tdfs4ds 0.2.4.17__py3-none-any.whl → 0.2.4.18__py3-none-any.whl

tdfs4ds/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.2.4.17'
+__version__ = '0.2.4.18'
 import logging
 # Setup the logger
 logging.basicConfig(

tdfs4ds/utils/time_management.py

@@ -45,47 +45,89 @@ class TimeManager:
 
     def load_time_steps(self, df, time_column):
         """
-        Loads a new filter into the table and updates the view to reflect this filter.
+        Load time steps into the table and update the view accordingly.
 
-        This method takes a DataFrame as input, assigns filter IDs to each row, and updates or replaces the table and view to reflect the new filter configuration.
+        This method:
+        1. Creates a new DataFrame with a sequential time_id and BUSINESS_DATE.
+        2. Ensures BUSINESS_DATE has the correct SQL data type.
+        3. Drops and recreates the target table with the appropriate schema.
+        4. Inserts the new data into the table.
+        5. Updates the view to reference the first time step.
+        6. Stores the number of time steps in `self.nb_time_steps`.
 
         Args:
-            df (DataFrame): The data containing the new filter configuration.
+            df (pd.DataFrame): The input DataFrame containing time data.
+            time_column (str): The column name representing time.
         """
 
-        df_            = df.assign(**{
-            'time_id': tdml.sqlalchemy.literal_column(
-            f"ROW_NUMBER() OVER (PARTITION BY 1 ORDER BY {time_column})", tdml.BIGINT()),
-            'BUSINESS_DATE' : df[time_column]
-        })[['time_id','BUSINESS_DATE']]
-
-        type_BUSINESS_DATE = tdfs4ds.utils.info.get_feature_types_sql_format(df_)['BUSINESS_DATE']
-        if 'TIMESTAMP' in type_BUSINESS_DATE.upper() and 'ZONE' not in type_BUSINESS_DATE.upper():
-            print(f"data type of the time colum has been modified from {type_BUSINESS_DATE} to {type_BUSINESS_DATE + ' WITH TIME ZONE'}")
-            type_BUSINESS_DATE = type_BUSINESS_DATE + ' WITH TIME ZONE'
-            df_ = df_.assign(type_BUSINESS_DATE = tdml.sqlalchemy.literal_column(f"CAST(BUSINESS_DATE AS {type_BUSINESS_DATE})"))
-
-        d_ = {x[0]: x[1] for x in df_._td_column_names_and_types}
-        self.data_type = type_BUSINESS_DATE #d_['BUSINESS_DATE']
+        # Step 1: Build DataFrame with time_id and BUSINESS_DATE
+        df_ = df.assign(
+            time_id=tdml.sqlalchemy.literal_column(
+                f"ROW_NUMBER() OVER (PARTITION BY 1 ORDER BY {time_column})", 
+                tdml.BIGINT()
+            ),
+            BUSINESS_DATE=df[time_column]
+        )[["time_id", "BUSINESS_DATE"]]
+
+        # Step 2: Get SQL types and adjust BUSINESS_DATE if necessary
+        sql_types = tdfs4ds.utils.info.get_feature_types_sql_format(df_)
+        type_business_date = sql_types["BUSINESS_DATE"]
+
+        if "TIMESTAMP" in type_business_date.upper() and "ZONE" not in type_business_date.upper():
+            new_type = f"{type_business_date} WITH TIME ZONE"
+            print(
+                f"Data type of the time column modified from {type_business_date} "
+                f"to {new_type}"
+            )
+            type_business_date = new_type
+            sql_types["BUSINESS_DATE"] = new_type
+
+            df_ = df_.assign(
+                BUSINESS_DATE=tdml.sqlalchemy.literal_column(
+                    f"CAST(BUSINESS_DATE AS {new_type})"
+                )
+            )
+
+        self.data_type = type_business_date
+
+        # Step 3: Drop table if it exists
+        try:
+            tdml.execute_sql(f"DROP TABLE {self.schema_name}.{self.table_name}")
+        except Exception as e:
+            if tdfs4ds.DEBUG_MODE:
+                print(f"Error dropping table {self.schema_name}.{self.table_name}: {e}")
+
+        # Step 4: Recreate table
+        ddl = ",\n".join([f"{col} {dtype}" for col, dtype in sql_types.items()])
+        create_table_sql = f"""
+            CREATE TABLE {self.schema_name}.{self.table_name} (
+                {ddl}
+            )
+            PRIMARY INDEX (time_id)
+        """
+        tdml.execute_sql(create_table_sql)
 
-        df_.to_sql(
-            table_name    = self.table_name,
-            schema_name   = self.schema_name,
-            if_exists     = 'replace',
-            primary_index = ['time_id'],
+        # Step 5: Insert data
+        df_[list(sql_types.keys())].to_sql(
+            table_name=self.table_name,
+            schema_name=self.schema_name,
+            if_exists="append"
         )
 
-        query = f"""
-         REPLACE VIEW {self.schema_name}.{self.view_name} AS
-         SEL BUSINESS_DATE
-         FROM {self.schema_name}.{self.table_name}
-         WHERE time_id = 1
-         """
-
-        tdml.execute_sql(query)
+        # Step 6: Update view
+        create_view_sql = f"""
+            REPLACE VIEW {self.schema_name}.{self.view_name} AS
+            SELECT BUSINESS_DATE
+            FROM {self.schema_name}.{self.table_name}
+            WHERE time_id = 1
+        """
+        tdml.execute_sql(create_view_sql)
 
-        self.nb_time_steps = tdml.execute_sql(
-            f"SEL MAX(time_id) AS nb_filters FROM {self.schema_name}.{self.table_name}").fetchall()[0][0]
+        # Step 7: Store number of time steps
+        result = tdml.execute_sql(
+            f"SELECT MAX(time_id) AS nb_filters FROM {self.schema_name}.{self.table_name}"
+        ).fetchall()
+        self.nb_time_steps = result[0][0]
 
 
     def _exists(self):

{tdfs4ds-0.2.4.17.dist-info → tdfs4ds-0.2.4.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tdfs4ds
-Version: 0.2.4.17
+Version: 0.2.4.18
 Summary: A python package to simplify the usage of feature store using Teradata Vantage ...
 Author: Denis Molin
 Requires-Python: >=3.6

{tdfs4ds-0.2.4.17.dist-info → tdfs4ds-0.2.4.18.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=CU5AFwETPm__QJJhmyxIE35XgkKB8rNmJaSrA-0GgFk,64168
+tdfs4ds/__init__.py,sha256=pDeTVUVWwzAj5A7GxZy6KTKJkAYuzm5NbmKwhFOFa7I,64168
 tdfs4ds/datasets.py,sha256=LE4Gn0muwdyrIrCrbkE92cnafUML63z1lj5bFIIVzmc,3524
 tdfs4ds/feature_engineering.py,sha256=oVnZ2V_XNGE12LKC_fNfkrWSQZLgtYRmaf8Dispi6S4,7081
 tdfs4ds/feature_store.py,sha256=y-oItPZw6nBkBcGAceaATZbkLPTsvpk0OnpzTxYofDs,68576
@@ -27,9 +27,9 @@ tdfs4ds/utils/filter_management.py,sha256=7D47N_hnTSUVOkaV2XuKrlUFMxzWjDsCBvRYsH
 tdfs4ds/utils/info.py,sha256=sShnUxXMlvCtQ6xtShDhqdpTr6sMG0dZQhNBFgUENDY,12058
 tdfs4ds/utils/lineage.py,sha256=LI-5pG7D8lO3-YFa9qA6CrEackiYugV23_Vz9IpF5xw,28670
 tdfs4ds/utils/query_management.py,sha256=nAcE8QY1GWAKgOtb-ubSfDVcnYbU7Ge8CruVRLoPtmY,6356
-tdfs4ds/utils/time_management.py,sha256=rVxtIXcFtQih2UabAtos4DK-j9MPqzYVieIz_SvySZE,9241
+tdfs4ds/utils/time_management.py,sha256=1eqGs7rT3SGag0F30R3PzwiC7Aa7DKia2Ud0aSNKcPg,10593
 tdfs4ds/utils/visualization.py,sha256=5S528KoKzzkrAdCxfy7ecyqKvAXBoibNvHwz_u5ISMs,23167
-tdfs4ds-0.2.4.17.dist-info/METADATA,sha256=p_BzFpsW4I4oBIQryiPuid20dyzJbHw23_R8hrj_quQ,11944
-tdfs4ds-0.2.4.17.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-tdfs4ds-0.2.4.17.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
-tdfs4ds-0.2.4.17.dist-info/RECORD,,
+tdfs4ds-0.2.4.18.dist-info/METADATA,sha256=I3XSCDdFlXlJBYpj4B5liyIU99fkAGWstaaZGvQYDdg,11944
+tdfs4ds-0.2.4.18.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+tdfs4ds-0.2.4.18.dist-info/top_level.txt,sha256=wMyVkMvnBn8RRt1xBveGQxOpWFijPMPkMiE7G2mi8zo,8
+tdfs4ds-0.2.4.18.dist-info/RECORD,,