import streamlit as st
import pandas as pd
import joblib
import os

# ======================
# LOAD MODEL
# ======================
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
model = joblib.load(os.path.join(BASE_DIR, "house_price_model.pkl"))

# ======================
# PAGE CONFIG
# ======================
st.set_page_config(
    page_title="House Price Prediction",
    page_icon="🏡",
    layout="centered"
)

st.title("🏡 House Price Prediction")
st.write("Predict the house price based on key features")

# ======================
# SIDEBAR INPUTS
# ======================
st.sidebar.header("House Features")

OverallQual = st.sidebar.slider("Overall Quality", 1, 10, 5)
GrLivArea = st.sidebar.number_input("Above Ground Living Area (sq ft)", 300, 5000, 1500)
GarageCars = st.sidebar.slider("Garage Capacity (cars)", 0, 4, 2)
TotalBsmtSF = st.sidebar.number_input("Total Basement Area (sq ft)", 0, 3000, 800)
FullBath = st.sidebar.slider("Full Bathrooms", 0, 4, 2)
YearBuilt = st.sidebar.slider("Year Built", 1900, 2024, 2000)

Neighborhood = st.sidebar.selectbox(
    "Neighborhood",
    [
        "NAmes", "CollgCr", "OldTown", "Edwards", "Somerst",
        "Gilbert", "NridgHt", "Sawyer", "NWAmes", "SawyerW"
    ]
)

# ======================
# DATAFRAME
# ======================
input_df = pd.DataFrame({
    "OverallQual": [OverallQual],
    "GrLivArea": [GrLivArea],
    "GarageCars": [GarageCars],
    "TotalBsmtSF": [TotalBsmtSF],
    "FullBath": [FullBath],
    "YearBuilt": [YearBuilt],
    "Neighborhood": [Neighborhood]
})

st.subheader("Input Data")
st.write(input_df)

# ======================
# PREDICTION
# ======================
if st.button("Predict Price"):

    prediction = model.predict(input_df)[0]

    st.subheader("Estimated House Price 💰")
    st.success(f"${prediction:,.0f}")