upgini 1.1.236a1__tar.gz → 1.1.237__tar.gz

{upgini-1.1.236a1/src/upgini.egg-info → upgini-1.1.237}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.236a1
+Version: 1.1.237
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.236a1 → upgini-1.1.237}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.236a1"
+version = "1.1.237"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.236a1 → upgini-1.1.237}/src/upgini/data_source/data_source_publisher.py

@@ -62,6 +62,7 @@ class DataSourcePublisher:
         trace_id = str(uuid.uuid4())
 
         with MDC(trace_id=trace_id):
+            task_id = None
             try:
                 if data_table_uri is None or not data_table_uri.startswith("bq://"):
                     raise ValidationError(
@@ -148,6 +149,12 @@ class DataSourcePublisher:
                 self.logger.info(msg)
                 print(msg)
                 return data_table_id
+            except KeyboardInterrupt:
+                if task_id is not None:
+                    msg = f"Stopping AdsManagementTask {task_id}"
+                    print(msg)
+                    self.logger.info(msg)
+                    self._rest_client.stop_ads_management_task(task_id, trace_id)
             except Exception:
                 self.logger.exception("Failed to register data table")
                 raise

{upgini-1.1.236a1 → upgini-1.1.237}/src/upgini/dataset.py

@@ -382,7 +382,7 @@ class Dataset:  # (pd.DataFrame):
 
             if is_string_dtype(self.data[postal_code]):
                 try:
-                    self.data[postal_code] = self.data[postal_code].astype("Float64").astype("Int64").astype("string")
+                    self.data[postal_code] = self.data[postal_code].astype("float64").astype("Int64").astype("string")
                 except Exception:
                     pass
             elif is_float_dtype(self.data[postal_code]):

{upgini-1.1.236a1 → upgini-1.1.237}/src/upgini/features_enricher.py

@@ -21,8 +21,8 @@ from scipy.stats import ks_2samp
 from sklearn.base import TransformerMixin
 from sklearn.exceptions import NotFittedError
 from sklearn.model_selection import BaseCrossValidator
-from upgini.autofe.feature import Feature
 
+from upgini.autofe.feature import Feature
 from upgini.data_source.data_source_publisher import CommercialSchema
 from upgini.dataset import Dataset
 from upgini.errors import HttpError, ValidationError
@@ -1450,15 +1450,17 @@ class FeaturesEnricher(TransformerMixin):
             rows_to_drop=rows_to_drop,
         )
 
-        original_df_sampled = self.df_with_original_index[self.df_with_original_index[SYSTEM_RECORD_ID].isin(fit_features[SYSTEM_RECORD_ID])]
+        original_df_sampled = self.df_with_original_index[
+            self.df_with_original_index[SYSTEM_RECORD_ID].isin(fit_features[SYSTEM_RECORD_ID])
+            ]
         enriched_X = drop_existing_columns(enriched_Xy, TARGET)
         if EVAL_SET_INDEX in original_df_sampled.columns:
-            X_sampled = original_df_sampled.query(f"{EVAL_SET_INDEX} == 0")
+            Xy_sampled = original_df_sampled.query(f"{EVAL_SET_INDEX} == 0")
         else:
-            X_sampled = original_df_sampled
-        X_sampled = drop_existing_columns(X_sampled, [SYSTEM_RECORD_ID, EVAL_SET_INDEX, TARGET])
+            Xy_sampled = original_df_sampled
+        X_sampled = drop_existing_columns(Xy_sampled, [SYSTEM_RECORD_ID, EVAL_SET_INDEX, TARGET])
         search_keys = self.fit_search_keys
-        y_sampled = enriched_Xy[TARGET].copy()
+        y_sampled = Xy_sampled[TARGET].copy()
 
         self.logger.info(f"Shape of enriched_X: {enriched_X.shape}")
         self.logger.info(f"Shape of X after sampling: {X_sampled.shape}")
@@ -1472,9 +1474,9 @@ class FeaturesEnricher(TransformerMixin):
 
             for idx in range(len(eval_set)):
                 enriched_eval_X = drop_existing_columns(enriched_eval_sets[idx + 1], TARGET)
-                eval_X_sampled = original_df_sampled.query(f"{EVAL_SET_INDEX} == {idx + 1}")
-                eval_X_sampled = drop_existing_columns(eval_X_sampled, [SYSTEM_RECORD_ID, EVAL_SET_INDEX, TARGET])
-                eval_y_sampled = enriched_eval_sets[idx + 1][TARGET].copy()
+                eval_Xy_sampled = original_df_sampled.query(f"{EVAL_SET_INDEX} == {idx + 1}")
+                eval_X_sampled = drop_existing_columns(eval_Xy_sampled, [SYSTEM_RECORD_ID, EVAL_SET_INDEX, TARGET])
+                eval_y_sampled = eval_Xy_sampled[TARGET].copy()
                 eval_set_sampled_dict[idx] = (eval_X_sampled, enriched_eval_X, eval_y_sampled)
 
         self.__cached_sampled_datasets = (X_sampled, y_sampled, enriched_X, eval_set_sampled_dict, search_keys)

{upgini-1.1.236a1 → upgini-1.1.237}/src/upgini/http.py

@@ -289,7 +289,7 @@ class _RestClient:
     GET_ALL_ADS_DESCRIPTIONS_URI = "private/api/v2/ads/descriptions"
     GET_ACTIVE_ADS_DEFINITIONS_URI = "private/api/v2/ads/definitions"
     UPLOAD_ONLINE_URI = "private/api/v2/ads/upload-online"
-    UPLOAD_ONLINE_ALL_URI = "private/api/v2/ads/upload-online-all"
+    STOP_ADS_MANAGEMENT_TASK_URI_FMT = "private/api/v2/ads/management-task/{0}/stop"
 
     ACCESS_TOKEN_HEADER_NAME = "Authorization"
     CONTENT_TYPE_HEADER_NAME = "Content-Type"
@@ -751,6 +751,10 @@ class _RestClient:
         response = self._with_unauth_retry(lambda: self._send_post_req(api_path, trace_id, request, result_format=None))
         return response["adsManagementTaskId"]
 
+    def stop_ads_management_task(self, ads_management_task_id: str, trace_id: str):
+        api_path = self.STOP_ADS_MANAGEMENT_TASK_URI_FMT.format(ads_management_task_id)
+        self._with_unauth_retry(lambda: self._send_post_req(api_path, trace_id))
+
     # ---
 
     def _send_get_req(self, api_path: str, trace_id: Optional[str], additional_headers: Optional[dict] = None):

{upgini-1.1.236a1 → upgini-1.1.237/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.236a1
+Version: 1.1.237
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers