stoffelmauro
/
ConsultancyProject_2_ETL
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixed calculation of monthly data, closes #18

main
mmaurostoffel 2025-01-17 17:51:27 +01:00
parent 4e233da745
commit 2560d43c3f
2 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
etl/src/data/etl_property_capacities_monthly.py
View File

@ -24,12 +24,15 @@ def property_capacities_monthly(id: int, scrapeDate: str):
df_calendar = df_calendar.transpose()
df_calendar = df_calendar.with_columns(pl.Series(name="dates", values=columnTitles))
df_calendar = df_calendar.with_columns((pl.col("dates").str.to_date()))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.month_end().dt.day().alias('numDays')))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.strftime("%b") + " " + (pl.col("dates").dt.strftime("%Y"))).alias('date_short'))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.strftime("%Y") + " " + (pl.col("dates").dt.strftime("%m"))).alias('dates'))
df_calendar = df_calendar.group_by(['dates', 'date_short']).agg(pl.col("column_0").sum())
df_calendar = df_calendar.group_by(['dates', 'date_short', 'numDays']).agg(pl.col("column_0").sum())
df_calendar = df_calendar.with_columns((pl.col("column_0") / pl.col("numDays") / 2 * 100).alias("column_0"))
df_calendar = df_calendar.sort('dates')
df_calendar = df_calendar.drop('dates')
result = {"scraping-date": scrapeDate, "months": df_calendar['date_short'].to_list(), 'capacities': df_calendar['column_0'].to_list()}
etl_cache.saveObj(file, result)
return result

5
etl/src/data/etl_region_capacities_monthly.py
View File

@ -41,11 +41,14 @@ def region_capacities_monthly(id: int, scrapeDate_start: str):
df_calendar = df_calendar.transpose()
df_calendar = df_calendar.with_columns(pl.Series(name="dates", values=columnTitles))
df_calendar = df_calendar.with_columns((pl.col("dates").str.to_date()))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.month_end().dt.day().alias('numDays')))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.strftime("%b") + " " + (pl.col("dates").dt.strftime("%Y"))).alias('date_short'))
df_calendar = df_calendar.with_columns((pl.col("dates").dt.strftime("%Y") + " " + (pl.col("dates").dt.strftime("%m"))).alias('dates'))
df_calendar = df_calendar.group_by(['dates', 'date_short']).agg(pl.col("column_0").sum())
df_calendar = df_calendar.group_by(['dates', 'date_short','numDays']).agg(pl.col("column_0").sum())
df_calendar = df_calendar.with_columns((pl.col("column_0") / pl.col("numDays") / 2 * 100).alias("column_0"))
df_calendar = df_calendar.sort('dates')
df_calendar = df_calendar.drop('dates')
df_calendar = df_calendar.drop('numDays')
df_calendar = df_calendar.rename({'column_0': str(counter)})