File size: 8,062 Bytes
386e426 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
import codecs
import csv
import http.client
import os
import re
import sys
import urllib.request
from datetime import date, timedelta
from io import StringIO
import pandas as pd
def pollution_data():
particles = ["NO2", "O3"]
stations = ["NL10636", "NL10639", "NL10643"]
last_year_date = date.today() - timedelta(days=365)
start_date = last_year_date - timedelta(days=7)
end_date = last_year_date + timedelta(days=3)
date_list = [start_date + timedelta(days=x) for x in range((end_date - start_date).days + 1)]
for current_date in date_list:
today = current_date.isoformat() + "T09:00:00Z"
yesterday = (current_date - timedelta(1)).isoformat() + "T09:00:00Z"
for particle in particles:
all_dataframes = [] # Reset for each particle
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)
if all_dataframes:
combined_data = pd.concat(all_dataframes, ignore_index=True)
combined_data.to_csv(f'{particle}_{today}.csv', index=False)
def delete_csv(csvs):
for csv_file in csvs:
if(os.path.exists(csv_file) and os.path.isfile(csv_file)):
os.remove(csv_file)
def clean_values():
particles = ["NO2", "O3"]
csvs = []
NO2 = []
O3 = []
last_year_date = date.today() - timedelta(days=365)
start_date = last_year_date - timedelta(days=7)
end_date = last_year_date + timedelta(days=3)
date_list = [start_date + timedelta(days=x) for x in range((end_date - start_date).days + 1)]
for current_date in date_list:
today = current_date.isoformat() + "T09:00:00Z"
for particle in particles:
name = f'{particle}_{today}.csv'
csvs.append(name)
for csv_file in csvs:
if not os.path.exists(csv_file):
continue # Skip if the file doesn't exist
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)
return df
def scale(data):
df = data
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 = df.sort_values(by='date').reset_index(drop=True)
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']
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)
return df
def insert_pollution(NO2, O3, data):
df = data
df['NO2'] = NO2
df['O3'] = O3
return df
def weather_data():
# Get last year's same day
last_year_date = date.today() - timedelta(days=365)
# Start date is 7 days prior
start_date = (last_year_date - timedelta(days=7)).isoformat()
# End date is 3 days ahead
end_date = (last_year_date + timedelta(days=3)).isoformat()
try:
ResultBytes = urllib.request.urlopen(f"https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Utrecht/{start_date}/{end_date}?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 weather_data():
# Set up dates for last year: 7 days before today last year, and 3 days ahead of this day last year
today_last_year = date.today() - timedelta(365)
start_last_year = today_last_year - timedelta(8)
end_last_year = today_last_year + timedelta(2)
try:
# API call with new date range for last year
ResultBytes = urllib.request.urlopen(f"https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Utrecht/{start_last_year}/{end_last_year}?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_past_data():
weather_data()
pollution_data()
NO2, O3 = clean_values()
df = add_columns()
scaled_df = scale(df)
output_df = insert_pollution(NO2, O3, scaled_df)
os.remove('weather_data.csv')
return output_df |