upgini 1.2.53__tar.gz → 1.2.55a1__tar.gz

{upgini-1.2.53 → upgini-1.2.55a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.53
+Version: 1.2.55a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.2.55a1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.55a1"

{upgini-1.2.53 → upgini-1.2.55a1}/src/upgini/dataset.py

@@ -587,15 +587,23 @@ class Dataset:  # (pd.DataFrame):
         if (
             runtime_parameters is not None
             and runtime_parameters.properties is not None
-            and "generate_features" in runtime_parameters.properties
         ):
-            generate_features = runtime_parameters.properties["generate_features"].split(",")
-            renamed_generate_features = []
-            for f in generate_features:
-                for new_column, orig_column in self.columns_renaming.items():
-                    if f == orig_column:
-                        renamed_generate_features.append(new_column)
-            runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+            if "generate_features" in runtime_parameters.properties:
+                generate_features = runtime_parameters.properties["generate_features"].split(",")
+                renamed_generate_features = []
+                for f in generate_features:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_generate_features.append(new_column)
+                runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+            if "columns_for_online_api" in runtime_parameters.properties:
+                columns_for_online_api = runtime_parameters.properties["columns_for_online_api"].split(",")
+                renamed_columns_for_online_api = []
+                for f in columns_for_online_api:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_columns_for_online_api.append(new_column)
+                runtime_parameters.properties["columns_for_online_api"] = ",".join(renamed_columns_for_online_api)
 
         return runtime_parameters
 

{upgini-1.2.53 → upgini-1.2.55a1}/src/upgini/features_enricher.py

@@ -222,6 +222,7 @@ class FeaturesEnricher(TransformerMixin):
         loss: Optional[str] = None,
         detect_missing_search_keys: bool = True,
         generate_features: Optional[List[str]] = None,
+        columns_for_online_api: Optional[List[str]] = None,
         round_embeddings: Optional[int] = None,
         logs_enabled: bool = True,
         raise_validation_error: bool = True,
@@ -268,7 +269,7 @@ class FeaturesEnricher(TransformerMixin):
         self.eval_set: Optional[List[Tuple]] = None
         self.autodetected_search_keys: Dict[str, SearchKey] = {}
         self.imbalanced = False
-        self.fit_select_features = False
+        self.fit_select_features = True
         self.__cached_sampled_datasets: Dict[str, Tuple[pd.DataFrame, pd.DataFrame, pd.Series, Dict, Dict, Dict]] = (
             dict()
         )
@@ -345,6 +346,9 @@ class FeaturesEnricher(TransformerMixin):
                     self.logger.error(msg)
                     raise ValidationError(msg)
                 self.runtime_parameters.properties["round_embeddings"] = round_embeddings
+        self.columns_for_online_api = columns_for_online_api
+        if columns_for_online_api is not None:
+            self.runtime_parameters.properties["columns_for_online_api"] = ",".join(columns_for_online_api)
         maybe_downsampling_limit = self.runtime_parameters.properties.get("downsampling_limit")
         if maybe_downsampling_limit is not None:
             Dataset.FIT_SAMPLE_THRESHOLD = int(maybe_downsampling_limit)
@@ -2608,17 +2612,18 @@ if response.status_code == 200:
             checked_generate_features = []
             for gen_feature in self.generate_features:
                 if gen_feature not in x_columns:
-                    if gen_feature == self._get_phone_column(self.search_keys):
-                        raise ValidationError(
-                            self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
-                        )
-                    else:
-                        self.__log_warning(self.bundle.get("missing_generate_feature").format(gen_feature, x_columns))
+                    msg = self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
+                    self.__log_warning(msg)
                 else:
                     checked_generate_features.append(gen_feature)
             self.generate_features = checked_generate_features
             self.runtime_parameters.properties["generate_features"] = ",".join(self.generate_features)
 
+        if self.columns_for_online_api is not None and len(self.columns_for_online_api) > 0:
+            for column in self.columns_for_online_api:
+                if column not in validated_X.columns:
+                    raise ValidationError(self.bundle.get("missing_column_for_online_api").format(column))
+
         if self.id_columns is not None:
             for id_column in self.id_columns:
                 if id_column not in validated_X.columns:

{upgini-1.2.53 → upgini-1.2.55a1}/src/upgini/resource_bundle/strings.properties

@@ -111,6 +111,7 @@ x_is_empty=X is empty
 y_is_empty=y is empty
 x_contains_reserved_column_name=Column name {} is reserved. Please rename column and try again
 missing_generate_feature=Feature {} specified in `generate_features` is not present in input columns: {}
+missing_column_for_online_api=Column {} specified in `columns_for_online_api` is not present in input columns: {}
 x_unstable_by_date=Your training sample is unstable in number of rows per date. It is recommended to redesign the training sample
 train_unstable_target=Your training sample contains an unstable target event, PSI = {}. This will lead to unstable scoring on deferred samples. It is recommended to redesign the training sample
 eval_unstable_target=Your training and evaluation samples have a difference in target distribution. PSI = {}. The results will be unstable. It is recommended to redesign the training and evaluation samples

{upgini-1.2.53 → upgini-1.2.55a1}/src/upgini/utils/email_utils.py

@@ -116,17 +116,17 @@ class EmailSearchKeyConverter:
         else:
             df[self.hem_column] = df[self.hem_column].astype("string").str.lower()
 
-        del self.search_keys[self.email_column]
-        if self.email_column in self.unnest_search_keys:
-            self.unnest_search_keys.remove(self.email_column)
+        # del self.search_keys[self.email_column]
+        # if self.email_column in self.unnest_search_keys:
+        #     self.unnest_search_keys.remove(self.email_column)
 
         one_domain_name = self.email_column + self.ONE_DOMAIN_SUFFIX
         df[one_domain_name] = df[self.email_column].apply(self._email_to_one_domain)
         self.columns_renaming[one_domain_name] = original_email_column
         self.search_keys[one_domain_name] = SearchKey.EMAIL_ONE_DOMAIN
 
-        if self.email_converted_to_hem:
-            df = df.drop(columns=self.email_column)
-            del self.columns_renaming[self.email_column]
+        # if self.email_converted_to_hem:
+        #     df = df.drop(columns=self.email_column)
+        #     del self.columns_renaming[self.email_column]
 
         return df

upgini-1.2.53/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.53"