Upload folder using huggingface_hub

app.py

@@ -1,35 +1,30 @@
-
 import streamlit as st
 import pandas as pd
 import joblib
 
-# Load the trained regression model and preprocessor
+# Load the trained regression model
 def load_model():
     return joblib.load("boston_housing_model_v1_0.joblib")
 
-# def load_preprocessor():
-#     return joblib.load("preprocessor_v1_0.joblib")
-
 model = load_model()
-# preprocessor = load_preprocessor()
 
 # Streamlit UI for Boston Housing Price Prediction
-st.title("Boston Housing Price Prediction App")
+st.title("🏠 Boston Housing Price Prediction App")
 st.write("This app predicts the median value of owner-occupied homes (`MEDV`) in $1000s based on Boston housing dataset features.")
-st.write("Please enter the details below to get a prediction.")
-
-# Collect user input for numeric features with realistic ranges
-CRIM = st.number_input("Per capita crime rate by town (CRIM)", min_value=0.0, max_value=100.0, value=0.2, format="%.3f")
-ZN = st.number_input("Proportion of residential land zoned for lots over 25,000 sq.ft. (ZN)", min_value=0.0, max_value=100.0, value=12.0)
-INDUS = st.number_input("Proportion of non-retail business acres per town (INDUS)", min_value=0.0, max_value=30.0, value=11.0)
-NX = st.number_input("Nitric oxides concentration (parts per 10 million) (NX)", min_value=0.0, max_value=1.0, value=0.55, format="%.3f")
-RM = st.number_input("Average number of rooms per dwelling (RM)", min_value=3.0, max_value=9.0, value=6.3, format="%.2f")
-AGE = st.number_input("Proportion of owner-occupied units built prior to 1940 (AGE)", min_value=0.0, max_value=100.0, value=65.0)
-DIS = st.number_input("Weighted distances to employment centers (DIS)", min_value=1.0, max_value=12.0, value=4.0, format="%.3f")
-RAD = st.number_input("Index of accessibility to radial highways (RAD)", min_value=1, max_value=24, value=4)
-TAX = st.number_input("Full-value property tax rate per $10,000 (TAX)", min_value=100, max_value=700, value=300)
-PTRATIO = st.number_input("Pupil-teacher ratio by town (PTRATIO)", min_value=10.0, max_value=25.0, value=19.0, format="%.2f")
-LSTAT = st.number_input("% lower status of the population (LSTAT)", min_value=0.0, max_value=40.0, value=12.0, format="%.2f")
+st.write("Move the sliders below to adjust values and get a prediction.")
+
+# Collect user input using sliders
+CRIM = st.slider("Per capita crime rate by town (CRIM)", 0.0, 100.0, 0.2, 0.1)
+ZN = st.slider("Proportion of residential land zoned for lots over 25,000 sq.ft. (ZN)", 0.0, 100.0, 12.0, 1.0)
+INDUS = st.slider("Proportion of non-retail business acres per town (INDUS)", 0.0, 30.0, 11.0, 0.5)
+NX = st.slider("Nitric oxides concentration (NX)", 0.0, 1.0, 0.55, 0.01)
+RM = st.slider("Average number of rooms per dwelling (RM)", 3.0, 9.0, 6.3, 0.1)
+AGE = st.slider("Proportion of owner-occupied units built prior to 1940 (AGE)", 0.0, 100.0, 65.0, 1.0)
+DIS = st.slider("Weighted distances to employment centers (DIS)", 1.0, 12.0, 4.0, 0.1)
+RAD = st.slider("Index of accessibility to radial highways (RAD)", 1, 24, 4, 1)
+TAX = st.slider("Full-value property tax rate per $10,000 (TAX)", 100, 700, 300, 1)
+PTRATIO = st.slider("Pupil-teacher ratio by town (PTRATIO)", 10.0, 25.0, 19.0, 0.1)
+LSTAT = st.slider("% lower status of the population (LSTAT)", 0.0, 40.0, 12.0, 0.1)
 
 # Categorical feature
 CHAS = st.selectbox("Charles River dummy variable (CHAS)", ["0 (No)", "1 (Yes)"])
@@ -51,10 +46,7 @@ input_data = pd.DataFrame([{
     'CHAS': CHAS_value
 }])
 
-# Apply preprocessing
-# input_data_preprocessed = preprocessor.transform(input_data)
-
 # Predict button
 if st.button("Predict MEDV"):
     predicted_price = model.predict(input_data)[0]
-    st.write(f"Estimated median value of owner-occupied home (MEDV): ${predicted_price*1000:,.2f}")
+    st.success(f"💰 Estimated Median Value of Home (MEDV): ${predicted_price*1000:,.2f}")