Spaces:
Sleeping
Sleeping
import streamlit as st | |
import hopsworks | |
import joblib | |
import pandas as pd | |
import datetime | |
from functions import get_weather_data_weekly, data_encoder, get_aplevel, get_color | |
from PIL import Image | |
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) | |
st.set_page_config(layout="wide") | |
st.title('Air Quality Prediction Project for Vienna! 🌩') | |
vienna_image = Image.open('vienna.jpg') | |
st.image(vienna_image, use_column_width='auto', caption='Vienna') | |
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 predictions for the next 7 days") | |
preds = model.predict(data_encoder(weekly_data)).astype(int) | |
air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous'] | |
poll_level = get_aplevel(preds.T.reshape(-1, 1), air_pollution_level) | |
next_week_datetime = [today + datetime.timedelta(days=d) for d in range(7)] | |
next_week_str = [f"{days.strftime('%A')}, {days.strftime('%Y-%m-%d')}" 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(get_color, subset=(["Air pollution level"], slice(None)))) | |
st.button("Re-run") |