upgini 1.2.50__tar.gz → 1.2.52__tar.gz

{upgini-1.2.50 → upgini-1.2.52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.50
+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-1.2.50 → upgini-1.2.52}/src/upgini/features_enricher.py

@@ -2776,7 +2776,6 @@ if response.status_code == 200:
                 self.logger,
             )
             df = converter.convert(df)
-
         phone_column = self._get_phone_column(self.fit_search_keys)
         country_column = self._get_country_column(self.fit_search_keys)
         if phone_column:
@@ -2792,9 +2791,12 @@ if response.status_code == 200:
             converter = PostalCodeSearchKeyConverter(postal_code)
             df = converter.convert(df)
 
-        non_feature_columns = [self.TARGET_NAME, EVAL_SET_INDEX, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST] + list(
-            self.fit_search_keys.keys()
-        )
+        non_feature_columns = [
+            self.TARGET_NAME,
+            EVAL_SET_INDEX,
+            ENTITY_SYSTEM_RECORD_ID,
+            SEARCH_KEY_UNNEST,
+        ] + list(self.fit_search_keys.keys())
         if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
             non_feature_columns.append(DateTimeSearchKeyConverter.DATETIME_COL)
 

{upgini-1.2.50 → upgini-1.2.52}/src/upgini/metadata.py

@@ -44,6 +44,7 @@ class FileColumnMeaningType(Enum):
     ENTITY_SYSTEM_RECORD_ID = "ENTITY_SYSTEM_RECORD_ID"
     UNNEST_KEY = "UNNEST_KEY"
     IP_BINARY = "IP_BINARY"
+    IP_PREFIX = "IP_PREFIX"
     IP_RANGE_FROM_BINARY = "IP_RANGE_FROM_BINARY"
     IP_RANGE_TO_BINARY = "IP_RANGE_TO_BINARY"
 
@@ -66,6 +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-1.2.50 → upgini-1.2.52}/src/upgini/utils/ip_utils.py

@@ -36,6 +36,8 @@ class IpSearchKeyConverter:
 
     @staticmethod
     def _ip_to_int(ip: Optional[_BaseAddress]) -> Optional[int]:
+        if ip is None:
+            return None
         try:
             if isinstance(ip, (IPv4Address, IPv6Address)):
                 return int(ip)
@@ -44,6 +46,8 @@ class IpSearchKeyConverter:
 
     @staticmethod
     def _ip_to_binary(ip: Optional[_BaseAddress]) -> Optional[bytes]:
+        if ip is None:
+            return None
         try:
             if isinstance(ip, IPv6Address) and ip.ipv4_mapped is not None:
                 return ip.ipv4_mapped.packed
@@ -52,6 +56,20 @@ class IpSearchKeyConverter:
         except Exception:
             pass
 
+    @staticmethod
+    def _ip_to_prefix(ip: Optional[_BaseAddress]) -> Optional[str]:
+        if ip is None:
+            return None
+        try:
+            if isinstance(ip, IPv6Address):
+                if ip.ipv4_mapped is not None:
+                    return ".".join(ip.ipv4_mapped.exploded.split(".")[:2])
+                return ":".join(ip.exploded.split(":")[:2])  # TODO use 3 in future
+            else:
+                return ".".join(ip.exploded.split(".")[:2])
+        except Exception:
+            pass
+
     @staticmethod
     def _ip_to_int_str(ip: Optional[_BaseAddress]) -> Optional[str]:
         try:
@@ -102,24 +120,28 @@ class IpSearchKeyConverter:
         # self.search_keys[ipv4] = SearchKey.IP
         # self.columns_renaming[ipv4] = original_ip
 
-        ipv6 = self.ip_column + "_v6"
-        df[ipv6] = (
-            df[self.ip_column]
-            .apply(self._to_ipv6)
-            .apply(self._ip_to_int_str)
-            .astype("string")
-            # .str.replace(".0", "", regex=False)
-        )
-        # ip_binary = self.ip_column + "_binary"
-        # df[ip_binary] = df[self.ip_column].apply(self._ip_to_binary)
+        # ipv6 = self.ip_column + "_v6"
+        # df[ipv6] = (
+        #     df[self.ip_column]
+        #     .apply(self._to_ipv6)
+        #     .apply(self._ip_to_int_str)
+        #     .astype("string")
+        #     # .str.replace(".0", "", regex=False)
+        # )
+        ip_binary = self.ip_column + "_binary"
+        df[ip_binary] = df[self.ip_column].apply(self._ip_to_binary)
+        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.columns_renaming[ipv6] = original_ip
-        # self.columns_renaming[ip_binary] = original_ip
+        # 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-1.2.50/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.50"