Update app.py

app.py

@@ -2,14 +2,28 @@ import streamlit as st
 import pickle
 
 # Load the model
-with open('house_price_model.pkl', 'rb') as f:
-    model = pickle.load(f)
+#with open('house_price_model.pkl', 'rb') as f:
+#    model = pickle.load(f)
     
-st.title('House Price Prediction 🏡')
+#st.title('House Price Prediction 🏡')
 # User inputs
-living_area = st.number_input('Living Area (sqft)')
-bedrooms = st.number_input('Number of Bedrooms')
+#living_area = st.number_input('Living Area (sqft)')
+#bedrooms = st.number_input('Number of Bedrooms')
+
+# Predict house price
+#if st.button('Predict Price'):
+#    prediction = model.predict([[living_area, bedrooms]])
+#    st.write(f'Predicted House Price: ${prediction[0]:.2f}')
+
+Load the model
+with open('best_model_chi2.pkl', 'rb') as f:
+    model = pickle.load(f)
+
+avg_train_score = st.text_input("AVG Train Score", "")
+awards_won = st.text_input("Awards Won", "")
+kpi_met = st.text_input("KPI Met 80", "")
+previous_rating = st.text_input("Previous Rating", "")
 # Predict house price
-if st.button('Predict Price'):
-    prediction = model.predict([[living_area, bedrooms]])
-    st.write(f'Predicted House Price: ${prediction[0]:.2f}')
+if st.button('Predict Promosi'):
+    prediction = model.predict([[avg_train_score, awards_won, kpi_met, previous_rating]])
+    st.write(f'Predicted Result: ${prediction[0]:.2f}')