upgini 1.1.293__tar.gz → 1.1.295__tar.gz

{upgini-1.1.293 → upgini-1.1.295}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.293
+Version: 1.1.295
 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-1.1.295/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.295"

{upgini-1.1.293 → upgini-1.1.295}/src/upgini/data_source/data_source_publisher.py

@@ -95,6 +95,11 @@ class DataSourcePublisher:
                         "With MSISDN and DATE keys one of the snapshot_frequency_days or"
                         " join_date_abs_limit_days parameters is required"
                     )
+                if (
+                    set(search_keys.values()) == {SearchKey.PHONE, SearchKey.DATE}
+                    or set(search_keys.values()) == {SearchKey.HEM, SearchKey.DATE}
+                ) and not date_format:
+                    raise ValidationError("date_format argument is required for PHONE+DATE and HEM+DATE search keys")
 
                 request = {
                     "dataTableUri": data_table_uri,

{upgini-1.1.293 → upgini-1.1.295}/src/upgini/metrics.py

@@ -679,6 +679,11 @@ def validate_scoring_argument(scoring: Union[Callable, str, None]):
             raise ValidationError(
                 f"Invalid scoring function passed {scoring}. It should accept 3 input arguments: estimator, x, y"
             )
+    elif scoring is not None:
+        raise ValidationError(
+            f"Invalid scoring argument passed {scoring}. It should be string with scoring name or function"
+            " that accepts 3 input arguments: estimator, x, y"
+        )
 
 
 def _get_scorer_by_name(scoring: str) -> Tuple[Callable, str, int]:

upgini-1.1.293/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.293"

{upgini-1.1.293 → upgini-1.1.295}/src/upgini/features_enricher.py

@@ -2557,9 +2557,6 @@ class FeaturesEnricher(TransformerMixin):
         return [c for c, v in search_keys_with_autodetection.items() if v.value.value in keys]
 
     def _validate_X(self, X, is_transform=False) -> pd.DataFrame:
-        if _num_samples(X) == 0:
-            raise ValidationError(self.bundle.get("x_is_empty"))
-
         if isinstance(X, pd.DataFrame):
             if isinstance(X.columns, pd.MultiIndex) or isinstance(X.index, pd.MultiIndex):
                 raise ValidationError(self.bundle.get("x_multiindex_unsupported"))
@@ -2573,6 +2570,9 @@ class FeaturesEnricher(TransformerMixin):
         else:
             raise ValidationError(self.bundle.get("unsupported_x_type").format(type(X)))
 
+        if _num_samples(X) == 0:
+            raise ValidationError(self.bundle.get("x_is_empty"))
+
         if len(set(validated_X.columns)) != len(validated_X.columns):
             raise ValidationError(self.bundle.get("x_contains_dup_columns"))
         if not is_transform and not validated_X.index.is_unique: