upgini 1.2.33__py3-none-any.whl → 1.2.34a1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.33"
+__version__ = "1.2.34a1"

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/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/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.dist-info → upgini-1.2.34a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.33
+Version: 1.2.34a1
 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-1.2.33.dist-info → upgini-1.2.34a1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=ozUAhuj1IzPzq1FQeoqbf-7laxntI-m4qA0LSTBVtrw,23
+upgini/__about__.py,sha256=SukQ1Uy5sk-JVIQnHlOf7tk3UiWGJcs49nQJPj7NTPU,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=KnkqV7Nnx3kxfQ89giDao3bmCm4MFJWqJUrONy85E-k,32030
+upgini/dataset.py,sha256=rUBE7_G7CLaaHAviFEyVPqjVSsX1DaLmi1dGFQR-eEo,32279
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=q11aMFPlCJy1m4sOFfGZFfb4vdG3-hdd0wgm2BXgs9A,194748
 upgini/http.py,sha256=plZGTGoi1h2edd8Cnjt4eYB8t4NbBGnZz7DtPTByiNc,42885
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
-upgini/metadata.py,sha256=ACzIQQwCHCFHlUqXqKpxd3IQ4bBAaVvy8UaCGTqLGQs,11278
+upgini/metadata.py,sha256=sB5uU-fdz_dA6g-PO6A8FzwIfDbkcFOewcpNs2xZzoY,11943
 upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
@@ -51,7 +51,7 @@ upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0-
 upgini/utils/feature_info.py,sha256=Tp_2g5-rCjY4NpzKhzxwNxuqH5FFL8vG94OU5kH6wzk,6702
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
-upgini/utils/ip_utils.py,sha256=Q6vb7Sr5Khx3Sq3eENjW2qCXKej_S5jZbneH6zEOkzQ,5171
+upgini/utils/ip_utils.py,sha256=n_ZY2PPVsby6Iq3N_uZsBMWjD2i5cY8WnoEnGcgpYH4,5717
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Ed5IXkPjV9AfAZQAwCYksAmKaPGQliplvDYS_yeWdfk,11330
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.33.dist-info/METADATA,sha256=EG9Nr1Z8cls4rBaqrPykCTWZhSSoSxPaICd1EylsiKE,48587
-upgini-1.2.33.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.33.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.33.dist-info/RECORD,,
+upgini-1.2.34a1.dist-info/METADATA,sha256=JXU1l_ufUpd3UDrDM93WUN9zraD-BECLoI7AFczeB2A,48589
+upgini-1.2.34a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.34a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.34a1.dist-info/RECORD,,