src/streamlit_app.py

import streamlit as st
import pandas as pd
import joblib
import numpy as np

# Load Model
@st.cache_resource
def load_artifacts():
    try:
        return joblib.load('src/backpack_model.joblib')
    except FileNotFoundError:
        st.error("Model file 'backpack_model.joblib' not found. Please upload it to the Files section.")
        return None

artifacts = load_artifacts()

if artifacts:
    model = artifacts['model']
    encoders = artifacts['encoders']
    size_mapping = artifacts['size_mapping']
    medians = artifacts.get('medians', {})

# Page Configuration
st.set_page_config(
    page_title="Backpack Price Predictor",
    page_icon="🎒",
    layout="centered")

st.title("🎒 Backpack Price Prediction AI")
st.markdown("""
    This AI tool predicts the price of a backpack based on its features.
    \n**Adjust the values below and click 'Predict Price'.**
""")

# Input 
if artifacts:
    with st.form("prediction_form"):
        st.subheader("1. Backpack Features")
        
        col1, col2 = st.columns(2)
        
        with col1:
            brand = st.selectbox("Brand", options=encoders['Brand'].classes_)
            material = st.selectbox("Material", options=encoders['Material'].classes_)
            style = st.selectbox("Style", options=encoders['Style'].classes_)
            color = st.selectbox("Color", options=encoders['Color'].classes_)
            
        with col2:
            size = st.selectbox("Size", options=['Small', 'Medium', 'Large', 'Unknown'])
            compartments = st.number_input("Number of Compartments", min_value=0, max_value=20, value=5, step=1)
            weight_capacity = st.number_input("Weight Capacity (kg)", min_value=0.0, max_value=100.0, value=10.0, step=0.5)
            
        st.subheader("2. Extra Features")
        col3, col4 = st.columns(2)
        with col3:
            laptop = st.selectbox("Laptop Compartment?", options=['Yes', 'No'])
        with col4:
            waterproof = st.selectbox("Waterproof?", options=['Yes', 'No'])

        submit_btn = st.form_submit_button("Predict Price 🚀", type="primary")

    # Prediction 
    if submit_btn:
        input_data = {
            'Brand': brand,
            'Material': material,
            'Style': style,
            'Color': color,
            'Laptop Compartment': laptop,
            'Waterproof': waterproof,
            'Size': size,
            'Compartments': compartments,
            'Weight Capacity (kg)': weight_capacity}
        
        df_input = pd.DataFrame([input_data])
        
        try:
            
            df_input['Size_Encoded'] = df_input['Size'].map(size_mapping).fillna(-1)
            
            encode_cols = ['Brand', 'Material', 'Style', 'Color', 'Laptop Compartment', 'Waterproof']
            
            for col in encode_cols:
                df_input[f'{col}_Encoded'] = encoders[col].transform([input_data[col]])
            
            model_features = model.get_booster().feature_names
            
            X_pred = df_input[model_features]
            
            prediction = model.predict(X_pred)[0]
            
            st.success(f"💰 Estimated Price: **${prediction:.2f}**")
            
            st.progress(min(int(prediction), 300) / 300)
            
        except Exception as e:
            st.error(f"An error occurred during prediction: {e}")
            st.warning("Technical Detail: Ensure the input categories match the training data.")

else:
    st.warning("Please upload the 'backpack_model.joblib' file to the app files.")