tdfs4ds 0.2.4.44__py3-none-any.whl → 0.2.4.46__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.44'
+__version__ = '0.2.4.46'
 import logging
 import json
 

tdfs4ds/feature_store/feature_data_processing.py

@@ -287,10 +287,10 @@ def prepare_feature_ingestion(df, entity_id, feature_names, feature_versions=Non
     # Execute: create volatile table and test unicity
     try:
         tdml.DataFrame.from_query(nested_query).to_sql(
-            table_name=volatile_table_name,
-            temporary=True,
-            primary_index=primary_index.split(','),
-            if_exists='replace'
+            table_name    = volatile_table_name,
+            temporary     = True,
+            primary_index = primary_index.split(','),
+            if_exists     = 'replace'
         )
         nb_duplicates = tdml.execute_sql(query_test_unicity).fetchall()[0][0]
         if nb_duplicates is not None and nb_duplicates > 0:

tdfs4ds/feature_store/feature_store_management.py

@@ -217,7 +217,7 @@ def feature_store_table_creation(entity_id, feature_type, if_exists='fail', prim
     query2 = f"CREATE INDEX (FEATURE_ID) ON {tdfs4ds.SCHEMA}.{table_name};"
 
     # SQL query to comment the table indicating the entity id it is related to
-    query3 = f"COMMENT ON TABLE {tdfs4ds.SCHEMA}.{table_name} IS ' entity id {ENTITY_ID}'"
+    query3 = f"COMMENT ON TABLE {tdfs4ds.SCHEMA}.{table_name} IS 'Feature Store Table'"
 
     # SQL query to create the view
     query_view = f"""

tdfs4ds/utils/filter_management.py

@@ -228,11 +228,26 @@ class FilterManager:
             primary_index = [self.filter_id_name]
 
         logger.debug("Writing hidden table", extra={"primary_index": primary_index})
+        data_types = tdfs4ds.utils.info.get_feature_types_sql_format(df_filter)
+        query_creation = f"""
+        CREATE TABLE {self.schema_name}.{self.table_name} (
+            {', '.join([f'"{k}" {v}' for k,v in data_types.items()])}
+        ) UNIQUE PRIMARY INDEX ({primary_index[0]})
+        """
+        
+        logger.debug("Creating hidden table with SQL:\n%s", query_creation)
+        try:
+            tdml.execute_sql(f"DROP TABLE {self.schema_name}.{self.table_name}")
+        except Exception:
+            logger.debug("Hidden table did not exist; proceeding to create.")
+            pass  # Ignore if table does not exist 
+        tdml.execute_sql(query_creation)
+        logger.debug("Inserting filter data into hidden table")
+
         df_filter.to_sql(
             table_name=self.table_name,
             schema_name=self.schema_name,
-            if_exists="replace",
-            primary_index=primary_index,
+            if_exists="append"
         )
 
         # Create/replace public view with filter_id = 1
@@ -246,6 +261,8 @@ class FilterManager:
         tdml.execute_sql(view_sql)
 
         # Collect stats to help the optimizer
+        for col in df_filter.columns:
+            tdml.execute_sql(f"COLLECT STATISTICS ON {self.schema_name}.{self.table_name} COLUMN ({col})")  
         stats_sql = f"""
         COLLECT STATISTICS USING NO SAMPLE AND NO THRESHOLD
                COLUMN ({self.filter_id_name})

{tdfs4ds-0.2.4.44.dist-info → tdfs4ds-0.2.4.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.44
+Version: 0.2.4.46
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.44.dist-info → tdfs4ds-0.2.4.46.dist-info}/RECORD

@@ -2,7 +2,7 @@ tdfs/__init__.py,sha256=7AcO7uB1opRCt7t2JOHworKimfAaDeO3boRW7u9Geo8,23
 tdfs/datasets.py,sha256=-b2MPEKGki2V1M8iUcoDR9uc2krIK7u1CK-EhChvihs,985
 tdfs/feature_store.py,sha256=Honu7eOAXxP4Ivz0mRlhuNkfTDzgZl5HB1WlQUwzcZ0,31354
 tdfs/data/curves.csv,sha256=q0Tm-0yu7VMK4lHvHpgi1LMeRq0lO5gJy2Q17brKbEM,112488
-tdfs4ds/__init__.py,sha256=6FZfAkc-N5B4M2tvljteayRE1RAbDtSJ8JfWHjaRQWg,61203
+tdfs4ds/__init__.py,sha256=TvxBT_6N5-u3u1qFarsTl4Td7DDBUhH_r_E6XAH6kWg,61203
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -17,22 +17,22 @@ tdfs4ds/dataset/dataset.py,sha256=J_fgfsVdR9zSOXrUOqyotqsUD-GlQMGyuld6ueov45w,76
 tdfs4ds/dataset/dataset_catalog.py,sha256=qxS2thDW2MvsRouSFaX1M0sX2J7IzBAYD8Yf22Tsd5k,16638
 tdfs4ds/feature_store/__init__.py,sha256=a7NPCkpTx40UR5LRErwnskpABG2Vuib7F5wUjaUGCnI,209
 tdfs4ds/feature_store/entity_management.py,sha256=9ltytv3yCTG84NZXBpb1Tlkf9pOxvrNb0MVidU4pwvE,10157
-tdfs4ds/feature_store/feature_data_processing.py,sha256=gjwypiTfwTyGyrP20v35Vu2uGIrCY80OBBeMVBsdjuk,45020
+tdfs4ds/feature_store/feature_data_processing.py,sha256=IrjoL8Q6jI5QELGxSfXu0G5IeqTEEnNJKEoY9ySZF4k,45039
 tdfs4ds/feature_store/feature_query_retrieval.py,sha256=51c6ZNlLFiBIxNPinS8ot8bjWEIb1QV2eVg69yzVF80,35381
-tdfs4ds/feature_store/feature_store_management.py,sha256=mtPQkdMDhcOrhj9IAaH-FEP_znK53cYtEv8zXAbsigg,52123
+tdfs4ds/feature_store/feature_store_management.py,sha256=RZrjjTKjJBmc3wate8A5NsnBsqtY0be18lFx5WdcWy4,52120
 tdfs4ds/process_store/__init__.py,sha256=npHR_xju5ecGmWfYHDyteLwiU3x-cL4HD3sFK_th7xY,229
 tdfs4ds/process_store/process_followup.py,sha256=E4jgQahjhVRBbfAW3JXNLId7H5qV8ozRt-6PyAQuPzg,12583
 tdfs4ds/process_store/process_query_administration.py,sha256=AOufkJ6DFUpBiGm-6Q6Dq0Aovw31UGTscZ3Ya0ewS-0,7851
 tdfs4ds/process_store/process_registration_management.py,sha256=2fFjt4Pmh3An1BUFvRX3xABSlQrlWiEiPQStH3A9Xpk,36130
 tdfs4ds/process_store/process_store_catalog_management.py,sha256=eVUU9uanyXCUkzi2vcHbJPL9qFiXVasnCxPGr-r9EY8,16090
 tdfs4ds/utils/__init__.py,sha256=-yTMfDLZbQnIRQ64s_bczzT21tDW2A8FZeq9PX5SgFU,168
-tdfs4ds/utils/filter_management.py,sha256=bNT2_68fsIMHU_36Giy3VHeuyl4hso60wnpcl3fjyj0,27463
+tdfs4ds/utils/filter_management.py,sha256=zEV3COrxqS_GfE9ogpzKJEfWM_WAnEkTUz8s2OR8JJk,28329
 tdfs4ds/utils/info.py,sha256=sShnUxXMlvCtQ6xtShDhqdpTr6sMG0dZQhNBFgUENDY,12058
 tdfs4ds/utils/lineage.py,sha256=gy5M42qy5fvdWmlohAY3WPYoqAyp5VakeEmeT1YjrJQ,37839
 tdfs4ds/utils/query_management.py,sha256=kWDeTdsYcbpV5Tyhh-8uLRWvXh16nIdXNIJ97w76aNU,4848
 tdfs4ds/utils/time_management.py,sha256=oq_vlMliLuD4hO1G2zwWbj-wv4UzGWhB6-nXIsIyiMk,31935
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.44.dist-info/METADATA,sha256=Pis1-Bf5wXNzAV-6C07_rhPpgjJUpXzDOTC96Hdj02w,14326
-tdfs4ds-0.2.4.44.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.44.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.44.dist-info/RECORD,,
+tdfs4ds-0.2.4.46.dist-info/METADATA,sha256=jS_dfp2mmCTy8mDFZb9OhknREDPrW8dAPQROxRGb4rE,14326
+tdfs4ds-0.2.4.46.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.46.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.46.dist-info/RECORD,,