upgini 1.2.51__tar.gz → 1.2.52__tar.gz

{upgini-1.2.51 → upgini-1.2.52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.51
+Version: 1.2.52
 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-1.2.52/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.52"

{upgini-1.2.51 → upgini-1.2.52}/src/upgini/features_enricher.py

@@ -2270,7 +2270,6 @@ if response.status_code == 200:
                 df = converter.convert(df)
 
             ip_column = self._get_ip_column(search_keys)
-            ip_prefix_column = None
             if ip_column:
                 converter = IpSearchKeyConverter(
                     ip_column,
@@ -2281,7 +2280,6 @@ if response.status_code == 200:
                     self.logger,
                 )
                 df = converter.convert(df)
-                ip_prefix_column = converter.ip_prefix_column
 
             phone_column = self._get_phone_column(search_keys)
             country_column = self._get_country_column(search_keys)
@@ -2301,15 +2299,12 @@ if response.status_code == 200:
             # 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()}
-            if ip_prefix_column:
-                meaning_types[ip_prefix_column] = FileColumnMeaningType.IP_PREFIX
             for col in features_for_transform:
                 meaning_types[col] = FileColumnMeaningType.FEATURE
             features_not_to_pass = [
                 c
                 for c in df.columns
                 if c not in search_keys.keys()
-                and c != ip_prefix_column
                 and c not in features_for_transform
                 and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
             ]
@@ -2771,7 +2766,6 @@ if response.status_code == 200:
             df = converter.convert(df)
 
         ip_column = self._get_ip_column(self.fit_search_keys)
-        ip_prefix_column = None
         if ip_column:
             converter = IpSearchKeyConverter(
                 ip_column,
@@ -2782,7 +2776,6 @@ if response.status_code == 200:
                 self.logger,
             )
             df = converter.convert(df)
-            ip_prefix_column = converter.ip_prefix_column
         phone_column = self._get_phone_column(self.fit_search_keys)
         country_column = self._get_country_column(self.fit_search_keys)
         if phone_column:
@@ -2803,7 +2796,6 @@ if response.status_code == 200:
             EVAL_SET_INDEX,
             ENTITY_SYSTEM_RECORD_ID,
             SEARCH_KEY_UNNEST,
-            ip_prefix_column,
         ] + list(self.fit_search_keys.keys())
         if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
             non_feature_columns.append(DateTimeSearchKeyConverter.DATETIME_COL)
@@ -2825,8 +2817,6 @@ if response.status_code == 200:
             **{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},
         }
-        if ip_prefix_column:
-            meaning_types[ip_prefix_column] = FileColumnMeaningType.IP_PREFIX
         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:

{upgini-1.2.51 → upgini-1.2.52}/src/upgini/metadata.py

@@ -67,6 +67,7 @@ class SearchKey(Enum):
     IP_BINARY = FileColumnMeaningType.IP_BINARY
     IP_RANGE_FROM_BINARY = FileColumnMeaningType.IP_RANGE_FROM_BINARY
     IP_RANGE_TO_BINARY = FileColumnMeaningType.IP_RANGE_TO_BINARY
+    IP_PREFIX = FileColumnMeaningType.IP_PREFIX
 
     # For data source registration. Don't use it for FeaturesEnricher
     EMAIL_ONE_DOMAIN = FileColumnMeaningType.EMAIL_ONE_DOMAIN

{upgini-1.2.51 → upgini-1.2.52}/src/upgini/utils/ip_utils.py

@@ -33,7 +33,6 @@ class IpSearchKeyConverter:
         else:
             self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
-        self.ip_prefix_column = None
 
     @staticmethod
     def _ip_to_int(ip: Optional[_BaseAddress]) -> Optional[int]:
@@ -131,16 +130,18 @@ class IpSearchKeyConverter:
         # )
         ip_binary = self.ip_column + "_binary"
         df[ip_binary] = df[self.ip_column].apply(self._ip_to_binary)
-        self.ip_prefix_column = self.ip_column + "_prefix"
-        df[self.ip_prefix_column] = df[self.ip_column].apply(self._ip_to_prefix)
+        ip_prefix_column = self.ip_column + "_prefix"
+        df[ip_prefix_column] = df[self.ip_column].apply(self._ip_to_prefix)
 
         df = df.drop(columns=self.ip_column)
         del self.search_keys[self.ip_column]
         del self.columns_renaming[self.ip_column]
         # self.search_keys[ipv6] = SearchKey.IPV6_ADDRESS
         self.search_keys[ip_binary] = SearchKey.IP_BINARY
+        self.search_keys[ip_prefix_column] = SearchKey.IP_PREFIX
         # self.columns_renaming[ipv6] = original_ip
         self.columns_renaming[ip_binary] = original_ip
+        self.columns_renaming[ip_prefix_column] = original_ip
 
         return df
 

upgini-1.2.51/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.51"