etl_region_capacities_monthly eingefügt closes #10

etl/src/api/main.py

@@ -5,12 +5,12 @@ from data import etl_property_capacities_monthly as etl_pcm
 from data import etl_property_capacities_weekdays as etl_pcw
 from data import etl_property_neighbours as etl_pn
 from data import etl_region_capacities as etl_rc
+from data import etl_region_capacities_monthly as etl_rcm
 from data import etl_region_capacities_weekdays as etl_rcw
 from data import etl_region_movAverage as etl_rmA
 from data import etl_region_properties_capacities as etl_rpc
 from data import etl_region_capacities_comparison as etl_rcc
-from data import etl_region_movAverage as etl_rmA
-from data import etl_region_properties_capacities as etl_rpc
+
 from fastapi import FastAPI, Response
 
 d = data.load()
@@ -79,6 +79,11 @@ def region_capacities_data(id: int):
 	capacities = etl_rc.region_capacities(id)
 	return capacities
 
+@app.get("/region/{id}/capacities/monthly/{scrapeDate}")
+def region_capacities_data(id: int, scrapeDate: str):
+	capacities = (etl_rcm.region_capacities_monthly(id, scrapeDate)
+	return capacities
+
 @app.get("/region/{id}/capacities/weekdays/{scrapeDate}")
 def region_capacities_data(id: int, scrapeDate: str):
 	capacities = etl_rcw.region_capacities_weekdays(id, scrapeDate)
@@ -98,7 +103,3 @@ def region_capacities_data(id: int, startDate: str):
 def region_base_data(id: int):
 	return d.region_base_data(id).pl().to_dicts()
 
-@app.get("/region/{id}/properties/capacities")
-def region_property_capacities_data(id: int):
-	capacities = etl_rpc.region_properties_capacities(id)
-	return capacities

etl/src/data/etl_region_capacities_monthly.py

@@ -0,0 +1,53 @@
+from io import StringIO
+
+import polars as pl
+
+import data
+
+from datetime import datetime, timedelta
+
+d = data.load()
+
+
+def region_capacities_monthly(id: int, scrapeDate_start: str):
+    # String to Date
+    scrapeDate_start = datetime.strptime(scrapeDate_start, '%Y-%m-%d')
+
+    # Get end date of start search-window
+    scrapeDate_end = scrapeDate_start + timedelta(days=1)
+
+    extractions = d.singleScrape_of_region_scrapDate(id, scrapeDate_start, scrapeDate_end).pl()
+    df_calendar = pl.DataFrame()
+    numWeeks = 0
+    firstExe = True
+    counter = 0
+    for row in extractions.rows(named=True):
+        scrapeDate = row['created_at']
+        if row['calendarBody']:
+            counter += 1
+            df_calendar = pl.read_json(StringIO(row['calendarBody']))
+            columnTitles = df_calendar.columns
+            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.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.sort('dates')
+            df_calendar = df_calendar.drop('dates')
+
+            df_calendar = df_calendar.rename({'column_0': str(counter)})
+
+            if firstExe:
+                outDf = df_calendar
+                firstExe = False
+            else:
+                outDf = outDf.join(df_calendar, on='date_short')
+
+    # Calculate horizontal Mean
+    means = outDf.mean_horizontal()
+    outDf = outDf.insert_column(1, means)
+    outDf = outDf[['date_short', 'mean']]
+
+    result = {"scraping-date": scrapeDate, "months": outDf['date_short'].to_list(),'capacities': outDf['mean'].to_list()}
+    return result