app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, mean_squared_error

# Title
st.title("Real Estate Price Prediction")

# Instructions
st.write("## Instructions")
st.write("1. Upload a CSV file containing real estate data.")
st.write("2. Select the target column (Price) from the dataset.")
st.write("3. Choose feature columns that influence the price.")
st.write("4. The model will be trained on the provided data and evaluated.")
st.write("5. Enter values for the selected features to predict the price of a property.")

# Upload Dataset
uploaded_file = st.file_uploader("Upload a CSV file", type=["csv"])

if uploaded_file:
    df = pd.read_csv(uploaded_file)
    st.write("Dataset Preview:")
    st.write(df.head())
    
    # Select Features and Target
    target_column = st.selectbox("Select the target column (Price)", df.columns)
    feature_columns = st.multiselect("Select feature columns", [col for col in df.columns if col != target_column])
    
    if feature_columns and target_column:
        X = df[feature_columns]
        y = df[target_column]
        
        # Handling missing values
        X.fillna(X.mean(), inplace=True)
        y.fillna(y.mean(), inplace=True)
        
        # Train-test split
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
        
        # Train model
        model = LinearRegression()
        model.fit(X_train, y_train)
        
        # Predict
        y_pred = model.predict(X_test)
        
        # Display Metrics
        st.write("### Model Performance")
        st.write(f"Mean Absolute Error: {mean_absolute_error(y_test, y_pred):.2f}")
        st.write(f"Mean Squared Error: {mean_squared_error(y_test, y_pred):.2f}")
        st.write(f"R² Score: {model.score(X_test, y_test):.2f}")
        
        # Prediction
        st.write("### Make a Prediction")
        user_input = {col: st.number_input(f"{col}", value=float(X[col].mean())) for col in feature_columns}
        
        if st.button("Predict Price"):
            user_df = pd.DataFrame([user_input])
            prediction = model.predict(user_df)[0]
            st.success(f"Predicted Price: ${prediction:,.2f}")