upgini 1.2.154a4146.dev9__tar.gz → 1.2.155.dev1__tar.gz

{upgini-1.2.154a4146.dev9 → upgini-1.2.155.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.154a4146.dev9
+Version: 1.2.155.dev1
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -34,7 +34,7 @@ Requires-Dist: more-itertools==10.7.0
 Requires-Dist: numpy<3.0.0,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
 Requires-Dist: psutil>=5.9.0
-Requires-Dist: pyarrow==18.1.0
+Requires-Dist: pyarrow==23.0.1
 Requires-Dist: pydantic<3.0.0,>1.0.0
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: python-bidi==0.4.2

{upgini-1.2.154a4146.dev9 → upgini-1.2.155.dev1}/pyproject.toml

@@ -56,7 +56,7 @@ dependencies = [
     "psutil>=5.9.0",
     "category-encoders>=2.8.1",
     "more_itertools==10.7.0",
-    "pyarrow==18.1.0",
+    "pyarrow==23.0.1",
 ]
 
 [project.urls]

upgini-1.2.155.dev1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.155.dev1"

{upgini-1.2.154a4146.dev9 → upgini-1.2.155.dev1}/src/upgini/data_source/data_source_publisher.py

@@ -540,7 +540,8 @@ class DataSourcePublisher:
                         )
 
     @staticmethod
-    def build_place_request(data_table_uri: str,
+    def build_place_request(
+        data_table_uri: str,
         search_keys: Dict[str, SearchKey],
         update_frequency: Union[
             Literal["Daily"], Literal["Weekly"], Literal["Monthly"], Literal["Quarterly"], Literal["Annually"]
@@ -564,7 +565,8 @@ class DataSourcePublisher:
         force_percentile_generation: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
-        ads_hints: Optional[list[AdsHint]] = None) -> Dict:
+        ads_hints: Optional[list[AdsHint]] = None,
+    ) -> Dict:
         if data_table_uri is None or not data_table_uri.startswith("bq://"):
             raise ValidationError(
                 "Unsupported data table uri. It should looks like bq://projectId.datasetId.tableId"

{upgini-1.2.154a4146.dev9 → upgini-1.2.155.dev1}/src/upgini/features_enricher.py

@@ -1772,7 +1772,7 @@ class FeaturesEnricher(TransformerMixin):
         }
         date_column = self._get_date_column(search_keys)
         if date_column:
-            cat_features.discard(date_column)
+            cat_features.discard(to_renamed(date_column))
         return sorted(cat_features)
 
     def _resolve_client_features_in_sampled(
@@ -1878,7 +1878,8 @@ class FeaturesEnricher(TransformerMixin):
 
         file_meta = self._search_task.get_file_metadata(self._get_trace_id())
         fit_dropped_features = list(self.fit_dropped_features or file_meta.droppedColumns or [])
-        renamed_to_original = {renamed: original for original, renamed in columns_renaming.items()}
+        renamed_to_original = dict(columns_renaming)
+        original_to_renamed = {original: hashed for hashed, original in columns_renaming.items()}
         excluding_search_keys_original = [renamed_to_original.get(sk, sk) for sk in excluding_search_keys]
 
         excluded_client_columns = (
@@ -1886,7 +1887,7 @@ class FeaturesEnricher(TransformerMixin):
             + fit_dropped_features
             + [DateTimeConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
         )
-        excluded_client_columns_renamed = {columns_renaming.get(c, c) for c in excluded_client_columns}
+        excluded_client_columns_renamed = {original_to_renamed.get(c, c) for c in excluded_client_columns}
 
         # Client columns for enriched metrics (respects select_features).
         client_features = [
@@ -1937,9 +1938,13 @@ class FeaturesEnricher(TransformerMixin):
             )
 
         fitting_X = X_sorted[baseline_client_features_in_sampled].copy()
-        fitting_enriched_X = enriched_X_sorted[
-            enriched_client_features_in_sampled + existing_selected_enriched_features
-        ].copy()
+        enriched_columns_for_fitting = []
+        seen_enriched_columns: set[str] = set()
+        for column in enriched_client_features_in_sampled + existing_selected_enriched_features:
+            if column not in seen_enriched_columns:
+                enriched_columns_for_fitting.append(column)
+                seen_enriched_columns.add(column)
+        fitting_enriched_X = enriched_X_sorted[enriched_columns_for_fitting].copy()
 
         renamed_generate_features = [columns_renaming.get(c, c) for c in (self.generate_features or [])]
         renamed_client_cat_features = [columns_renaming.get(c, c) for c in (client_cat_features or [])]

{upgini-1.2.154a4146.dev9 → upgini-1.2.155.dev1}/src/upgini/metadata.py

@@ -397,12 +397,13 @@ class AddInfo(BaseModel):
 
 class AdsHintType(str, Enum):
     # BW table column must have type `DATE`
-    DATE_CLUSTER_KEY = "DATE_CLUSTER_KEY" # cluster column also plays role of ADS search key
-    DATE_CLUSTER_SYNTHETIC = "DATE_CLUSTER_SYNTHETIC" # cluster column used only for partition elimination
+    DATE_CLUSTER_KEY = "DATE_CLUSTER_KEY"  # cluster column also plays role of ADS search key
+    DATE_CLUSTER_SYNTHETIC = "DATE_CLUSTER_SYNTHETIC"  # cluster column used only for partition elimination
+
 
 class AdsHint(BaseModel):
     adsHintType: AdsHintType
     hintColumnName: str
     # must be set if registered ADS defined as view and has clustered column in underlying table
     # format: myDatasetId.myTableUsedInViewWithClusterField
-    fullyQualifiedTableName: Optional[str] = None
+    fullyQualifiedTableName: Optional[str] = None

upgini-1.2.154a4146.dev9/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.154a4146.dev9"