tdfs4ds 0.2.4.25__py3-none-any.whl → 0.2.4.27__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.25'
+__version__ = '0.2.4.27'
 import logging
 # Setup the logger
 logging.basicConfig(
@@ -935,6 +935,10 @@ def build_dataset(entity_id, selected_features, view_name, schema_name=None, com
     selected_features : dict
         A dictionary where the keys are feature table names, and the values are lists of tuples
         (feature_id, feature_version, feature_name) specifying the features to retrieve.
+        NOTE: feature_version may be either:
+          - a single UUID string, or
+          - a list of dicts like:
+              {"process_id": <UUID>, "process_view_name": <str>}
 
     view_name : str
         The name of the view to be created in the database.
@@ -1004,6 +1008,24 @@ def build_dataset(entity_id, selected_features, view_name, schema_name=None, com
     # Sort the entity ID list for consistent query generation
     list_entity_id.sort()
 
+    # Helpers
+    import re
+    def _sanitize_identifier(name: str) -> str:
+        # Keep letters, numbers, and underscores; replace others with '_'
+        return re.sub(r'[^0-9A-Za-z_]', '_', name)
+
+    used_alias_counts = {}  # base_alias -> count
+
+    def _unique_alias(base: str) -> str:
+        """
+        Ensure alias uniqueness: if base already used, append _2, _3, ...
+        """
+        if base not in used_alias_counts:
+            used_alias_counts[base] = 1
+            return base
+        used_alias_counts[base] += 1
+        return f"{base}_{used_alias_counts[base]}"
+
     # Initialize sub-query construction
     tdfs4ds.logger.info("Generating the sub-queries for feature retrieval.")
     sub_queries = []
@@ -1014,21 +1036,52 @@ def build_dataset(entity_id, selected_features, view_name, schema_name=None, com
     # Construct sub-queries for each feature
     for k, v in list_features.items():
         for feature_id, feature_version, feature_name in v:
-            txt_where = f"(FEATURE_ID = {feature_id} AND FEATURE_VERSION='{feature_version}')"
-            feature_str = ',B1.FEATURE_VALUE AS ' + feature_name
-            sub_queries.append(
-                {
-                    'feature_name': feature_name,
-                    'query': f"""
-                    SEQUENCED VALIDTIME
-                    SELECT 
-                       {txt_entity}
-                      {feature_str}
-                    FROM {k} B1
-                    WHERE {txt_where}
-                    """
-                }
-            )
+
+            # Multiple processes: list of dicts
+            if isinstance(feature_version, list):
+                for item in feature_version:
+                    process_id = item.get("process_id")
+                    process_view_name = item.get("process_view_name") or "PROCESS"
+                    base_alias = _sanitize_identifier(f"{feature_name}_{process_view_name}")
+                    alias = _unique_alias(base_alias)
+
+                    txt_where = f"(FEATURE_ID = {feature_id} AND FEATURE_VERSION='{process_id}')"
+                    feature_str = ',B1.FEATURE_VALUE AS ' + alias
+
+                    sub_queries.append(
+                        {
+                            'feature_name': alias,
+                            'query': f"""
+                            SEQUENCED VALIDTIME
+                            SELECT 
+                               {txt_entity}
+                              {feature_str}
+                            FROM {k} B1
+                            WHERE {txt_where}
+                            """
+                        }
+                    )
+
+            # Single UUID
+            else:
+                base_alias = _sanitize_identifier(feature_name)
+                alias = _unique_alias(base_alias)
+
+                txt_where = f"(FEATURE_ID = {feature_id} AND FEATURE_VERSION='{feature_version}')"
+                feature_str = ',B1.FEATURE_VALUE AS ' + alias
+                sub_queries.append(
+                    {
+                        'feature_name': alias,
+                        'query': f"""
+                        SEQUENCED VALIDTIME
+                        SELECT 
+                           {txt_entity}
+                          {feature_str}
+                        FROM {k} B1
+                        WHERE {txt_where}
+                        """
+                    }
+                )
 
     # Handle case where no features are available
     if len(sub_queries) == 0:
@@ -1102,6 +1155,7 @@ def build_dataset(entity_id, selected_features, view_name, schema_name=None, com
         return tdml.DataFrame.from_table(tdml.in_schema(schema_name, view_name))
 
 
+
 def build_dataset_opt(entity_id, selected_features, view_name = None, schema_name=tdfs4ds.SCHEMA,
                   comment='dataset', no_temporal=False, time_manager=None, query_only=False, entity_null_substitute={},
                   other=None, time_column=None, filtermanager = None, filter_conditions = None

tdfs4ds/feature_store/feature_query_retrieval.py

@@ -249,48 +249,49 @@ def get_list_features(entity_name, domain=None):
     return tdml.DataFrame.from_query(query)
 
 
-def get_feature_versions(entity_name, features, domain=None, latest_version_only=True, version_lag=0):
+def get_feature_versions(entity_name, features, domain=None):
     """
-    Retrieve feature versions for specified features associated with certain entities
-    from a given data domain. This function allows fetching either all versions or
-    just the latest versions of the features.
+    Retrieve version UUID(s) for the given features of an entity within a domain.
 
     Parameters:
-    entity_name (str or list): The name of the entity or a list of entity names
-                               for which feature versions are to be fetched.
-    features (list): A list of features for which versions are required.
-    domain (str, optional): The data domain to filter the feature versions.
-                            Defaults to None, where a predefined domain is used.
-    latest_version_only (bool, optional): Flag to fetch only the latest version
-                                          of each feature. Defaults to True.
-    version_lag (int, optional): The number of versions to lag behind the latest.
-                                 Only effective if latest_version_only is True. Defaults to 0.
+    - entity_name (str): The entity name to which the features belong.
+    - features (str | list[str]): Feature name or list of feature names.
+    - domain (str, optional): Data domain to filter on. If None, defaults to tdfs4ds.DATA_DOMAIN.
 
     Returns:
-    dict: A dictionary with feature names as keys and their corresponding versions as values.
+    - dict[str, str | list[dict]]: Maps each requested feature name to either:
+        - a single version UUID string if exactly one row exists, or
+        - a list of dicts if multiple rows exist; each dict has:
+            {
+              "process_id": <FEATURE_VERSION UUID>,
+              "process_view_name": <PROCESS_VIEW_NAME string>
+            }
+      If a requested feature has no entries, it will be present with value None.
+
+    Notes:
+    - Uses {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME} as A and
+      {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME} as B (must exist) joined on PROCESS_ID.
+    - Respects tdfs4ds.DEBUG_MODE to print the generated SQL.
     """
 
-    # Default to a predefined data domain if none is provided
+    # Normalize inputs
+    if isinstance(features, str):
+        features = [features]
+
     if domain is None:
         domain = tdfs4ds.DATA_DOMAIN
 
+    # Basic escaping for single quotes in values used in SQL literals
+    def _esc(s: str) -> str:
+        return s.replace("'", "''")
 
-
-    # Convert the entity_name to a string if it is a list
-    if type(entity_name) == list:
-        entity_name.sort()
-        entity_name = ','.join(entity_name)
-
-    # Preparing the feature names for inclusion in the SQL query
-    if type(features) == list:
-        features = ["'" + f + "'" for f in features]
-    else:
-        features = "'" + features + "'"
+    features_lits = ",".join(f"'{_esc(f)}'" for f in features)
 
     query = f"""
         SELECT
             A.FEATURE_NAME
         ,   B.PROCESS_ID AS FEATURE_VERSION
+        ,   B.VIEW_NAME AS PROCESS_VIEW_NAME
         FROM {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME_VIEW} A
         INNER JOIN {tdfs4ds.SCHEMA}.{tdfs4ds.PROCESS_CATALOG_NAME_VIEW_FEATURE_SPLIT} B
         ON A.DATA_DOMAIN = B.DATA_DOMAIN
@@ -298,35 +299,45 @@ def get_feature_versions(entity_name, features, domain=None, latest_version_only
         AND A.FEATURE_NAME = B.FEATURE_NAME
         WHERE A.DATA_DOMAIN = '{domain}'
         AND A.ENTITY_NAME = '{entity_name}'
-        AND A.FEATURE_NAME IN ({','.join(features)})
+        AND A.FEATURE_NAME IN ({features_lits})
     """
 
-    # Executing the first query and converting the results to a pandas DataFrame
-    df = tdml.DataFrame.from_query(query).to_pandas()
-
-    # if df is empty
-    if df.shape[0] == 0:
-        print('the features you are requesting for this entity and data domain do not exist. Here is what you requested:')
-        print('feature store database :', tdfs4ds.SCHEMA)
-        print('feature catalog        :', tdfs4ds.FEATURE_CATALOG_NAME_VIEW)
-        print('entity name            :', entity_name)
-        print('data domain            :', domain)
-        print('features               :', ','.join(features))
-        print('')
+    if tdfs4ds.DEBUG_MODE:
         print(query)
-        return
 
-    if tdfs4ds.DEBUG_MODE == True:
-        print(query)
+    rows = tdml.execute_sql(query).fetchall()
+
+    # Initialize result for all requested features
+    result = {f: None for f in features}
+
+    # Collect (version, view) per feature, deduplicating while preserving order
+    tmp = {f: [] for f in features}
+    seen = {f: set() for f in features}
+
+    for feat, version, view_name in rows:
+        key = (version, view_name)
+        if key not in seen.setdefault(feat, set()):
+            seen[feat].add(key)
+            tmp.setdefault(feat, []).append(key)
+
+    # Shape:
+    # - if exactly one row: return UUID string
+    # - if multiple rows: list of {"process_id": <uuid>, "process_view_name": <str>}
+    for feat in result:
+        pairs = tmp.get(feat, [])
+        if len(pairs) == 0:
+            result[feat] = None
+        elif len(pairs) == 1:
+            result[feat] = pairs[0][0]  # UUID only
+        else:
+            result[feat] = [
+                {"process_id": ver, "process_view_name": view}
+                for (ver, view) in pairs
+            ]
+
+    return result
 
-    # results in dictionary:
-    results = {row['FEATURE_NAME']: row['FEATURE_VERSION'] for i, row in df.iterrows()}
-    if tdfs4ds.DEBUG_MODE == True:
-        print('---> RESULTS <---')
-        print(results)
 
-    # Returning the results as a dictionary with feature names as keys and their versions as values
-    return results
 def get_entity_tables(entity_id, data_domain=None):
     """
     Retrieves a list of table names associated with a given entity ID or IDs from a feature catalog within a specific data domain.

tdfs4ds/feature_store/feature_store_management.py

@@ -869,39 +869,6 @@ def Gettdtypes(tddf, features_columns, entity_id):
             # Increment the feature ID for the next iteration.
             feature_id += 1
 
-    # # Iterate over the data types of the columns in the DataFrame.
-    # for k, v in types.items():
-    #     # If the column name does not exist in the feature catalog table and is in the list of feature column names...
-    #     if k.upper() not in [n.upper() for n in existing_features] and k.upper() in [n.upper() for n in features_columns]:
-    #         # If the data type of the column is integer...
-    #         if 'int' in str(v.lower()):
-    #             # Add an entry to the result dictionary for the column name with its data type and new feature ID.
-    #             res[k] = {'type': 'BIGINT', 'id': feature_id}
-    #         # If the data type of the column is float...
-    #         elif 'float' in str(v.lower()):
-    #             # Add an entry to the result dictionary for the column name with its data type and new feature ID.
-    #             res[k] = {'type': 'FLOAT', 'id': feature_id}
-    #         # If the data type of the column is varchar with unicode encoding ...
-    #         elif 'unicode' in str(v.lower()):
-    #             res[k] = {'type': 'VARCHAR_UNICODE', 'id': feature_id}
-    #             # Print a message that the data type is not yet managed.
-    #             #if tdfs4ds.DISPLAY_LOGS: print(f'{k} has a type that is not yet managed')
-    #         # If the data type of the column is varchar with unicode encoding ...
-    #         elif 'latin' in str(v.lower()):
-    #             res[k] = {'type': 'VARCHAR_LATIN', 'id': feature_id}
-    #             # Print a message that the data type is not yet managed.
-    #             #if tdfs4ds.DISPLAY_LOGS: print(f'{k} has a type that is not yet managed')
-    #         elif 'decimal' in str(v.lower()):
-    #             res[k] = {'type': 'DECIMAL', 'id': feature_id}
-    #             # Print a message that the data type is not yet managed.
-    #             # if tdfs4ds.DISPLAY_LOGS: print(f'{k} has a type that is not yet managed')
-    #         else:
-    #             res[k] = {'type': 'VARCHAR_LATIN', 'id': feature_id}
-    #             # Print a message that the data type is not yet managed.
-    #             # if tdfs4ds.DISPLAY_LOGS: print(f'{k} has a type that is not yet managed')
-    #         # Increment the feature ID for the next iteration.
-    #         feature_id += 1
-
     # Return the result dictionary.
     return res
 
@@ -979,36 +946,50 @@ def tdstone2_Gettdtypes(existing_model, entity_id, display_logs=False):
     # Return the dictionary containing feature names, types, and IDs.
     return res
 
-def delete_feature(feature_name, data_domain=None):
+def delete_feature(feature_name, entity_id, data_domain=None):
     """
-    Delete the values of a specific feature from the feature table within a given data domain.
+    Delete the values of a specific feature for given entities from the feature table 
+    within a specified data domain.
 
     This function constructs and executes two SQL queries against a Teradata database
-    to remove a feature specified by its name. The first query retrieves the table name
-    where the feature resides, based on the feature name and data domain. The second query
-    deletes the feature from the identified table.
+    to remove a feature specified by its name and entity identifiers. The first query 
+    retrieves the table name where the feature resides, based on the feature name, 
+    entity, and data domain. The second query deletes the feature values from the 
+    identified table.
 
     Parameters:
     - feature_name (str): The name of the feature to be removed.
-    - data_domain (str, optional): The data domain where the feature is located. If not specified,
-      the function uses the default data domain defined in tdfs4ds.DATA_DOMAIN.
-
-    The function checks if the DEBUG_MODE flag in the tdfs4ds module is set to True. If so,
-    it prints the SQL queries and the resolved table name for debugging purposes.
+    - entity_id (str or list of str): Entity identifier(s). If a string is provided, 
+      it will be converted to a single-element list. The list is always sorted 
+      alphabetically before use.
+    - data_domain (str, optional): The data domain where the feature is located. 
+      If not specified, the function uses the default data domain defined in 
+      `tdfs4ds.DATA_DOMAIN`.
+
+    Behavior:
+    - The function checks if the `DEBUG_MODE` flag in the `tdfs4ds` module is set to True. 
+      If so, it prints the generated SQL queries and the resolved table name for debugging.
+    - If the feature table cannot be resolved, the function returns without executing 
+      a delete query.
 
-    The function does not return any value.
+    Returns:
+    - None
 
     Note:
     - The function assumes the presence of a module `tdfs4ds` with predefined constants
-      such as `DATA_DOMAIN`, `SCHEMA`, `FEATURE_CATALOG_NAME`, and a flag `DEBUG_MODE`.
+      such as `DATA_DOMAIN`, `SCHEMA`, `FEATURE_CATALOG_NAME_VIEW`, and a flag `DEBUG_MODE`.
     - It also assumes a `tdml` module or object with an `execute_sql` method capable of
       executing SQL queries against a Teradata database and fetching the results.
 
     Raises:
-    - This function might raise exceptions related to SQL execution or connection issues,
-      which are not explicitly handled within the function itself.
+    - Exceptions related to SQL execution or connection issues may be raised but are not 
+      explicitly handled, except for printing the error message.
     """
 
+    if isinstance(entity_id, str):
+        entity_id = [entity_id]
+    entity_id = sorted(entity_id)
+
     if data_domain is None:
         data_domain = tdfs4ds.DATA_DOMAIN
 
@@ -1016,17 +997,19 @@ def delete_feature(feature_name, data_domain=None):
     SEL FEATURE_DATABASE||'.'||FEATURE_TABLE AS TABLE_NAME
     FROM {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME_VIEW}
     WHERE FEATURE_NAME = '{feature_name}'
-    AND DATA_DOMAIN = '{data_domain}'"""
+    AND DATA_DOMAIN = '{data_domain}'
+    AND ENTITY_NAME = '{','.join([e.upper() for e in entity_id])}'"""
     if tdfs4ds.DEBUG_MODE:
         print(query0)
 
     table_name = tdml.execute_sql(query0).fetchall()
-    if len(table_name)>0:
+    if len(table_name) > 0:
         table_name = table_name[0][0]
     else:
         return
     if tdfs4ds.DEBUG_MODE:
         print('table name : ', table_name)
+
     query = f"""
     DELETE {table_name}
     WHERE FEATURE_ID = (
@@ -1044,6 +1027,7 @@ def delete_feature(feature_name, data_domain=None):
 
     return
 
+
 def remove_feature(feature_name, entity_id, data_domain=None):
     """
     Attempts to remove a specific feature from the feature catalog and any associated data,
@@ -1060,7 +1044,9 @@ def remove_feature(feature_name, entity_id, data_domain=None):
 
     Parameters:
     - feature_name (str): The name of the feature to be removed.
-    - entity_id (list of str): A list of entity identifiers associated with the feature.
+    - entity_id (str or list of str): Entity identifier(s). If a string is provided, 
+      it will be converted to a single-element list. The list is always sorted 
+      alphabetically before use.
     - data_domain (str, optional): The data domain where the feature is located. If not provided,
       the function uses the default data domain from the `tdfs4ds.DATA_DOMAIN` setting.
 
@@ -1084,16 +1070,19 @@ def remove_feature(feature_name, entity_id, data_domain=None):
     - SQL execution or connection exceptions might occur but are not explicitly handled by this function.
     """
 
+    if isinstance(entity_id, str):
+        entity_id = [entity_id]
+    entity_id = sorted(entity_id)
+
     if data_domain is None:
         data_domain = tdfs4ds.DATA_DOMAIN
 
     try:
-        delete_feature(feature_name, data_domain)
+        delete_feature(feature_name, entity_id, data_domain)
     except Exception as e:
         print(str(e).split('\n')[0])
         return
 
-    entity_id.sort()
     query = f"""
     NONSEQUENCED VALIDTIME DELETE {tdfs4ds.SCHEMA}.{tdfs4ds.FEATURE_CATALOG_NAME}
     WHERE FEATURE_NAME = '{feature_name}'
@@ -1102,7 +1091,6 @@ def remove_feature(feature_name, entity_id, data_domain=None):
     """
     if tdfs4ds.DEBUG_MODE:
         print(query)
+
     tdml.execute_sql(query)
     return
-
-

{tdfs4ds-0.2.4.25.dist-info → tdfs4ds-0.2.4.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.25
+Version: 0.2.4.27
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.25.dist-info → tdfs4ds-0.2.4.27.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=SLBlY2M4Z7IyvMYnd8wRWUeXJeWJhDYLD7FdWXII7lI,64168
+tdfs4ds/__init__.py,sha256=sHzEWvxrBA_DBbOBJOsFuIxz0qX9MAY3zdS20gnCz_Q,66290
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -18,8 +18,8 @@ tdfs4ds/dataset/dataset_catalog.py,sha256=qxS2thDW2MvsRouSFaX1M0sX2J7IzBAYD8Yf22
 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=rvpnFrV6Tmg8C6xcSQLT_lrFYqZsdSzFXmS-4suK9qg,42847
-tdfs4ds/feature_store/feature_query_retrieval.py,sha256=zuHRZhL6-qyLpPS7mWgRy1WingSN5iibkbi53Q7jfAs,33834
-tdfs4ds/feature_store/feature_store_management.py,sha256=bVJbGZx1zj8Ph3q_qb939bxXSqsDl6e6SZw_GGzJ0qk,56238
+tdfs4ds/feature_store/feature_query_retrieval.py,sha256=0ZLJWtV13tjaUdYCiQvPvYWxKs0f_3LZ2HgfQzHyaW4,33705
+tdfs4ds/feature_store/feature_store_management.py,sha256=ufIBTdrnHBvGdXggavJoTVoZjOHFtH5ZiYqJr5eIBhg,54713
 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
@@ -32,7 +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-0.2.4.25.dist-info/METADATA,sha256=u4jn-r_y-KkfxsVcBRAQ07OQw7vkSUEwvtNp0BS2WKs,14326
-tdfs4ds-0.2.4.25.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.25.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.25.dist-info/RECORD,,
+tdfs4ds-0.2.4.27.dist-info/METADATA,sha256=0zXOf1EjCvIPgXK3EyOtMDlF4ZB5nArvMsKcqFqknTg,14326
+tdfs4ds-0.2.4.27.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.27.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.27.dist-info/RECORD,,