tdfs4ds 0.2.4.15__py3-none-any.whl → 0.2.4.16__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.15'
+__version__ = '0.2.4.16'
 import logging
 # Setup the logger
 logging.basicConfig(
@@ -165,99 +165,76 @@ def connect(
     followup_name             = tdfs4ds.FOLLOW_UP_NAME,
     feature_catalog_name_view = tdfs4ds.FEATURE_CATALOG_NAME_VIEW,
     process_catalog_name_view = tdfs4ds.PROCESS_CATALOG_NAME_VIEW,
-    dataset_catalog_name      = tdfs4ds.DATASET_CATALOG_NAME
+    dataset_catalog_name      = tdfs4ds.DATASET_CATALOG_NAME,
+    create_if_missing         = False  # New argument
 ):
-    """
-    Configures the database environment by setting schema names and checking the existence of specified catalog tables.
-
-    This function initializes the database schema and verifies the presence of the feature catalog, process catalog,
-    data distribution tables, and the filter manager. It updates the module-level configuration for these names if they exist.
-    If any of the specified tables or manager do not exist, it raises an assertion error.
-
-    Parameters:
-    - database (str): The name of the database schema to use. Defaults to tdfs4ds.SCHEMA.
-    - feature_catalog_name (str, optional): The name of the feature catalog table. Defaults to tdfs4ds.FEATURE_CATALOG_NAME.
-    - process_catalog_name (str, optional): The name of the process catalog table. Defaults to tdfs4ds.PROCESS_CATALOG_NAME.
-    - data_distribution_name (str, optional): The name of the data distribution table. Defaults to tdfs4ds.DATA_DISTRIBUTION_NAME.
-    - filter_manager_name (str, optional): The name of the filter manager. Defaults to tdfs4ds.FILTER_MANAGER_NAME.
-
-    Steps Performed:
-    1. Set the database schema to the provided 'database' name.
-    2. Retrieve the list of tables in the specified schema and check for the existence of the feature catalog, process catalog,
-       data distribution tables, and filter manager.
-    3. Update the module-level names for these tables and manager if they exist.
-    4. Raise an assertion error if any of the specified tables or manager do not exist, specifying which are missing.
-
-    Returns:
-    None
-
-    Raises:
-    AssertionError: An error indicating which of the feature catalog, process catalog, data distribution table, or filter manager do not exist.
-    """
     if database is not None:
         tdfs4ds.SCHEMA = database
     else:
-        assert False, "database parameter is None."
+        raise ValueError("database parameter is None.")
 
     tables = [x.lower() for x in list(tdml.db_list_tables(schema_name=tdfs4ds.SCHEMA, object_type='table').TableName.values)]
+    
     feature_exists = feature_catalog_name.lower() in tables
     process_exists = process_catalog_name.lower() in tables
     distrib_exists = data_distribution_name.lower() in tables
     filter_manager_exists = filter_manager_name.lower() in tables
     followup_name_exists = followup_name.lower() in tables
-    
-    
-    if followup_name_exists:
-        tdfs4ds.FOLLOW_UP_NAME = followup_name
-    else:
-        tdfs4ds.process_store.process_followup.follow_up_table_creation()
-        tdfs4ds.FOLLOW_UP_NAME = followup_name
-
-    if feature_exists and process_exists and distrib_exists and filter_manager_exists:
-        tdfs4ds.FEATURE_CATALOG_NAME = feature_catalog_name
-        tdfs4ds.PROCESS_CATALOG_NAME = process_catalog_name
-        tdfs4ds.DATA_DISTRIBUTION_NAME = data_distribution_name
-        tdfs4ds.FILTER_MANAGER_NAME = filter_manager_name
-        tdfs4ds.PROCESS_CATALOG_NAME_VIEW = process_catalog_name_view
-        tdfs4ds.FEATURE_CATALOG_NAME_VIEW = feature_catalog_name_view
-        
 
-        process_list = tdml.DataFrame(tdml.in_schema(database, process_catalog_name))
-        if 'ENTITY_NULL_SUBSTITUTE' not in process_list.columns:
-            print('ENTITY_NULL_SUBSTITUTE column does not exist in the existing process catalog')
-            print('upgrade to the latest DDL')
-            tdfs4ds.process_store.process_store_catalog_management.upgrade_process_catalog()
+    if not (feature_exists and process_exists and distrib_exists and filter_manager_exists):
+        if not create_if_missing:
+            return False  # Feature store does not exist
+        else:
+            # Create the missing components
+            if not feature_exists:
+                tdfs4ds.feature_store.feature_store_management.feature_store_catalog_creation()
+            if not process_exists:
+                tdfs4ds.process_store.process_store_catalog_management.process_store_catalog_creation()
+            if not distrib_exists:
+                tdfs4ds.data_distribution.data_distribution_catalog_creation()
+            if not filter_manager_exists:
+                tdfs4ds.filter_manager.filter_manager_catalog_creation()
+
+    # Follow-up table handling
+    if not followup_name_exists:
+        tdfs4ds.process_store.process_followup.follow_up_table_creation()
+    tdfs4ds.FOLLOW_UP_NAME = followup_name
+
+    # Set catalog names
+    tdfs4ds.FEATURE_CATALOG_NAME = feature_catalog_name
+    tdfs4ds.PROCESS_CATALOG_NAME = process_catalog_name
+    tdfs4ds.DATA_DISTRIBUTION_NAME = data_distribution_name
+    tdfs4ds.FILTER_MANAGER_NAME = filter_manager_name
+    tdfs4ds.PROCESS_CATALOG_NAME_VIEW = process_catalog_name_view
+    tdfs4ds.FEATURE_CATALOG_NAME_VIEW = feature_catalog_name_view
+
+    process_list = tdml.DataFrame(tdml.in_schema(database, process_catalog_name))
+    if 'ENTITY_NULL_SUBSTITUTE' not in process_list.columns:
+        print('ENTITY_NULL_SUBSTITUTE column does not exist in the existing process catalog')
+        print('upgrade to the latest DDL')
+        tdfs4ds.process_store.process_store_catalog_management.upgrade_process_catalog()
 
-        tdfs4ds.feature_store.feature_store_management.feature_store_catalog_view_creation()
-        tdfs4ds.process_store.process_store_catalog_management.process_store_catalog_view_creation()
-    else:
-        missing = []
-        if not feature_exists:
-            missing.append("feature catalog")
-        if not process_exists:
-            missing.append("process catalog")
-        if not distrib_exists:
-            missing.append("data distribution table")
-        if not filter_manager_exists:
-            missing.append("filter manager")
-        assert False, f"""{', '.join(missing)} {'do' if len(missing) > 1 else 'does'} not exist.
-        Please run setup to create the missing table ou speficy the correct name in the arguments.
-        type help(tdfs4ds.connect) for more information."""
+    tdfs4ds.feature_store.feature_store_management.feature_store_catalog_view_creation()
+    tdfs4ds.process_store.process_store_catalog_management.process_store_catalog_view_creation()
 
-    def is_data_distribution_temporal():
-        return 'PERIOD' in tdfs4ds.utils.lineage.get_ddl(view_name=tdfs4ds.DATA_DISTRIBUTION_NAME,
-                                                         schema_name=tdfs4ds.SCHEMA, object_type='table')
-    
+    # Dataset catalog setup
     tdfs4ds.DATASET_CATALOG_NAME = dataset_catalog_name
     dataset_catalog = DatasetCatalog(schema_name=database, name=tdfs4ds.DATASET_CATALOG_NAME)
     if not dataset_catalog._exists():
         dataset_catalog.create_catalog()
 
-    if is_data_distribution_temporal():
-        tdfs4ds.DATA_DISTRIBUTION_TEMPORAL = True
-    else:
-        tdfs4ds.DATA_DISTRIBUTION_TEMPORAL = False
-    return
+    # Check if distribution is temporal
+    def is_data_distribution_temporal():
+        return 'PERIOD' in tdfs4ds.utils.lineage.get_ddl(
+            view_name=tdfs4ds.DATA_DISTRIBUTION_NAME,
+            schema_name=tdfs4ds.SCHEMA,
+            object_type='table'
+        )
+    
+    tdfs4ds.DATA_DISTRIBUTION_TEMPORAL = is_data_distribution_temporal()
+    
+    return True  # Feature store exists or was created
+
 
 
 def feature_catalog():

{tdfs4ds-0.2.4.15.dist-info → tdfs4ds-0.2.4.16.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.15
+Version: 0.2.4.16
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
-Requires-Dist: teradataml >=17.20
+Requires-Dist: teradataml>=17.20
 Requires-Dist: pandas
 Requires-Dist: numpy
 Requires-Dist: plotly

{tdfs4ds-0.2.4.15.dist-info → tdfs4ds-0.2.4.16.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=iMvZ-8xpVJmDd1XYF_OmiBiuNbuKEh0gCT99hgJp778,65845
+tdfs4ds/__init__.py,sha256=tgwWXaw1AlYeTSLOEkn4Q35xtSvITL-tK0KAevVvUcA,64168
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -29,7 +29,7 @@ tdfs4ds/utils/lineage.py,sha256=LI-5pG7D8lO3-YFa9qA6CrEackiYugV23_Vz9IpF5xw,2867
 tdfs4ds/utils/query_management.py,sha256=nAcE8QY1GWAKgOtb-ubSfDVcnYbU7Ge8CruVRLoPtmY,6356
 tdfs4ds/utils/time_management.py,sha256=rVxtIXcFtQih2UabAtos4DK-j9MPqzYVieIz_SvySZE,9241
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.15.dist-info/METADATA,sha256=Hzu1GmQ0jQ9i2kwusgrpBN3CcXDnsZxK42qALwBkVRM,11945
-tdfs4ds-0.2.4.15.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.15.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.15.dist-info/RECORD,,
+tdfs4ds-0.2.4.16.dist-info/METADATA,sha256=tD09svo_gk0JMYgg1aI3L8GbzZHjsKKeCFVw7b21D98,11944
+tdfs4ds-0.2.4.16.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.16.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.16.dist-info/RECORD,,