upgini 1.1.275a1__py3-none-any.whl → 1.1.276__py3-none-any.whl

upgini/features_enricher.py

@@ -1,4 +1,5 @@
 import dataclasses
+import datetime
 import gc
 import hashlib
 import itertools
@@ -10,7 +11,6 @@ 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
@@ -21,6 +21,7 @@ from pandas.api.types import (
     is_bool,
     is_datetime64_any_dtype,
     is_numeric_dtype,
+    is_object_dtype,
     is_period_dtype,
     is_string_dtype,
 )
@@ -44,11 +45,9 @@ 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,
@@ -149,6 +148,7 @@ class FeaturesEnricher(TransformerMixin):
     """
 
     TARGET_NAME = "target"
+    CURRENT_DATE = "current_date"
     RANDOM_STATE = 42
     CALCULATE_METRICS_THRESHOLD = 50_000_000
     CALCULATE_METRICS_MIN_THRESHOLD = 500
@@ -210,6 +210,7 @@ class FeaturesEnricher(TransformerMixin):
         client_ip: Optional[str] = None,
         client_visitorid: Optional[str] = None,
         custom_bundle_config: Optional[str] = None,
+        add_date_if_missing: bool = True,
         **kwargs,
     ):
         self.bundle = get_custom_bundle(custom_bundle_config)
@@ -320,6 +321,7 @@ class FeaturesEnricher(TransformerMixin):
         self.raise_validation_error = raise_validation_error
         self.exclude_columns = exclude_columns
         self.baseline_score_column = baseline_score_column
+        self.add_date_if_missing = add_date_if_missing
 
     def _get_api_key(self):
         return self._api_key
@@ -423,6 +425,9 @@ class FeaturesEnricher(TransformerMixin):
 
             self.__validate_search_keys(self.search_keys, self.search_id)
 
+            # Validate client estimator params
+            self._get_client_cat_features(estimator, X, self.search_keys)
+
             try:
                 self.X = X
                 self.y = y
@@ -816,6 +821,7 @@ class FeaturesEnricher(TransformerMixin):
         trace_id = trace_id or str(uuid.uuid4())
         start_time = time.time()
         with MDC(trace_id=trace_id):
+            self.logger.info("Start calculate metrics")
             if len(args) > 0:
                 msg = f"WARNING: Unsupported positional arguments for calculate_metrics: {args}"
                 self.logger.warning(msg)
@@ -867,22 +873,9 @@ class FeaturesEnricher(TransformerMixin):
                     self.__display_support_link(msg)
                     return None
 
-                cat_features = None
-                search_keys_for_metrics = []
-                if (
-                    estimator is not None
-                    and hasattr(estimator, "get_param")
-                    and estimator.get_param("cat_features") is not None
-                ):
-                    cat_features = estimator.get_param("cat_features")
-                    if len(cat_features) > 0 and isinstance(cat_features[0], int):
-                        cat_features = [effective_X.columns[i] for i in cat_features]
-                        for cat_feature in cat_features:
-                            if cat_feature in self.search_keys:
-                                if self.search_keys[cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
-                                    search_keys_for_metrics.append(cat_feature)
-                                else:
-                                    raise ValidationError(self.bundle.get("cat_feature_search_key").format(cat_feature))
+                cat_features, search_keys_for_metrics = self._get_client_cat_features(
+                    estimator, effective_X, self.search_keys
+                )
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -897,6 +890,7 @@ class FeaturesEnricher(TransformerMixin):
                     search_keys_for_metrics=search_keys_for_metrics,
                     progress_bar=progress_bar,
                     progress_callback=progress_callback,
+                    cat_features=cat_features,
                 )
                 if prepared_data is None:
                     return None
@@ -1184,8 +1178,6 @@ 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)
@@ -1196,7 +1188,7 @@ 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, unnest_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 (
@@ -1274,6 +1266,29 @@ class FeaturesEnricher(TransformerMixin):
 
         return _cv, groups
 
+    def _get_client_cat_features(
+        self, estimator: Optional[Any], X: pd.DataFrame, search_keys: Dict[str, SearchKey]
+    ) -> Optional[List[str]]:
+        cat_features = None
+        search_keys_for_metrics = []
+        if (
+            estimator is not None
+            and hasattr(estimator, "get_param")
+            and estimator.get_param("cat_features") is not None
+        ):
+            cat_features = estimator.get_param("cat_features")
+            if len(cat_features) > 0:
+                if all([isinstance(f, int) for f in cat_features]):
+                    cat_features = [X.columns[i] for i in cat_features]
+                self.logger.info(f"Collected categorical features {cat_features} from user estimator")
+                for cat_feature in cat_features:
+                    if cat_feature in search_keys:
+                        if search_keys[cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
+                            search_keys_for_metrics.append(cat_feature)
+                        else:
+                            raise ValidationError(self.bundle.get("cat_feature_search_key").format(cat_feature))
+        return cat_features, search_keys_for_metrics
+
     def _prepare_data_for_metrics(
         self,
         trace_id: str,
@@ -1288,6 +1303,7 @@ class FeaturesEnricher(TransformerMixin):
         search_keys_for_metrics: Optional[List[str]] = None,
         progress_bar: Optional[ProgressBar] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
+        cat_features: Optional[List[str]] = None,
     ):
         is_input_same_as_fit, X, y, eval_set = self._is_input_same_as_fit(X, y, eval_set)
         is_demo_dataset = hash_input(X, y, eval_set) in DEMO_DATASET_HASHES
@@ -1345,9 +1361,8 @@ class FeaturesEnricher(TransformerMixin):
 
         # Detect and drop high cardinality columns in train
         columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        columns_with_high_cardinality = [
-            c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
-        ]
+        non_excluding_columns = (self.generate_features or []) + (cat_features or [])
+        columns_with_high_cardinality = [c for c in columns_with_high_cardinality if c not in non_excluding_columns]
         if len(columns_with_high_cardinality) > 0:
             self.logger.warning(
                 f"High cardinality columns {columns_with_high_cardinality} will be dropped for metrics calculation"
@@ -1809,10 +1824,11 @@ class FeaturesEnricher(TransformerMixin):
         else:
             features_section = ""
 
-        api_example = f"""curl 'https://inference-upgini.azurewebsites.net/api/http_inference_trigger' \\
+        search_id = self._search_task.search_task_id
+        api_example = f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
-    -d '{{"search_id": "{self._search_task.search_task_id}", "search_keys": {keys}{features_section}}}'"""
+    -d '{{"search_keys": {keys}{features_section}}}'"""
         return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
@@ -1907,38 +1923,13 @@ 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)
-
+                if self.add_date_if_missing:
+                    df = self._add_current_date_as_key(df, search_keys, self.logger, self.bundle)
             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, unnest_search_keys, self.logger
-                )
+                converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, self.logger)
                 df = converter.convert(df)
                 generated_features.extend(converter.generated_features)
                 email_converted_to_hem = converter.email_converted_to_hem
@@ -1952,21 +1943,30 @@ 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()]
-            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()]
+            non_keys_columns = [column for column in df.columns if column not in search_keys.keys()]
 
             if email_converted_to_hem:
-                features_not_to_pass.append(email_column)
+                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 = [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))
+                    runtime_parameters.properties["features_for_embeddings"] = ",".join(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})
-                features_not_to_pass.append(SORT_ID)
+                non_keys_columns.append(SORT_ID)
 
             columns_for_system_record_id = sorted(list(search_keys.keys()) + (original_features_for_transform or []))
 
@@ -1974,19 +1974,16 @@ 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, ENTITY_SYSTEM_RECORD_ID] + generated_features
+            system_columns_with_original_index = [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=features_not_to_pass)
+            df_without_features = df.drop(columns=non_keys_columns)
 
             df_without_features = clean_full_duplicates(
                 df_without_features, self.logger, silent=silent_mode, bundle=self.bundle
@@ -2142,14 +2139,6 @@ 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)
@@ -2165,11 +2154,11 @@ 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 (
@@ -2305,7 +2294,16 @@ class FeaturesEnricher(TransformerMixin):
             self.fit_generated_features.extend(converter.generated_features)
         else:
             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]
@@ -2314,37 +2312,7 @@ 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:
@@ -2368,14 +2336,12 @@ 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, SYSTEM_RECORD_ID)
+        df = self.__add_fit_system_record_id(df, meaning_types, self.fit_search_keys)
 
+        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())
@@ -2383,15 +2349,14 @@ 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]
 
@@ -2911,6 +2876,25 @@ class FeaturesEnricher(TransformerMixin):
             if t in [SearchKey.DATE, SearchKey.DATETIME]:
                 return col
 
+    @staticmethod
+    def _add_current_date_as_key(
+        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
+    ) -> pd.DataFrame:
+        if (
+            set(search_keys.values()) == {SearchKey.PHONE}
+            or set(search_keys.values()) == {SearchKey.EMAIL}
+            or set(search_keys.values()) == {SearchKey.HEM}
+            or set(search_keys.values()) == {SearchKey.COUNTRY, SearchKey.POSTAL_CODE}
+        ):
+            msg = bundle.get("current_date_added")
+            print(msg)
+            logger.warning(msg)
+            df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
+            search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
+            converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE, None, logger, bundle)
+            df = converter.convert(df)
+        return df
+
     @staticmethod
     def _get_group_columns(df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> List[str]:
         return [
@@ -2921,19 +2905,15 @@ class FeaturesEnricher(TransformerMixin):
 
     @staticmethod
     def _get_email_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
-        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]
+        for col, t in search_keys.items():
+            if t == SearchKey.EMAIL:
+                return col
 
     @staticmethod
     def _get_hem_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
-        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]
+        for col, t in search_keys.items():
+            if t == SearchKey.HEM:
+                return col
 
     @staticmethod
     def _get_phone_column(search_keys: Dict[str, SearchKey]) -> Optional[str]:
@@ -2941,42 +2921,8 @@ 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],
-        id_name: str,
+        self, df: pd.DataFrame, meaning_types: Dict[str, FileColumnMeaningType], search_keys: Dict[str, SearchKey]
     ) -> pd.DataFrame:
         # save original order or rows
         original_index_name = df.index.name
@@ -3025,23 +2971,19 @@ 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: id_name})
+        df = df.rename(columns={DEFAULT_INDEX: SYSTEM_RECORD_ID})
 
         # 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[id_name] = (
-            FileColumnMeaningType.SYSTEM_RECORD_ID 
-            if id_name == SYSTEM_RECORD_ID 
-            else FileColumnMeaningType.ENTITY_SYSTEM_RECORD_ID
-        )
+        meaning_types[SYSTEM_RECORD_ID] = FileColumnMeaningType.SYSTEM_RECORD_ID
         return df
 
     def __correct_target(self, df: pd.DataFrame) -> pd.DataFrame:
         target = df[self.TARGET_NAME]
-        if is_string_dtype(target):
+        if is_string_dtype(target) or is_object_dtype(target):
             maybe_numeric_target = pd.to_numeric(target, errors="coerce")
             # If less than 5% is non numeric then leave this rows with NaN target and later it will be dropped
             if maybe_numeric_target.isna().sum() <= _num_samples(df) * 0.05:
@@ -3091,10 +3033,7 @@ 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 not in [SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
-        ]
+        dup_features = [c for c in comparing_columns if c in result_features.columns and c != 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))
@@ -3105,7 +3044,8 @@ class FeaturesEnricher(TransformerMixin):
         result_features = pd.merge(
             df_with_original_index,
             result_features,
-            on=ENTITY_SYSTEM_RECORD_ID,
+            left_on=SYSTEM_RECORD_ID,
+            right_on=SYSTEM_RECORD_ID,
             how="left" if is_transform else "inner",
         )
         result_features = result_features.set_index(original_index_name or DEFAULT_INDEX)
@@ -3316,6 +3256,8 @@ class FeaturesEnricher(TransformerMixin):
             descriptions = []
             for m in autofe_meta:
                 autofe_feature = Feature.from_formula(m.formula)
+                orig_to_hashed = {base_column.original_name: base_column.hashed_name for base_column in m.base_columns}
+                autofe_feature.rename_columns(orig_to_hashed)
                 autofe_feature.set_display_index(m.display_index)
                 if autofe_feature.op.is_vector:
                     continue
@@ -3443,7 +3385,8 @@ class FeaturesEnricher(TransformerMixin):
                 valid_search_keys[column_name] = SearchKey.CUSTOM_KEY
             else:
                 if x[column_name].isnull().all() or (
-                    is_string_dtype(x[column_name]) and (x[column_name].astype("string").str.strip() == "").all()
+                    (is_string_dtype(x[column_name]) or is_object_dtype(x[column_name]))
+                    and (x[column_name].astype("string").str.strip() == "").all()
                 ):
                     raise ValidationError(self.bundle.get("empty_search_key").format(column_name))
 
@@ -3485,13 +3428,13 @@ class FeaturesEnricher(TransformerMixin):
                 self.warning_counter.increment()
 
         if len(valid_search_keys) == 1:
-            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()
+            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()
 
         self.logger.info(f"Prepared search keys: {valid_search_keys}")
 
@@ -3601,68 +3544,61 @@ 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):
-        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 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 not silent_mode:
-                    print(self.bundle.get("postal_code_detected").format(maybe_keys))
+                    print(self.bundle.get("postal_code_detected").format(maybe_key))
 
         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_columns(sample, search_keys)
-            if maybe_key:
-                search_keys[maybe_key[0]] = SearchKey.COUNTRY
-                self.autodetected_search_keys[maybe_key[0]] = 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
                 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()
-            SearchKey.HEM not in search_keys.values()
+            SearchKey.EMAIL not in search_keys.values()
+            and SearchKey.HEM not in search_keys.values()
             and check_need_detect(SearchKey.HEM)
         ):
-            maybe_keys = EmailSearchKeyDetector().get_search_key_columns(sample, search_keys)
-            if maybe_keys:
+            maybe_key = EmailSearchKeyDetector().get_search_key_column(sample)
+            if maybe_key is not None and maybe_key not in search_keys.keys():
                 if self.__is_registered or is_demo_dataset:
-                    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}")
+                    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}")
                     if not silent_mode:
-                        print(self.bundle.get("email_detected").format(maybe_keys))
+                        print(self.bundle.get("email_detected").format(maybe_key))
                 else:
                     self.logger.warning(
-                        f"Autodetected search key EMAIL in column {maybe_keys}."
-                        " But not used because not registered user"
+                        f"Autodetected search key EMAIL in column {maybe_key}. But not used because not registered user"
                     )
                     if not silent_mode:
-                        print(self.bundle.get("email_detected_not_registered").format(maybe_keys))
+                        print(self.bundle.get("email_detected_not_registered").format(maybe_key))
                     self.warning_counter.increment()
 
-        # 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 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 self.__is_registered or is_demo_dataset:
-                    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}")
+                    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}")
                     if not silent_mode:
-                        print(self.bundle.get("phone_detected").format(maybe_keys))
+                        print(self.bundle.get("phone_detected").format(maybe_key))
                 else:
                     self.logger.warning(
-                        f"Autodetected search key PHONE in column {maybe_keys}. "
-                        "But not used because not registered user"
+                        f"Autodetected search key PHONE in column {maybe_key}. But not used because not registered user"
                     )
                     if not silent_mode:
                         print(self.bundle.get("phone_detected_not_registered"))