monthly aggregation of historic weather data

data_pipelines/historical_weather_data.py

@@ -4,17 +4,19 @@ import requests_cache
 import pandas as pd
 from retry_requests import retry
 
+from compute_et0_adjusted import compute_et0_future
+
 
 def download_historical_weather_data(
-		latitude: float,
-		longitude: float,
-		start_year: int,
-		end_year: int,
+        latitude: float,
+        longitude: float,
+        start_year: int,
+        end_year: int,
 ) -> pd.DataFrame:
 	# Setup the Open-Meteo API client with cache and retry on error
-	cache_session = requests_cache.CachedSession('.cache', expire_after = -1)
-	retry_session = retry(cache_session, retries = 5, backoff_factor = 0.2)
-	openmeteo = openmeteo_requests.Client(session = retry_session)
+	cache_session = requests_cache.CachedSession('.cache', expire_after=-1)
+	retry_session = retry(cache_session, retries=5, backoff_factor=0.2)
+	openmeteo = openmeteo_requests.Client(session=retry_session)
 
 	# Make sure all required weather variables are listed here
 	# The order of variables in hourly or daily is important to assign them correctly below
@@ -22,12 +24,11 @@ def download_historical_weather_data(
 	params = {
 		"latitude": latitude,
 		"longitude": longitude,
-		"start_date": f"{start_year}-01-01",
-		"end_date": f"{end_year}-12-31",
-		"daily": ["temperature_2m_max", "temperature_2m_min", "temperature_2m_mean",
-				  "precipitation_sum", "precipitation_hours",
-				  "shortwave_radiation_sum",
-				  "et0_fao_evapotranspiration"],
+		"start_date": f"{start_year}-02-08",
+		"end_date": f"{end_year}-02-22",
+		"hourly": ["temperature_2m", "relative_humidity_2m",
+				   "precipitation", "et0_fao_evapotranspiration",
+				   "wind_speed_10m", "shortwave_radiation"],
 		"timezone": "GMT"
 	}
 	responses = openmeteo.weather_api(url, params=params)
@@ -39,32 +40,68 @@ def download_historical_weather_data(
 	print(f"Timezone {response.Timezone()} {response.TimezoneAbbreviation()}")
 	print(f"Timezone difference to GMT+0 {response.UtcOffsetSeconds()} s")
 
-	# Process daily data. The order of variables needs to be the same as requested.
-	daily = response.Daily()
-	daily_temperature_2m_max = daily.Variables(0).ValuesAsNumpy()
-	daily_temperature_2m_min = daily.Variables(1).ValuesAsNumpy()
-	daily_temperature_2m_mean = daily.Variables(2).ValuesAsNumpy()
-	daily_precipitation_sum = daily.Variables(3).ValuesAsNumpy()
-	daily_precipitation_hours = daily.Variables(4).ValuesAsNumpy()
-	daily_shortwave_radiation_sum = daily.Variables(5).ValuesAsNumpy()
-	daily_et0_fao_evapotranspiration = daily.Variables(6).ValuesAsNumpy()
-
-	daily_data = {
-		"date": pd.date_range(
-			start=pd.to_datetime(daily.Time(), unit="s", utc=True),
-			end=pd.to_datetime(daily.TimeEnd(), unit="s", utc=True),
-			freq=pd.Timedelta(seconds=daily.Interval()),
+	# Process hourly data. The order of variables needs to be the same as requested.
+	hourly = response.Hourly()
+	hourly_temperature_2m = hourly.Variables(0).ValuesAsNumpy()
+	hourly_relative_humidity_2m = hourly.Variables(1).ValuesAsNumpy()
+	hourly_precipitation = hourly.Variables(2).ValuesAsNumpy()
+	hourly_et0_fao_evapotranspiration = hourly.Variables(3).ValuesAsNumpy()
+	hourly_wind_speed_10m = hourly.Variables(4).ValuesAsNumpy()
+	hourly_shortwave_radiation = hourly.Variables(5).ValuesAsNumpy()
+
+	hourly_data = {
+		"temperature_2m": hourly_temperature_2m,
+		"relative_humidity_2m": hourly_relative_humidity_2m,
+		"precipitation": hourly_precipitation,
+		"et0_fao_evapotranspiration": hourly_et0_fao_evapotranspiration,
+		"wind_speed_10m": hourly_wind_speed_10m,
+		"shortwave_radiation": hourly_shortwave_radiation,
+	}
+	hourly_dataframe = pd.DataFrame(
+		index=pd.date_range(
+			start=pd.to_datetime(hourly.Time(), unit="s", utc=True),
+			end=pd.to_datetime(hourly.TimeEnd(), unit="s", utc=True),
+			freq=pd.Timedelta(seconds=hourly.Interval()),
 			inclusive="left"
 		),
-		"temperature_2m_max": daily_temperature_2m_max,
-		"temperature_2m_min": daily_temperature_2m_min,
-		"temperature_2m_mean": daily_temperature_2m_mean,
-		"precipitation_sum": daily_precipitation_sum,
-		"precipitation_hours": daily_precipitation_hours,
-		"shortwave_radiation_sum": daily_shortwave_radiation_sum,
-		"et0_fao_evapotranspiration": daily_et0_fao_evapotranspiration
-	}
+		data=hourly_data,
+	)
+
+	return hourly_dataframe
+
+
+def aggregate_hourly_weather_data(
+		hourly_data: pd.DataFrame,
+) -> pd.DataFrame:
+	resampled_data = hourly_data.resample("1ME").agg({
+		"temperature_2m": ["min", "max"],
+		"relative_humidity_2m": ["min", "max"],
+		"wind_speed_10m": "mean",
+		"shortwave_radiation": "mean",
+	})
+
+	monthly_data = pd.DataFrame.from_dict({
+		"month": resampled_data.index.month,
+		"year": resampled_data.index.year,
+		"air_temperature_min": resampled_data[("temperature_2m", "min")],
+		"air_temperature_max": resampled_data[("temperature_2m", "max")],
+		"relative_humidity_min": resampled_data[("relative_humidity_2m", "min")],
+		"relative_humidity_max": resampled_data[("relative_humidity_2m", "max")],
+		"wind_speed": resampled_data[("wind_speed_10m", "mean")],
+		"irradiance": resampled_data[("shortwave_radiation", "mean")],
+	})
+
+	return monthly_data
+
 
-	daily_dataframe = pd.DataFrame(data = daily_data)
+if __name__ == '__main__':
+	latitude = 47
+	longitude = 3
+	start_year = 2020
+	end_year = 2021
+	df = download_historical_weather_data(latitude, longitude, start_year, end_year)
+	monthly_df = aggregate_hourly_weather_data(df)
 
-	return daily_dataframe
+	for i in range(len(monthly_df)):
+		et0 = compute_et0_future(monthly_df.iloc[i], latitude, longitude)
+		print(et0)

requirements.txt

@@ -16,4 +16,5 @@ openmeteo_requests
 requests_cache
 retry_requests
 fuzzywuzzy
-plotly
+plotly
+pvlib