data_api_calls.py

import http.client
from datetime import date, timedelta
import pandas as pd
from io import StringIO
import os
import re
import csv
import urllib.request
import sys
import codecs

def pollution_data():
    particles = ["NO2", "O3"]
    stations = ["NL10636", "NL10639", "NL10643"]
    all_dataframes = []
    today = date.today().isoformat() + "T09:00:00Z"
    yesterday = (date.today() - timedelta(1)).isoformat() + "T09:00:00Z"
    latest_date = (date.today() - timedelta(7)).isoformat() + "T09:00:00Z"
    days_today = 0
    days_yesterday = 1
    while(today != latest_date):
        days_today += 1
        days_yesterday += 1
        for particle in particles:
            for station in stations:
                conn = http.client.HTTPSConnection("api.luchtmeetnet.nl")
                payload = ''
                headers = {}
                conn.request("GET", f"/open_api/measurements?station_number={station}&formula={particle}&page=1&order_by=timestamp_measured&order_direction=desc&end={today}&start={yesterday}", payload, headers)
                res = conn.getresponse()
                data = res.read()
                decoded_data = data.decode("utf-8")
                df = pd.read_csv(StringIO(decoded_data))
                df = df.filter(like='value')
                all_dataframes.append(df)
            combined_data = pd.concat(all_dataframes, ignore_index=True)
            combined_data.to_csv(f'{particle}_{today}.csv', index=False)
        today = (date.today() - timedelta(days_today)).isoformat() + "T09:00:00Z"
        yesterday = (date.today() - timedelta(days_yesterday)).isoformat() + "T09:00:00Z"

def delete_csv(csvs):
    for csv in csvs:
        if(os.path.exists(csv) and os.path.isfile(csv)): 
            os.remove(csv)

def clean_values():
    particles = ["NO2", "O3"]
    csvs = []
    NO2 = []
    O3 = []
    today = date.today().isoformat() + "T09:00:00Z"
    yesterday = (date.today() - timedelta(1)).isoformat() + "T09:00:00Z"
    latest_date = (date.today() - timedelta(7)).isoformat() + "T09:00:00Z"
    days_today = 0
    while(today != latest_date):
        for particle in particles:
            name = f'{particle}_{today}.csv'
            csvs.append(name)
        days_today += 1
        today = (date.today() - timedelta(days_today)).isoformat() + "T09:00:00Z"
    for csv_file in csvs:
        values = []  # Reset values for each CSV file
        # Open the CSV file and read the values
        with open(csv_file, 'r') as file:
            reader = csv.reader(file)
            for row in reader:
                for value in row:
                    # Use regular expressions to extract numeric part
                    cleaned_value = re.findall(r"[-+]?\d*\.\d+|\d+", value)
                    if cleaned_value:  # If we successfully extract a number
                        values.append(float(cleaned_value[0]))  # Convert the first match to float
        
        # Compute the average if the values list is not empty
        if values:
            avg = sum(values) / len(values)
            if "NO2" in csv_file:
                NO2.append(avg)
            else:
                O3.append(avg)
        
    delete_csv(csvs)
    
    return NO2, O3


def add_columns():
    file_path = 'weather_data.csv'
    df = pd.read_csv(file_path)

    df.insert(1, 'NO2', None)
    df.insert(2, 'O3', None)
    df.insert(10, 'weekday', None)

    df.to_csv('combined_data.csv', index=False) 


def scale():
    file_path = 'combined_data.csv'
    df = pd.read_csv(file_path)
    columns = list(df.columns)


    columns.insert(3, columns.pop(6))

    df = df[columns]

    columns.insert(5, columns.pop(9))

    df = df[columns]

    columns.insert(9, columns.pop(6))

    df = df[columns]

    df = df.rename(columns={
        'datetime':'date',
        'windspeed': 'wind_speed',
        'temp': 'mean_temp',
        'solarradiation':'global_radiation',
        'precip':'percipitation',
        'sealevelpressure':'pressure',
        'visibility':'minimum_visibility'
    })

    df['date'] = pd.to_datetime(df['date'])
    df['weekday'] = df['date'].dt.day_name()


    df['wind_speed'] = (df['wind_speed'] / 3.6) * 10
    df['mean_temp'] = df['mean_temp'] * 10
    df['minimum_visibility'] = df['minimum_visibility'] * 10
    df['percipitation'] = df['percipitation'] * 10
    df['pressure'] = df['pressure'] * 10

    df['wind_speed'] = df['wind_speed'].astype(int)
    df['mean_temp'] = df['mean_temp'].astype(int)
    df['minimum_visibility'] = df['minimum_visibility'].astype(int)
    df['percipitation'] = df['percipitation'].astype(int)
    df['pressure'] = df['pressure'].astype(int)
    df['humidity'] = df['humidity'].astype(int)
    df['global_radiation'] = df['global_radiation'].astype(int)

    df.to_csv('recorded_data.csv', index=False)

def insert_pollution(NO2, O3):
    file_path = 'recorded_data.csv'
    df = pd.read_csv(file_path)
    start_index = 0
    while NO2:
        df.loc[start_index, 'NO2'] = NO2.pop()
        start_index += 1
    start_index = 0
    while O3:
        df.loc[start_index, 'O3'] = O3.pop()
        start_index += 1
        df.to_csv('dataset.csv', index=False)

def weather_data():
  today = date.today().isoformat()
  seven_days = (date.today() - timedelta(6)).isoformat()
  try: 
    ResultBytes = urllib.request.urlopen(f"https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Utrecht/{seven_days}/{today}?unitGroup=metric&elements=datetime%2Cwindspeed%2Ctemp%2Csolarradiation%2Cprecip%2Cpressure%2Cvisibility%2Chumidity&include=days&key=7Y6AY56M6RWVNHQ3SAVHNJWFS&maxStations=1&contentType=csv")
    
    # Parse the results as CSV
    CSVText = csv.reader(codecs.iterdecode(ResultBytes, 'utf-8'))
    # Saving the CSV content to a file
    current_dir = os.path.dirname(os.path.realpath(__file__))
    file_path = os.path.join(current_dir, 'weather_data.csv')
    with open(file_path, 'w', newline='', encoding='utf-8') as csvfile:
          csv_writer = csv.writer(csvfile)
          csv_writer.writerows(CSVText)

  except urllib.error.HTTPError  as e:
    ErrorInfo= e.read().decode() 
    print('Error code: ', e.code, ErrorInfo)
    sys.exit()
  except  urllib.error.URLError as e:
    ErrorInfo= e.read().decode() 
    print('Error code: ', e.code,ErrorInfo)
    sys.exit()


def get_data():
    weather_data()
    pollution_data()
    NO2, O3 = clean_values()
    add_columns()
    scale()
    insert_pollution(NO2, O3)
    os.remove('combined_data.csv')
    os.remove('weather_data.csv')