File size: 2,189 Bytes
1ae03dd
 
 
 
 
a6e15b1
1ae03dd
60999f9
1ae03dd
a6e15b1
60999f9
 
a6e15b1
 
 
 
1ae03dd
a6e15b1
 
 
1ae03dd
 
 
 
 
 
a6e15b1
 
1ae03dd
 
 
 
a6e15b1
1ae03dd
a6e15b1
1ae03dd
a6e15b1
1ae03dd
 
 
 
 
a6e15b1
 
1ae03dd
a6e15b1
60999f9
1ae03dd
a6e15b1
1ae03dd
 
a6e15b1
 
 
1ae03dd
a6e15b1
1ae03dd
a6e15b1
 
60999f9
1ae03dd
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
import streamlit as st
import hopsworks
import joblib
import pandas as pd
from datetime import timedelta, datetime
from functions import get_weather_data_weekly, data_encoder, get_aplevel


def fancy_header(text, font_size=24):
    res = f'<p style="color:#ff5f27; font-size: {font_size}px;text-align:center">{text}</p>'
    st.markdown(res, unsafe_allow_html=True)

# TODO: set the screen to widehardo
st.title('Air Quality Prediction Project 🌩')
st.image("bienna.jpg", use_column_width='auto')
st.write(36 * "-")

st.markdown("# This is a final project in the course ID2223 Scalable Machine Learning and Deep Learning :computer:")
st.markdown("My task was to predict the Air Quality Index (AQI) for one city (I choose Vienna) based on different weather data (pressure, snow-and cloud-coverage, temperature, etc.).")
st.markdown("For the full list of weather data, please click [here][https://visualcrossing.com/resources/documentation/weather-api/timeline-weather-api]")
fancy_header('\n Connecting to Hopsworks Feature Store...')

project = hopsworks.login()

st.write("Successfully connected!✔️")

st.write(36 * "-")
fancy_header('\n Collecting the weather data from Vienna...')

today = datetime.date.today()
city = "vienna"
weekly_data = get_weather_data_weekly(city, today)
st.write("Successfully collected!✔️")

st.write(36 * "-")

fancy_header("Loading the fitted XGBoost model...")
mr = project.get_model_registry()
model = mr.get_best_model("aqi_model", "rmse", "min")
model_dir = model.download()
model = joblib.load(model_dir + "/aqi_model.pkl")

st.write("Succesfully loaded!✔️")
st.sidebar.write("-" * 36)

fancy_header("Making AQI pedictions for the next week..")

preds = model.predict(data_encoder(weekly_data)).astype(int)

poll_level = get_aplevel(preds.T.reshape(-1, 1))

next_week_datetime = [today + timedelta(days=d) for d in range(7)]

next_week_str = [f"{days.strftime('%Y-%m-%d')}, {days.strftime('%A')}" for days in next_week_datetime]

df = pd.DataFrame(data=[preds, poll_level], index=["AQI", "Air pollution level"], columns=next_week_str)

st.write("Here they are!")
st.dataframe(df.style.apply) # ref to function color_aq

st.button("Re-run")