tdfs4ds 0.2.4.24__py3-none-any.whl → 0.2.4.26__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.24'
+__version__ = '0.2.4.26'
 import logging
 # Setup the logger
 logging.basicConfig(

tdfs4ds/dataset/dataset.py

@@ -43,7 +43,7 @@ class Dataset:
             return getattr(self.df, item)
         raise AttributeError(f"'{type(self).__name__}' object has no attribute '{item}'")
     
-    def _retrieve_entities_and_features(self):
+    def _retrieve_entities_and_features_old(self):
 
         if self._get_dataset_type() == 'snapshot':
 
@@ -75,6 +75,63 @@ class Dataset:
             logger.error(f"not implemented yet for dataset type: {self._get_dataset_type()}")
             raise
     
+    def _retrieve_entities_and_features(self):
+        if self._get_dataset_type() != 'snapshot':
+            logger.error(f"not implemented yet for dataset type: {self._get_dataset_type()}")
+            raise
+
+        import re
+
+        ddl = self._get_ddl()
+
+        # Column types from the materialized dataframe
+        columns_types = get_feature_types_sql_format(self.df)
+
+        # Regex to capture each feature subquery:
+        #  - grabs feature name alias, FEATURE_ID, FEATURE_VERSION
+        #  - grabs database and view/table (quoted or unquoted)
+        pattern = re.compile(
+            r"""
+            SEQUENCED\s+VALIDTIME\s+SELECT
+            .*?                               # anything before the feature value
+            B1\.FEATURE_VALUE\s+AS\s+(?P<fname>[A-Za-z_][\w]*)   # AS <feature_name>
+            \s+FROM\s+
+            (?:
+                "(?P<dbq>[^"]+)"\."(?P<viewq>[^"]+)"             # "DB"."VIEW"
+                |
+                (?P<db>[A-Za-z_]\w*)\.(?P<view>[A-Za-z_]\w*)     # DB.VIEW
+            )
+            \s+B1\s+WHERE\s*\(
+                \s*FEATURE_ID\s*=\s*(?P<fid>\d+)\s+
+                AND\s+FEATURE_VERSION\s*=\s*'(?P<fver>[^']+)'
+            \s*\)
+            """,
+            re.IGNORECASE | re.DOTALL | re.VERBOSE
+        )
+
+        features = {}
+        for m in pattern.finditer(ddl):
+            fname = m.group('fname')
+            fid   = int(m.group('fid'))
+            fver  = m.group('fver')
+            db    = (m.group('dbq') or m.group('db') or '').upper()
+            view  = (m.group('viewq') or m.group('view') or '').upper()
+            ftype = columns_types[fname].upper()
+            features[fname.upper()] = {
+                'id': fid,
+                'version': fver,
+                'type': ftype,
+                'database': db,
+                'view': view
+            }
+
+        # Anything in the dataframe that isn't a feature column is an entity column.
+        feature_names_upper = set(features.keys())
+        entity_names = [c for c in self.df.columns if c.upper() not in feature_names_upper]
+        entity = {n: columns_types[n] for n in entity_names}
+
+        return entity, features
+    
     def _get_dataset_type(self):
         return 'snapshot'
     

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-0.2.4.24.dist-info → tdfs4ds-0.2.4.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.24
+Version: 0.2.4.26
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.24.dist-info → tdfs4ds-0.2.4.26.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=vKZp_W-fEms4vEvXDyUSdBA4o5-YWU8cx16tq57jNPY,64168
+tdfs4ds/__init__.py,sha256=_UnSzqinlnbLOM4wOTxJrT1a_qTn6mRiNHz4jE6bRaI,64168
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -13,13 +13,13 @@ tdfs4ds/data/logo/tdfs4ds_logo.png,sha256=OCKQnH0gQbRyupwZeiIgo-9c6mdRtjE2E2Zunr
 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.py,sha256=J_fgfsVdR9zSOXrUOqyotqsUD-GlQMGyuld6ueov45w,7603
 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=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_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-0.2.4.24.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,,
+tdfs4ds-0.2.4.26.dist-info/METADATA,sha256=15eq8Z08VdFjD-GXC2cLqGvfb8OQoDRi3oPlmTyiq00,14326
+tdfs4ds-0.2.4.26.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.26.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.26.dist-info/RECORD,,