etl_region_capacities erstellt + database und api/main Anpassungen dafür

etl/src/api/main.py

@@ -44,4 +44,10 @@ def property_capacities_data(id: int):
 def property_base_data(id: int):
 	return d.property_base_data(id).pl().to_dicts()
 
+@app.get("/region/{id}/capacities")
+def region_capacities_data(id: int):
+	capacities = etl_pc.region_capacities(id)
+	return capacities
+
+
 

etl/src/data/database.py

@@ -28,8 +28,6 @@ class Database:
 		if(spatial_installed and not spatial_installed[0]):
 			self.connection.sql("INSTALL spatial")
 
-
-
 	def db_overview(self):
 		return self.connection.sql("DESCRIBE;").show()
 
@@ -403,5 +401,20 @@ class Database:
 				consultancy_d.properties p
 		""")
 
+	def capacity_of_region(self, region_id):
+		return self.connection.sql(f"""
+			SELECT 
+				JSON_EXTRACT(body, '$.content.days') as calendarBody, 
+				strftime(extractions.created_at, '%Y-%m-%d') AS ScrapeDate,
+				extractions.property_id, 
+			FROM 
+				consultancy_d.extractions 
+			LEFT JOIN 
+				consultancy_d.properties ON properties.id = extractions.property_id 
+			WHERE
+				type == 'calendar' AND
+				properties.seed_id = {region_id}		
+			""")
+
 
 

etl/src/data/etl_region_capacities.py

@@ -0,0 +1,57 @@
+from etl.src import data
+import polars as pl
+from io import StringIO
+import numpy as np
+
+
+d = data.load()
+
+def region_capacities(id: int):
+    # Get Data
+    df = d.capacity_of_region(id).pl()
+    # turn PropertyIDs to ints for sorting
+    df = df.cast({"property_id": int})
+
+    # Get uniques for dates and propIDs and sort them
+    listOfDates = df.get_column("ScrapeDate").unique().sort()
+    listOfPropertyIDs = df.get_column("property_id").unique().sort()
+
+    # Create DFs from lists to merge later
+    datesDF = pl.DataFrame(listOfDates).with_row_index("date_index")
+    propIdDF = pl.DataFrame(listOfPropertyIDs).with_row_index("prop_index")
+
+    # Merge Dataframe to generate indices
+    df = df.join(datesDF, on='ScrapeDate')
+    df = df.join(propIdDF, on='property_id')
+
+    # Drop now useless columns ScrapeDate and property_id
+    df = df[['calendarBody', 'date_index', 'prop_index']]
+
+    # Calculate grid values
+    gridData = []
+    for row in df.rows(named=True):
+        # Return 0 for sum if calendar is null
+        if row['calendarBody']:
+            calDF = pl.read_json(StringIO(row['calendarBody']))
+            sum_hor = calDF.sum_horizontal()[0]
+        else:
+            sum_hor = 0
+        gridData.append([row['prop_index'], row['date_index'], sum_hor])
+    gridData = np.array(gridData)
+
+    # get all values to calculate Max
+    allValues = gridData[:, 2]
+    maxValue = np.max(allValues)
+    gridData[:, 2] = (gridData[:, 2]*100)/maxValue
+
+    # Return back to list
+    gridData = gridData.tolist()
+
+    # Cast listOfDates to datetime
+    listOfDates = listOfDates.cast(pl.Date).to_list()
+    listOfPropertyIDs = listOfPropertyIDs.to_list()
+
+    # Create JSON
+    outDict = {'scrapeDates': listOfDates, 'property_ids': listOfPropertyIDs, 'values': gridData}
+
+    return outDict

etl/src/mauro/data_quality.py

@@ -31,8 +31,6 @@ dfNew = pl.from_dicts(data)
 dfNew.write_csv('results/data_quality.csv')
 print(dfNew)
 
-
-
 '''
 dfNew = pl.read_csv('results/data_quality.csv')
 dfNew = dfNew.with_columns(pl.col("created_at").map_elements(lambda x: datetime.strptime(x, "%Y-%m-%d").date()))