tdfs4ds 0.2.4.22__py3-none-any.whl → 0.2.4.24__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.22'
+__version__ = '0.2.4.24'
 import logging
 # Setup the logger
 logging.basicConfig(

tdfs4ds/feature_store/feature_store_management.py

@@ -743,6 +743,9 @@ def GetTheLargestFeatureID():
         return feature_id
 
 
+import pandas as pd
+import uuid
+
 def GetAlreadyExistingFeatureNames(feature_name, entity_id):
     """
     Retrieves a list of already existing feature names from the feature catalog table in a Teradata database.
@@ -751,8 +754,6 @@ def GetAlreadyExistingFeatureNames(feature_name, entity_id):
     Parameters:
     - feature_name (str/list): The name(s) of the feature(s) to check. Can be a single feature name or a list of names.
     - entity_id (dict): A dictionary representing the entity ID, where keys are used to identify the entity.
-    - schema (str): The schema name where the feature catalog table is located.
-    - table_name (str, optional): The name of the feature catalog table. Defaults to 'FS_FEATURE_CATALOG'.
 
     Returns:
     list: A list of feature names that already exist in the feature catalog table and match the given feature name and entity ID.
@@ -761,40 +762,54 @@ def GetAlreadyExistingFeatureNames(feature_name, entity_id):
     - The function creates a temporary table in the database to facilitate the comparison.
     - It assumes that the feature catalog table exists and is accessible in the specified schema.
     - The function is designed for use with Teradata databases and assumes appropriate database access.
-
-    Example Usage:
-    >>> entity_id_dict = {'customer_id': 'INTEGER'}
-    >>> existing_features = GetAlreadyExistingFeatureNames('age', entity_id_dict)
-    >>> print(f"Existing features: {existing_features}")
     """
 
-    # Create a temporary DataFrame with the feature name.
-    list_entity = list(entity_id.keys())
-    list_entity.sort()
+    # Ensure feature_name is a list
+    if isinstance(feature_name, str):
+        feature_name = [feature_name]
+
+    # Create a temporary DataFrame with the feature name(s)
+    list_entity = sorted(entity_id.keys())
     df = pd.DataFrame({
         'FEATURE_NAME': feature_name,
         'DATA_DOMAIN': tdfs4ds.DATA_DOMAIN,
-        'ENTITY_NAME': ','.join([k for k in list_entity])
+        'ENTITY_NAME': ','.join(list_entity)
     })
 
-    # Define a temporary table name.
-    tmp_name = 'tdfs__fgjnojnsmdoignmosnig'
-
-    # Copy the temporary DataFrame to a temporary table in the Teradata database.
-    tdml.copy_to_sql(df, schema_name=tdfs4ds.SCHEMA, table_name=tmp_name, if_exists='replace',
-                     types={'FEATURE_NAME': tdml.VARCHAR(length=255, charset='LATIN')})
+    # Generate a unique temporary table name
+    tmp_name = f"tdfs_tmp_{uuid.uuid4().hex[:12]}"
 
-    # Execute a SQL query to get the feature names that exist in both the temporary table and the feature catalog table.
-    existing_features = list(tdml.DataFrame.from_query(f"""
-        SEL A.FEATURE_NAME
-        FROM {tdfs4ds.SCHEMA}.{tmp_name} A
-        INNER JOIN {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME_VIEW} B
-        ON A.FEATURE_NAME = B.FEATURE_NAME
-        AND A.ENTITY_NAME = B.ENTITY_NAME
-        AND A.DATA_DOMAIN = B.DATA_DOMAIN
-        """).to_pandas().FEATURE_NAME.values)
+    try:
+        # Copy the temporary DataFrame to a temporary table in the Teradata database
+        tdml.copy_to_sql(
+            df,
+            schema_name=tdfs4ds.SCHEMA,
+            table_name=tmp_name,
+            if_exists='replace',
+            types={'FEATURE_NAME': tdml.VARCHAR(length=255, charset='LATIN')}
+        )
+
+        # Execute a SQL query to get the feature names that exist in both the temporary table and the feature catalog table
+        query = f"""
+            SEL A.FEATURE_NAME
+            FROM {tdfs4ds.SCHEMA}.{tmp_name} A
+            INNER JOIN {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME_VIEW} B
+            ON A.FEATURE_NAME = B.FEATURE_NAME
+            AND A.ENTITY_NAME = B.ENTITY_NAME
+            AND A.DATA_DOMAIN = B.DATA_DOMAIN
+        """
+        existing_features = list(
+            tdml.DataFrame.from_query(query).to_pandas().FEATURE_NAME.values
+        )
+
+    finally:
+        # Clean up: drop the temporary table
+        try:
+            tdml.execute(f"DROP TABLE {tdfs4ds.SCHEMA}.{tmp_name};")
+        except Exception as e:
+            # Ignore if already dropped or not found
+            pass
 
-    # Return the list of existing features.
     return existing_features
 
 

{tdfs4ds-0.2.4.22.dist-info → tdfs4ds-0.2.4.24.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.22
+Version: 0.2.4.24
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6
@@ -156,12 +156,15 @@ Here is the structure of the package:
     │   └── Function: outstanding_amounts_dataset
     │   └── Function: upload_outstanding_amounts_dataset
     ├── __init__.py
-    │   └── Function: _build_time_series
     │   └── Function: _upload_features
+    │   └── Function: augment_source_with_features
     │   └── Function: build_dataset
-    │   └── Function: build_dataset_time_series
+    │   └── Function: build_dataset_opt
     │   └── Function: connect
+    │   └── Function: dataset_catalog
     │   └── Function: feature_catalog
+    │   └── Function: get_dataset_entity
+    │   └── Function: get_dataset_features
     │   └── Function: process_catalog
     │   └── Function: roll_out
     │   └── Function: run
@@ -169,6 +172,13 @@ Here is the structure of the package:
     │   └── Function: upload_features
     │   └── Function: upload_tdstone2_scores
     └── data
+        └── logo
+    └── dataset
+        ├── dataset.py
+        │   └── Class: Dataset
+        ├── dataset_catalog.py
+        │   └── Class: DatasetCatalog
+        ├── __init__.py
     └── feature_store
         ├── entity_management.py
         │   └── Function: register_entity
@@ -177,56 +187,89 @@ Here is the structure of the package:
         ├── feature_data_processing.py
         │   └── Function: _store_feature_merge
         │   └── Function: _store_feature_update_insert
+        │   └── Function: apply_collect_stats
+        │   └── Function: generate_collect_stats
+        │   └── Function: generate_on_clause
+        │   └── Function: get_feature_id_and_conversion
         │   └── Function: prepare_feature_ingestion
         │   └── Function: prepare_feature_ingestion_tdstone2
         │   └── Function: store_feature
         ├── feature_query_retrieval.py
+        │   └── Function: generate_uuid_from_string
+        │   └── Function: get_available_entity_id_records
         │   └── Function: get_available_features
         │   └── Function: get_entity_tables
+        │   └── Function: get_feature_location
         │   └── Function: get_feature_store_content
         │   └── Function: get_feature_store_table_name
         │   └── Function: get_feature_versions
         │   └── Function: get_list_entity
         │   └── Function: get_list_features
         │   └── Function: list_features
+        │   └── Function: write_where_clause_filter
         ├── feature_store_management.py
         │   └── Function: GetAlreadyExistingFeatureNames
         │   └── Function: GetTheLargestFeatureID
         │   └── Function: Gettdtypes
+        │   └── Function: _register_features_merge
+        │   └── Function: _register_features_update_insert
         │   └── Function: delete_feature
         │   └── Function: feature_store_catalog_creation
+        │   └── Function: feature_store_catalog_view_creation
         │   └── Function: feature_store_table_creation
         │   └── Function: register_features
         │   └── Function: remove_feature
         │   └── Function: tdstone2_Gettdtypes
         ├── __init__.py
     └── process_store
+        ├── process_followup.py
+        │   └── Function: follow_up_report
+        │   └── Function: follow_up_table_creation
+        │   └── Function: followup_close
+        │   └── Function: followup_open
         ├── process_query_administration.py
         │   └── Function: get_process_id
         │   └── Function: list_processes
+        │   └── Function: list_processes_feature_split
         │   └── Function: remove_process
         ├── process_registration_management.py
+        │   └── Function: _register_process_view_merge
+        │   └── Function: _register_process_view_update_insert
         │   └── Function: register_process_tdstone
         │   └── Function: register_process_view
         ├── process_store_catalog_management.py
         │   └── Function: process_store_catalog_creation
+        │   └── Function: process_store_catalog_view_creation
+        │   └── Function: upgrade_process_catalog
         ├── __init__.py
     └── utils
+        ├── filter_management.py
+        │   └── Function: get_hidden_table_name
+        │   └── Class: FilterManager
         ├── info.py
+        │   └── Function: extract_partition_content
+        │   └── Function: generate_partitioning_clause
         │   └── Function: get_column_types
         │   └── Function: get_column_types_simple
+        │   └── Function: get_feature_types_sql_format
+        │   └── Function: seconds_to_dhms
+        │   └── Function: update_varchar_length
         ├── lineage.py
         │   └── Function: _analyze_sql_query
         │   └── Function: analyze_sql_query
         │   └── Function: crystallize_view
+        │   └── Function: generate_process_report
         │   └── Function: generate_view_dependency_network
         │   └── Function: generate_view_dependency_network_fs
         │   └── Function: get_ddl
+        │   └── Function: query_change_case
+        │   └── Function: query_replace
         ├── query_management.py
         │   └── Function: execute_query
         │   └── Function: execute_query_wrapper
         │   └── Function: is_version_greater_than
         ├── time_management.py
+        │   └── Function: get_hidden_table_name
         │   └── Class: TimeManager
         ├── visualization.py
         │   └── Function: display_table

{tdfs4ds-0.2.4.22.dist-info → tdfs4ds-0.2.4.24.dist-info}/RECORD

@@ -2,13 +2,16 @@ 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=WzWW4Y3np8wKqfw20jm2nhvqW3lggGFxuxGC4tj9GRc,64168
+tdfs4ds/__init__.py,sha256=vKZp_W-fEms4vEvXDyUSdBA4o5-YWU8cx16tq57jNPY,64168
 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
+tdfs4ds/data/logo/teradata_sym_rgb_wht_rev.png,sha256=ETznIUnS38vlHek_CzjmcjnpthfCATCp2Ww0Dx8Th3Q,7803
 tdfs4ds/dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tdfs4ds/dataset/dataset.py,sha256=caiQwT-RtdPe5MDtsynWMm1n12OxftgMp7_BR9SCHKw,5360
 tdfs4ds/dataset/dataset_catalog.py,sha256=qxS2thDW2MvsRouSFaX1M0sX2J7IzBAYD8Yf22Tsd5k,16638
@@ -16,7 +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=rvpnFrV6Tmg8C6xcSQLT_lrFYqZsdSzFXmS-4suK9qg,42847
 tdfs4ds/feature_store/feature_query_retrieval.py,sha256=zuHRZhL6-qyLpPS7mWgRy1WingSN5iibkbi53Q7jfAs,33834
-tdfs4ds/feature_store/feature_store_management.py,sha256=e_hBsGhtqA6vHBu2Mhy4URkYe4SFaHijXXdqqWr-3tg,56154
+tdfs4ds/feature_store/feature_store_management.py,sha256=bVJbGZx1zj8Ph3q_qb939bxXSqsDl6e6SZw_GGzJ0qk,56238
 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=DsIt97cBoJ7NcpQzbQt55eUFNgXGdOMm5Hh2aX5v0PY,7762
@@ -29,7 +32,7 @@ tdfs4ds/utils/lineage.py,sha256=gy5M42qy5fvdWmlohAY3WPYoqAyp5VakeEmeT1YjrJQ,3783
 tdfs4ds/utils/query_management.py,sha256=nAcE8QY1GWAKgOtb-ubSfDVcnYbU7Ge8CruVRLoPtmY,6356
 tdfs4ds/utils/time_management.py,sha256=1eqGs7rT3SGag0F30R3PzwiC7Aa7DKia2Ud0aSNKcPg,10593
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.22.dist-info/METADATA,sha256=KLi85PSCJhjZAVo3o30jBXQ1XZM-4BjqFTtMVgshBPc,12028
-tdfs4ds-0.2.4.22.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.22.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.22.dist-info/RECORD,,
+tdfs4ds-0.2.4.24.dist-info/METADATA,sha256=et6II_3-JvvDjxw4JJWNEMGtpMtGPpF70MKHFy3K6RM,14326
+tdfs4ds-0.2.4.24.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.24.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.24.dist-info/RECORD,,