functions.py

from datetime import datetime
import requests
import os
import joblib
import pandas as pd
import numpy as np
import json

from dotenv import load_dotenv
load_dotenv()

def get_weather_json(date, WEATHER_API_KEY):
    return requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/london/{date}?unitGroup=metric&include=days&key={WEATHER_API_KEY}&contentType=json').json()

def get_weather_data(date):
    WEATHER_API_KEY = os.getenv('WEATHER_API_KEY')
    json = get_weather_json(date, WEATHER_API_KEY)
    data = json['days'][0]

    return [
        json['address'].capitalize(),
        data['datetime'],
        data['tempmax'],
        data['tempmin'],
        data['temp'],
        data['feelslikemax'],
        data['feelslikemin'],
        data['feelslike'],
        data['dew'],
        data['humidity'],
        data['precip'],
        data['precipprob'],
        data['precipcover'],
        data['snow'],
        data['snowdepth'],
        data['windgust'],
        data['windspeed'],
        data['winddir'],
        data['pressure'],
        data['cloudcover'],
        data['visibility'],
        data['solarradiation'],
        data['solarenergy'],
        data['uvindex'],
        data['conditions']
    ]


def get_weather_df(data):
    col_names = [
        'city',
        'date',
        'tempmax',
        'tempmin',
        'temp',
        'feelslikemax',
        'feelslikemin',
        'feelslike',
        'dew',
        'humidity',
        'precip',
        'precipprob',
        'precipcover',
        'snow',
        'snowdepth',
        'windgust',
        'windspeed',
        'winddir',
        'pressure',
        'cloudcover',
        'visibility',
        'solarradiation',
        'solarenergy',
        'uvindex',
        'conditions'
    ]

    new_data = pd.DataFrame(
        data,
        columns=col_names
    )
    new_data.date = new_data.date.apply(timestamp_2_time)

    return new_data

def timestamp_2_time(x):
    dt_obj = datetime.strptime(str(x), '%Y-%m-%d')
    dt_obj = dt_obj.timestamp() * 1000
    return int(dt_obj)

def encoder_range(temps):
    boundary_list = np.array([0, 50, 100, 150, 200, 300]) 
    redf = np.logical_not(temps<=boundary_list) 
    hift = np.concatenate((np.roll(redf, -1)[:, :-1], np.full((temps.shape[0], 1), False)), axis = 1)
    cat = np.nonzero(np.not_equal(redf,hift))
    air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
    level = [air_pollution_level[el] for el in cat[1]]
    return level

def get_aplevel(temps:np.ndarray) -> list:
    boundary_list = np.array([0, 50, 100, 150, 200, 300]) # assert temps.shape == [x, 1]
    redf = np.logical_not(temps<=boundary_list) # temps.shape[0] x boundary_list.shape[0] ndarray
    hift = np.concatenate((np.roll(redf, -1)[:, :-1], np.full((temps.shape[0], 1), False)), axis = 1)
    cat = np.nonzero(np.not_equal(redf,hift))

    air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
    level = [air_pollution_level[el] for el in cat[1]]
    return level