ungenutzte Datei etl_pipelines.py gelöscht

etl/src/data/etl_pipelines.py

@@ -1,46 +0,0 @@
-import polars as pl
-import json
-from datetime import datetime, timedelta
-def expansion_Pipeline(df):
-    '''
-    Rearranges a given extractions Dataframe into an expanded Dataframe.
-    New Columns :propId, created_at calendar_date, calendar_value
-    :param df: Inputs from database.py/extractions or database.py/extractions_for functions
-    :return: expanded dataframe
-    '''
-    data = []
-
-    for row in df.iter_rows():
-        propId = row[1]
-        createdAt = row[2]
-        if row[0]:
-            temp = json.loads(row[0])
-            keys = temp.keys()
-            for key in keys:
-                out = [propId, createdAt.date(), datetime.strptime(key, '%Y-%m-%d').date(), temp[key]]
-                data.append(out)
-
-    df = pl.DataFrame(data, schema=["property_id", "created_at", "calendar_date", "calendar_value"])
-    return df
-
-def liveDates_Pipeline(df):
-    '''
-    Returns the expanded Dataframe with only the live data and no future data
-    :param df: Inputs from database.py/extractions or database.py/extractions_for functions
-    :return: expanded and filtered dataframe
-    '''
-    df = expansion_Pipeline(df)
-    print(df)
-    df = df.filter(pl.col("calendar_date") == pl.col("created_at")+timedelta(days=2))
-    return df
-
-def liveDates_PipelineFromExpanded(df):
-    '''
-    Filters an already expanded df and returns only the live data and no future data
-    NOTE: The actual live date and the next is always 0. The reason is most likely that it is forbidden to
-    book on the current or next day. Workaround: Compare with the day after tomorrow
-    :param df: Inputs from expansion_Pipeline
-    :return: expanded and filtered dataframe
-    '''
-    df = df.filter(pl.col("calendar_date") == pl.col("created_at")+timedelta(days=2))
-    return df