Spaces:
Runtime error
Runtime error
| from typing import Type | |
| from crewai.tools import BaseTool | |
| from pydantic import BaseModel, Field | |
| import openmeteo_requests | |
| import requests_cache | |
| from retry_requests import retry | |
| import pandas as pd | |
| class MyCustomToolInput(BaseModel): | |
| """Input schema for MyCustomTool.""" | |
| argument: str = Field(..., description="Description of the argument.") | |
| class MyCustomTool(BaseTool): | |
| name: str = "Name of my tool" | |
| description: str = ( | |
| "Clear description for what this tool is useful for, your agent will need this information to use it." | |
| ) | |
| args_schema: Type[BaseModel] = MyCustomToolInput | |
| def _run(self, argument: str) -> str: | |
| # Implementation goes here | |
| return "this is an example of a tool output, ignore it and move along." | |
| class rgp_cultures_regions(BaseTool): | |
| name: str = "rgp_cultures_regions" | |
| description: str = "Extraite les cultures les plus populaires en terme de surface cultuvé en hectare pour une région donnée en france métropolitaine" | |
| def _run(self, region: str) -> pd.DataFrame: | |
| """ | |
| Extract the most popular cultures in terms of cultivated area in hectares for a given region in metropolitan France | |
| schema of the DataFrame: | |
| CODE_CULTU : code of the culture | |
| REGION: name of the region | |
| SURF_PARC: cultivated area in hectares | |
| CODE_CULTURE: code of the culture | |
| LIBELLE_CULTURE: name of the culture | |
| LIBELLE_GROUPE_CULTURE: name of the culture group | |
| ACTIF: oui or non | |
| Args: | |
| region (str): name of region in metropolitan France | |
| Returns: | |
| pd.DataFrame: DataFrame containing the most popular cultures in terms of cultivated area in hectares for a given region in metropolitan France | |
| """ | |
| # load the data | |
| df_rpg = pd.read_csv("data/data_rpg/data_prepared_rpg.csv") | |
| # filter the data (lower case) | |
| df_rpg["REGION"] = df_rpg["REGION"].str.lower() | |
| region = region.lower() | |
| df_rpg = df_rpg[df_rpg["REGION"] == region] | |
| # kepp only the top 10 more cultivae cultures | |
| df_rpg = df_rpg.sort_values(by="SURF_PARC", ascending=False).head(10) | |
| return df_rpg | |
| class MeteoTool(BaseTool): | |
| name: str = "meteo_tool" | |
| description: str = "Extraite les données météorologiques des dix dernières années pour la région identifiée en utilisant des localisations GPS du centre de la région" | |
| def _run(self, latitude: float, longitude: float) -> pd.DataFrame: | |
| """ | |
| Extract the meteorological data for the last ten years for the identified region using GPS locations of the center of the region | |
| schema of the DataFrame: | |
| year_month : month and year | |
| month : month | |
| year : year | |
| temperature_2m_max : temperature in celsius at 2m height | |
| temperature_2m_min : temperature in celsius at 2m height | |
| precipitation_sum : precipitation in mm | |
| sunchine_duration : sunshine duration in hours | |
| Args: | |
| latitude (float): latitude of the center of the region | |
| longitude (float): longitude of the center of the region | |
| Returns: | |
| pd.DataFrame: DataFrame containing the meteorological data for the identified region using GPS locations of the center of the region | |
| """ | |
| cache_session = requests_cache.CachedSession('.cache', expire_after = 300) | |
| retry_session = retry(cache_session, retries = 5, backoff_factor = 0.2) | |
| openmeteo = openmeteo_requests.Client(session = retry_session) | |
| url = "https://archive-api.open-meteo.com/v1/archive" | |
| params = { | |
| "latitude": latitude, | |
| "longitude": longitude, | |
| "start_date": "2015-01-01", | |
| "end_date": "2024-12-31", | |
| "daily": ["temperature_2m_max", "temperature_2m_min", "sunshine_duration", "precipitation_sum"] } | |
| 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_sunshine_duration = daily.Variables(2).ValuesAsNumpy() | |
| daily_precipitation_sum = daily.Variables(3).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" | |
| )} | |
| daily_data["temperature_2m_max"] = daily_temperature_2m_max | |
| daily_data["temperature_2m_min"] = daily_temperature_2m_min | |
| daily_data["sunshine_duration"] = daily_sunshine_duration | |
| daily_data["precipitation_sum"] = daily_precipitation_sum | |
| daily_dataframe = pd.DataFrame(data = daily_data) | |
| daily_dataframe["sunshine_duration"] = daily_dataframe["sunshine_duration"] / 3600 | |
| # aggregate data to monthly | |
| daily_dataframe["month"] = daily_dataframe["date"].dt.month | |
| daily_dataframe["year"] = daily_dataframe["date"].dt.year | |
| daily_dataframe["year_month"] = daily_dataframe.apply(lambda x: x["date"].strftime("%Y%m"), axis=1) | |
| monthly_dataframe = daily_dataframe.groupby(["year_month","year","month"]).agg( | |
| temperature_2m_max = ("temperature_2m_max", "mean"), | |
| temperature_2m_min = ("temperature_2m_min", "mean"), | |
| precipitation_sum = ("precipitation_sum", "sum"), | |
| sunchine_duration = ("sunshine_duration", "sum") | |
| ).reset_index() | |
| return monthly_dataframe | |