Update app.py

app.py

@@ -1,48 +1,79 @@
 import streamlit as st
 import pandas as pd
-import joblib
 import numpy as np
+import joblib
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+
+# Load the trained Random Forest model
+@st.cache
+def load_model():
+    # Replace with path to your trained Random Forest model if necessary
+    return joblib.load('random_forest_model.pkl')
+
+model = load_model()
+
+# Sample Data
+url = "https://raw.githubusercontent.com/manishkr1754/CarDekho_Used_Car_Price_Prediction/main/notebooks/data/cardekho_dataset.csv"
+df = pd.read_csv(url)
+
+# Extract features for preprocessing
+num_features = ['vehicle_age', 'km_driven', 'mileage', 'engine', 'max_power', 'seats']
+cat_features = ['brand', 'model', 'seller_type', 'fuel_type', 'transmission_type']
 
-# Load the trained model
-model = joblib.load('random_forest_model.pkl')
+# Preprocessing pipeline
+numeric_transformer = StandardScaler()
+onehot_transformer = OneHotEncoder()
+
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', numeric_transformer, num_features),
+        ('cat', onehot_transformer, cat_features)
+    ])
 
 # Streamlit app
-st.title('Used Car Price Predictor')
-
-# User input fields
-st.sidebar.header('Enter Car Details')
-
-# Dropdown fields
-brand = st.sidebar.selectbox('Brand', ['Toyota', 'Honda', 'Ford', 'BMW', 'Audi'])  # Adjust based on dataset
-model_input = st.sidebar.text_input('Model')
-vehicle_age = st.sidebar.number_input('Vehicle Age (in years)', min_value=0, max_value=30, value=5)
-km_driven = st.sidebar.number_input('Kilometers Driven', min_value=0, max_value=300000, value=50000)
-mileage = st.sidebar.number_input('Mileage (in km/l)', value=15.0)
-engine = st.sidebar.number_input('Engine Capacity (in cc)', value=1500)
-max_power = st.sidebar.number_input('Maximum Power (in bhp)', value=100)
-seats = st.sidebar.number_input('Number of Seats', min_value=2, max_value=8, value=4)
-seller_type = st.sidebar.selectbox('Seller Type', ['Dealer', 'Individual'])
-fuel_type = st.sidebar.selectbox('Fuel Type', ['Petrol', 'Diesel', 'CNG', 'LPG'])
-transmission_type = st.sidebar.selectbox('Transmission Type', ['Manual', 'Automatic'])
+st.title('Used Car Price Prediction')
+
+# Main form for user input
+st.header('Enter Car Details')
+
+# Input fields
+brand = st.selectbox('Brand', df['brand'].unique())
+model = st.text_input('Model', '')
+vehicle_age = st.number_input('Vehicle Age (in years)', min_value=0, max_value=50, value=5)
+km_driven = st.number_input('Kilometers Driven', min_value=0, max_value=300000, value=50000)
+mileage = st.number_input('Mileage (kmpl)', min_value=0.0, max_value=50.0, value=15.0)
+engine = st.number_input('Engine (cc)', min_value=500, max_value=5000, value=1500)
+max_power = st.number_input('Max Power (bhp)', min_value=0, max_value=500, value=100)
+seats = st.number_input('Seats', min_value=2, max_value=8, value=5)
+seller_type = st.selectbox('Seller Type', df['seller_type'].unique())
+fuel_type = st.selectbox('Fuel Type', df['fuel_type'].unique())
+transmission_type = st.selectbox('Transmission Type', df['transmission_type'].unique())
 
 # Button to trigger the prediction
-if st.sidebar.button('Predict Price'):
+if st.button('Predict Price'):
+    # Create input dataframe
     input_data = pd.DataFrame({
+        'brand': [brand],
+        'model': [model],
         'vehicle_age': [vehicle_age],
         'km_driven': [km_driven],
         'mileage': [mileage],
         'engine': [engine],
         'max_power': [max_power],
         'seats': [seats],
-        'brand': [brand],
-        'model': [model_input],
         'seller_type': [seller_type],
         'fuel_type': [fuel_type],
         'transmission_type': [transmission_type]
     })
 
+    # Preprocess the input
+    input_data_transformed = preprocessor.fit_transform(input_data)
+
     # Predict the price
-    predicted_price = model.predict(input_data)
+    predicted_price = model.predict(input_data_transformed)
 
     # Display the result
     st.write(f'The predicted selling price for the car is: ₹ {predicted_price[0]:,.2f}')