upgini 1.1.274a3388.post2__py3-none-any.whl → 1.1.275a1__py3-none-any.whl

upgini/autofe/date.py

@@ -1,9 +1,9 @@
-from typing import Any, List, Optional, Union
+from typing import Any, Optional, Union
 import numpy as np
 import pandas as pd
 from pydantic import BaseModel
 
-from upgini.autofe.operand import MultiOperand, Operand, PandasOperand
+from upgini.autofe.operand import PandasOperand
 
 
 class DateDiffMixin(BaseModel):
@@ -24,7 +24,6 @@ class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
     is_binary = True
     has_symmetry_importance = True
-    common_type = "date_diff"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
@@ -40,7 +39,6 @@ class DateDiffType2(PandasOperand, DateDiffMixin):
     name = "date_diff_type2"
     is_binary = True
     has_symmetry_importance = True
-    common_type = "date_diff"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
@@ -62,7 +60,6 @@ class DateListDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
     aggregation: str
-    common_type = "date_diff_list"
 
     def __init__(self, **data: Any) -> None:
         if "name" not in data:
@@ -89,9 +86,6 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
         return method(x) if len(x) > 0 else default
 
-    def make_multi_operand(self, operands: List[Operand]) -> Optional[MultiOperand]:
-        return DateListDiffMulti(children=operands, aggregation="")
-
 
 class DateListDiffBounded(DateListDiff):
     lower_bound: Optional[int]
@@ -114,12 +108,3 @@ class DateListDiffBounded(DateListDiff):
     def _agg(self, x):
         x = x[(x >= (self.lower_bound or -np.inf)) & (x < (self.upper_bound or np.inf))]
         return super()._agg(x)
-
-
-class DateListDiffMulti(DateListDiff, MultiOperand):
-    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        left = self._convert_to_date(left, self.left_unit)
-        right = right.apply(lambda x: pd.arrays.DatetimeArray(self._convert_to_date(x, self.right_unit)))
-
-        diff = pd.Series(left - right.values).apply(self._diff)
-        return diff.apply(lambda x: [c._agg(x) for c in self.children])

upgini/autofe/feature.py

@@ -1,15 +1,13 @@
 import hashlib
 import itertools
-import operator
 from typing import Dict, List, Optional, Tuple, Union
 
-from more_itertools import map_reduce
 import numpy as np
 import pandas as pd
 from pandas._typing import DtypeObj
 
 from upgini.autofe.all_operands import find_op
-from upgini.autofe.operand import MultiOperand, Operand, PandasOperand
+from upgini.autofe.operand import Operand, PandasOperand
 
 
 class Column:
@@ -31,9 +29,6 @@ class Column:
         else:
             return feature_name[2:last_component_idx]
 
-    def get_display_name(self, **kwargs):
-        return self.name
-
     def delete_data(self):
         self.data = None
 
@@ -162,8 +157,6 @@ class Feature:
         else:
             new_data = new_data.replace([-np.inf, np.inf], np.nan)
 
-        new_data = new_data.rename(self.get_display_name())
-
         if is_root:
             self.data = new_data
         return new_data
@@ -333,65 +326,3 @@ class FeatureGroup:
             self.main_column_node.delete_data()
         for child in self.children:
             child.delete_data()
-
-
-class OperandGroup:
-    def __init__(self, operand: MultiOperand, children: List[Union[Column, Feature]]):
-        self.op = operand
-        self.children = children
-        self.data: Optional[pd.DataFrame] = None
-
-    def get_columns(self, **kwargs) -> List[str]:
-        column_list = []
-        seen = set()
-        for child in self.children:
-            columns = child.get_columns(**kwargs)
-            column_list.extend([f for f in columns if f not in seen])
-            seen.update(columns)
-        return column_list
-
-    def get_display_names(self, **kwargs) -> List[str]:
-        names = [Feature(op, self.children).get_display_name(**kwargs) for op in self.op.children]
-        return names
-
-    def calculate(self, data: pd.DataFrame, is_root=False) -> pd.DataFrame:
-        if isinstance(self.op, PandasOperand):
-            if self.op.is_vector:
-                ds = [child.calculate(data) for child in self.children]
-                new_data = self.op.calculate(data=ds)
-            else:
-                d1 = self.children[0].calculate(data)
-                d2 = None if len(self.children) < 2 else self.children[1].calculate(data)
-                new_data = self.op.calculate(data=d1, left=d1, right=d2)
-
-            new_data = pd.DataFrame(new_data.values.tolist())
-            new_data.columns = self.get_display_names()
-        else:
-            raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
-
-        if is_root:
-            self.data = new_data
-        return new_data
-
-    @staticmethod
-    def make_groups(candidates: List[Feature]) -> List[Union[Feature, "FeatureGroup"]]:
-        grouped_features = []
-
-        for _, features in sorted(
-            map_reduce(
-                candidates, lambda f: (f.op.common_type or "", ",".join([c.get_display_name() for c in f.children]))
-            ).items(),
-            key=operator.itemgetter(0),
-        ):
-            feature_list = list(features)
-            multi_op = feature_list[0].op.make_multi_operand([f.op for f in feature_list])
-            if multi_op is not None:
-                grouped_features.append(OperandGroup(multi_op, feature_list[0].children))
-            else:
-                grouped_features.extend(feature_list)
-        return grouped_features
-
-    def delete_data(self):
-        self.data = None
-        for child in self.children:
-            child.delete_data()

upgini/autofe/operand.py

@@ -5,9 +5,6 @@ import pandas as pd
 import numpy as np
 
 
-MAIN_COLUMN = "main_column"
-
-
 class Operand(BaseModel):
     name: str
     alias: Optional[str]
@@ -21,7 +18,6 @@ class Operand(BaseModel):
     is_binary: bool = False
     is_vector: bool = False
     is_distribution_dependent: bool = False
-    common_type: Optional[str] = None
     params: Optional[Dict[str, str]]
 
     def set_params(self, params: Dict[str, str]):
@@ -31,8 +27,8 @@ class Operand(BaseModel):
     def get_params(self) -> Dict[str, str]:
         return self.params
 
-    def make_multi_operand(self, operands: List["Operand"]) -> Optional["MultiOperand"]:
-        return None
+
+MAIN_COLUMN = "main_column"
 
 
 class PandasOperand(Operand, abc.ABC):
@@ -86,7 +82,3 @@ class VectorizableMixin(Operand):
         value_columns = [col for col in input_columns if col != group_column]
 
         return group_column, value_columns
-
-
-class MultiOperand(Operand):
-    children: List[Operand]

upgini/dataset.py

@@ -22,7 +22,9 @@ from pandas.api.types import (
 from upgini.errors import ValidationError
 from upgini.http import ProgressStage, SearchProgress, _RestClient
 from upgini.metadata import (
+    ENTITY_SYSTEM_RECORD_ID,
     EVAL_SET_INDEX,
+    SEARCH_KEY_UNNEST,
     SYSTEM_COLUMNS,
     SYSTEM_RECORD_ID,
     TARGET,
@@ -78,6 +80,7 @@ class Dataset:  # (pd.DataFrame):
         path: Optional[str] = None,
         meaning_types: Optional[Dict[str, FileColumnMeaningType]] = None,
         search_keys: Optional[List[Tuple[str, ...]]] = None,
+        unnest_search_keys: Optional[List[str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
@@ -112,6 +115,7 @@ class Dataset:  # (pd.DataFrame):
         self.description = description
         self.meaning_types = meaning_types
         self.search_keys = search_keys
+        self.unnest_search_keys = unnest_search_keys
         self.ignore_columns = []
         self.hierarchical_group_keys = []
         self.hierarchical_subgroup_keys = []
@@ -171,7 +175,7 @@ class Dataset:  # (pd.DataFrame):
         new_columns = []
         dup_counter = 0
         for column in self.data.columns:
-            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID]:
+            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]:
                 self.columns_renaming[column] = column
                 new_columns.append(column)
                 continue
@@ -352,7 +356,9 @@ class Dataset:  # (pd.DataFrame):
 
             if is_string_dtype(self.data[postal_code]):
                 try:
-                    self.data[postal_code] = self.data[postal_code].astype("float64").astype("Int64").astype("string")
+                    self.data[postal_code] = (
+                        self.data[postal_code].astype("string").astype("Float64").astype("Int64").astype("string")
+                    )
                 except Exception:
                     pass
             elif is_float_dtype(self.data[postal_code]):
@@ -802,6 +808,8 @@ class Dataset:  # (pd.DataFrame):
                     meaningType=meaning_type,
                     minMaxValues=min_max_values,
                 )
+                if self.unnest_search_keys and column_meta.originalName in self.unnest_search_keys:
+                    column_meta.isUnnest = True
 
                 columns.append(column_meta)
 

upgini/features_enricher.py

@@ -10,6 +10,7 @@ import sys
 import tempfile
 import time
 import uuid
+from collections import Counter
 from dataclasses import dataclass
 from threading import Thread
 from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
@@ -43,9 +44,11 @@ from upgini.mdc import MDC
 from upgini.metadata import (
     COUNTRY,
     DEFAULT_INDEX,
+    ENTITY_SYSTEM_RECORD_ID,
     EVAL_SET_INDEX,
     ORIGINAL_INDEX,
     RENAMED_INDEX,
+    SEARCH_KEY_UNNEST,
     SORT_ID,
     SYSTEM_RECORD_ID,
     TARGET,
@@ -1181,6 +1184,8 @@ class FeaturesEnricher(TransformerMixin):
         search_keys = self.search_keys.copy()
         search_keys = self.__prepare_search_keys(x, search_keys, is_demo_dataset, is_transform=True, silent_mode=True)
 
+        unnest_search_keys = []
+
         extended_X = x.copy()
         generated_features = []
         date_column = self._get_date_column(search_keys)
@@ -1191,7 +1196,7 @@ class FeaturesEnricher(TransformerMixin):
         email_column = self._get_email_column(search_keys)
         hem_column = self._get_hem_column(search_keys)
         if email_column:
-            converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, self.logger)
+            converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, unnest_search_keys, self.logger)
             extended_X = converter.convert(extended_X)
             generated_features.extend(converter.generated_features)
         if (
@@ -1902,11 +1907,38 @@ class FeaturesEnricher(TransformerMixin):
                 generated_features.extend(converter.generated_features)
             else:
                 self.logger.info("Input dataset hasn't date column")
+
+            # Don't pass all features in backend on transform
+            original_features_for_transform = []
+            runtime_parameters = self._get_copy_of_runtime_parameters()
+            features_not_to_pass = [column for column in df.columns if column not in search_keys.keys()]
+            if len(features_not_to_pass) > 0:
+                # Pass only features that need for transform
+                features_for_transform = self._search_task.get_features_for_transform()
+                if features_for_transform is not None and len(features_for_transform) > 0:
+                    file_metadata = self._search_task.get_file_metadata(trace_id)
+                    original_features_for_transform = [
+                        c.originalName or c.name for c in file_metadata.columns if c.name in features_for_transform
+                    ]
+
+                    runtime_parameters.properties["features_for_embeddings"] = ",".join(features_for_transform)
+
+            columns_for_system_record_id = sorted(list(search_keys.keys()) + (original_features_for_transform))
+
+            df[ENTITY_SYSTEM_RECORD_ID] = pd.util.hash_pandas_object(
+                df[columns_for_system_record_id], index=False
+            ).astype("Float64")
+
+            # Explode multiple search keys
+            df, unnest_search_keys = self._explode_multiple_search_keys(df, search_keys)
+
             email_column = self._get_email_column(search_keys)
             hem_column = self._get_hem_column(search_keys)
             email_converted_to_hem = False
             if email_column:
-                converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, self.logger)
+                converter = EmailSearchKeyConverter(
+                    email_column, hem_column, search_keys, unnest_search_keys, self.logger
+                )
                 df = converter.convert(df)
                 generated_features.extend(converter.generated_features)
                 email_converted_to_hem = converter.email_converted_to_hem
@@ -1920,30 +1952,21 @@ class FeaturesEnricher(TransformerMixin):
             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()}
-            non_keys_columns = [column for column in df.columns if column not in search_keys.keys()]
+            # non_keys_columns = [column for column in df.columns if column not in search_keys.keys()]
+            for col in original_features_for_transform:
+                meaning_types[col] = FileColumnMeaningType.FEATURE
+            features_not_to_pass = [column for column in features_not_to_pass if column not in search_keys.keys()]
 
             if email_converted_to_hem:
-                non_keys_columns.append(email_column)
+                features_not_to_pass.append(email_column)
 
-            # Don't pass features in backend on transform
-            original_features_for_transform = None
-            runtime_parameters = self._get_copy_of_runtime_parameters()
-            if len(non_keys_columns) > 0:
-                # Pass only features that need for transform
-                features_for_transform = self._search_task.get_features_for_transform()
-                if features_for_transform is not None and len(features_for_transform) > 0:
-                    file_metadata = self._search_task.get_file_metadata(trace_id)
-                    original_features_for_transform = [
-                        c.originalName or c.name for c in file_metadata.columns if c.name in features_for_transform
-                    ]
-                    non_keys_columns = [c for c in non_keys_columns if c not in original_features_for_transform]
-
-                    runtime_parameters.properties["features_for_embeddings"] = ",".join(features_for_transform)
+            features_not_to_pass = [c for c in features_not_to_pass if c not in original_features_for_transform]
+            columns_for_system_record_id = sorted(list(search_keys.keys()) + (original_features_for_transform))
 
             if add_fit_system_record_id:
                 df = self.__add_fit_system_record_id(df, dict(), search_keys)
                 df = df.rename(columns={SYSTEM_RECORD_ID: SORT_ID})
-                non_keys_columns.append(SORT_ID)
+                features_not_to_pass.append(SORT_ID)
 
             columns_for_system_record_id = sorted(list(search_keys.keys()) + (original_features_for_transform or []))
 
@@ -1951,16 +1974,19 @@ class FeaturesEnricher(TransformerMixin):
                 "Float64"
             )
             meaning_types[SYSTEM_RECORD_ID] = FileColumnMeaningType.SYSTEM_RECORD_ID
+            meaning_types[ENTITY_SYSTEM_RECORD_ID] = FileColumnMeaningType.ENTITY_SYSTEM_RECORD_ID
+            if SEARCH_KEY_UNNEST in df.columns:
+                meaning_types[SEARCH_KEY_UNNEST] = FileColumnMeaningType.UNNEST_KEY
 
             df = df.reset_index(drop=True)
-            system_columns_with_original_index = [SYSTEM_RECORD_ID] + generated_features
+            system_columns_with_original_index = [SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID] + generated_features
             if add_fit_system_record_id:
                 system_columns_with_original_index.append(SORT_ID)
             df_with_original_index = df[system_columns_with_original_index].copy()
 
             combined_search_keys = combine_search_keys(search_keys.keys())
 
-            df_without_features = df.drop(columns=non_keys_columns)
+            df_without_features = df.drop(columns=features_not_to_pass)
 
             df_without_features = clean_full_duplicates(
                 df_without_features, self.logger, silent=silent_mode, bundle=self.bundle
@@ -2116,6 +2142,14 @@ class FeaturesEnricher(TransformerMixin):
 
         key_types = search_keys.values()
 
+        # Multiple search keys allowed only for PHONE, IP, POSTAL_CODE, EMAIL, HEM
+        multi_keys = [key for key, count in Counter(key_types).items() if count > 1]
+        for multi_key in multi_keys:
+            if multi_key not in [SearchKey.PHONE, SearchKey.IP, SearchKey.POSTAL_CODE, SearchKey.EMAIL, SearchKey.HEM]:
+                msg = self.bundle.get("unsupported_multi_key").format(multi_key)
+                self.logger.warning(msg)
+                raise ValidationError(msg)
+
         if SearchKey.DATE in key_types and SearchKey.DATETIME in key_types:
             msg = self.bundle.get("date_and_datetime_simultanious")
             self.logger.warning(msg)
@@ -2131,11 +2165,11 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.warning(msg)
             raise ValidationError(msg)
 
-        for key_type in SearchKey.__members__.values():
-            if key_type != SearchKey.CUSTOM_KEY and list(key_types).count(key_type) > 1:
-                msg = self.bundle.get("multiple_search_key").format(key_type)
-                self.logger.warning(msg)
-                raise ValidationError(msg)
+        # for key_type in SearchKey.__members__.values():
+        #     if key_type != SearchKey.CUSTOM_KEY and list(key_types).count(key_type) > 1:
+        #         msg = self.bundle.get("multiple_search_key").format(key_type)
+        #         self.logger.warning(msg)
+        #         raise ValidationError(msg)
 
         # non_personal_keys = set(SearchKey.__members__.values()) - set(SearchKey.personal_keys())
         # if (
@@ -2220,9 +2254,7 @@ 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
-        )
+        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
@@ -2273,14 +2305,7 @@ class FeaturesEnricher(TransformerMixin):
             self.fit_generated_features.extend(converter.generated_features)
         else:
             self.logger.info("Input dataset hasn't date column")
-        email_column = self._get_email_column(self.fit_search_keys)
-        hem_column = self._get_hem_column(self.fit_search_keys)
-        email_converted_to_hem = False
-        if email_column:
-            converter = EmailSearchKeyConverter(email_column, hem_column, self.fit_search_keys, self.logger)
-            df = converter.convert(df)
-            self.fit_generated_features.extend(converter.generated_features)
-            email_converted_to_hem = converter.email_converted_to_hem
+
         if (
             self.detect_missing_search_keys
             and list(self.fit_search_keys.values()) == [SearchKey.DATE]
@@ -2289,7 +2314,37 @@ class FeaturesEnricher(TransformerMixin):
             converter = IpToCountrySearchKeyConverter(self.fit_search_keys, self.logger)
             df = converter.convert(df)
 
+        # Explode multiple search keys
         non_feature_columns = [self.TARGET_NAME, EVAL_SET_INDEX] + list(self.fit_search_keys.keys())
+        meaning_types = {
+            **{col: key.value for col, key in self.fit_search_keys.items()},
+            **{str(c): FileColumnMeaningType.FEATURE for c in df.columns if c not in non_feature_columns},
+        }
+        meaning_types[self.TARGET_NAME] = FileColumnMeaningType.TARGET
+        if eval_set is not None and len(eval_set) > 0:
+            meaning_types[EVAL_SET_INDEX] = FileColumnMeaningType.EVAL_SET_INDEX
+        df = self.__add_fit_system_record_id(df, meaning_types, self.fit_search_keys, ENTITY_SYSTEM_RECORD_ID)
+
+        # TODO check that this is correct for enrichment
+        self.df_with_original_index = df.copy()
+
+        df, unnest_search_keys = self._explode_multiple_search_keys(df, self.fit_search_keys)
+
+        # Convert EMAIL to HEM after unnesting to do it only with one column
+        email_column = self._get_email_column(self.fit_search_keys)
+        hem_column = self._get_hem_column(self.fit_search_keys)
+        email_converted_to_hem = False
+        if email_column:
+            converter = EmailSearchKeyConverter(
+                email_column, hem_column, self.fit_search_keys, unnest_search_keys, self.logger
+            )
+            df = converter.convert(df)
+            self.fit_generated_features.extend(converter.generated_features)
+            email_converted_to_hem = converter.email_converted_to_hem
+
+        non_feature_columns = [self.TARGET_NAME, EVAL_SET_INDEX, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST] + list(
+            self.fit_search_keys.keys()
+        )
         if email_converted_to_hem:
             non_feature_columns.append(email_column)
         if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
@@ -2313,12 +2368,14 @@ class FeaturesEnricher(TransformerMixin):
             **{str(c): FileColumnMeaningType.FEATURE for c in df.columns if c not in non_feature_columns},
         }
         meaning_types[self.TARGET_NAME] = FileColumnMeaningType.TARGET
+        meaning_types[ENTITY_SYSTEM_RECORD_ID] = FileColumnMeaningType.ENTITY_SYSTEM_RECORD_ID
+        if SEARCH_KEY_UNNEST in df.columns:
+            meaning_types[SEARCH_KEY_UNNEST] = FileColumnMeaningType.UNNEST_KEY
         if eval_set is not None and len(eval_set) > 0:
             meaning_types[EVAL_SET_INDEX] = FileColumnMeaningType.EVAL_SET_INDEX
 
-        df = self.__add_fit_system_record_id(df, meaning_types, self.fit_search_keys)
+        df = self.__add_fit_system_record_id(df, meaning_types, self.fit_search_keys, SYSTEM_RECORD_ID)
 
-        self.df_with_original_index = df.copy()
         df = df.reset_index(drop=True).sort_values(by=SYSTEM_RECORD_ID).reset_index(drop=True)
 
         combined_search_keys = combine_search_keys(self.fit_search_keys.keys())
@@ -2326,14 +2383,15 @@ class FeaturesEnricher(TransformerMixin):
         dataset = Dataset(
             "tds_" + str(uuid.uuid4()),
             df=df,
+            meaning_types=meaning_types,
+            search_keys=combined_search_keys,
+            unnest_search_keys=unnest_search_keys,
             model_task_type=model_task_type,
             date_format=self.date_format,
             random_state=self.random_state,
             rest_client=self.rest_client,
             logger=self.logger,
         )
-        dataset.meaning_types = meaning_types
-        dataset.search_keys = combined_search_keys
         if email_converted_to_hem:
             dataset.ignore_columns = [email_column]
 
@@ -2863,15 +2921,19 @@ class FeaturesEnricher(TransformerMixin):
 
     @staticmethod
     def _get_email_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
-        for col, t in search_keys.items():
-            if t == SearchKey.EMAIL:
-                return col
+        cols = [col for col, t in search_keys.items() if t == SearchKey.EMAIL]
+        if len(cols) > 1:
+            raise Exception("More than one email column found after unnest")
+        if len(cols) == 1:
+            return cols[0]
 
     @staticmethod
     def _get_hem_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
-        for col, t in search_keys.items():
-            if t == SearchKey.HEM:
-                return col
+        cols = [col for col, t in search_keys.items() if t == SearchKey.HEM]
+        if len(cols) > 1:
+            raise Exception("More than one hem column found after unnest")
+        if len(cols) == 1:
+            return cols[0]
 
     @staticmethod
     def _get_phone_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
@@ -2879,8 +2941,42 @@ class FeaturesEnricher(TransformerMixin):
             if t == SearchKey.PHONE:
                 return col
 
+    def _explode_multiple_search_keys(self, df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> pd.DataFrame:
+        # find groups of multiple search keys
+        search_key_names_by_type: Dict[SearchKey, str] = dict()
+        for key_name, key_type in search_keys.items():
+            search_key_names_by_type[key_type] = search_key_names_by_type.get(key_type, []) + [key_name]
+        search_key_names_by_type = {
+            key_type: key_names for key_type, key_names in search_key_names_by_type.items() if len(key_names) > 1
+        }
+        if len(search_key_names_by_type) == 0:
+            return df, []
+
+        multiple_keys_columns = [col for cols in search_key_names_by_type.values() for col in cols]
+        other_columns = [col for col in df.columns if col not in multiple_keys_columns]
+        exploded_dfs = []
+        unnest_search_keys = []
+
+        for key_type, key_names in search_key_names_by_type.items():
+            new_search_key = f"upgini_{key_type.name.lower()}_unnest"
+            exploded_df = pd.melt(
+                df, id_vars=other_columns, value_vars=key_names, var_name=SEARCH_KEY_UNNEST, value_name=new_search_key
+            )
+            exploded_dfs.append(exploded_df)
+            for old_key in key_names:
+                del search_keys[old_key]
+            search_keys[new_search_key] = key_type
+            unnest_search_keys.append(new_search_key)
+
+        df = pd.concat(exploded_dfs, ignore_index=True)
+        return df, unnest_search_keys
+
     def __add_fit_system_record_id(
-        self, df: pd.DataFrame, meaning_types: Dict[str, FileColumnMeaningType], search_keys: Dict[str, SearchKey]
+        self,
+        df: pd.DataFrame,
+        meaning_types: Dict[str, FileColumnMeaningType],
+        search_keys: Dict[str, SearchKey],
+        id_name: str,
     ) -> pd.DataFrame:
         # save original order or rows
         original_index_name = df.index.name
@@ -2903,9 +2999,7 @@ class FeaturesEnricher(TransformerMixin):
                 [
                     c
                     for c in df.columns
-                    if c not in sort_columns
-                    and c not in sort_exclude_columns
-                    and df[c].nunique() > 1
+                    if c not in sort_columns and c not in sort_exclude_columns and df[c].nunique() > 1
                 ]
                 # [
                 #     sk
@@ -2931,14 +3025,18 @@ class FeaturesEnricher(TransformerMixin):
 
         df = df.reset_index(drop=True).reset_index()
         # system_record_id saves correct order for fit
-        df = df.rename(columns={DEFAULT_INDEX: SYSTEM_RECORD_ID})
+        df = df.rename(columns={DEFAULT_INDEX: id_name})
 
         # return original order
         df = df.set_index(ORIGINAL_INDEX)
         df.index.name = original_index_name
         df = df.sort_values(by=original_order_name).drop(columns=original_order_name)
 
-        meaning_types[SYSTEM_RECORD_ID] = FileColumnMeaningType.SYSTEM_RECORD_ID
+        meaning_types[id_name] = (
+            FileColumnMeaningType.SYSTEM_RECORD_ID 
+            if id_name == SYSTEM_RECORD_ID 
+            else FileColumnMeaningType.ENTITY_SYSTEM_RECORD_ID
+        )
         return df
 
     def __correct_target(self, df: pd.DataFrame) -> pd.DataFrame:
@@ -2993,7 +3091,10 @@ class FeaturesEnricher(TransformerMixin):
         )
 
         comparing_columns = X.columns if is_transform else df_with_original_index.columns
-        dup_features = [c for c in comparing_columns if c in result_features.columns and c != SYSTEM_RECORD_ID]
+        dup_features = [
+            c for c in comparing_columns 
+            if c in result_features.columns and c not in [SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
+        ]
         if len(dup_features) > 0:
             self.logger.warning(f"X contain columns with same name as returned from backend: {dup_features}")
             raise ValidationError(self.bundle.get("returned_features_same_as_passed").format(dup_features))
@@ -3004,8 +3105,7 @@ class FeaturesEnricher(TransformerMixin):
         result_features = pd.merge(
             df_with_original_index,
             result_features,
-            left_on=SYSTEM_RECORD_ID,
-            right_on=SYSTEM_RECORD_ID,
+            on=ENTITY_SYSTEM_RECORD_ID,
             how="left" if is_transform else "inner",
         )
         result_features = result_features.set_index(original_index_name or DEFAULT_INDEX)
@@ -3385,13 +3485,13 @@ class FeaturesEnricher(TransformerMixin):
                 self.warning_counter.increment()
 
         if len(valid_search_keys) == 1:
-            for k, v in valid_search_keys.items():
-                # Show warning for country only if country is the only key
-                if x[k].nunique() == 1 and (v != SearchKey.COUNTRY or len(valid_search_keys) == 1):
-                    msg = self.bundle.get("single_constant_search_key").format(v, x[k].values[0])
-                    print(msg)
-                    self.logger.warning(msg)
-                    self.warning_counter.increment()
+            key, value = list(valid_search_keys.items())[0]
+            # Show warning for country only if country is the only key
+            if x[key].nunique() == 1:
+                msg = self.bundle.get("single_constant_search_key").format(value, x[key].values[0])
+                print(msg)
+                self.logger.warning(msg)
+                self.warning_counter.increment()
 
         self.logger.info(f"Prepared search keys: {valid_search_keys}")
 
@@ -3501,61 +3601,68 @@ class FeaturesEnricher(TransformerMixin):
         def check_need_detect(search_key: SearchKey):
             return not is_transform or search_key in self.fit_search_keys.values()
 
-        if SearchKey.POSTAL_CODE not in search_keys.values() and check_need_detect(SearchKey.POSTAL_CODE):
-            maybe_key = PostalCodeSearchKeyDetector().get_search_key_column(sample)
-            if maybe_key is not None:
-                search_keys[maybe_key] = SearchKey.POSTAL_CODE
-                self.autodetected_search_keys[maybe_key] = SearchKey.POSTAL_CODE
-                self.logger.info(f"Autodetected search key POSTAL_CODE in column {maybe_key}")
+        # if SearchKey.POSTAL_CODE not in search_keys.values() and check_need_detect(SearchKey.POSTAL_CODE):
+        if check_need_detect(SearchKey.POSTAL_CODE):
+            maybe_keys = PostalCodeSearchKeyDetector().get_search_key_columns(sample, search_keys)
+            if maybe_keys:
+                new_keys = {key: SearchKey.POSTAL_CODE for key in maybe_keys}
+                search_keys.update(new_keys)
+                self.autodetected_search_keys.update(new_keys)
+                self.logger.info(f"Autodetected search key POSTAL_CODE in column {maybe_keys}")
                 if not silent_mode:
-                    print(self.bundle.get("postal_code_detected").format(maybe_key))
+                    print(self.bundle.get("postal_code_detected").format(maybe_keys))
 
         if (
             SearchKey.COUNTRY not in search_keys.values()
             and self.country_code is None
             and check_need_detect(SearchKey.COUNTRY)
         ):
-            maybe_key = CountrySearchKeyDetector().get_search_key_column(sample)
-            if maybe_key is not None:
-                search_keys[maybe_key] = SearchKey.COUNTRY
-                self.autodetected_search_keys[maybe_key] = SearchKey.COUNTRY
+            maybe_key = CountrySearchKeyDetector().get_search_key_columns(sample, search_keys)
+            if maybe_key:
+                search_keys[maybe_key[0]] = SearchKey.COUNTRY
+                self.autodetected_search_keys[maybe_key[0]] = SearchKey.COUNTRY
                 self.logger.info(f"Autodetected search key COUNTRY in column {maybe_key}")
                 if not silent_mode:
                     print(self.bundle.get("country_detected").format(maybe_key))
 
         if (
-            SearchKey.EMAIL not in search_keys.values()
-            and SearchKey.HEM not in search_keys.values()
+            # SearchKey.EMAIL not in search_keys.values()
+            SearchKey.HEM not in search_keys.values()
             and check_need_detect(SearchKey.HEM)
         ):
-            maybe_key = EmailSearchKeyDetector().get_search_key_column(sample)
-            if maybe_key is not None and maybe_key not in search_keys.keys():
+            maybe_keys = EmailSearchKeyDetector().get_search_key_columns(sample, search_keys)
+            if maybe_keys:
                 if self.__is_registered or is_demo_dataset:
-                    search_keys[maybe_key] = SearchKey.EMAIL
-                    self.autodetected_search_keys[maybe_key] = SearchKey.EMAIL
-                    self.logger.info(f"Autodetected search key EMAIL in column {maybe_key}")
+                    new_keys = {key: SearchKey.EMAIL for key in maybe_keys}
+                    search_keys.update(new_keys)
+                    self.autodetected_search_keys.update(new_keys)
+                    self.logger.info(f"Autodetected search key EMAIL in column {maybe_keys}")
                     if not silent_mode:
-                        print(self.bundle.get("email_detected").format(maybe_key))
+                        print(self.bundle.get("email_detected").format(maybe_keys))
                 else:
                     self.logger.warning(
-                        f"Autodetected search key EMAIL in column {maybe_key}. But not used because not registered user"
+                        f"Autodetected search key EMAIL in column {maybe_keys}."
+                        " But not used because not registered user"
                     )
                     if not silent_mode:
-                        print(self.bundle.get("email_detected_not_registered").format(maybe_key))
+                        print(self.bundle.get("email_detected_not_registered").format(maybe_keys))
                     self.warning_counter.increment()
 
-        if SearchKey.PHONE not in search_keys.values() and check_need_detect(SearchKey.PHONE):
-            maybe_key = PhoneSearchKeyDetector().get_search_key_column(sample)
-            if maybe_key is not None and maybe_key not in search_keys.keys():
+        # if SearchKey.PHONE not in search_keys.values() and check_need_detect(SearchKey.PHONE):
+        if check_need_detect(SearchKey.PHONE):
+            maybe_keys = PhoneSearchKeyDetector().get_search_key_columns(sample, search_keys)
+            if maybe_keys:
                 if self.__is_registered or is_demo_dataset:
-                    search_keys[maybe_key] = SearchKey.PHONE
-                    self.autodetected_search_keys[maybe_key] = SearchKey.PHONE
-                    self.logger.info(f"Autodetected search key PHONE in column {maybe_key}")
+                    new_keys = {key: SearchKey.PHONE for key in maybe_keys}
+                    search_keys.update(new_keys)
+                    self.autodetected_search_keys.update(new_keys)
+                    self.logger.info(f"Autodetected search key PHONE in column {maybe_keys}")
                     if not silent_mode:
-                        print(self.bundle.get("phone_detected").format(maybe_key))
+                        print(self.bundle.get("phone_detected").format(maybe_keys))
                 else:
                     self.logger.warning(
-                        f"Autodetected search key PHONE in column {maybe_key}. But not used because not registered user"
+                        f"Autodetected search key PHONE in column {maybe_keys}. "
+                        "But not used because not registered user"
                     )
                     if not silent_mode:
                         print(self.bundle.get("phone_detected_not_registered"))

upgini/fingerprint.js

@@ -0,0 +1,8 @@
+/**
+ * FingerprintJS v3.4.2 - Copyright (c) FingerprintJS, Inc, 2023 (https://fingerprint.com)
+ * Licensed under the MIT (http://www.opensource.org/licenses/mit-license.php) license.
+ *
+ * This software contains code from open-source projects:
+ * MurmurHash3 by Karan Lyons (https://github.com/karanlyons/murmurHash3.js)
+ */
+var e=function(){return e=Object.assign||function(e){for(var n,t=1,r=arguments.length;t<r;t++)for(var o in n=arguments[t])Object.prototype.hasOwnProperty.call(n,o)&&(e[o]=n[o]);return e},e.apply(this,arguments)};function n(e,n,t,r){return new(t||(t=Promise))((function(o,a){function i(e){try{u(r.next(e))}catch(n){a(n)}}function c(e){try{u(r.throw(e))}catch(n){a(n)}}function u(e){var n;e.done?o(e.value):(n=e.value,n instanceof t?n:new t((function(e){e(n)}))).then(i,c)}u((r=r.apply(e,n||[])).next())}))}function t(e,n){var t,r,o,a,i={label:0,sent:function(){if(1&o[0])throw o[1];return o[1]},trys:[],ops:[]};return a={next:c(0),throw:c(1),return:c(2)},"function"==typeof Symbol&&(a[Symbol.iterator]=function(){return this}),a;function c(c){return function(u){return function(c){if(t)throw new TypeError("Generator is already executing.");for(;a&&(a=0,c[0]&&(i=0)),i;)try{if(t=1,r&&(o=2&c[0]?r.return:c[0]?r.throw||((o=r.return)&&o.call(r),0):r.next)&&!(o=o.call(r,c[1])).done)return o;switch(r=0,o&&(c=[2&c[0],o.value]),c[0]){case 0:case 1:o=c;break;case 4:return i.label++,{value:c[1],done:!1};case 5:i.label++,r=c[1],c=[0];continue;case 7:c=i.ops.pop(),i.trys.pop();continue;default:if(!(o=i.trys,(o=o.length>0&&o[o.length-1])||6!==c[0]&&2!==c[0])){i=0;continue}if(3===c[0]&&(!o||c[1]>o[0]&&c[1]<o[3])){i.label=c[1];break}if(6===c[0]&&i.label<o[1]){i.label=o[1],o=c;break}if(o&&i.label<o[2]){i.label=o[2],i.ops.push(c);break}o[2]&&i.ops.pop(),i.trys.pop();continue}c=n.call(e,i)}catch(u){c=[6,u],r=0}finally{t=o=0}if(5&c[0])throw c[1];return{value:c[0]?c[1]:void 0,done:!0}}([c,u])}}}function r(e,n,t){if(t||2===arguments.length)for(var r,o=0,a=n.length;o<a;o++)!r&&o in n||(r||(r=Array.prototype.slice.call(n,0,o)),r[o]=n[o]);return e.concat(r||Array.prototype.slice.call(n))}function o(e,n){return new Promise((function(t){return setTimeout(t,e,n)}))}function a(e){return!!e&&"function"==typeof e.then}function i(e,n){try{var t=e();a(t)?t.then((function(e){return n(!0,e)}),(function(e){return n(!1,e)})):n(!0,t)}catch(r){n(!1,r)}}function c(e,r,a){return void 0===a&&(a=16),n(this,void 0,void 0,(function(){var n,i,c,u;return t(this,(function(t){switch(t.label){case 0:n=Array(e.length),i=Date.now(),c=0,t.label=1;case 1:return c<e.length?(n[c]=r(e[c],c),(u=Date.now())>=i+a?(i=u,[4,o(0)]):[3,3]):[3,4];case 2:t.sent(),t.label=3;case 3:return++c,[3,1];case 4:return[2,n]}}))}))}function u(e){e.then(void 0,(function(){}))}function l(e,n){e=[e[0]>>>16,65535&e[0],e[1]>>>16,65535&e[1]],n=[n[0]>>>16,65535&n[0],n[1]>>>16,65535&n[1]];var t=[0,0,0,0];return t[3]+=e[3]+n[3],t[2]+=t[3]>>>16,t[3]&=65535,t[2]+=e[2]+n[2],t[1]+=t[2]>>>16,t[2]&=65535,t[1]+=e[1]+n[1],t[0]+=t[1]>>>16,t[1]&=65535,t[0]+=e[0]+n[0],t[0]&=65535,[t[0]<<16|t[1],t[2]<<16|t[3]]}function s(e,n){e=[e[0]>>>16,65535&e[0],e[1]>>>16,65535&e[1]],n=[n[0]>>>16,65535&n[0],n[1]>>>16,65535&n[1]];var t=[0,0,0,0];return t[3]+=e[3]*n[3],t[2]+=t[3]>>>16,t[3]&=65535,t[2]+=e[2]*n[3],t[1]+=t[2]>>>16,t[2]&=65535,t[2]+=e[3]*n[2],t[1]+=t[2]>>>16,t[2]&=65535,t[1]+=e[1]*n[3],t[0]+=t[1]>>>16,t[1]&=65535,t[1]+=e[2]*n[2],t[0]+=t[1]>>>16,t[1]&=65535,t[1]+=e[3]*n[1],t[0]+=t[1]>>>16,t[1]&=65535,t[0]+=e[0]*n[3]+e[1]*n[2]+e[2]*n[1]+e[3]*n[0],t[0]&=65535,[t[0]<<16|t[1],t[2]<<16|t[3]]}function d(e,n){return 32===(n%=64)?[e[1],e[0]]:n<32?[e[0]<<n|e[1]>>>32-n,e[1]<<n|e[0]>>>32-n]:(n-=32,[e[1]<<n|e[0]>>>32-n,e[0]<<n|e[1]>>>32-n])}function m(e,n){return 0===(n%=64)?e:n<32?[e[0]<<n|e[1]>>>32-n,e[1]<<n]:[e[1]<<n-32,0]}function f(e,n){return[e[0]^n[0],e[1]^n[1]]}function v(e){return e=f(e,[0,e[0]>>>1]),e=f(e=s(e,[4283543511,3981806797]),[0,e[0]>>>1]),e=f(e=s(e,[3301882366,444984403]),[0,e[0]>>>1])}function h(e,n){n=n||0;var t,r=(e=e||"").length%16,o=e.length-r,a=[0,n],i=[0,n],c=[0,0],u=[0,0],h=[2277735313,289559509],p=[1291169091,658871167];for(t=0;t<o;t+=16)c=[255&e.charCodeAt(t+4)|(255&e.charCodeAt(t+5))<<8|(255&e.charCodeAt(t+6))<<16|(255&e.charCodeAt(t+7))<<24,255&e.charCodeAt(t)|(255&e.charCodeAt(t+1))<<8|(255&e.charCodeAt(t+2))<<16|(255&e.charCodeAt(t+3))<<24],u=[255&e.charCodeAt(t+12)|(255&e.charCodeAt(t+13))<<8|(255&e.charCodeAt(t+14))<<16|(255&e.charCodeAt(t+15))<<24,255&e.charCodeAt(t+8)|(255&e.charCodeAt(t+9))<<8|(255&e.charCodeAt(t+10))<<16|(255&e.charCodeAt(t+11))<<24],c=d(c=s(c,h),31),a=l(a=d(a=f(a,c=s(c,p)),27),i),a=l(s(a,[0,5]),[0,1390208809]),u=d(u=s(u,p),33),i=l(i=d(i=f(i,u=s(u,h)),31),a),i=l(s(i,[0,5]),[0,944331445]);switch(c=[0,0],u=[0,0],r){case 15:u=f(u,m([0,e.charCodeAt(t+14)],48));case 14:u=f(u,m([0,e.charCodeAt(t+13)],40));case 13:u=f(u,m([0,e.charCodeAt(t+12)],32));case 12:u=f(u,m([0,e.charCodeAt(t+11)],24));case 11:u=f(u,m([0,e.charCodeAt(t+10)],16));case 10:u=f(u,m([0,e.charCodeAt(t+9)],8));case 9:u=s(u=f(u,[0,e.charCodeAt(t+8)]),p),i=f(i,u=s(u=d(u,33),h));case 8:c=f(c,m([0,e.charCodeAt(t+7)],56));case 7:c=f(c,m([0,e.charCodeAt(t+6)],48));case 6:c=f(c,m([0,e.charCodeAt(t+5)],40));case 5:c=f(c,m([0,e.charCodeAt(t+4)],32));case 4:c=f(c,m([0,e.charCodeAt(t+3)],24));case 3:c=f(c,m([0,e.charCodeAt(t+2)],16));case 2:c=f(c,m([0,e.charCodeAt(t+1)],8));case 1:c=s(c=f(c,[0,e.charCodeAt(t)]),h),a=f(a,c=s(c=d(c,31),p))}return a=l(a=f(a,[0,e.length]),i=f(i,[0,e.length])),i=l(i,a),a=l(a=v(a),i=v(i)),i=l(i,a),("00000000"+(a[0]>>>0).toString(16)).slice(-8)+("00000000"+(a[1]>>>0).toString(16)).slice(-8)+("00000000"+(i[0]>>>0).toString(16)).slice(-8)+("00000000"+(i[1]>>>0).toString(16)).slice(-8)}function p(e){return parseInt(e)}function b(e){return parseFloat(e)}function y(e,n){return"number"==typeof e&&isNaN(e)?n:e}function g(e){return e.reduce((function(e,n){return e+(n?1:0)}),0)}function w(e,n){if(void 0===n&&(n=1),Math.abs(n)>=1)return Math.round(e/n)*n;var t=1/n;return Math.round(e*t)/t}function L(e){return e&&"object"==typeof e&&"message"in e?e:{message:e}}function k(e){return"function"!=typeof e}function V(e,r,o){var a=Object.keys(e).filter((function(e){return!function(e,n){for(var t=0,r=e.length;t<r;++t)if(e[t]===n)return!0;return!1}(o,e)})),l=c(a,(function(n){return function(e,n){var t=new Promise((function(t){var r=Date.now();i(e.bind(null,n),(function(){for(var e=[],n=0;n<arguments.length;n++)e[n]=arguments[n];var o=Date.now()-r;if(!e[0])return t((function(){return{error:L(e[1]),duration:o}}));var a=e[1];if(k(a))return t((function(){return{value:a,duration:o}}));t((function(){return new Promise((function(e){var n=Date.now();i(a,(function(){for(var t=[],r=0;r<arguments.length;r++)t[r]=arguments[r];var a=o+Date.now()-n;if(!t[0])return e({error:L(t[1]),duration:a});e({value:t[1],duration:a})}))}))}))}))}));return u(t),function(){return t.then((function(e){return e()}))}}(e[n],r)}));return u(l),function(){return n(this,void 0,void 0,(function(){var e,n,r,o;return t(this,(function(t){switch(t.label){case 0:return[4,l];case 1:return[4,c(t.sent(),(function(e){var n=e();return u(n),n}))];case 2:return e=t.sent(),[4,Promise.all(e)];case 3:for(n=t.sent(),r={},o=0;o<a.length;++o)r[a[o]]=n[o];return[2,r]}}))}))}}function Z(e,n){var t=function(e){return k(e)?n(e):function(){var t=e();return a(t)?t.then(n):n(t)}};return function(n){var r=e(n);return a(r)?r.then(t):t(r)}}function W(){var e=window,n=navigator;return g(["MSCSSMatrix"in e,"msSetImmediate"in e,"msIndexedDB"in e,"msMaxTouchPoints"in n,"msPointerEnabled"in n])>=4}function C(){var e=window,n=navigator;return g(["msWriteProfilerMark"in e,"MSStream"in e,"msLaunchUri"in n,"msSaveBlob"in n])>=3&&!W()}function S(){var e=window,n=navigator;return g(["webkitPersistentStorage"in n,"webkitTemporaryStorage"in n,0===n.vendor.indexOf("Google"),"webkitResolveLocalFileSystemURL"in e,"BatteryManager"in e,"webkitMediaStream"in e,"webkitSpeechGrammar"in e])>=5}function x(){var e=window,n=navigator;return g(["ApplePayError"in e,"CSSPrimitiveValue"in e,"Counter"in e,0===n.vendor.indexOf("Apple"),"getStorageUpdates"in n,"WebKitMediaKeys"in e])>=4}function F(){var e=window;return g(["safari"in e,!("DeviceMotionEvent"in e),!("ongestureend"in e),!("standalone"in navigator)])>=3}function Y(){var e,n,t=window;return g(["buildID"in navigator,"MozAppearance"in(null!==(n=null===(e=document.documentElement)||void 0===e?void 0:e.style)&&void 0!==n?n:{}),"onmozfullscreenchange"in t,"mozInnerScreenX"in t,"CSSMozDocumentRule"in t,"CanvasCaptureMediaStream"in t])>=4}function M(){var e=document;return e.fullscreenElement||e.msFullscreenElement||e.mozFullScreenElement||e.webkitFullscreenElement||null}function G(){var e=S(),n=Y();if(!e&&!n)return!1;var t=window;return g(["onorientationchange"in t,"orientation"in t,e&&!("SharedWorker"in t),n&&/android/i.test(navigator.appVersion)])>=2}function R(e){var n=new Error(e);return n.name=e,n}function X(e,r,a){var i,c,u;return void 0===a&&(a=50),n(this,void 0,void 0,(function(){var n,l;return t(this,(function(t){switch(t.label){case 0:n=document,t.label=1;case 1:return n.body?[3,3]:[4,o(a)];case 2:return t.sent(),[3,1];case 3:l=n.createElement("iframe"),t.label=4;case 4:return t.trys.push([4,,10,11]),[4,new Promise((function(e,t){var o=!1,a=function(){o=!0,e()};l.onload=a,l.onerror=function(e){o=!0,t(e)};var i=l.style;i.setProperty("display","block","important"),i.position="absolute",i.top="0",i.left="0",i.visibility="hidden",r&&"srcdoc"in l?l.srcdoc=r:l.src="about:blank",n.body.appendChild(l);var c=function(){var e,n;o||("complete"===(null===(n=null===(e=l.contentWindow)||void 0===e?void 0:e.document)||void 0===n?void 0:n.readyState)?a():setTimeout(c,10))};c()}))];case 5:t.sent(),t.label=6;case 6:return(null===(c=null===(i=l.contentWindow)||void 0===i?void 0:i.document)||void 0===c?void 0:c.body)?[3,8]:[4,o(a)];case 7:return t.sent(),[3,6];case 8:return[4,e(l,l.contentWindow)];case 9:return[2,t.sent()];case 10:return null===(u=l.parentNode)||void 0===u||u.removeChild(l),[7];case 11:return[2]}}))}))}function A(e){for(var n=function(e){for(var n,t,r="Unexpected syntax '".concat(e,"'"),o=/^\s*([a-z-]*)(.*)$/i.exec(e),a=o[1]||void 0,i={},c=/([.:#][\w-]+|\[.+?\])/gi,u=function(e,n){i[e]=i[e]||[],i[e].push(n)};;){var l=c.exec(o[2]);if(!l)break;var s=l[0];switch(s[0]){case".":u("class",s.slice(1));break;case"#":u("id",s.slice(1));break;case"[":var d=/^\[([\w-]+)([~|^$*]?=("(.*?)"|([\w-]+)))?(\s+[is])?\]$/.exec(s);if(!d)throw new Error(r);u(d[1],null!==(t=null!==(n=d[4])&&void 0!==n?n:d[5])&&void 0!==t?t:"");break;default:throw new Error(r)}}return[a,i]}(e),t=n[0],r=n[1],o=document.createElement(null!=t?t:"div"),a=0,i=Object.keys(r);a<i.length;a++){var c=i[a],u=r[c].join(" ");"style"===c?j(o.style,u):o.setAttribute(c,u)}return o}function j(e,n){for(var t=0,r=n.split(";");t<r.length;t++){var o=r[t],a=/^\s*([\w-]+)\s*:\s*(.+?)(\s*!([\w-]+))?\s*$/.exec(o);if(a){var i=a[1],c=a[2],u=a[4];e.setProperty(i,c,u||"")}}}var I=["monospace","sans-serif","serif"],J=["sans-serif-thin","ARNO PRO","Agency FB","Arabic Typesetting","Arial Unicode MS","AvantGarde Bk BT","BankGothic Md BT","Batang","Bitstream Vera Sans Mono","Calibri","Century","Century Gothic","Clarendon","EUROSTILE","Franklin Gothic","Futura Bk BT","Futura Md BT","GOTHAM","Gill Sans","HELV","Haettenschweiler","Helvetica Neue","Humanst521 BT","Leelawadee","Letter Gothic","Levenim MT","Lucida Bright","Lucida Sans","Menlo","MS Mincho","MS Outlook","MS Reference Specialty","MS UI Gothic","MT Extra","MYRIAD PRO","Marlett","Meiryo UI","Microsoft Uighur","Minion Pro","Monotype Corsiva","PMingLiU","Pristina","SCRIPTINA","Segoe UI Light","Serifa","SimHei","Small Fonts","Staccato222 BT","TRAJAN PRO","Univers CE 55 Medium","Vrinda","ZWAdobeF"];function H(e){return e.toDataURL()}var P,N;function z(){var e=this;return function(){if(void 0===N){var e=function(){var n=D();E(n)?N=setTimeout(e,2500):(P=n,N=void 0)};e()}}(),function(){return n(e,void 0,void 0,(function(){var e;return t(this,(function(n){switch(n.label){case 0:return E(e=D())?P?[2,r([],P,!0)]:M()?[4,(t=document,(t.exitFullscreen||t.msExitFullscreen||t.mozCancelFullScreen||t.webkitExitFullscreen).call(t))]:[3,2]:[3,2];case 1:n.sent(),e=D(),n.label=2;case 2:return E(e)||(P=e),[2,e]}var t}))}))}}function D(){var e=screen;return[y(b(e.availTop),null),y(b(e.width)-b(e.availWidth)-y(b(e.availLeft),0),null),y(b(e.height)-b(e.availHeight)-y(b(e.availTop),0),null),y(b(e.availLeft),null)]}function E(e){for(var n=0;n<4;++n)if(e[n])return!1;return!0}function T(e){var r;return n(this,void 0,void 0,(function(){var n,a,i,c,u,l,s;return t(this,(function(t){switch(t.label){case 0:for(n=document,a=n.createElement("div"),i=new Array(e.length),c={},B(a),s=0;s<e.length;++s)"DIALOG"===(u=A(e[s])).tagName&&u.show(),B(l=n.createElement("div")),l.appendChild(u),a.appendChild(l),i[s]=u;t.label=1;case 1:return n.body?[3,3]:[4,o(50)];case 2:return t.sent(),[3,1];case 3:n.body.appendChild(a);try{for(s=0;s<e.length;++s)i[s].offsetParent||(c[e[s]]=!0)}finally{null===(r=a.parentNode)||void 0===r||r.removeChild(a)}return[2,c]}}))}))}function B(e){e.style.setProperty("display","block","important")}function _(e){return matchMedia("(inverted-colors: ".concat(e,")")).matches}function O(e){return matchMedia("(forced-colors: ".concat(e,")")).matches}function U(e){return matchMedia("(prefers-contrast: ".concat(e,")")).matches}function Q(e){return matchMedia("(prefers-reduced-motion: ".concat(e,")")).matches}function K(e){return matchMedia("(dynamic-range: ".concat(e,")")).matches}var q=Math,$=function(){return 0};var ee={default:[],apple:[{font:"-apple-system-body"}],serif:[{fontFamily:"serif"}],sans:[{fontFamily:"sans-serif"}],mono:[{fontFamily:"monospace"}],min:[{fontSize:"1px"}],system:[{fontFamily:"system-ui"}]};var ne={fonts:function(){return X((function(e,n){var t=n.document,r=t.body;r.style.fontSize="48px";var o=t.createElement("div"),a={},i={},c=function(e){var n=t.createElement("span"),r=n.style;return r.position="absolute",r.top="0",r.left="0",r.fontFamily=e,n.textContent="mmMwWLliI0O&1",o.appendChild(n),n},u=I.map(c),l=function(){for(var e={},n=function(n){e[n]=I.map((function(e){return function(e,n){return c("'".concat(e,"',").concat(n))}(n,e)}))},t=0,r=J;t<r.length;t++){n(r[t])}return e}();r.appendChild(o);for(var s=0;s<I.length;s++)a[I[s]]=u[s].offsetWidth,i[I[s]]=u[s].offsetHeight;return J.filter((function(e){return n=l[e],I.some((function(e,t){return n[t].offsetWidth!==a[e]||n[t].offsetHeight!==i[e]}));var n}))}))},domBlockers:function(e){var r=(void 0===e?{}:e).debug;return n(this,void 0,void 0,(function(){var e,n,o,a,i;return t(this,(function(t){switch(t.label){case 0:return x()||G()?(c=atob,e={abpIndo:["#Iklan-Melayang","#Kolom-Iklan-728","#SidebarIklan-wrapper",'[title="ALIENBOLA" i]',c("I0JveC1CYW5uZXItYWRz")],abpvn:[".quangcao","#mobileCatfish",c("LmNsb3NlLWFkcw=="),'[id^="bn_bottom_fixed_"]',"#pmadv"],adBlockFinland:[".mainostila",c("LnNwb25zb3JpdA=="),".ylamainos",c("YVtocmVmKj0iL2NsaWNrdGhyZ2guYXNwPyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hcHAucmVhZHBlYWsuY29tL2FkcyJd")],adBlockPersian:["#navbar_notice_50",".kadr",'TABLE[width="140px"]',"#divAgahi",c("YVtocmVmXj0iaHR0cDovL2cxLnYuZndtcm0ubmV0L2FkLyJd")],adBlockWarningRemoval:["#adblock-honeypot",".adblocker-root",".wp_adblock_detect",c("LmhlYWRlci1ibG9ja2VkLWFk"),c("I2FkX2Jsb2NrZXI=")],adGuardAnnoyances:[".hs-sosyal","#cookieconsentdiv",'div[class^="app_gdpr"]',".as-oil",'[data-cypress="soft-push-notification-modal"]'],adGuardBase:[".BetterJsPopOverlay",c("I2FkXzMwMFgyNTA="),c("I2Jhbm5lcmZsb2F0MjI="),c("I2NhbXBhaWduLWJhbm5lcg=="),c("I0FkLUNvbnRlbnQ=")],adGuardChinese:[c("LlppX2FkX2FfSA=="),c("YVtocmVmKj0iLmh0aGJldDM0LmNvbSJd"),"#widget-quan",c("YVtocmVmKj0iLzg0OTkyMDIwLnh5eiJd"),c("YVtocmVmKj0iLjE5NTZobC5jb20vIl0=")],adGuardFrench:["#pavePub",c("LmFkLWRlc2t0b3AtcmVjdGFuZ2xl"),".mobile_adhesion",".widgetadv",c("LmFkc19iYW4=")],adGuardGerman:['aside[data-portal-id="leaderboard"]'],adGuardJapanese:["#kauli_yad_1",c("YVtocmVmXj0iaHR0cDovL2FkMi50cmFmZmljZ2F0ZS5uZXQvIl0="),c("Ll9wb3BJbl9pbmZpbml0ZV9hZA=="),c("LmFkZ29vZ2xl"),c("Ll9faXNib29zdFJldHVybkFk")],adGuardMobile:[c("YW1wLWF1dG8tYWRz"),c("LmFtcF9hZA=="),'amp-embed[type="24smi"]',"#mgid_iframe1",c("I2FkX2ludmlld19hcmVh")],adGuardRussian:[c("YVtocmVmXj0iaHR0cHM6Ly9hZC5sZXRtZWFkcy5jb20vIl0="),c("LnJlY2xhbWE="),'div[id^="smi2adblock"]',c("ZGl2W2lkXj0iQWRGb3hfYmFubmVyXyJd"),"#psyduckpockeball"],adGuardSocial:[c("YVtocmVmXj0iLy93d3cuc3R1bWJsZXVwb24uY29tL3N1Ym1pdD91cmw9Il0="),c("YVtocmVmXj0iLy90ZWxlZ3JhbS5tZS9zaGFyZS91cmw/Il0="),".etsy-tweet","#inlineShare",".popup-social"],adGuardSpanishPortuguese:["#barraPublicidade","#Publicidade","#publiEspecial","#queTooltip",".cnt-publi"],adGuardTrackingProtection:["#qoo-counter",c("YVtocmVmXj0iaHR0cDovL2NsaWNrLmhvdGxvZy5ydS8iXQ=="),c("YVtocmVmXj0iaHR0cDovL2hpdGNvdW50ZXIucnUvdG9wL3N0YXQucGhwIl0="),c("YVtocmVmXj0iaHR0cDovL3RvcC5tYWlsLnJ1L2p1bXAiXQ=="),"#top100counter"],adGuardTurkish:["#backkapat",c("I3Jla2xhbWk="),c("YVtocmVmXj0iaHR0cDovL2Fkc2Vydi5vbnRlay5jb20udHIvIl0="),c("YVtocmVmXj0iaHR0cDovL2l6bGVuemkuY29tL2NhbXBhaWduLyJd"),c("YVtocmVmXj0iaHR0cDovL3d3dy5pbnN0YWxsYWRzLm5ldC8iXQ==")],bulgarian:[c("dGQjZnJlZW5ldF90YWJsZV9hZHM="),"#ea_intext_div",".lapni-pop-over","#xenium_hot_offers"],easyList:[".yb-floorad",c("LndpZGdldF9wb19hZHNfd2lkZ2V0"),c("LnRyYWZmaWNqdW5reS1hZA=="),".textad_headline",c("LnNwb25zb3JlZC10ZXh0LWxpbmtz")],easyListChina:[c("LmFwcGd1aWRlLXdyYXBbb25jbGljayo9ImJjZWJvcy5jb20iXQ=="),c("LmZyb250cGFnZUFkdk0="),"#taotaole","#aafoot.top_box",".cfa_popup"],easyListCookie:[".ezmob-footer",".cc-CookieWarning","[data-cookie-number]",c("LmF3LWNvb2tpZS1iYW5uZXI="),".sygnal24-gdpr-modal-wrap"],easyListCzechSlovak:["#onlajny-stickers",c("I3Jla2xhbW5pLWJveA=="),c("LnJla2xhbWEtbWVnYWJvYXJk"),".sklik",c("W2lkXj0ic2tsaWtSZWtsYW1hIl0=")],easyListDutch:[c("I2FkdmVydGVudGll"),c("I3ZpcEFkbWFya3RCYW5uZXJCbG9jaw=="),".adstekst",c("YVtocmVmXj0iaHR0cHM6Ly94bHR1YmUubmwvY2xpY2svIl0="),"#semilo-lrectangle"],easyListGermany:["#SSpotIMPopSlider",c("LnNwb25zb3JsaW5rZ3J1ZW4="),c("I3dlcmJ1bmdza3k="),c("I3Jla2xhbWUtcmVjaHRzLW1pdHRl"),c("YVtocmVmXj0iaHR0cHM6Ly9iZDc0Mi5jb20vIl0=")],easyListItaly:[c("LmJveF9hZHZfYW5udW5jaQ=="),".sb-box-pubbliredazionale",c("YVtocmVmXj0iaHR0cDovL2FmZmlsaWF6aW9uaWFkcy5zbmFpLml0LyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hZHNlcnZlci5odG1sLml0LyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hZmZpbGlhemlvbmlhZHMuc25haS5pdC8iXQ==")],easyListLithuania:[c("LnJla2xhbW9zX3RhcnBhcw=="),c("LnJla2xhbW9zX251b3JvZG9z"),c("aW1nW2FsdD0iUmVrbGFtaW5pcyBza3lkZWxpcyJd"),c("aW1nW2FsdD0iRGVkaWt1b3RpLmx0IHNlcnZlcmlhaSJd"),c("aW1nW2FsdD0iSG9zdGluZ2FzIFNlcnZlcmlhaS5sdCJd")],estonian:[c("QVtocmVmKj0iaHR0cDovL3BheTRyZXN1bHRzMjQuZXUiXQ==")],fanboyAnnoyances:["#ac-lre-player",".navigate-to-top","#subscribe_popup",".newsletter_holder","#back-top"],fanboyAntiFacebook:[".util-bar-module-firefly-visible"],fanboyEnhancedTrackers:[".open.pushModal","#issuem-leaky-paywall-articles-zero-remaining-nag","#sovrn_container",'div[class$="-hide"][zoompage-fontsize][style="display: block;"]',".BlockNag__Card"],fanboySocial:["#FollowUs","#meteored_share","#social_follow",".article-sharer",".community__social-desc"],frellwitSwedish:[c("YVtocmVmKj0iY2FzaW5vcHJvLnNlIl1bdGFyZ2V0PSJfYmxhbmsiXQ=="),c("YVtocmVmKj0iZG9rdG9yLXNlLm9uZWxpbmsubWUiXQ=="),"article.category-samarbete",c("ZGl2LmhvbGlkQWRz"),"ul.adsmodern"],greekAdBlock:[c("QVtocmVmKj0iYWRtYW4ub3RlbmV0LmdyL2NsaWNrPyJd"),c("QVtocmVmKj0iaHR0cDovL2F4aWFiYW5uZXJzLmV4b2R1cy5nci8iXQ=="),c("QVtocmVmKj0iaHR0cDovL2ludGVyYWN0aXZlLmZvcnRobmV0LmdyL2NsaWNrPyJd"),"DIV.agores300","TABLE.advright"],hungarian:["#cemp_doboz",".optimonk-iframe-container",c("LmFkX19tYWlu"),c("W2NsYXNzKj0iR29vZ2xlQWRzIl0="),"#hirdetesek_box"],iDontCareAboutCookies:['.alert-info[data-block-track*="CookieNotice"]',".ModuleTemplateCookieIndicator",".o--cookies--container","#cookies-policy-sticky","#stickyCookieBar"],icelandicAbp:[c("QVtocmVmXj0iL2ZyYW1ld29yay9yZXNvdXJjZXMvZm9ybXMvYWRzLmFzcHgiXQ==")],latvian:[c("YVtocmVmPSJodHRwOi8vd3d3LnNhbGlkemluaS5sdi8iXVtzdHlsZT0iZGlzcGxheTogYmxvY2s7IHdpZHRoOiAxMjBweDsgaGVpZ2h0OiA0MHB4OyBvdmVyZmxvdzogaGlkZGVuOyBwb3NpdGlvbjogcmVsYXRpdmU7Il0="),c("YVtocmVmPSJodHRwOi8vd3d3LnNhbGlkemluaS5sdi8iXVtzdHlsZT0iZGlzcGxheTogYmxvY2s7IHdpZHRoOiA4OHB4OyBoZWlnaHQ6IDMxcHg7IG92ZXJmbG93OiBoaWRkZW47IHBvc2l0aW9uOiByZWxhdGl2ZTsiXQ==")],listKr:[c("YVtocmVmKj0iLy9hZC5wbGFuYnBsdXMuY28ua3IvIl0="),c("I2xpdmVyZUFkV3JhcHBlcg=="),c("YVtocmVmKj0iLy9hZHYuaW1hZHJlcC5jby5rci8iXQ=="),c("aW5zLmZhc3R2aWV3LWFk"),".revenue_unit_item.dable"],listeAr:[c("LmdlbWluaUxCMUFk"),".right-and-left-sponsers",c("YVtocmVmKj0iLmFmbGFtLmluZm8iXQ=="),c("YVtocmVmKj0iYm9vcmFxLm9yZyJd"),c("YVtocmVmKj0iZHViaXp6bGUuY29tL2FyLz91dG1fc291cmNlPSJd")],listeFr:[c("YVtocmVmXj0iaHR0cDovL3Byb21vLnZhZG9yLmNvbS8iXQ=="),c("I2FkY29udGFpbmVyX3JlY2hlcmNoZQ=="),c("YVtocmVmKj0id2Vib3JhbWEuZnIvZmNnaS1iaW4vIl0="),".site-pub-interstitiel",'div[id^="crt-"][data-criteo-id]'],officialPolish:["#ceneo-placeholder-ceneo-12",c("W2hyZWZePSJodHRwczovL2FmZi5zZW5kaHViLnBsLyJd"),c("YVtocmVmXj0iaHR0cDovL2Fkdm1hbmFnZXIudGVjaGZ1bi5wbC9yZWRpcmVjdC8iXQ=="),c("YVtocmVmXj0iaHR0cDovL3d3dy50cml6ZXIucGwvP3V0bV9zb3VyY2UiXQ=="),c("ZGl2I3NrYXBpZWNfYWQ=")],ro:[c("YVtocmVmXj0iLy9hZmZ0cmsuYWx0ZXgucm8vQ291bnRlci9DbGljayJd"),c("YVtocmVmXj0iaHR0cHM6Ly9ibGFja2ZyaWRheXNhbGVzLnJvL3Ryay9zaG9wLyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9ldmVudC4ycGVyZm9ybWFudC5jb20vZXZlbnRzL2NsaWNrIl0="),c("YVtocmVmXj0iaHR0cHM6Ly9sLnByb2ZpdHNoYXJlLnJvLyJd"),'a[href^="/url/"]'],ruAd:[c("YVtocmVmKj0iLy9mZWJyYXJlLnJ1LyJd"),c("YVtocmVmKj0iLy91dGltZy5ydS8iXQ=="),c("YVtocmVmKj0iOi8vY2hpa2lkaWtpLnJ1Il0="),"#pgeldiz",".yandex-rtb-block"],thaiAds:["a[href*=macau-uta-popup]",c("I2Fkcy1nb29nbGUtbWlkZGxlX3JlY3RhbmdsZS1ncm91cA=="),c("LmFkczMwMHM="),".bumq",".img-kosana"],webAnnoyancesUltralist:["#mod-social-share-2","#social-tools",c("LmN0cGwtZnVsbGJhbm5lcg=="),".zergnet-recommend",".yt.btn-link.btn-md.btn"]},n=Object.keys(e),[4,T((i=[]).concat.apply(i,n.map((function(n){return e[n]}))))]):[2,void 0];case 1:return o=t.sent(),r&&function(e,n){for(var t="DOM blockers debug:\n```",r=0,o=Object.keys(e);r<o.length;r++){var a=o[r];t+="\n".concat(a,":");for(var i=0,c=e[a];i<c.length;i++){var u=c[i];t+="\n  ".concat(n[u]?"🚫":"➡️"," ").concat(u)}}console.log("".concat(t,"\n```"))}(e,o),(a=n.filter((function(n){var t=e[n];return g(t.map((function(e){return o[e]})))>.6*t.length}))).sort(),[2,a]}var c}))}))},fontPreferences:function(){return function(e,n){void 0===n&&(n=4e3);return X((function(t,o){var a=o.document,i=a.body,c=i.style;c.width="".concat(n,"px"),c.webkitTextSizeAdjust=c.textSizeAdjust="none",S()?i.style.zoom="".concat(1/o.devicePixelRatio):x()&&(i.style.zoom="reset");var u=a.createElement("div");return u.textContent=r([],Array(n/20<<0),!0).map((function(){return"word"})).join(" "),i.appendChild(u),e(a,i)}),'<!doctype html><html><head><meta name="viewport" content="width=device-width, initial-scale=1">')}((function(e,n){for(var t={},r={},o=0,a=Object.keys(ee);o<a.length;o++){var i=a[o],c=ee[i],u=c[0],l=void 0===u?{}:u,s=c[1],d=void 0===s?"mmMwWLliI0fiflO&1":s,m=e.createElement("span");m.textContent=d,m.style.whiteSpace="nowrap";for(var f=0,v=Object.keys(l);f<v.length;f++){var h=v[f],p=l[h];void 0!==p&&(m.style[h]=p)}t[i]=m,n.appendChild(e.createElement("br")),n.appendChild(m)}for(var b=0,y=Object.keys(ee);b<y.length;b++){r[i=y[b]]=t[i].getBoundingClientRect().width}return r}))},audio:function(){var e=window,n=e.OfflineAudioContext||e.webkitOfflineAudioContext;if(!n)return-2;if(x()&&!F()&&!function(){var e=window;return g(["DOMRectList"in e,"RTCPeerConnectionIceEvent"in e,"SVGGeometryElement"in e,"ontransitioncancel"in e])>=3}())return-1;var t=new n(1,5e3,44100),r=t.createOscillator();r.type="triangle",r.frequency.value=1e4;var o=t.createDynamicsCompressor();o.threshold.value=-50,o.knee.value=40,o.ratio.value=12,o.attack.value=0,o.release.value=.25,r.connect(o),o.connect(t.destination),r.start(0);var i=function(e){var n=3,t=500,r=500,o=5e3,i=function(){};return[new Promise((function(c,l){var s=!1,d=0,m=0;e.oncomplete=function(e){return c(e.renderedBuffer)};var f=function(){setTimeout((function(){return l(R("timeout"))}),Math.min(r,m+o-Date.now()))},v=function(){try{var r=e.startRendering();switch(a(r)&&u(r),e.state){case"running":m=Date.now(),s&&f();break;case"suspended":document.hidden||d++,s&&d>=n?l(R("suspended")):setTimeout(v,t)}}catch(o){l(o)}};v(),i=function(){s||(s=!0,m>0&&f())}})),i]}(t),c=i[0],l=i[1],s=c.then((function(e){return function(e){for(var n=0,t=0;t<e.length;++t)n+=Math.abs(e[t]);return n}(e.getChannelData(0).subarray(4500))}),(function(e){if("timeout"===e.name||"suspended"===e.name)return-3;throw e}));return u(s),function(){return l(),s}},screenFrame:function(){var e=this,r=z();return function(){return n(e,void 0,void 0,(function(){var e,n;return t(this,(function(t){switch(t.label){case 0:return[4,r()];case 1:return e=t.sent(),[2,[(n=function(e){return null===e?null:w(e,10)})(e[0]),n(e[1]),n(e[2]),n(e[3])]]}}))}))}},osCpu:function(){return navigator.oscpu},languages:function(){var e,n=navigator,t=[],r=n.language||n.userLanguage||n.browserLanguage||n.systemLanguage;if(void 0!==r&&t.push([r]),Array.isArray(n.languages))S()&&g([!("MediaSettingsRange"in(e=window)),"RTCEncodedAudioFrame"in e,""+e.Intl=="[object Intl]",""+e.Reflect=="[object Reflect]"])>=3||t.push(n.languages);else if("string"==typeof n.languages){var o=n.languages;o&&t.push(o.split(","))}return t},colorDepth:function(){return window.screen.colorDepth},deviceMemory:function(){return y(b(navigator.deviceMemory),void 0)},screenResolution:function(){var e=screen,n=function(e){return y(p(e),null)},t=[n(e.width),n(e.height)];return t.sort().reverse(),t},hardwareConcurrency:function(){return y(p(navigator.hardwareConcurrency),void 0)},timezone:function(){var e,n=null===(e=window.Intl)||void 0===e?void 0:e.DateTimeFormat;if(n){var t=(new n).resolvedOptions().timeZone;if(t)return t}var r,o=(r=(new Date).getFullYear(),-Math.max(b(new Date(r,0,1).getTimezoneOffset()),b(new Date(r,6,1).getTimezoneOffset())));return"UTC".concat(o>=0?"+":"").concat(Math.abs(o))},sessionStorage:function(){try{return!!window.sessionStorage}catch(e){return!0}},localStorage:function(){try{return!!window.localStorage}catch(e){return!0}},indexedDB:function(){if(!W()&&!C())try{return!!window.indexedDB}catch(e){return!0}},openDatabase:function(){return!!window.openDatabase},cpuClass:function(){return navigator.cpuClass},platform:function(){var e=navigator.platform;return"MacIntel"===e&&x()&&!F()?function(){if("iPad"===navigator.platform)return!0;var e=screen,n=e.width/e.height;return g(["MediaSource"in window,!!Element.prototype.webkitRequestFullscreen,n>.65&&n<1.53])>=2}()?"iPad":"iPhone":e},plugins:function(){var e=navigator.plugins;if(e){for(var n=[],t=0;t<e.length;++t){var r=e[t];if(r){for(var o=[],a=0;a<r.length;++a){var i=r[a];o.push({type:i.type,suffixes:i.suffixes})}n.push({name:r.name,description:r.description,mimeTypes:o})}}return n}},canvas:function(){var e,n,t=!1,r=function(){var e=document.createElement("canvas");return e.width=1,e.height=1,[e,e.getContext("2d")]}(),o=r[0],a=r[1];if(function(e,n){return!(!n||!e.toDataURL)}(o,a)){t=function(e){return e.rect(0,0,10,10),e.rect(2,2,6,6),!e.isPointInPath(5,5,"evenodd")}(a),function(e,n){e.width=240,e.height=60,n.textBaseline="alphabetic",n.fillStyle="#f60",n.fillRect(100,1,62,20),n.fillStyle="#069",n.font='11pt "Times New Roman"';var t="Cwm fjordbank gly ".concat(String.fromCharCode(55357,56835));n.fillText(t,2,15),n.fillStyle="rgba(102, 204, 0, 0.2)",n.font="18pt Arial",n.fillText(t,4,45)}(o,a);var i=H(o);i!==H(o)?e=n="unstable":(n=i,function(e,n){e.width=122,e.height=110,n.globalCompositeOperation="multiply";for(var t=0,r=[["#f2f",40,40],["#2ff",80,40],["#ff2",60,80]];t<r.length;t++){var o=r[t],a=o[0],i=o[1],c=o[2];n.fillStyle=a,n.beginPath(),n.arc(i,c,40,0,2*Math.PI,!0),n.closePath(),n.fill()}n.fillStyle="#f9c",n.arc(60,60,60,0,2*Math.PI,!0),n.arc(60,60,20,0,2*Math.PI,!0),n.fill("evenodd")}(o,a),e=H(o))}else e=n="";return{winding:t,geometry:e,text:n}},touchSupport:function(){var e,n=navigator,t=0;void 0!==n.maxTouchPoints?t=p(n.maxTouchPoints):void 0!==n.msMaxTouchPoints&&(t=n.msMaxTouchPoints);try{document.createEvent("TouchEvent"),e=!0}catch(r){e=!1}return{maxTouchPoints:t,touchEvent:e,touchStart:"ontouchstart"in window}},vendor:function(){return navigator.vendor||""},vendorFlavors:function(){for(var e=[],n=0,t=["chrome","safari","__crWeb","__gCrWeb","yandex","__yb","__ybro","__firefox__","__edgeTrackingPreventionStatistics","webkit","oprt","samsungAr","ucweb","UCShellJava","puffinDevice"];n<t.length;n++){var r=t[n],o=window[r];o&&"object"==typeof o&&e.push(r)}return e.sort()},cookiesEnabled:function(){var e=document;try{e.cookie="cookietest=1; SameSite=Strict;";var n=-1!==e.cookie.indexOf("cookietest=");return e.cookie="cookietest=1; SameSite=Strict; expires=Thu, 01-Jan-1970 00:00:01 GMT",n}catch(t){return!1}},colorGamut:function(){for(var e=0,n=["rec2020","p3","srgb"];e<n.length;e++){var t=n[e];if(matchMedia("(color-gamut: ".concat(t,")")).matches)return t}},invertedColors:function(){return!!_("inverted")||!_("none")&&void 0},forcedColors:function(){return!!O("active")||!O("none")&&void 0},monochrome:function(){if(matchMedia("(min-monochrome: 0)").matches){for(var e=0;e<=100;++e)if(matchMedia("(max-monochrome: ".concat(e,")")).matches)return e;throw new Error("Too high value")}},contrast:function(){return U("no-preference")?0:U("high")||U("more")?1:U("low")||U("less")?-1:U("forced")?10:void 0},reducedMotion:function(){return!!Q("reduce")||!Q("no-preference")&&void 0},hdr:function(){return!!K("high")||!K("standard")&&void 0},math:function(){var e,n=q.acos||$,t=q.acosh||$,r=q.asin||$,o=q.asinh||$,a=q.atanh||$,i=q.atan||$,c=q.sin||$,u=q.sinh||$,l=q.cos||$,s=q.cosh||$,d=q.tan||$,m=q.tanh||$,f=q.exp||$,v=q.expm1||$,h=q.log1p||$;return{acos:n(.12312423423423424),acosh:t(1e308),acoshPf:(e=1e154,q.log(e+q.sqrt(e*e-1))),asin:r(.12312423423423424),asinh:o(1),asinhPf:function(e){return q.log(e+q.sqrt(e*e+1))}(1),atanh:a(.5),atanhPf:function(e){return q.log((1+e)/(1-e))/2}(.5),atan:i(.5),sin:c(-1e300),sinh:u(1),sinhPf:function(e){return q.exp(e)-1/q.exp(e)/2}(1),cos:l(10.000000000123),cosh:s(1),coshPf:function(e){return(q.exp(e)+1/q.exp(e))/2}(1),tan:d(-1e300),tanh:m(1),tanhPf:function(e){return(q.exp(2*e)-1)/(q.exp(2*e)+1)}(1),exp:f(1),expm1:v(1),expm1Pf:function(e){return q.exp(e)-1}(1),log1p:h(10),log1pPf:function(e){return q.log(1+e)}(10),powPI:function(e){return q.pow(q.PI,e)}(-100)}},videoCard:function(){var e,n=document.createElement("canvas"),t=null!==(e=n.getContext("webgl"))&&void 0!==e?e:n.getContext("experimental-webgl");if(t&&"getExtension"in t){var r=t.getExtension("WEBGL_debug_renderer_info");if(r)return{vendor:(t.getParameter(r.UNMASKED_VENDOR_WEBGL)||"").toString(),renderer:(t.getParameter(r.UNMASKED_RENDERER_WEBGL)||"").toString()}}},pdfViewerEnabled:function(){return navigator.pdfViewerEnabled},architecture:function(){var e=new Float32Array(1),n=new Uint8Array(e.buffer);return e[0]=1/0,e[0]=e[0]-e[0],n[3]}};function te(e){var n=function(e){if(G())return.4;if(x())return F()?.5:.3;var n=e.platform.value||"";if(/^Win/.test(n))return.6;if(/^Mac/.test(n))return.5;return.7}(e),t=function(e){return w(.99+.01*e,1e-4)}(n);return{score:n,comment:"$ if upgrade to Pro: https://fpjs.dev/pro".replace(/\$/g,"".concat(t))}}function re(n){return JSON.stringify(n,(function(n,t){return t instanceof Error?e({name:(r=t).name,message:r.message,stack:null===(o=r.stack)||void 0===o?void 0:o.split("\n")},r):t;var r,o}),2)}function oe(e){return h(function(e){for(var n="",t=0,r=Object.keys(e).sort();t<r.length;t++){var o=r[t],a=e[o],i=a.error?"error":JSON.stringify(a.value);n+="".concat(n?"|":"").concat(o.replace(/([:|\\])/g,"\\$1"),":").concat(i)}return n}(e))}function ae(e){return void 0===e&&(e=50),function(e,n){void 0===n&&(n=1/0);var t=window.requestIdleCallback;return t?new Promise((function(e){return t.call(window,(function(){return e()}),{timeout:n})})):o(Math.min(e,n))}(e,2*e)}function ie(e,r){var o=Date.now();return{get:function(a){return n(this,void 0,void 0,(function(){var n,i,c;return t(this,(function(t){switch(t.label){case 0:return n=Date.now(),[4,e()];case 1:return i=t.sent(),c=function(e){var n;return{get visitorId(){return void 0===n&&(n=oe(this.components)),n},set visitorId(e){n=e},confidence:te(e),components:e,version:"3.4.2"}}(i),(r||(null==a?void 0:a.debug))&&console.log("Copy the text below to get the debug data:\n\n```\nversion: ".concat(c.version,"\nuserAgent: ").concat(navigator.userAgent,"\ntimeBetweenLoadAndGet: ").concat(n-o,"\nvisitorId: ").concat(c.visitorId,"\ncomponents: ").concat(re(i),"\n```")),[2,c]}}))}))}}}function ce(e){var r=void 0===e?{}:e,o=r.delayFallback,a=r.debug;return r.monitoring,n(this,void 0,void 0,(function(){return t(this,(function(e){switch(e.label){case 0:return[4,ae(o)];case 1:return e.sent(),[2,ie(V(ne,{debug:a},[]),a)]}}))}))}var ue={load:ce,hashComponents:oe,componentsToDebugString:re},le=h;export{re as componentsToDebugString,ue as default,M as getFullscreenElement,z as getScreenFrame,oe as hashComponents,G as isAndroid,S as isChromium,F as isDesktopSafari,C as isEdgeHTML,Y as isGecko,W as isTrident,x as isWebKit,ce as load,V as loadSources,le as murmurX64Hash128,ae as prepareForSources,ne as sources,Z as transformSource,X as withIframe};

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/resource_bundle/strings.properties

@@ -87,6 +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

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/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

@@ -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-1.1.274a3388.post2.dist-info → upgini-1.1.275a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.274a3388.post2
+Version: 1.1.275a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.274a3388.post2.dist-info → upgini-1.1.275a1.dist-info}/RECORD

@@ -1,10 +1,11 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=xb4gIANyGbdcuM8Awyq2pJPiH_3k_LEbETApJgAoRBA,45529
+upgini/dataset.py,sha256=g10BnbayclZMno9mAabpz_Zu0iyMiW0f_jOwt_xJr8U,45947
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=LPYSCGq89WLaL5iQNikTyhICUs_APtqEvhn5XRENn1U,174105
+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/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
@@ -14,10 +15,10 @@ 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=DreiGPDrPT5hThjmtp6_LOsByWV6FP0XlWhpPEYeEQo,4610
-upgini/autofe/feature.py,sha256=LAVXZL5zJEwZbuhB8Zqcrbev7yDvTveTnkEUKpMx21U,14434
+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=1eF3-6-dW7MwD34LH-csTDN2xqcyFuIJbIUKU59bjB0,3012
+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
@@ -28,22 +29,22 @@ 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=TM9OykiEXNpcgFN3DpqBGbQs4N9m4mzHBn-k6aazc30,26111
+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=dQ4-s8-sZ5eOBZ-mH3gEwDHTdI0wI1bUAVgVqUKKPx4,786
-upgini/utils/base_search_key_detector.py,sha256=DGwhXLvc8i5VZWMDr0rncFfV5GEHdsCSnLGon_W9TPs,859
+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=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=4ii5WphAHlb_NRmdJx35VZpTarJbAr-AnDw3XSzUSow,10346
-upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
+upgini/utils/deduplicate_utils.py,sha256=Zvs7zW4QzaERQmJNPrTVf2ZTVBkBLOycFCzyMwtXuV8,8770
 upgini/utils/display_utils.py,sha256=LKoSwjrE0xgS5_cqVhc2og2CQ1UCZ1nTI2VKboIhoQA,10858
-upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
+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=P-dfjBLAMxgzOcUX1Jo1bhVp8-8WyTyF3Ef0YZ5nfRI,3269
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
@@ -55,8 +56,8 @@ upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,4
 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-1.1.274a3388.post2.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.274a3388.post2.dist-info/METADATA,sha256=vF30QjGCqiXg5iU8_Gp299EHu5uvlUEoN9e04VlpCSw,48167
-upgini-1.1.274a3388.post2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.274a3388.post2.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.274a3388.post2.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,,