pipeline for historical weather data

data_pipelines/historical_weather_data.py

@@ -0,0 +1,70 @@
+import openmeteo_requests
+
+import requests_cache
+import pandas as pd
+from retry_requests import retry
+
+
+def download_historical_weather_data(
+		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)
+
+	# Make sure all required weather variables are listed here
+	# The order of variables in hourly or daily is important to assign them correctly below
+	url = "https://archive-api.open-meteo.com/v1/archive"
+	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"],
+		"timezone": "GMT"
+	}
+	responses = openmeteo.weather_api(url, params=params)
+
+	# Process first location. Add a for-loop for multiple locations or weather models
+	response = responses[0]
+	print(f"Coordinates {response.Latitude()}°N {response.Longitude()}°E")
+	print(f"Elevation {response.Elevation()} m asl")
+	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()),
+			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
+	}
+
+	daily_dataframe = pd.DataFrame(data = daily_data)
+
+	return daily_dataframe

requirements.txt

@@ -0,0 +1,17 @@
+mistralai==1.5.0
+gradio==5.15.0
+ipykernel==6.29.5
+fiona==1.10.1
+chardet==5.2.0
+crewai==0.100.0
+crewai-tools==0.33.0
+pydantic==2.10.6
+openmeteo-requests==1.3.0
+requests-cache==1.2.1
+retry-requests==2.0.0
+plotly==6.0.0
+nbformat>=4.2.0
+pandas
+openmeteo_requests
+requests_cache
+retry_requests