upgini 1.1.276__py3-none-any.whl → 1.1.278a1__py3-none-any.whl

upgini/dataset.py

@@ -23,7 +23,9 @@ 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,
@@ -79,6 +81,7 @@ 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[Dict[str, str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
@@ -113,6 +116,7 @@ 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 = []
@@ -172,7 +176,7 @@ 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
@@ -353,7 +357,9 @@ class Dataset:  # (pd.DataFrame):
 
             if is_string_dtype(self.data[postal_code]) or is_object_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]):
@@ -803,6 +809,9 @@ 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
+                    column_meta.unnestKeyNames = self.unnest_search_keys[column_meta.originalName]
 
                 columns.append(column_meta)
 

upgini/features_enricher.py

@@ -11,6 +11,7 @@ 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
@@ -45,9 +46,11 @@ 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,
@@ -248,7 +251,7 @@ class FeaturesEnricher(TransformerMixin):
         self.__cached_sampled_datasets: Optional[Tuple[pd.DataFrame, pd.DataFrame, pd.Series, Dict, Dict]] = None
 
         validate_version(self.logger)
-        self.search_keys = search_keys or dict()
+        self.search_keys = search_keys or {}
         self.country_code = country_code
         self.__validate_search_keys(search_keys, search_id)
         self.model_task_type = model_task_type
@@ -1188,7 +1191,7 @@ 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, [], self.logger)
             extended_X = converter.convert(extended_X)
             generated_features.extend(converter.generated_features)
         if (
@@ -1404,7 +1407,7 @@ class FeaturesEnricher(TransformerMixin):
                     fitting_enriched_X[col].astype("string").str.replace(",", ".").astype(np.float64)
                 )
 
-        fitting_eval_set_dict = dict()
+        fitting_eval_set_dict = {}
         for idx, eval_tuple in eval_set_sampled_dict.items():
             eval_X_sampled, enriched_eval_X, eval_y_sampled = eval_tuple
             eval_X_sorted, eval_y_sorted = self._sort_by_system_record_id(eval_X_sampled, eval_y_sampled, self.cv)
@@ -1516,7 +1519,7 @@ class FeaturesEnricher(TransformerMixin):
     def __sample_only_input(
         self, validated_X: pd.DataFrame, validated_y: pd.Series, eval_set: Optional[List[tuple]], is_demo_dataset: bool
     ) -> _SampledDataForMetrics:
-        eval_set_sampled_dict = dict()
+        eval_set_sampled_dict = {}
 
         df = validated_X.copy()
         df[TARGET] = validated_y
@@ -1542,7 +1545,7 @@ class FeaturesEnricher(TransformerMixin):
             df = df.sample(n=sample_rows, random_state=self.random_state)
 
         df_extended, search_keys = self._extend_x(df, is_demo_dataset)
-        df_extended = self.__add_fit_system_record_id(df_extended, dict(), search_keys)
+        df_extended = self.__add_fit_system_record_id(df_extended, {}, search_keys)
 
         train_df = df_extended.query(f"{EVAL_SET_INDEX} == 0") if eval_set is not None else df_extended
         X_sampled = train_df.drop(columns=[TARGET, EVAL_SET_INDEX], errors="ignore")
@@ -1566,7 +1569,7 @@ class FeaturesEnricher(TransformerMixin):
         trace_id: str,
         remove_outliers_calc_metrics: Optional[bool],
     ) -> _SampledDataForMetrics:
-        eval_set_sampled_dict = dict()
+        eval_set_sampled_dict = {}
         search_keys = self.fit_search_keys
 
         rows_to_drop = None
@@ -1640,7 +1643,7 @@ class FeaturesEnricher(TransformerMixin):
         progress_bar: Optional[ProgressBar],
         progress_callback: Optional[Callable[[SearchProgress], Any]],
     ) -> _SampledDataForMetrics:
-        eval_set_sampled_dict = dict()
+        eval_set_sampled_dict = {}
         if eval_set is not None:
             self.logger.info("Transform with eval_set")
             # concatenate X and eval_set with eval_set_index
@@ -1662,7 +1665,7 @@ class FeaturesEnricher(TransformerMixin):
                 self.logger.info(f"Downsampling from {num_samples} to {Dataset.FIT_SAMPLE_WITH_EVAL_SET_ROWS}")
                 df = df.sample(n=Dataset.FIT_SAMPLE_WITH_EVAL_SET_ROWS, random_state=self.random_state)
 
-            eval_set_sampled_dict = dict()
+            eval_set_sampled_dict = {}
 
             tmp_target_name = "__target"
             df = df.rename(columns={TARGET: tmp_target_name})
@@ -1925,11 +1928,38 @@ class FeaturesEnricher(TransformerMixin):
                 self.logger.info("Input dataset hasn't date column")
                 if self.add_date_if_missing:
                     df = self._add_current_date_as_key(df, search_keys, self.logger, self.bundle)
+
+            # 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, list(unnest_search_keys.keys()), self.logger
+                )
                 df = converter.convert(df)
                 generated_features.extend(converter.generated_features)
                 email_converted_to_hem = converter.email_converted_to_hem
@@ -1943,30 +1973,21 @@ 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)
-
-            # 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]
+                features_not_to_pass.append(email_column)
 
-                    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 = self.__add_fit_system_record_id(df, {}, 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 []))
 
@@ -1974,16 +1995,19 @@ 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
@@ -1995,12 +2019,13 @@ class FeaturesEnricher(TransformerMixin):
             dataset = Dataset(
                 "sample_" + str(uuid.uuid4()),
                 df=df_without_features,
+                meaning_types=meaning_types,
+                search_keys=combined_search_keys,
+                unnest_search_keys=unnest_search_keys,
                 date_format=self.date_format,
                 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]
 
@@ -2139,6 +2164,14 @@ 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)
@@ -2154,11 +2187,11 @@ 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 (
@@ -2296,14 +2329,6 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.info("Input dataset hasn't date column")
             if self.add_date_if_missing:
                 df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
-        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]
@@ -2312,7 +2337,37 @@ 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, list(unnest_search_keys.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:
@@ -2336,12 +2391,14 @@ 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())
@@ -2349,14 +2406,15 @@ 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]
 
@@ -2905,15 +2963,19 @@ 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]:
@@ -2921,8 +2983,44 @@ class FeaturesEnricher(TransformerMixin):
             if t == SearchKey.PHONE:
                 return col
 
+    def _explode_multiple_search_keys(
+        self, df: pd.DataFrame, search_keys: Dict[str, SearchKey]
+    ) -> Tuple[pd.DataFrame, Dict[str, List[str]]]:
+        # find groups of multiple search keys
+        search_key_names_by_type: Dict[SearchKey, str] = {}
+        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[new_search_key] = key_names
+
+        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
@@ -2971,14 +3069,18 @@ 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:
@@ -3033,7 +3135,11 @@ 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))
@@ -3044,8 +3150,7 @@ 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)
@@ -3056,7 +3161,7 @@ class FeaturesEnricher(TransformerMixin):
             result_features = result_features[~result_features[SYSTEM_RECORD_ID].isin(rows_to_drop[SYSTEM_RECORD_ID])]
             self.logger.info(f"After dropping target outliers size: {len(result_features)}")
 
-        result_eval_sets = dict()
+        result_eval_sets = {}
         if not is_transform and EVAL_SET_INDEX in result_features.columns:
             result_train_features = result_features.loc[result_features[EVAL_SET_INDEX] == 0].copy()
             eval_set_indices = list(result_features[EVAL_SET_INDEX].unique())
@@ -3262,7 +3367,7 @@ class FeaturesEnricher(TransformerMixin):
                 if autofe_feature.op.is_vector:
                     continue
 
-                description = dict()
+                description = {}
 
                 feature_meta = get_feature_by_name(autofe_feature.get_display_name(shorten=True))
                 if feature_meta is None:
@@ -3428,13 +3533,13 @@ 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}")
 
@@ -3544,61 +3649,68 @@ 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/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):
@@ -276,7 +284,7 @@ class FeaturesFilter(BaseModel):
 
 
 class RuntimeParameters(BaseModel):
-    properties: Dict[str, str] = dict()
+    properties: Dict[str, str] = {}
 
 
 class SearchCustomization(BaseModel):

upgini/metrics.py

@@ -357,7 +357,7 @@ class EstimatorWrapper:
             "logger": logger,
         }
         if estimator is None:
-            params = dict()
+            params = {}
             # if metric_name.upper() in SUPPORTED_CATBOOST_METRICS:
             #     params["eval_metric"] = SUPPORTED_CATBOOST_METRICS[metric_name.upper()]
             if target_type == ModelTaskType.MULTICLASS:

upgini/resource_bundle/strings.properties

@@ -88,6 +88,7 @@ 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/datetime_utils.py

@@ -126,9 +126,9 @@ class DateTimeSearchKeyConverter:
         df.drop(columns=seconds, inplace=True)
 
         if keep_time:
-            df[self.DATETIME_COL] = df[self.date_column].view(np.int64) // 1_000_000
+            df[self.DATETIME_COL] = df[self.date_column].astype(np.int64) // 1_000_000
             df[self.DATETIME_COL] = df[self.DATETIME_COL].apply(self._int_to_opt).astype("Int64")
-        df[self.date_column] = df[self.date_column].dt.floor("D").view(np.int64) // 1_000_000
+        df[self.date_column] = df[self.date_column].dt.floor("D").astype(np.int64) // 1_000_000
         df[self.date_column] = df[self.date_column].apply(self._int_to_opt).astype("Int64")
 
         self.logger.info(f"Date after convertion to timestamp: {df[self.date_column]}")
@@ -249,7 +249,8 @@ def validate_dates_distribution(
             if col in search_keys:
                 continue
             try:
-                pd.to_datetime(X[col])
+                # Format mixed to avoid massive warnings
+                pd.to_datetime(X[col], format="mixed")
                 maybe_date_col = col
                 break
             except Exception:

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-1.1.276.dist-info → upgini-1.1.278a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.276
+Version: 1.1.278a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.276.dist-info → upgini-1.1.278a1.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/dataset.py,sha256=qdIxHiDGZT_iNTBswNeIuc9TPfvUlNqvSmRqMyigZBM,46187
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=ys7RQoZsyY8-NkUZyp12K8z5aQmg7pyx0LtwclFtXkc,176358
+upgini/features_enricher.py,sha256=wsrm9uwIr7hCNLBXTEuw4nIuIXfJrsZ7RWFeG24tTzI,181665
 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=TNZbtIuxYkBFGQu3gGm2flA6vsKyUPN4Q-Du3fFjmSM,10101
+upgini/metrics.py,sha256=YhyPik38cBI5x5KfdiE_qocJnUjZbSqUj8GUtCqnG0g,29648
 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
@@ -29,22 +29,22 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/phone_normalizer.py,sha256=_SYMX4GTgwzRXArK54Jp3vUBE5d4jZxSVyze-0tqzg0,9996
 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=-JDIa0nAoA5utK7UZZAUgLDsozJNI08dDcbIaOSsvQg,26353
 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/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/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=RW9eGCGQyYBsIU9XbYKt4hQiXUNppb4Grszg4EdKeY4,10398
+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=KHqIUagBWd3jOj3V7mW0ZkBOc-2XzAIA3p1xxZgy-L4,3813
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
 upgini/utils/features_validator.py,sha256=PgKNt5dyqfErTvjtRNNUS9g7GFqHBtAtnsfA-V5UO1A,3307
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
@@ -56,8 +56,8 @@ upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=p8gmuHhLamZF5JG7K9DeK-PcytQhlFCR29lyRr-wq_U,5665
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.276.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.276.dist-info/METADATA,sha256=Dgb4UJ82UknhtKS9DHiGRu-a9i3LeoKZiVWpCzkJfF4,48156
-upgini-1.1.276.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.276.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.276.dist-info/RECORD,,
+upgini-1.1.278a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.278a1.dist-info/METADATA,sha256=q6o1ge7o56ZvJk11K_v2tfPAREHvZMW9kHPbotGeJEo,48158
+upgini-1.1.278a1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.278a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.278a1.dist-info/RECORD,,