monthly aggregation of historic weather data

compute_et0_adjusted.py

@@ -4,7 +4,7 @@ import pandas as pd
 import numpy as np
 
 
-def compute_et0_future(
+def compute_et0(
     df: pd.DataFrame,
     latitude: float,
     longitude: float
@@ -35,11 +35,7 @@ def compute_et0_future(
     RHmin = df.relative_humidity_min
     RHmax = df.relative_humidity_max
     WS = df.wind_speed
-    month = df.month
-    year = df.year
-    first_day = datetime.date(year, month, 1)
-    day_of_year = first_day.timetuple().tm_yday
-    JJulien = day_of_year
+    JJulien = df.day_of_year
 
     l = agro_indicators.et0(
             irradiance,
@@ -65,12 +61,10 @@ if __name__ == "__main__":
     data_test["relative_humidity_min"] = [50, 60, 70]
     data_test["relative_humidity_max"] = [50, 60, 70]
     data_test["wind_speed"] = [5, 10, 15]
-    data_test["month"] = [1, 2, 3]
-    data_test["year"] = [2020, 2020, 2020]
+    data_test["day_of_year"] = [1, 32, 60]
 
     latitude = 40.7128
     longitude = 74.0060
     
-    for i in range(len(data_test)):
-        et0 = compute_et0_future(data_test.iloc[i], latitude, longitude)
-        print(et0)
+    et0 = compute_et0(data_test, latitude, longitude)
+    print(et0)

data_pipelines/historical_weather_data.py

@@ -4,7 +4,7 @@ import requests_cache
 import pandas as pd
 from retry_requests import retry
 
-from compute_et0_adjusted import compute_et0_future
+from compute_et0_adjusted import compute_et0
 
 
 def download_historical_weather_data(
@@ -81,8 +81,7 @@ def aggregate_hourly_weather_data(
 	})
 
 	monthly_data = pd.DataFrame.from_dict({
-		"month": resampled_data.index.month,
-		"year": resampled_data.index.year,
+		"day_of_year": resampled_data.index.dayofyear,
 		"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")],
@@ -102,6 +101,5 @@ if __name__ == '__main__':
 	df = download_historical_weather_data(latitude, longitude, start_year, end_year)
 	monthly_df = aggregate_hourly_weather_data(df)
 
-	for i in range(len(monthly_df)):
-		et0 = compute_et0_future(monthly_df.iloc[i], latitude, longitude)
-		print(et0)
+	et0 = compute_et0(monthly_df, latitude, longitude)
+	print(et0)