tdfs4ds 0.2.4.24__py3-none-any.whl → 0.2.4.25__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.24'
+__version__ = '0.2.4.25'
 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-0.2.4.24.dist-info → tdfs4ds-0.2.4.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.24
+Version: 0.2.4.25
 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-0.2.4.25.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=SLBlY2M4Z7IyvMYnd8wRWUeXJeWJhDYLD7FdWXII7lI,64168
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -13,7 +13,7 @@ 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
@@ -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-0.2.4.25.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,,