upgini 1.1.301__tar.gz → 1.1.303__tar.gz

{upgini-1.1.301 → upgini-1.1.303}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.301
+Version: 1.1.303
 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-1.1.303/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.303"

{upgini-1.1.301 → upgini-1.1.303}/src/upgini/data_source/data_source_publisher.py

@@ -82,6 +82,9 @@ class DataSourcePublisher:
 
         date_format - optional str - format of date if it is present in search keys
 
+        features_for_embeddings - optional list of str - list of features that should be used for GPT features
+            generation
+
         ...
 
         data_table_id_to_replace - optional str - id of registered ADS that should be replaced by new table

{upgini-1.1.301 → upgini-1.1.303}/src/upgini/features_enricher.py

@@ -3483,6 +3483,9 @@ class FeaturesEnricher(TransformerMixin):
         is_transform=False,
         silent_mode=False,
     ):
+        for _, key_type in search_keys.items():
+            if not isinstance(key_type, SearchKey):
+                raise ValidationError(self.bundle.get("unsupported_type_of_search_key").format(key_type))
         valid_search_keys = {}
         unsupported_search_keys = {
             SearchKey.IP_RANGE_FROM,

{upgini-1.1.301 → upgini-1.1.303}/src/upgini/metadata.py

@@ -191,7 +191,7 @@ class FileColumnMetadata(BaseModel):
     # is this column contains keys from multiple key columns like msisdn1, msisdn2
     isUnnest: bool = False
     # list of original etalon key column names like msisdn1, msisdn2
-    unnestKeyNames: Optional[list[str]]
+    unnestKeyNames: Optional[List[str]]
 
 
 class FileMetadata(BaseModel):

{upgini-1.1.301 → upgini-1.1.303}/src/upgini/resource_bundle/strings.properties

@@ -85,6 +85,7 @@ unregistered_only_personal_keys=Only personal search keys used. Api_key from pro
 search_key_not_found=Column `{}` from search_keys was not found in X dataframe: {}
 numeric_search_key_not_found=Index {} in search_keys is out of bounds for {} columns of X dataframe
 unsupported_search_key_type=Unsupported type of key in search_keys: {}
+unsupported_type_of_search_key=Unsupported type of search key: {}. It should be a member of SearcKey
 search_key_country_and_country_code=\nWARNING: SearchKey.COUNTRY and country_code parameter were passed simultaniously. Parameter country_code will be ignored
 empty_search_key=Search key {} is empty. Please fill values or remove this search key
 single_constant_search_key=\nWARNING: Constant value detected for the {} search key in the X dataframe: {}.\nThat search key will add constant features for different y values.\nPlease add extra search keys with non constant values, like the COUNTRY, POSTAL_CODE, DATE, PHONE NUMBER, EMAIL/HEM or IPv4

{upgini-1.1.301 → upgini-1.1.303}/src/upgini/utils/datetime_utils.py

@@ -31,7 +31,7 @@ DATE_FORMATS = [
     "%Y-%m-%dT%H:%M:%S.%f",
 ]
 
-DATETIME_PATTERN = r"^[\d\s\.\-:T]+$"
+DATETIME_PATTERN = r"^[\d\s\.\-:T/]+$"
 
 
 class DateTimeSearchKeyConverter:
@@ -147,7 +147,10 @@ class DateTimeSearchKeyConverter:
                     return pd.to_datetime(df[self.date_column], format=date_format)
                 except ValueError:
                     pass
-            raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
+            try:
+                return pd.to_datetime(df[self.date_column])
+            except ValueError:
+                raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
 
 
 def is_time_series(df: pd.DataFrame, date_col: str) -> bool:

upgini-1.1.301/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.301"