upgini 1.2.33__tar.gz → 1.2.34__tar.gz

{upgini-1.2.33 → upgini-1.2.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.33
+Version: 1.2.34
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -37,7 +37,7 @@ Requires-Dist: python-dateutil>=2.8.0
 Requires-Dist: python-json-logger>=2.0.2
 Requires-Dist: requests>=2.8.0
 Requires-Dist: scikit-learn>=1.3.0
-Requires-Dist: xhtml2pdf==0.2.11
+Requires-Dist: xhtml2pdf<0.3.0,>=0.2.11
 Description-Content-Type: text/markdown
 
 

{upgini-1.2.33 → upgini-1.2.34}/pyproject.toml

@@ -47,7 +47,7 @@ dependencies = [
     "requests>=2.8.0",
     "scikit-learn>=1.3.0",
     "python-bidi==0.4.2",
-    "xhtml2pdf==0.2.11",
+    "xhtml2pdf>=0.2.11,<0.3.0",
     "jarowinkler>=2.0.0",
     "levenshtein>=0.25.1",
 ]

upgini-1.2.34/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.34"

{upgini-1.2.33 → upgini-1.2.34}/src/upgini/dataset.py

@@ -422,11 +422,11 @@ class Dataset:  # (pd.DataFrame):
                     + "".join("<tr>" + "".join(map(map_color, row[1:])) + "</tr>" for row in df_stats.itertuples())
                     + "</table>"
                 )
-                print()
                 display(HTML(html_stats))
-            except (ImportError, NameError):
                 print()
+            except (ImportError, NameError):
                 print(df_stats)
+                print()
 
         if len(self.data) == 0:
             raise ValidationError(self.bundle.get("all_search_keys_invalid"))
@@ -494,11 +494,17 @@ class Dataset:  # (pd.DataFrame):
             taskType=self.task_type,
         )
 
+    @staticmethod
+    def is_column_binary_type(column):
+        return column.apply(lambda x: x is None or isinstance(x, (bytes, bytearray))).all()
+
     def __get_data_type(self, pandas_data_type, column_name: str) -> DataType:
         if is_integer_dtype(pandas_data_type):
             return DataType.INT
         elif is_float_dtype(pandas_data_type):
             return DataType.DECIMAL
+        elif self.is_column_binary_type(self.data[column_name]):
+            return DataType.BYTES
         elif is_string_dtype(pandas_data_type) or is_object_dtype(pandas_data_type):
             return DataType.STRING
         else:

{upgini-1.2.33 → upgini-1.2.34}/src/upgini/features_enricher.py

@@ -1843,7 +1843,8 @@ class FeaturesEnricher(TransformerMixin):
                 not self.disable_force_downsampling
                 and self.generate_features is not None
                 and phone_column is not None
-                and self.fit_columns_renaming[phone_column] in self.generate_features
+                and self.fit_columns_renaming is not None
+                and self.fit_columns_renaming.get(phone_column) in self.generate_features
                 and num_samples > Dataset.FORCE_SAMPLE_SIZE
             )
             if force_downsampling:

{upgini-1.2.33 → upgini-1.2.34}/src/upgini/metadata.py

@@ -43,6 +43,9 @@ class FileColumnMeaningType(Enum):
     EVAL_SET_INDEX = "EVAL_SET_INDEX"
     ENTITY_SYSTEM_RECORD_ID = "ENTITY_SYSTEM_RECORD_ID"
     UNNEST_KEY = "UNNEST_KEY"
+    IP_BINARY = "IP_BINARY"
+    IP_RANGE_FROM_BINARY = "IP_RANGE_FROM_BINARY"
+    IP_RANGE_TO_BINARY = "IP_RANGE_TO_BINARY"
 
 
 class SearchKey(Enum):
@@ -60,6 +63,9 @@ class SearchKey(Enum):
     IPV6_ADDRESS = FileColumnMeaningType.IPV6_ADDRESS
     IPV6_RANGE_FROM = FileColumnMeaningType.IPV6_RANGE_FROM
     IPV6_RANGE_TO = FileColumnMeaningType.IPV6_RANGE_TO
+    IP_BINARY = FileColumnMeaningType.IP_BINARY
+    IP_RANGE_FROM_BINARY = FileColumnMeaningType.IP_RANGE_FROM_BINARY
+    IP_RANGE_TO_BINARY = FileColumnMeaningType.IP_RANGE_TO_BINARY
 
     # For data source registration. Don't use it for FeaturesEnricher
     EMAIL_ONE_DOMAIN = FileColumnMeaningType.EMAIL_ONE_DOMAIN
@@ -112,6 +118,12 @@ class SearchKey(Enum):
             return SearchKey.MSISDN_RANGE_FROM
         if meaning_type == FileColumnMeaningType.MSISDN_RANGE_TO:
             return SearchKey.MSISDN_RANGE_TO
+        if meaning_type == FileColumnMeaningType.IP_BINARY:
+            return SearchKey.IP_BINARY
+        if meaning_type == FileColumnMeaningType.IP_RANGE_FROM_BINARY:
+            return SearchKey.IP_RANGE_FROM_BINARY
+        if meaning_type == FileColumnMeaningType.IP_RANGE_TO_BINARY:
+            return SearchKey.IP_RANGE_TO_BINARY
 
     @staticmethod
     def find_key(search_keys: Dict[str, SearchKey], keys: Union[SearchKey, List[SearchKey]]) -> Optional[SearchKey]:
@@ -136,6 +148,7 @@ class DataType(Enum):
     DATE_TIME = "DATE_TIME"
     STRING = "STRING"
     BOOLEAN = "BOOLEAN"
+    BYTES = "BYTES"
 
 
 class ModelTaskType(Enum):

{upgini-1.2.33 → upgini-1.2.34}/src/upgini/utils/ip_utils.py

@@ -42,6 +42,16 @@ class IpSearchKeyConverter:
         except Exception:
             pass
 
+    @staticmethod
+    def _ip_to_binary(ip: Optional[_BaseAddress]) -> Optional[bytes]:
+        try:
+            if isinstance(ip, IPv6Address) and ip.ipv4_mapped is not None:
+                return ip.ipv4_mapped.packed
+            else:
+                return ip.packed
+        except Exception:
+            pass
+
     @staticmethod
     def _ip_to_int_str(ip: Optional[_BaseAddress]) -> Optional[str]:
         try:
@@ -100,11 +110,16 @@ class IpSearchKeyConverter:
             .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)
+
         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  # could be __unnest_ip...
+        self.columns_renaming[ip_binary] = original_ip
 
         return df
 

upgini-1.2.33/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.33"