Upload app.py

app.py

@@ -0,0 +1,213 @@
+# -*- coding: utf-8 -*-
+"""app
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1-jiUnfRGcb_iRcTXISQT__JTrBD7QqFM
+"""
+
+import gradio as gr
+import pandas as pd
+import numpy as np
+import joblib
+import plotly.graph_objects as go
+import plotly.express as px
+from huggingface_hub import hf_hub_download
+import os
+from pathlib import Path
+import warnings
+warnings.filterwarnings('ignore')
+
+# Load models using Hugging Face Hub (handles Xet pointers)
+def load_models():
+    """Load models using Hugging Face Hub library"""
+    models = {}
+
+    try:
+        # Download XGBoost model (handles Xet pointer automatically)
+        xgboost_path = hf_hub_download(
+            repo_id="Lesterchia174/HDB_Price_Predictor",
+            filename="best_model_xgboost.joblib",
+            repo_type="space"
+        )
+        models['xgboost'] = joblib.load(xgboost_path)
+        print("✅ XGBoost model loaded successfully via Hugging Face Hub")
+        print(f"   File size: {os.path.getsize(xgboost_path)} bytes")
+
+    except Exception as e:
+        print(f"❌ Error loading XGBoost model: {e}")
+        models['xgboost'] = None
+
+    try:
+        # Download Linear Regression model
+        linear_path = hf_hub_download(
+            repo_id="Lesterchia174/HDB_Price_Predictor",
+            filename="linear_regression.joblib",
+            repo_type="space"
+        )
+        models['linear_regression'] = joblib.load(linear_path)
+        print("✅ Linear Regression model loaded successfully via Hugging Face Hub")
+        print(f"   File size: {os.path.getsize(linear_path)} bytes")
+
+    except Exception as e:
+        print(f"❌ Error loading Linear Regression model: {e}")
+        models['linear_regression'] = None
+
+    return models
+
+def load_data():
+    """Load data using Hugging Face Hub"""
+    try:
+        # Download data file
+        data_path = hf_hub_download(
+            repo_id="Lesterchia174/HDB_Price_Predictor",
+            filename="base_hdb_resale_prices_2015Jan-2025Jun_processed.csv",
+            repo_type="space"
+        )
+        df = pd.read_csv(data_path)
+        print("✅ Data loaded successfully via Hugging Face Hub")
+        return df
+
+    except Exception as e:
+        print(f"❌ Error loading data: {e}")
+        # Fallback to creating sample data
+        print("⚠️  Creating sample data for demonstration")
+        return create_sample_data()
+
+def create_sample_data():
+    """Create sample data if real data isn't available"""
+    np.random.seed(42)
+    towns = ['ANG MO KIO', 'BEDOK', 'TAMPINES', 'WOODLANDS', 'JURONG WEST']
+    flat_types = ['4 ROOM', '5 ROOM', 'EXECUTIVE']
+    flat_models = ['Improved', 'Model A', 'New Generation']
+
+    data = []
+    for _ in range(100):
+        town = np.random.choice(towns)
+        flat_type = np.random.choice(flat_types)
+        flat_model = np.random.choice(flat_models)
+        floor_area = np.random.randint(85, 150)
+        storey = np.random.randint(1, 25)
+        age = np.random.randint(0, 40)
+
+        base_price = floor_area * 5000
+        town_bonus = towns.index(town) * 20000
+        storey_bonus = storey * 2000
+        age_discount = age * 1500
+        flat_type_bonus = flat_types.index(flat_type) * 30000
+
+        resale_price = base_price + town_bonus + storey_bonus - age_discount + flat_type_bonus
+        resale_price = max(300000, resale_price + np.random.randint(-20000, 20000))
+
+        data.append({
+            'town': town, 'flat_type': flat_type, 'flat_model': flat_model,
+            'floor_area_sqm': floor_area, 'storey_level': storey,
+            'flat_age': age, 'resale_price': resale_price
+        })
+
+    return pd.DataFrame(data)
+
+# Preload models and data
+print("Loading models and data using Hugging Face Hub...")
+models = load_models()
+data = load_data()
+
+# If models failed to load, create dummy ones
+if models['xgboost'] is None:
+    print("⚠️  Creating dummy XGBoost model for demonstration")
+    models['xgboost'] = create_dummy_model("xgboost")
+
+if models['linear_regression'] is None:
+    print("⚠️  Creating dummy Linear Regression model for demonstration")
+    models['linear_regression'] = create_dummy_model("linear_regression")
+
+def create_dummy_model(model_type):
+    """Create a realistic dummy model"""
+    class RealisticDummyModel:
+        def __init__(self, model_type):
+            self.model_type = model_type
+            self.n_features_in_ = 9
+            self.feature_names_in_ = [
+                'floor_area_sqm', 'storey_level', 'flat_age', 'remaining_lease',
+                'transaction_year', 'flat_type_encoded', 'town_encoded',
+                'flat_model_encoded', 'dummy_feature'
+            ]
+
+        def predict(self, X):
+            # Realistic prediction logic
+            floor_area = X[0][0]
+            storey_level = X[0][1]
+            flat_age = X[0][2]
+            town_encoded = X[0][6]
+            flat_type_encoded = X[0][5]
+
+            base_price = floor_area * (4800 + town_encoded * 200)
+            storey_bonus = storey_level * 2500
+            age_discount = flat_age * 1800
+
+            if self.model_type == "xgboost":
+                price = base_price + storey_bonus - age_discount + 35000
+                if storey_level > 20: price += 15000
+                if flat_age < 10: price += 20000
+            else:
+                price = base_price + storey_bonus - age_discount - 25000
+
+            return max(300000, price)
+
+    return RealisticDummyModel(model_type)
+
+# ... [rest of your functions remain the same: preprocess_input, create_market_insights_chart, predict_hdb_price] ...
+
+# Define Gradio interface
+towns_list = [
+    'SENGKANG', 'WOODLANDS', 'TAMPINES', 'PUNGGOL', 'JURONG WEST',
+    'YISHUN', 'BEDOK', 'HOUGANG', 'CHOA CHU KANG', 'ANG MO KIO'
+]
+
+flat_types = ['3 ROOM', '4 ROOM', '5 ROOM', 'EXECUTIVE', '2 ROOM', '1 ROOM']
+flat_models = ['Model A', 'Improved', 'New Generation', 'Standard', 'Premium']
+
+# Create Gradio interface
+with gr.Blocks(title="🏠 HDB Price Predictor", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🏠 HDB Price Predictor")
+    gr.Markdown("Predict HDB resale prices using different machine learning models")
+
+    with gr.Row():
+        with gr.Column():
+            town = gr.Dropdown(label="Town", choices=sorted(towns_list), value="ANG MO KIO")
+            flat_type = gr.Dropdown(label="Flat Type", choices=sorted(flat_types), value="4 ROOM")
+            flat_model = gr.Dropdown(label="Flat Model", choices=sorted(flat_models), value="Improved")
+            floor_area_sqm = gr.Slider(label="Floor Area (sqm)", minimum=30, maximum=200, value=95, step=5)
+            storey_level = gr.Slider(label="Storey Level", minimum=1, maximum=50, value=8, step=1)
+            flat_age = gr.Slider(label="Flat Age (years)", minimum=0, maximum=99, value=15, step=1)
+            model_choice = gr.Radio(label="Select Model",
+                                   choices=["XGBoost", "Linear Regression"],
+                                   value="XGBoost")
+
+            predict_btn = gr.Button("🔮 Predict Price", variant="primary")
+
+        with gr.Column():
+            predicted_price = gr.Label(label="💰 Predicted Price")
+            insights = gr.Markdown(label="📋 Property Summary")
+
+    with gr.Row():
+        chart_output = gr.Plot(label="📈 Market Insights (Both Models)")
+
+    # Connect button to function
+    predict_btn.click(
+        fn=predict_hdb_price,
+        inputs=[town, flat_type, flat_model, floor_area_sqm, storey_level, flat_age, model_choice],
+        outputs=[predicted_price, chart_output, insights]
+    )
+
+# For debugging
+if models['xgboost'] is not None:
+    print(f"XGBoost model expects {models['xgboost'].n_features_in_} features")
+
+if models['linear_regression'] is not None:
+    print(f"Linear Regression model expects {models['linear_regression'].n_features_in_} features")
+
+# To run in Colab
+if __name__ == "__main__":
+    demo.launch(share=True)