File size: 7,091 Bytes
1d3c9ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3dd6a8c
 
 
 
 
 
 
 
 
 
 
 
1d3c9ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3dd6a8c
 
 
 
1d3c9ee
 
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
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

WEATHER_DATA_FILE = "weather_data.csv"
POLLUTION_DATA_FILE = "pollution_data.csv"


def update_weather_data():
    today = date.today().isoformat()

    if os.path.exists(WEATHER_DATA_FILE):
        df = pd.read_csv(WEATHER_DATA_FILE)
        last_date = pd.to_datetime(df["date"]).max()
        start_date = (last_date + timedelta(1)).isoformat()
    else:
        df = pd.DataFrame()
        start_date = (date.today() - timedelta(7)).isoformat()

    try:
        ResultBytes = urllib.request.urlopen(
            f"https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Utrecht/{start_date}/{today}?unitGroup=metric&elements=datetime%2Cwindspeed%2Ctemp%2Csolarradiation%2Cprecip%2Cpressure%2Cvisibility%2Chumidity&include=days&key=7Y6AY56M6RWVNHQ3SAVHNJWFS&maxStations=1&contentType=csv"
        )
        CSVText = csv.reader(codecs.iterdecode(ResultBytes, "utf-8"))

        new_data = pd.DataFrame(list(CSVText))
        new_data.columns = new_data.iloc[0]
        new_data = new_data[1:]
        new_data = new_data.rename(columns={"datetime": "date"})

        updated_df = pd.concat([df, new_data], ignore_index=True)
        updated_df.drop_duplicates(subset="date", keep="last", inplace=True)
        updated_df.to_csv(WEATHER_DATA_FILE, index=False)

    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 update_pollution_data():
    O3 = []
    NO2 = []
    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(8)).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)
            values = []
            for row in combined_data:
                cleaned_value = re.findall(r"[-+]?\d*\.\d+|\d+", row)
                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 particle == "NO2":
                    NO2.append(avg)
                else:
                    O3.append(avg)
        today = (date.today() - timedelta(days_today)).isoformat() + "T09:00:00Z"
        yesterday = (
            date.today() - timedelta(days_yesterday)
        ).isoformat() + "T09:00:00Z"

    avg_combined_data = pd.DataFrame(
        {
            "date": pd.date_range(end=date.today(), periods=len(NO2)),
            "NO2": NO2,
            "O3": O3,
        }
    )

    avg_combined_data = reverse_pollution(NO2, O3, avg_combined_data)

    if os.path.exists(POLLUTION_DATA_FILE):
        existing_data = pd.read_csv(POLLUTION_DATA_FILE)
        last_date = pd.to_datetime(existing_data["date"]).max()
        new_data = avg_combined_data[avg_combined_data["date"] > last_date]
        updated_data = pd.concat([existing_data, new_data], ignore_index=True)
        updated_data.drop_duplicates(subset="date", keep="last", inplace=True)
    else:
        updated_data = avg_combined_data

    updated_data.to_csv(POLLUTION_DATA_FILE, index=False)


def reverse_pollution(NO2, O3, data):
    df = data
    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
    return df


def get_combined_data():
    update_weather_data()
    update_pollution_data()

    weather_df = pd.read_csv(WEATHER_DATA_FILE)

    weather_df.insert(1, "NO2", None)
    weather_df.insert(2, "O3", None)
    weather_df.insert(10, "weekday", None)
    columns = list(weather_df.columns)
    columns.insert(3, columns.pop(6))
    weather_df = weather_df[columns]
    columns.insert(5, columns.pop(9))
    weather_df = weather_df[columns]
    columns.insert(9, columns.pop(6))
    weather_df = weather_df[columns]
    
    combined_df = weather_df

    # Apply scaling and renaming similar to the scale function from previous code
    combined_df = combined_df.rename(
        columns={
            "date": "date",
            "windspeed": "wind_speed",
            "temp": "mean_temp",
            "solarradiation": "global_radiation",
            "precip": "percipitation",
            "sealevelpressure": "pressure",
            "visibility": "minimum_visibility",
        }
    )

    combined_df["date"] = pd.to_datetime(combined_df["date"])
    combined_df["weekday"] = combined_df["date"].dt.day_name()

    combined_df["wind_speed"] = (combined_df["wind_speed"] / 3.6) * 10
    combined_df["mean_temp"] = combined_df["mean_temp"] * 10
    combined_df["minimum_visibility"] = combined_df["minimum_visibility"] * 10
    combined_df["percipitation"] = combined_df["percipitation"] * 10
    combined_df["pressure"] = combined_df["pressure"] * 10

    combined_df["wind_speed"] = combined_df["wind_speed"].astype(int)
    combined_df["mean_temp"] = combined_df["mean_temp"].astype(int)
    combined_df["minimum_visibility"] = combined_df["minimum_visibility"].astype(int)
    combined_df["percipitation"] = combined_df["percipitation"].astype(int)
    combined_df["pressure"] = combined_df["pressure"].astype(int)
    combined_df["humidity"] = combined_df["humidity"].astype(int)
    combined_df["global_radiation"] = combined_df["global_radiation"].astype(int)
    
    pollution_df = pd.read_csv(POLLUTION_DATA_FILE)
    combined_df["NO2"] = pollution_df["NO2"]
    combined_df["O3"] = pollution_df["O3"]

    return combined_df