app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
import joblib

# App Title
st.title("Utrecht Pollution Prediction")

# Load the trained model
@st.cache(allow_output_mutation=True)
def load_model():
    try:
        # Try loading a pre-trained model
        model = joblib.load("path_to_your_model/linear_regression_model.pkl")
    except:
        # If the model is not available, train a simple Linear Regression model as a fallback
        st.write("No pre-trained model found. Training a new Linear Regression model...")
        
        # Fallback - Generate some random training data for demonstration purposes
        # In reality, replace this with your actual data
        np.random.seed(0)
        X_train = np.random.rand(100, 3)  # 100 samples, 3 features
        y_train = 3*X_train[:, 0] + 2*X_train[:, 1] + X_train[:, 2]  # Example: linear relationship
        
        # Train a linear regression model
        model = LinearRegression()
        model.fit(X_train, y_train)
        
        # Optionally, save the trained model to use later
        joblib.dump(model, "linear_regression_model.pkl")

    return model

model = load_model()

# Explain the app
st.write("""
### Predict Pollution Levels in Utrecht
This app allows you to input environmental features to predict pollution levels using a simple Linear Regression model.
""")

# Input features needed for your model
def get_user_input():
    feature_1 = st.number_input('Temperature (°C)', min_value=-10.0, max_value=40.0, value=20.0)
    feature_2 = st.number_input('Wind Speed (km/h)', min_value=0.0, max_value=100.0, value=10.0)
    feature_3 = st.number_input('Humidity (%)', min_value=0.0, max_value=100.0, value=50.0)
    
    # Create a DataFrame with user inputs
    input_data = {'Temperature': feature_1,
                  'Wind Speed': feature_2,
                  'Humidity': feature_3}
    
    features = pd.DataFrame([input_data])
    return features

# Get user input
input_df = get_user_input()

# Display user input
st.subheader('User Input:')
st.write(input_df)

# Make predictions using the linear regression model
prediction = model.predict(input_df)

# Display the prediction
st.subheader('Prediction:')
st.write(f'Predicted Pollution Level: {prediction[0]:.2f}')