tdfs4ds 0.2.4.38__py3-none-any.whl → 0.2.4.39__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.38'
+__version__ = '0.2.4.39'
 import logging
 import json
 

tdfs4ds/feature_store/feature_store_management.py

@@ -130,57 +130,27 @@ def feature_store_catalog_creation(if_exists='replace', comment='this table is a
     return tdfs4ds.FEATURE_CATALOG_NAME
 
 
-def feature_store_table_creation(entity_id, feature_type, if_exists='fail', primary_index = None, partitioning = ''):
+def feature_store_table_creation(entity_id, feature_type, if_exists='fail', primary_index=None, partitioning=''):
     """
     Creates a table and a corresponding view for feature storage in a Teradata database schema, based on specified entity ID and feature type.
-
-    This function automates the creation of a table and view tailored for storing features in a structured manner. It leverages provided entity identifiers and feature types to generate table and view names dynamically, integrating with an existing feature catalog for consistency and reference. The table and view are created with considerations for primary indexing and optional partitioning strategies to optimize data management and access.
-
-    Parameters:
-    - entity_id (dict): Maps column names to their respective data types, defining the structure of the entity identifier(s).
-    - feature_type (str): Specifies the data type of the feature (e.g., 'FLOAT', 'BIGINT', 'VARCHAR_LATIN', 'VARCHAR_UNICODE').
-    - if_exists (str, optional): Determines the action if the table already exists. Options include:
-                                 'fail' (default), which raises an error; and 'replace', which drops the existing table and creates a new one.
-    - primary_index (list, optional): Specifies the columns to be used as the primary index for the table. Enhances data retrieval performance.
-    - partitioning (str, optional): SQL clause to define table partitioning. Aids in managing large datasets efficiently.
-
-    Returns:
-    str: The name of the newly created feature store table.
-
-    Note:
-    - Utilizes default schema and feature catalog names as defined in the tdfs4ds module.
-    - The primary index typically includes the entity ID, feature ID, and feature version for optimal data organization.
-    - A secondary index on the feature ID facilitates efficient querying.
-    - Corresponding views offer a snapshot of the current valid-time features, simplifying temporal queries.
-    - Existing tables are handled based on the 'if_exists' parameter, with support for replacing or retaining the tables.
-    - Assumes necessary database access and permissions are available for table and view creation.
-
-    Example Usage:
-    >>> entity_id_dict = {'customer_id': 'INTEGER'}
-    >>> table_name = feature_store_table_creation(entity_id_dict, 'FLOAT')
-    >>> print(f"Feature store table {table_name} created successfully.")
     """
-
-
-    table_name, view_name = get_feature_store_table_name(entity_id, feature_type, primary_index = primary_index, partitioning = partitioning)
-    if len([t for t in tdml.db_list_tables(schema_name=tdfs4ds.SCHEMA).TableName if t.lower() ==table_name.lower()]) > 0:
-        if tdfs4ds.DISPLAY_LOGS:
-            print(f'table {table_name} in the {tdfs4ds.SCHEMA} database already exists. No need to create it.')
+    table_name, view_name = get_feature_store_table_name(entity_id, feature_type, primary_index=primary_index, partitioning=partitioning)
+    if len([t for t in tdml.db_list_tables(schema_name=tdfs4ds.SCHEMA).TableName if t.lower() == table_name.lower()]) > 0:
+        logger_safe('info', f'table {table_name} in the {tdfs4ds.SCHEMA} database already exists. No need to create it.')
         return table_name
     else:
-        if tdfs4ds.DISPLAY_LOGS:
-            print(f'table {table_name} in the {tdfs4ds.SCHEMA} database does not exists. Need to create it.')
+        logger_safe('info', f'table {table_name} in the {tdfs4ds.SCHEMA} database does not exists. Need to create it.')
 
     query_feature_value = {
         'FLOAT':            'FEATURE_VALUE FLOAT',
         'BIGINT':           'FEATURE_VALUE BIGINT',
         'VARCHAR_LATIN':    f'FEATURE_VALUE VARCHAR({tdfs4ds.VARCHAR_SIZE}) CHARACTER SET LATIN',
         'VARCHAR_UNICODE':  f'FEATURE_VALUE VARCHAR({tdfs4ds.VARCHAR_SIZE}) CHARACTER SET UNICODE',
-        'TIMESTAMP0' :      'FEATURE_VALUE TIMESTAMP(0)',
-        'TIMESTAMP0TZ' :    'FEATURE_VALUE TIMESTAMP(0) WITH TIME ZONE',
-        'PERIODTS0' :       'FEATURE_VALUE PERIOD(TIMESTAMP(0))',
+        'TIMESTAMP0':       'FEATURE_VALUE TIMESTAMP(0)',
+        'TIMESTAMP0TZ':     'FEATURE_VALUE TIMESTAMP(0) WITH TIME ZONE',
+        'PERIODTS0':        'FEATURE_VALUE PERIOD(TIMESTAMP(0))',
         'PERIODTS0TZ':      'FEATURE_VALUE PERIOD(TIMESTAMP(0) WITH TIME ZONE)',
-        'DECIMAL' :         'FEATURE_VALUE DECIMAL(38,19)'
+        'DECIMAL':          'FEATURE_VALUE DECIMAL(38,19)'
     }
 
     # Construct the column definitions for the table based on the entity ID
@@ -197,12 +167,14 @@ def feature_store_table_creation(entity_id, feature_type, if_exists='fail', prim
     # SQL query to create the feature store table
     if feature_type.lower() == 'ref':
         partitioning = partitioning.replace('"', "'")
-        partitioning = partitioning.replace(f'RANGE_N(FEATURE_ID BETWEEN 0 AND {tdfs4ds.FEATURE_PARTITION_N} EACH {tdfs4ds.FEATURE_PARTITION_EACH}),','')
+        partitioning = partitioning.replace(f'RANGE_N(FEATURE_ID BETWEEN 0 AND {tdfs4ds.FEATURE_PARTITION_N} EACH {tdfs4ds.FEATURE_PARTITION_EACH}),', '')
         partitioning = partitioning.replace(
             f'RANGE_N(FEATURE_ID BETWEEN 0 AND {tdfs4ds.FEATURE_PARTITION_N} EACH {tdfs4ds.FEATURE_PARTITION_EACH})',
-            '')
+            ''
+        )
         substr = extract_partition_content(partitioning.upper())
-        if len(substr)==0: partitioning =  ''
+        if len(substr) == 0:
+            partitioning = ''
         query = f"""
         CREATE MULTISET TABLE {tdfs4ds.SCHEMA}.{table_name},
             FALLBACK,
@@ -218,7 +190,7 @@ def feature_store_table_creation(entity_id, feature_type, if_exists='fail', prim
             {partitioning};
     """
     else:
-        partitioning = partitioning.replace('"',"'")
+        partitioning = partitioning.replace('"', "'")
         query = f"""
         CREATE MULTISET TABLE {tdfs4ds.SCHEMA}.{table_name},
                 FALLBACK,
@@ -267,39 +239,40 @@ def feature_store_table_creation(entity_id, feature_type, if_exists='fail', prim
 
     try:
         # Attempt to execute the create table query
-        execute_query(query)
-        execute_query(query3)
+        execute_query(query, raise_error=True)
+        execute_query(query3, raise_error=True)
         if tdml.display.print_sqlmr_query:
-            print(query)
-            print(query3)
-        if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been created')
-        #execute_query(query2)
+            logger_safe('info', query)
+            logger_safe('info', query3)
+        logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been created')
+        # execute_query(query2)
     except Exception as e:
-        # If the table already exists and if_exists is set to 'replace', drop the table and recreate it
-        print(str(e).split('\n')[0])
-        if str(e).split('\n')[0].endswith('already exists.') and (if_exists == 'replace'):
-            execute_query(f'DROP TABLE  {tdfs4ds.SCHEMA}.{table_name}')
-            if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been dropped')
+        msg = str(e).split('\n')[0]
+        logger_safe('error', msg)
+        if msg.endswith('already exists.') and (if_exists == 'replace'):
+            execute_query(f'DROP TABLE  {tdfs4ds.SCHEMA}.{table_name}', raise_error=True)
+            logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been dropped')
             try:
                 # Attempt to recreate the table after dropping it
-                execute_query(query)
-                if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been re-created')
+                execute_query(query, raise_error=True)
+                logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{table_name} has been re-created')
                 if tdml.display.print_sqlmr_query:
-                    print(query)
-            except Exception as e:
-                print(str(e).split('\n')[0])
+                    logger_safe('info', query)
+            except Exception as e2:
+                logger_safe('error', str(e2).split('\n')[0])
 
     try:
         # Attempt to create the view
-        execute_query(query_view)
+        execute_query(query_view, raise_error=True)
         if tdml.display.print_sqlmr_query:
-            print(query)
-        if tdfs4ds.DISPLAY_LOGS: print(f'VIEW {tdfs4ds.SCHEMA}.{view_name} has been created')
+            logger_safe('info', query_view)
+        logger_safe('info', f'VIEW {tdfs4ds.SCHEMA}.{view_name} has been created')
     except Exception as e:
-        print(str(e).split('\n')[0])
+        logger_safe('error', str(e).split('\n')[0])
 
     return table_name
 
+
 def register_features(entity_id, feature_names_types, primary_index = None, partitioning = ''):
     """
     Orchestrates the registration or update of feature definitions in a Teradata database's feature catalog.

tdfs4ds/utils/query_management.py

@@ -84,71 +84,49 @@ def execute_query_wrapper(f):
     return wrapped_f
 
 
-def execute_query(query):
+def execute_query(query, raise_error=False):
     """
     Execute a SQL query or a list of queries using the tdml module.
 
-    This function checks the version of the tdml module and executes the query or queries accordingly.
-    For versions greater than 17.20.00.03, it uses `tdml.execute_sql`; otherwise, it uses `tdml.get_context().execute`.
-
     Args:
         query (str or list): A single SQL query string or a list of SQL query strings.
+        raise_error (bool): If True, re-raise exceptions after printing them. Default is False.
 
     Returns:
         The result of the SQL execution if a single query is passed. None if a list of queries is passed or an exception occurs.
+    """
+    def handle_exception(e, q):
+        # Always print error
+        print(str(e).split('\n')[0])
+        print(q)
 
-    Example:
-        To execute a single SQL query and retrieve the result:
-        >>> result = execute_query("SELECT * FROM my_table")
-
-        To execute a list of SQL queries:
-        >>> execute_query(["UPDATE table1 SET column1 = 42", "DELETE FROM table2 WHERE condition"])
-
-    Note:
-        - If a single query is passed, the function returns the result of the SQL execution.
-        - If a list of queries is passed, the function executes each query and returns None.
-        - If an exception occurs during execution, the error message and the problematic query are printed,
-          and the function returns None.
+        # Raise exception only if requested
+        if raise_error:
+            raise e
 
-    """
-    # Check if the version of tdml is greater than the specified base version
     if is_version_greater_than(tdml.__version__, base_version="17.20.00.03"):
-        # If query is a list, iterate and execute each query
-        if type(query) == list:
+        if isinstance(query, list):
             for q in query:
                 try:
-                    tdml.execute_sql(q)  # Execute the query
+                    tdml.execute_sql(q)
                 except Exception as e:
-                    # Print the first line of the exception and the query that caused it
-                    print(str(e).split('\n')[0])
-                    print(q)
+                    handle_exception(e, q)
         else:
-            # If query is not a list, execute it and return the result
             try:
                 return tdml.execute_sql(query)
             except Exception as e:
-                # Print the first line of the exception and the query
-                print(str(e).split('\n')[0])
-                print(query)
+                handle_exception(e, query)
     else:
-        # For tdml versions not greater than the specified version
-        if type(query) == list:
+        if isinstance(query, list):
             for q in query:
                 try:
-                    # Use the older execution method for the query
                     tdml.get_context().execute(q)
                 except Exception as e:
-                    # Print the first line of the exception and the query
-                    print(str(e).split('\n')[0])
-                    print(q)
+                    handle_exception(e, q)
         else:
             try:
-                # Execute the single query using the older method and return the result
                 return tdml.get_context().execute(query)
             except Exception as e:
-                # Print the first line of the exception and the query
-                print(str(e).split('\n')[0])
-                print(query)
+                handle_exception(e, query)
 
-    # No return value if a list of queries is executed or if an exception occurs
-    return
+    return None

{tdfs4ds-0.2.4.38.dist-info → tdfs4ds-0.2.4.39.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.38
+Version: 0.2.4.39
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.38.dist-info → tdfs4ds-0.2.4.39.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=vOFDL9B3mamt3Cd6ponz4EpZ4BkTBmYFAoxXIkL7CqE,60855
+tdfs4ds/__init__.py,sha256=u0hoIQLWP7mLjqLJdGuyVtoxfKl-4mps8bVc5_c3EnI,60855
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -19,7 +19,7 @@ tdfs4ds/feature_store/__init__.py,sha256=a7NPCkpTx40UR5LRErwnskpABG2Vuib7F5wUjaU
 tdfs4ds/feature_store/entity_management.py,sha256=9ltytv3yCTG84NZXBpb1Tlkf9pOxvrNb0MVidU4pwvE,10157
 tdfs4ds/feature_store/feature_data_processing.py,sha256=gjwypiTfwTyGyrP20v35Vu2uGIrCY80OBBeMVBsdjuk,45020
 tdfs4ds/feature_store/feature_query_retrieval.py,sha256=51c6ZNlLFiBIxNPinS8ot8bjWEIb1QV2eVg69yzVF80,35381
-tdfs4ds/feature_store/feature_store_management.py,sha256=yXLbINYLA-lzd0t_6TzEe9a8Anlum4x8TRoxZU3FIr8,54276
+tdfs4ds/feature_store/feature_store_management.py,sha256=mtPQkdMDhcOrhj9IAaH-FEP_znK53cYtEv8zXAbsigg,52123
 tdfs4ds/process_store/__init__.py,sha256=npHR_xju5ecGmWfYHDyteLwiU3x-cL4HD3sFK_th7xY,229
 tdfs4ds/process_store/process_followup.py,sha256=PvLcU7meg3ljBlPfuez3qwTVqpHHhVJxYxGqjgiHE8E,7265
 tdfs4ds/process_store/process_query_administration.py,sha256=AOufkJ6DFUpBiGm-6Q6Dq0Aovw31UGTscZ3Ya0ewS-0,7851
@@ -29,10 +29,10 @@ tdfs4ds/utils/__init__.py,sha256=-yTMfDLZbQnIRQ64s_bczzT21tDW2A8FZeq9PX5SgFU,168
 tdfs4ds/utils/filter_management.py,sha256=5_8fYYtl8RQgbIi6L_1geNM0wJMm3t1n4QvNA5DnaQg,24760
 tdfs4ds/utils/info.py,sha256=sShnUxXMlvCtQ6xtShDhqdpTr6sMG0dZQhNBFgUENDY,12058
 tdfs4ds/utils/lineage.py,sha256=gy5M42qy5fvdWmlohAY3WPYoqAyp5VakeEmeT1YjrJQ,37839
-tdfs4ds/utils/query_management.py,sha256=nAcE8QY1GWAKgOtb-ubSfDVcnYbU7Ge8CruVRLoPtmY,6356
+tdfs4ds/utils/query_management.py,sha256=kWDeTdsYcbpV5Tyhh-8uLRWvXh16nIdXNIJ97w76aNU,4848
 tdfs4ds/utils/time_management.py,sha256=asIWvK5K81NNwAGqC-9Tv4Timscxyv0vyuPFs01whu0,31461
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.38.dist-info/METADATA,sha256=pQ1JgtC75eThV0c0tnNXblLCvIhWz5GQHmCLDmX_de8,14326
-tdfs4ds-0.2.4.38.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.38.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.38.dist-info/RECORD,,
+tdfs4ds-0.2.4.39.dist-info/METADATA,sha256=X-V3kUdNWlXm7SKllAbGKQ2yAeHfw1da7pK_METpB-Q,14326
+tdfs4ds-0.2.4.39.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.39.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.39.dist-info/RECORD,,