src/streamlit_app.py

import streamlit as st
import joblib
import numpy as np
from sklearn.preprocessing import StandardScaler

with open("src/House_Linear", "rb") as f:
    model = joblib.load(f)
with open("src/Scaler_Model", "rb") as f:
    scaler = joblib.load(f)


st.title(":orange[HOUSE] PRICE PREDICTION :house:")

sqft_living = st.number_input("SQFT_LIVING: ", min_value=50.0, max_value=10000.0, step=50.0)
sqft_lot = st.number_input("SQFT_LOT: ", min_value=60.0, max_value=10000.0, step=50.0)
floors = st.number_input("FLOORS: ", min_value=1.0, max_value=6.0, step=1.0)
bedrooms = st.number_input("BEDROOMS: ", min_value=1.0, max_value=6.0, step=1.0)
condition = st.number_input("CONDITION: ", min_value=1, max_value=5, step=1)

if st.button("Estimate"):
    raw_input = np.array([[sqft_living, sqft_lot, floors, bedrooms, condition]])
    scaled_input = scaler.transform(raw_input)
    prediction = model.predict(scaled_input)
    formatted_pred = round(prediction[0].item(), 2)
    st.success(f"🏡 Estimated House Price: ${formatted_pred}")