tdfs4ds 0.2.4.47__py3-none-any.whl → 0.2.5.0__py3-none-any.whl

tdfs4ds/process_store/process_store_catalog_management.py

@@ -1,6 +1,8 @@
 import teradataml as tdml
 import tdfs4ds
 from tdfs4ds.utils.query_management import execute_query,execute_query_wrapper
+from tdfs4ds import logger_safe
+
 
 def upgrade_process_catalog():
 
@@ -43,13 +45,13 @@ def upgrade_process_catalog():
     # Step 4: Rename the new table to the old table's name
     query_4 = f"""RENAME TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW TO {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME};"""
 
-    print('creation of the ', f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW","table" )
+    logger_safe('info', f'creation of the {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW table')
     tdml.execute_sql(query_1)
-    print('insert existing processes from',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}", 'to',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW")
+    logger_safe('info', f'insert existing processes from {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} to {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW')
     tdml.execute_sql(query_2)
-    print('rename ',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}",'to',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_OLD")
+    logger_safe('info', f'rename {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} to {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_OLD')
     tdml.execute_sql(query_3)
-    print('rename ,',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW",'to',f"{tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}")
+    logger_safe('info', f'rename {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}_NEW to {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME}')
     tdml.execute_sql(query_4)
 
 @execute_query_wrapper
@@ -263,79 +265,130 @@ def process_store_catalog_creation(if_exists='replace', comment='this table is a
         execute_query(query)
         if tdml.display.print_sqlmr_query:
             print(query)
-        if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been created')
+        logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been created')
         execute_query(query3)
     except Exception as e:
         # If the table already exists and if_exists is set to 'replace', drop the table and recreate it
-        if tdfs4ds.DISPLAY_LOGS: print(str(e).split('\n')[0])
+        logger_safe('error', 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}.{tdfs4ds.PROCESS_CATALOG_NAME}')
-            print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been dropped')
+            logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_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}.{tdfs4ds.PROCESS_CATALOG_NAME} has been re-created')
+                logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been re-created')
                 if tdml.display.print_sqlmr_query:
                     print(query)
                 execute_query(query3)
             except Exception as e:
-                print(str(e).split('\n')[0])
+                logger_safe('error', str(e).split('\n')[0])
 
     try:
         # Attempt to execute the create table query
         execute_query(query4)
         if tdml.display.print_sqlmr_query:
             print(query4)
-        if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been created')
+        logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been created')
         execute_query(query5)
     except Exception as e:
         # If the table already exists and if_exists is set to 'replace', drop the table and recreate it
-        if tdfs4ds.DISPLAY_LOGS: print(str(e).split('\n')[0])
+        logger_safe('error', 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}.{tdfs4ds.DATA_DISTRIBUTION_NAME}')
-            print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been dropped')
+            logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been dropped')
             try:
                 # Attempt to recreate the table after dropping it
                 execute_query(query4)
-                if tdfs4ds.DISPLAY_LOGS: print(
-                    f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been re-created')
+                logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.DATA_DISTRIBUTION_NAME} has been re-created')
                 if tdml.display.print_sqlmr_query:
                     print(query4)
                 execute_query(query5)
             except Exception as e:
-                print(str(e).split('\n')[0])
+                logger_safe('error', str(e).split('\n')[0])
 
     try:
         # Attempt to execute the create table query
         execute_query(query6)
         if tdml.display.print_sqlmr_query:
             print(query6)
-        if tdfs4ds.DISPLAY_LOGS: print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been created')
+        logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been created')
         execute_query(query7)
     except Exception as e:
         # If the table already exists and if_exists is set to 'replace', drop the table and recreate it
-        if tdfs4ds.DISPLAY_LOGS: print(str(e).split('\n')[0])
+        logger_safe('error', 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}.{tdfs4ds.FILTER_MANAGER_NAME}')
-            print(f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been dropped')
+            logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been dropped')
             try:
                 # Attempt to recreate the table after dropping it
                 execute_query(query6)
-                if tdfs4ds.DISPLAY_LOGS: print(
-                    f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been re-created')
+                logger_safe('info', f'TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.FILTER_MANAGER_NAME} has been re-created')
                 if tdml.display.print_sqlmr_query:
                     print(query6)
                 execute_query(query7)
             except Exception as e:
-                print(str(e).split('\n')[0])
+                logger_safe('error', str(e).split('\n')[0])
 
     try:
         # Attempt to create the secondary index
         execute_query(query2)
         if tdml.display.print_sqlmr_query:
             print(query)
-        if tdfs4ds.DISPLAY_LOGS: print(f'SECONDARY INDEX ON TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been created')
+        logger_safe('info', f'SECONDARY INDEX ON TABLE {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} has been created')
+    except Exception as e:
+        logger_safe('error', str(e).split('\n')[0])
+
+    return tdfs4ds.PROCESS_CATALOG_NAME, tdfs4ds.DATA_DISTRIBUTION_NAME, tdfs4ds.FILTER_MANAGER_NAME
+
+def get_process_info(process_id: str) -> dict:
+    """
+    Retrieve process information including SQL and columns from the process catalog.
+
+    Args:
+        process_id (str): The unique identifier of the process.
+    Returns:
+        dict: A dictionary containing process SQL and columns.
+    """
+    # Retrieve process SQL and columns
+    process_catalog = tdfs4ds.process_catalog()
+    try:
+        process_info = process_catalog[process_catalog['PROCESS_ID'] == process_id].to_pandas().to_dict(orient='records')[0]
+        process_info['ENTITY_COLUMNS']  = process_info['ENTITY_ID'].split(',')
+        process_info['FEATURE_COLUMNS'] = process_info['FEATURE_NAMES'].split(',')
+    except Exception as e:
+        logger_safe('error', f"Error retrieving process info: {e}")
+        return None
+    
+    # get the SQL query:
+    if process_info:
+        process_sql = tdfs4ds.utils.lineage.get_ddl(
+            view_name = process_info['VIEW_NAME'].split('.')[1],
+            schema_name = process_info['VIEW_NAME'].split('.')[0],
+            object_type='view'
+            )
+        process_info['PROCESS_SQL'] = process_sql
+
+    # retrieve feature documentation
+    from tdfs4ds.genai.documentation import retrieve_documentation, retrieve_explain_documentation
+
+    try:
+        documentation = retrieve_documentation(process_id)
+        process_info['DOCUMENTED_SQL']                 = documentation['DOCUMENTED_SQL']
+        process_info['DOCUMENTED_ENTITY_COLUMNS']      = documentation['DOCUMENTED_ENTITY_COLUMNS']
+        process_info['DOCUMENTED_FEATURE_COLUMNS']     = documentation['DOCUMENTED_FEATURE_COLUMNS']
+        process_info['ENTITY_DESCRIPTION']             = documentation['ENTITY_DESCRIPTION']
+        logger_safe('info', f"Successfully retrieved documentation for process_id {process_id}")
+    except Exception as e:
+        logger_safe('error', f"Error retrieving documentation: {e}")
+
+    try:
+        explain_documentation = retrieve_explain_documentation(process_id)
+        process_info['EXPLAIN_ANALYSIS']               = explain_documentation['EXPLAIN_ANALYSIS']
+        process_info['OPTIMIZATION_SCORE']             = explain_documentation['OPTIMIZATION_SCORE']
+        process_info['EXPLAIN_WARNINGS']               = explain_documentation['EXPLAIN_WARNINGS']
+        process_info['EXPLAIN_RECOMMENDATIONS']        = explain_documentation['EXPLAIN_RECOMMENDATIONS']
+        logger_safe('info', f"Successfully retrieved explanation for process_id {process_id}")
     except Exception as e:
-        print(str(e).split('\n')[0])
+        logger_safe('error', f"Error retrieving explanation: {e}")  
 
-    return tdfs4ds.PROCESS_CATALOG_NAME, tdfs4ds.DATA_DISTRIBUTION_NAME, tdfs4ds.FILTER_MANAGER_NAME
+    return process_info

tdfs4ds/utils/filter_management.py

@@ -7,21 +7,30 @@ import json
 
 
 def get_hidden_table_name(schema_name, view_name):
-    """
-    Return the backing 'hidden' table name for a public view/table.
-
-    Args:
-        table_name (str): Public-facing table/view name.
+    try:
+        ddl = tdfs4ds.utils.lineage.get_ddl(schema_name=schema_name, view_name=view_name)
 
-    Returns:
-        str: The corresponding hidden table name (suffix '_HIDDEN').
-    """
+        # Your current parsing is fragile; but keeping your intent:
+        backing = ddl.split("\n")[-2].split(".")[1]
+        return backing
 
-    try:
-        view_name = tdfs4ds.utils.lineage.get_ddl(schema_name=schema_name, view_name=view_name).split('\n')[-2].split('.')[1]
-        return view_name
     except Exception as e:
-        logger_safe("warning", "Failed to extract hidden table name from DDL; defaulting to suffix method.", str(e).split('\n')[0])
+        msg = str(e)
+
+        # Teradata "object does not exist" -> normal for first-time setup
+        if "Error 3807" in msg or "does not exist" in msg.lower():
+            logger_safe(
+                "info",
+                "View %s.%s not found; using default hidden table name %s_HIDDEN.",
+                schema_name, view_name, view_name
+            )
+        else:
+            logger_safe(
+                "warning",
+                "Failed to extract hidden table name from DDL; defaulting to suffix method. Error: %s",
+                msg.splitlines()[0]
+            )
+
         return view_name + "_HIDDEN"
 
 

tdfs4ds/utils/time_management.py

@@ -9,24 +9,34 @@ import pandas as pd
 
 
 def get_hidden_table_name(schema_name, view_name):
-    """
-    Return the backing 'hidden' table name for a public view/table.
-
-    Args:
-        table_name (str): Public-facing table/view name.
+    try:
+        ddl = tdfs4ds.utils.lineage.get_ddl(schema_name=schema_name, view_name=view_name)
 
-    Returns:
-        str: The corresponding hidden table name (suffix '_HIDDEN').
-    """
+        # Your current parsing is fragile; but keeping your intent:
+        backing = ddl.split("\n")[-2].split(".")[1]
+        return backing
 
-    try:
-        view_name = tdfs4ds.utils.lineage.get_ddl(schema_name=schema_name, view_name=view_name).split('\n')[-2].split('.')[1]
-        return view_name
     except Exception as e:
-        logger_safe("warning", "Failed to extract hidden table name from DDL; defaulting to suffix method.", str(e).split('\n')[0])
+        msg = str(e)
+
+        # Teradata "object does not exist" -> normal for first-time setup
+        if "Error 3807" in msg or "does not exist" in msg.lower():
+            logger_safe(
+                "info",
+                "View %s.%s not found; using default hidden table name %s_HIDDEN.",
+                schema_name, view_name, view_name
+            )
+        else:
+            logger_safe(
+                "warning",
+                "Failed to extract hidden table name from DDL; defaulting to suffix method. Error: %s",
+                msg.splitlines()[0]
+            )
+
         return view_name + "_HIDDEN"
 
 
+
 class TimeManager:
     """
     Manage versioned business time steps behind a Teradata-backed public view.

{tdfs4ds-0.2.4.47.dist-info → tdfs4ds-0.2.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.47
+Version: 0.2.5.0
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.47.dist-info → tdfs4ds-0.2.5.0.dist-info}/RECORD

@@ -1,13 +1,5 @@
-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=WsOG-nk0VyiZ7HBqxVS-xxhbyp9TjogeVF8wfCSl8Rw,61213
+tdfs4ds/__init__.py,sha256=elmc5_fMAaUncQeit1jj_5z4mE3ssTJvy_hHv1rNzx8,70555
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
-tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
-tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
-tdfs4ds/process_store.py,sha256=W97pwqOwabo062ow_LfAXZmlSkcq8xTuwhwAX1EStlQ,16939
-tdfs4ds/utils.py,sha256=xF1VP0NCgosXcKymOo_ofMMnvLEF228IxaxIl-f65uA,23312
 tdfs4ds/data/curves.csv,sha256=q0Tm-0yu7VMK4lHvHpgi1LMeRq0lO5gJy2Q17brKbEM,112488
 tdfs4ds/data/logo/tdfs4ds_logo.png,sha256=OCKQnH0gQbRyupwZeiIgo-9c6mdRtjE2E2Zunr_4Ae0,363980
 tdfs4ds/data/logo/teradata_sym_rgb_pos.png,sha256=Zq-QzLb04PIQ4iN8C6ssaLuNVVI1Q_TqBkFx_f7aNOI,8052
@@ -17,23 +9,24 @@ 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=Hva2GRVRygHgbpQlkpplmCyrWpRKs8FEGPmzmVjC7C0,45686
+tdfs4ds/feature_store/feature_data_processing.py,sha256=gXBsr1H05zxM4tWE7y29ucxeoTu1jQITOwTXqi1Y2pk,45214
 tdfs4ds/feature_store/feature_query_retrieval.py,sha256=51c6ZNlLFiBIxNPinS8ot8bjWEIb1QV2eVg69yzVF80,35381
-tdfs4ds/feature_store/feature_store_management.py,sha256=RZrjjTKjJBmc3wate8A5NsnBsqtY0be18lFx5WdcWy4,52120
-tdfs4ds/genai/__init__.py,sha256=b5HwEnBhAwHu2qYwPTBZ9wkRKL4HSl_4uHTEHf5Vn1Q,13785
+tdfs4ds/feature_store/feature_store_management.py,sha256=mtPQkdMDhcOrhj9IAaH-FEP_znK53cYtEv8zXAbsigg,52123
+tdfs4ds/genai/__init__.py,sha256=Hal13Kw75nDYKHtfvHZNdm98exqmY6qaqGZkJA2TQ6E,723
+tdfs4ds/genai/documentation.py,sha256=bKi2a6TJ9GbdToK9n3OKRqnAVXO1v6aT92aQ6JksCM4,82027
 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/process_store/process_store_catalog_management.py,sha256=s-2JAaOx-m_hANVWGLCRL-FnoD_dzT_BqQdN74Vxzcw,18770
 tdfs4ds/utils/__init__.py,sha256=-yTMfDLZbQnIRQ64s_bczzT21tDW2A8FZeq9PX5SgFU,168
-tdfs4ds/utils/filter_management.py,sha256=zEV3COrxqS_GfE9ogpzKJEfWM_WAnEkTUz8s2OR8JJk,28329
+tdfs4ds/utils/filter_management.py,sha256=rF8v0fws-ZR9og7x2TBqS5VWpOit1cwgF2xNkb_Hw1w,28635
 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/time_management.py,sha256=g3EJO7I8ERoZ4X7yq5SyDqSE4O9p0BRcv__QPuAxbGA,32243
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.47.dist-info/METADATA,sha256=eIdXWOBQF9N12xALV-EIJzj8tCefp_kdcV4oWpaEc8E,14326
-tdfs4ds-0.2.4.47.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.47.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.47.dist-info/RECORD,,
+tdfs4ds-0.2.5.0.dist-info/METADATA,sha256=yGUNmOxAt89lwPGcSPZRHpnIFE27RfH70CqlyMHrkg0,14325
+tdfs4ds-0.2.5.0.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.5.0.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.5.0.dist-info/RECORD,,

tdfs/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.1.0.0'