File size: 7,209 Bytes
1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 1d3c9ee f4930a4 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 |
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
PAST_WEATHER_DATA_FILE = "past_weather_data.csv"
PAST_POLLUTION_DATA_FILE = "past_pollution_data.csv"
def update_past_weather_data():
last_year_date = date.today() - timedelta(days=365)
if os.path.exists(PAST_WEATHER_DATA_FILE):
df = pd.read_csv(PAST_WEATHER_DATA_FILE)
start_date = pd.to_datetime(df["date"]).max().date().isoformat()
end_date = (last_year_date + timedelta(days=2)).isoformat()
else:
df = pd.DataFrame()
start_date = (last_year_date - timedelta(days=8)).isoformat()
end_date = (last_year_date + timedelta(days=2)).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"
)
CSVText = csv.reader(codecs.iterdecode(ResultBytes, "utf-8"))
data = pd.DataFrame(list(CSVText))
data.columns = data.iloc[0]
data = data[1:]
data = data.rename(columns={"datetime": "date"})
updated_df = pd.concat([df, data], ignore_index=True)
updated_df.drop_duplicates(subset="date", keep="last", inplace=True)
updated_df.to_csv(PAST_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_past_pollution_data():
O3 = []
NO2 = []
particles = ["NO2", "O3"]
stations = ["NL10636", "NL10639", "NL10643"]
all_dataframes = []
last_year_date = date.today() - timedelta(days=365)
if os.path.exists(PAST_POLLUTION_DATA_FILE):
existing_data = pd.read_csv(PAST_POLLUTION_DATA_FILE)
last_date = pd.to_datetime(existing_data["date"]).max()
if last_date >= pd.to_datetime(last_year_date):
print("Data is already up to date.")
return
else:
start_date = last_date.date()
end_date = last_year_date + timedelta(days=3)
else:
existing_data = pd.DataFrame()
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)
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:
values.append(float(cleaned_value[0]))
if values:
avg = sum(values) / len(values)
if particle == "NO2":
NO2.append(avg)
else:
O3.append(avg)
new_data = pd.DataFrame(
{
"date": date_list,
"NO2": NO2,
"O3": O3,
}
)
updated_data = pd.concat([existing_data, new_data], ignore_index=True)
updated_data.drop_duplicates(subset="date", keep="last", inplace=True)
updated_data.to_csv(PAST_POLLUTION_DATA_FILE, index=False)
return NO2, O3
def get_past_combined_data():
update_past_weather_data()
update_past_pollution_data()
combined_df = pd.read_csv(PAST_WEATHER_DATA_FILE)
pollution_data = pd.read_csv(PAST_POLLUTION_DATA_FILE)
combined_df["NO2"] = pollution_data["NO2"]
combined_df["O3"] = pollution_data["O3"]
# 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"].astype(float)
combined_df["mean_temp"] = combined_df["mean_temp"].astype(float)
combined_df["minimum_visibility"] = combined_df["minimum_visibility"].astype(float)
combined_df["percipitation"] = combined_df["percipitation"].astype(float)
combined_df["pressure"] = combined_df["pressure"].astype(float).round()
combined_df["humidity"] = combined_df["humidity"].astype(float).round()
combined_df["global_radiation"] = combined_df["global_radiation"].astype(float)
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(float).round().astype(int)
)
combined_df["mean_temp"] = (
combined_df["mean_temp"].astype(float).round().astype(int)
)
combined_df["minimum_visibility"] = (
combined_df["minimum_visibility"].astype(float).round().astype(int)
)
combined_df["percipitation"] = (
combined_df["percipitation"].astype(float).round().astype(int)
)
combined_df["pressure"] = combined_df["pressure"].astype(float).round().astype(int)
combined_df["humidity"] = combined_df["humidity"].astype(float).round().astype(int)
combined_df["global_radiation"] = (
combined_df["global_radiation"].astype(float).round().astype(int)
)
return combined_df
|