationError(msg)
-        else:
-            df[self.date_column] = df[self.date_column].astype("string").apply(self.clean_date)
-            df[self.date_column] = self.parse_date(df)
 
         # If column with date is datetime then extract seconds of the day and minute of the hour
         # as additional features

upgini/utils/deduplicate_utils.py

@@ -3,7 +3,15 @@ from typing import Dict, List, Optional, Union
 
 import pandas as pd
 
-from upgini.metadata import EVAL_SET_INDEX, SORT_ID, SYSTEM_RECORD_ID, TARGET, ModelTaskType, SearchKey
+from upgini.metadata import (
+    ENTITY_SYSTEM_RECORD_ID,
+    EVAL_SET_INDEX,
+    SORT_ID,
+    SYSTEM_RECORD_ID,
+    TARGET,
+    ModelTaskType,
+    SearchKey,
+)
 from upgini.resource_bundle import ResourceBundle
 from upgini.utils.datetime_utils import DateTimeSearchKeyConverter
 from upgini.utils.target_utils import define_task
@@ -143,6 +151,8 @@ def clean_full_duplicates(
     unique_columns = df.columns.tolist()
     if SYSTEM_RECORD_ID in unique_columns:
         unique_columns.remove(SYSTEM_RECORD_ID)
+    if ENTITY_SYSTEM_RECORD_ID in unique_columns:
+        unique_columns.remove(ENTITY_SYSTEM_RECORD_ID)
     if SORT_ID in unique_columns:
         unique_columns.remove(SORT_ID)
     if EVAL_SET_INDEX in unique_columns:

upgini/utils/email_utils.py

@@ -4,7 +4,7 @@ from hashlib import sha256
 from typing import Dict, List, Optional
 
 import pandas as pd
-from pandas.api.types import is_string_dtype, is_object_dtype
+from pandas.api.types import is_string_dtype
 from upgini.resource_bundle import bundle
 
 from upgini.metadata import SearchKey
@@ -18,7 +18,7 @@ class EmailSearchKeyDetector(BaseSearchKeyDetector):
         return str(column_name).lower() in ["email", "e_mail", "e-mail"]
 
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
-        if not is_string_dtype(column) and not is_object_dtype:
+        if not is_string_dtype(column):
             return False
         if not column.astype("string").str.contains("@").any():
             return False
@@ -38,11 +38,13 @@ class EmailSearchKeyConverter:
         email_column: str,
         hem_column: Optional[str],
         search_keys: Dict[str, SearchKey],
+        unnest_search_keys: Optional[List[str]] = None,
         logger: Optional[logging.Logger] = None,
     ):
         self.email_column = email_column
         self.hem_column = hem_column
         self.search_keys = search_keys
+        self.unnest_search_keys = unnest_search_keys
         if logger is not None:
             self.logger = logger
         else:
@@ -80,9 +82,12 @@ class EmailSearchKeyConverter:
                 del self.search_keys[self.email_column]
                 return df
             self.search_keys[self.HEM_COLUMN_NAME] = SearchKey.HEM
+            self.unnest_search_keys.append(self.HEM_COLUMN_NAME)
             self.email_converted_to_hem = True
 
         del self.search_keys[self.email_column]
+        if self.email_column in self.unnest_search_keys:
+            self.unnest_search_keys.remove(self.email_column)
 
         df[self.EMAIL_ONE_DOMAIN_COLUMN_NAME] = df[self.email_column].apply(self._email_to_one_domain)
 

upgini/utils/features_validator.py

@@ -81,8 +81,7 @@ class FeaturesValidator:
         return [
             i
             for i in df
-            if (is_object_dtype(df[i]) or is_string_dtype(df[i]) or is_integer_dtype(df[i]))
-            and (df[i].nunique(dropna=False) / row_count >= 0.85)
+            if (is_string_dtype(df[i]) or is_integer_dtype(df[i])) and (df[i].nunique(dropna=False) / row_count >= 0.95)
         ]
 
     @staticmethod

upgini/utils/target_utils.py

@@ -107,7 +107,7 @@ def balance_undersample(
     min_class_count = vc[min_class_value]
 
     min_class_percent = imbalance_threshold / target_classes_count
-    min_class_threshold = int(min_class_percent * count)
+    min_class_threshold = min_class_percent * count
 
     resampled_data = df
     df = df.copy().sort_values(by=SYSTEM_RECORD_ID)

upgini/utils/track_info.py

@@ -55,7 +55,7 @@ def _get_execution_ide() -> str:
 def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optional[str] = None) -> dict:
     # default values
     track = {"ide": _get_execution_ide()}
-    ident_res = "https://api64.ipify.org"
+    ident_res = "https://api.ipify.org"
 
     try:
         track["hostname"] = socket.gethostname()
@@ -74,20 +74,17 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
             display(
                 Javascript(
                     """
-                    async function getVisitorId() {
-                        return import('https://upgini.github.io/upgini/js/a.js')
+                        import('https://upgini.github.io/upgini/js/a.js')
                             .then(FingerprintJS => FingerprintJS.load())
                             .then(fp => fp.get())
-                            .then(result => result.visitorId);
-                    }
+                            .then(result => window.visitorId = result.visitorId);
                     """
                 )
             )
-            track["visitorId"] = output.eval_js("getVisitorId()", timeout_sec=30)
+            track["visitorId"] = output.eval_js("window.visitorId", timeout_sec=10)
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["visitorId"] = "None"
         if client_ip:
             track["ip"] = client_ip
         else:
@@ -98,19 +95,16 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 display(
                     Javascript(
                         f"""
-                        async function getIP() {{
-                            return fetch("{ident_res}")
+                            fetch("{ident_res}")
                                 .then(response => response.text())
-                                .then(data => data);
-                        }}
+                                .then(data => window.clientIP = data);
                         """
                     )
                 )
-                track["ip"] = output.eval_js("getIP()", timeout_sec=10)
+                track["ip"] = output.eval_js("window.clientIP", timeout_sec=10)
             except Exception as e:
                 track["err"] = str(e)
-                if "ip" not in track:
-                    track["ip"] = "0.0.0.0"
+                track["ip"] = "0.0.0.0"
 
     elif track["ide"] == "binder":
         try:
@@ -122,10 +116,8 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 track["visitorId"] = sha256(os.environ["CLIENT_IP"].encode()).hexdigest()
         except Exception as e:
             track["err"] = str(e)
-            if "ip" not in track:
-                track["ip"] = "0.0.0.0"
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["ip"] = "0.0.0.0"
+            track["visitorId"] = "None"
 
     elif track["ide"] == "kaggle":
         try:
@@ -144,8 +136,8 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                     raise Exception(err)
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["ip"] = "0.0.0.0"
+            track["visitorId"] = "None"
     else:
         try:
             if client_ip:
@@ -158,9 +150,5 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 track["visitorId"] = sha256(str(getnode()).encode()).hexdigest()
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
-            if "ip" not in track:
-                track["ip"] = "0.0.0.0"
 
     return track

{upgini-1.1.275.dist-info → upgini-1.1.275a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.275
+Version: 1.1.275a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -28,7 +28,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: python-dateutil >=2.8.0
 Requires-Dist: requests >=2.8.0
-Requires-Dist: pandas <3.0.0,>=1.1.0
+Requires-Dist: pandas <2.0.0,>=1.1.0
 Requires-Dist: numpy >=1.19.0
 Requires-Dist: scikit-learn >=1.3.0
 Requires-Dist: pydantic <2.0.0,>=1.8.2

{upgini-1.1.275.dist-info → upgini-1.1.275a1.dist-info}/RECORD

@@ -1,12 +1,12 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
-upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=HwL2syoMf3F9k9SmsJJMhhqnAddZcx28RZ1aYam7Lhs,45665
+upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
+upgini/dataset.py,sha256=g10BnbayclZMno9mAabpz_Zu0iyMiW0f_jOwt_xJr8U,45947
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=XKN-SdzX5EHKJHiPWvmEGDiCy6iK2ZaNPw75DYfcev0,176176
+upgini/features_enricher.py,sha256=CgUBRCPW_itgBfaup3Tg_yfPYMbQpufoOqu4yYvn6VU,179316
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
-upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
-upgini/metrics.py,sha256=tGzdn0jgup86OlH_GS4eoza8ZJZ9wgaJr7SaX3Upwzo,29652
+upgini/metadata.py,sha256=FFwTnoMxdJ-7oKXbRgght1yk7e2u90WpeqljKDWUj18,10106
+upgini/metrics.py,sha256=VmxVc-plbRPZ1U3Ve3E-FZkhYqi0X2r7x8H5L-shux4,29058
 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
@@ -15,49 +15,49 @@ upgini/ads_management/ads_manager.py,sha256=fP4Yqx3h2Snw5X335TbXEwFoupq1RYsE7y0P
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operands.py,sha256=H66wqVLD-H9k8A4-q2wslhV9QaNxlb49f8YiT0Xfkps,2356
 upgini/autofe/binary.py,sha256=f8LQqZi9zyaMUAv-jASMmWNA_vT05ncYCjZq0qx3USs,3972
-upgini/autofe/date.py,sha256=408p8P2OTPM2D3LsEGGtaiCepKGgM1BbOCQNRzAmI6c,4223
+upgini/autofe/date.py,sha256=cc0GMAJR0QZOI_Qp2V5UDklaXLNS_79O1GhU6GlOYzg,3895
 upgini/autofe/feature.py,sha256=2FQRGtIumNz60hFAjfLReaY18SI7HxzYZOoC5avzSjQ,11847
 upgini/autofe/groupby.py,sha256=iXRfOmOc84ooSzRhsh9GmmG7rTafX0-ekXko8s9Qs68,3089
 upgini/autofe/operand.py,sha256=dhtToPDGWtP_0u_RjayUpezJJZAgq_TzNbPH0bI9OXI,2805
 upgini/autofe/unary.py,sha256=YRTzQLttbDdOnkogWBPnBexpu7uHWSLSFAxSCu3iFdY,3145
 upgini/autofe/vector.py,sha256=5qhI_bdwaWM1l7fgCkx1tMt9R9gxWzoYCl-7WO4KiOs,604
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=taRzyGgrPrTTSGw4Y-Ca5k4bf30aiTa68rxqT9zfqeI,16478
+upgini/data_source/data_source_publisher.py,sha256=J2lrpPuysUHPeqTSfoybBtPRTBCFu7R5KzaakhjaRDc,16485
 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=_SYMX4GTgwzRXArK54Jp3vUBE5d4jZxSVyze-0tqzg0,9996
+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=1O779a0-Ai0j7W-Z5AznvjuV69YkJvgGhJda-6VMLOQ,26287
+upgini/resource_bundle/strings.properties,sha256=AK5xktWWYa0smEa_ZVT7BFlXPSx7M_NTMIfXhgsnE2Y,26177
 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
 upgini/sampler/utils.py,sha256=PYOk3kKSnFlyxcpdtDNLBEEhTB4lO_iP7pQHqeUcmAc,20211
-upgini/utils/__init__.py,sha256=YVum3lRKpyfqoJy_7HJyU6SmIgbmG8QLkHIpibE_ud8,842
-upgini/utils/base_search_key_detector.py,sha256=DGwhXLvc8i5VZWMDr0rncFfV5GEHdsCSnLGon_W9TPs,859
+upgini/utils/__init__.py,sha256=dQ4-s8-sZ5eOBZ-mH3gEwDHTdI0wI1bUAVgVqUKKPx4,786
+upgini/utils/base_search_key_detector.py,sha256=VvEdamjJT1wypsH6NAfOkPp7dHo7nxhl7LhwX7Z9N5w,1025
 upgini/utils/blocked_time_series.py,sha256=dMz5ewk3PsoeOrc3lDzInCVPS9u_2XQkV0W6PuMMjPg,3380
-upgini/utils/country_utils.py,sha256=pV8TBURthYqwSOfH1lxfYc2blm3OvfLFCMvRv8rKTp4,6511
+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=_mfhWb5ogEThvanQ-py1Lb6VvUvF2vT20tQgNprNz6o,10321
-upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
+upgini/utils/datetime_utils.py,sha256=4ii5WphAHlb_NRmdJx35VZpTarJbAr-AnDw3XSzUSow,10346
+upgini/utils/deduplicate_utils.py,sha256=Zvs7zW4QzaERQmJNPrTVf2ZTVBkBLOycFCzyMwtXuV8,8770
 upgini/utils/display_utils.py,sha256=LKoSwjrE0xgS5_cqVhc2og2CQ1UCZ1nTI2VKboIhoQA,10858
-upgini/utils/email_utils.py,sha256=R9bVOfbS-oVkA8PdwZfQBxm7B4mQlRtkwqx2cf6zPCY,3520
+upgini/utils/email_utils.py,sha256=0EPCxMU-huzTgb_vySiAQ8tmSUhS31Mz2BpaHGwwYO4,3772
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
-upgini/utils/features_validator.py,sha256=PgKNt5dyqfErTvjtRNNUS9g7GFqHBtAtnsfA-V5UO1A,3307
+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
 upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3x_zs,409
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
 upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,44014
-upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
-upgini/utils/track_info.py,sha256=p8gmuHhLamZF5JG7K9DeK-PcytQhlFCR29lyRr-wq_U,5665
+upgini/utils/target_utils.py,sha256=9K67tkY7LWhQMO-vbbPqBaO-KriAmg_6fVz5RQRaLQc,7802
+upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.275.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.275.dist-info/METADATA,sha256=6RZCJLAqN3qIrXOvyAaQIr75-TZw4NcLkp5yXS637ls,48156
-upgini-1.1.275.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.275.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.275.dist-info/RECORD,,
+upgini-1.1.275a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.275a1.dist-info/METADATA,sha256=ocZUhdmjsYXKoCXt0W3M4gfPGQ8UlFtQlYIjdD_6_w0,48158
+upgini-1.1.275a1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.275a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.275a1.dist-info/RECORD,,