summary_test.py

import os
import pandas as pd
import pandas as pd
import numpy as np
from forecast import get_forecast_datasets, get_forecast_data
from data_pipelines.historical_weather_data import download_historical_weather_data, aggregate_hourly_weather_data

from utils.summary import get_meterological_summary, get_agricultural_yield_comparison


def get_meterological_past_data():
    download_historical_weather_data(latitude, longitude, start_year, end_year)

def process_all_data_for_meterological_summary(scenario: str, lat: float = 47.0, lon:float = 5.0):
   
    start_year, end_year = 2010, 2025
    historical_df = aggregate_hourly_weather_data(download_historical_weather_data(latitude=lat, longitude=lon, start_year=start_year, end_year= end_year))
    forecast_df = get_forecast_data(scenario=scenario, longitude=lon, latitude=lat, shading_coef=0)

    forecast_df["time"] = pd.to_datetime(forecast_df["time"])
    forecast_df['year'] = forecast_df["time"].dt.year
    new_forecast_df = forecast_df.groupby(by="year", as_index=False)[["Near Surface Air Temperature (°C)", "Surface Downwelling Shortwave Radiation (W/m²)", "Precipitation (kg m-2 s-1)"]].mean().reset_index()
    # new_forecast_df = new_forecast_df[new_forecast_df["year"] > 2025]

    historical_df = historical_df.reset_index().rename(columns={"index": "time"}).sort_values(by="time")
    historical_df["year"] = historical_df["time"].dt.year
    historical_df["precipitation"] = historical_df["precipitation"] / 3600  # to transform the data to kg m2 per s

    new_historical_df = historical_df.groupby(by="year", as_index=False)[["air_temperature_mean", "irradiance", "precipitation"]].mean().reset_index()
    new_historical_df = new_historical_df[new_historical_df["year"] < 2024]

    temperature_df = pd.concat([new_historical_df[["year", "air_temperature_mean"]].rename(columns={"air_temperature_mean": "Near Surface Air Temperature (°C)"}), 
                                new_forecast_df[["year", "Near Surface Air Temperature (°C)"]]], axis=0)

    irradiance_df = pd.concat([new_historical_df[["year", "irradiance"]].rename(columns={"irradiance": "Surface Downwelling Shortwave Radiation (W/m²)"}), 
                                new_forecast_df[["year", "Surface Downwelling Shortwave Radiation (W/m²)"]]], axis=0)
    
    rain_df = pd.concat([new_historical_df[["year", "precipitation"]].rename(columns={"precipitation": "Precipitation (kg m-2 s-1)"}), 
                                new_forecast_df[["year", "Precipitation (kg m-2 s-1)"]]], axis=0)

    return temperature_df, rain_df, irradiance_df


if __name__ == "__main__":

    scenario = "pessimist"
    lat, lon = 47.0, 5.0
    temperature_df, rain_df, irradiance_df = process_all_data_for_meterological_summary(scenario, lat, lon)
    
    meterological_summary = get_meterological_summary(scenario=scenario, 
                                                      temperature_df=temperature_df,
                                                      irradiance_df=irradiance_df,
                                                      rain_df=rain_df)
    print(meterological_summary)

    # from utils.soil_utils import find_nearest_point
    # city = "Bourgogne Franche Comté"
    # closest_soil_features = find_nearest_point(city)
    # print(closest_soil_features)

    # Example usage
    # import pandas as pd
    # import numpy as np

    # from utils.soil_utils import find_nearest_point

    # city = "Bourgogne Franche Comté"
    # closest_soil_features = find_nearest_point(city)
    # print(closest_soil_features)

    # # Définir la période de 4 ans dans le passé + 15 ans dans le futur (19 ans)
    # start_date = "2010-01"
    # end_date = "2029-12"

    # # Générer une série de dates mensuelles
    # dates = pd.date_range(start=start_date, end=end_date, freq='M')
    # Générer une série de dates mensuelles
    # dates = pd.date_range(start=start_date, end=end_date, freq="M")

    # # Générer des données fictives de rendement (en tonnes par hectare)
    # np.random.seed(42)  # Pour reproductibilité

    # # Tendance générale du rendement sans ombrage (augmentation progressive)
    # trend = np.linspace(2.5, 3.2, len(dates))  # Augmente légèrement sur les années

    # # Ajout de variations saisonnières et aléatoires
    # seasonality = 0.3 * np.sin(np.linspace(0, 12 * np.pi, len(dates)))  # Effet saisonnier
    # random_variation = np.random.normal(0, 0.1, len(dates))  # Bruit aléatoire

    # # Calcul du rendement sans ombrage
    # yield_no_shade = trend + seasonality + random_variation

    # # Appliquer un effet d'ombrage (réduction de 10-20% du rendement)
    # shade_factor = np.random.uniform(0.1, 0.2, len(dates))  # Entre 10% et 20% de réduction
    # yield_with_shade = yield_no_shade * (1 - shade_factor)

    # # Créer le DataFrame
    # df = pd.DataFrame({
    #     "date": dates,
    #     "yield_no_shade": yield_no_shade,
    #     "yield_with_shade": yield_with_shade
    # })
    # water_deficit_data = pd.DataFrame()
    # climate_data = pd.DataFrame()
    
    # print(get_agricultural_yield_comparison(culture="orge", 
    #                                         region="bourgogne franche comté",
    #                                         water_df=water_deficit_data, 
    #                                         climate_df=climate_data,
    #                                         soil_df=closest_soil_features, 
    #                                         agri_yield_df=df))