Create app.py

app.py

@@ -0,0 +1,84 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error, r2_score
+import gradio as gr
+
+# URL to the Excel dataset on Hugging Face
+data_url = "https://huggingface.co/datasets/leadingbridge/flat/resolve/main/NorthPoint30.xlsx"
+
+# Load dataset (using openpyxl as the engine)
+df = pd.read_excel(data_url, engine="openpyxl")
+
+# Drop columns that are not needed for prediction
+cols_to_drop = ['Usage', 'Address', 'PricePerSquareFeet', 'InstrumentDate', 'Floor', 'Unit']
+df.drop(columns=cols_to_drop, inplace=True, errors='ignore')
+
+# Rename useful columns for consistency
+df.rename(columns={"Floor.1": "Floor", "Unit.1": "Unit"}, inplace=True)
+
+# Ensure the dataset has the necessary columns
+required_columns = ['District', 'PriceInMillion', 'Longitude', 'Latitude', 'Floor', 'Unit', 'Area', 'Year', 'WeekNumber']
+if not all(col in df.columns for col in required_columns):
+    raise ValueError("Dataset is missing one or more required columns.")
+
+# Define features and target variable
+feature_names = ['District', 'Longitude', 'Latitude', 'Floor', 'Unit', 'Area', 'Year', 'WeekNumber']
+X = df[feature_names]
+y = df['PriceInMillion']
+
+# Split into training and test sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Define a parameter grid for RandomForestRegressor and perform grid search
+rf_param_grid = {
+    'n_estimators': [50, 100, 150],
+    "max_depth": [4, 6, 8],
+    "max_features": ['sqrt', 'log2', 3],
+    "random_state": [42]
+}
+
+rf_grid = GridSearchCV(RandomForestRegressor(), rf_param_grid, refit=True, verbose=1, cv=5, error_score='raise')
+rf_grid.fit(X_train, y_train)
+
+# Use the best estimator
+model = rf_grid.best_estimator_
+
+# Print model performance on the test set
+rf_pred = model.predict(X_test)
+rf_rmse = np.sqrt(mean_squared_error(y_test, rf_pred))
+rf_r2 = r2_score(y_test, rf_pred)
+print("Random Forest RMSE: ", rf_rmse)
+print("Random Forest R2:   ", rf_r2)
+
+def price_prediction(model, feature_names, new_data):
+    new_data_df = pd.DataFrame([new_data], columns=feature_names)
+    prediction = model.predict(new_data_df)
+    return prediction[0]
+
+def predict(district, longitude, latitude, floor, unit, area, year, weeknumber):
+    new_data = [district, longitude, latitude, floor, unit, area, year, weeknumber]
+    prediction = price_prediction(model, feature_names, new_data)
+    return f"${prediction:,.2f} Million"
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=[
+         gr.Dropdown(choices=list(range(1, 9)), label='District (1 = Taikoo Shing, 2 = Mei Foo Sun Chuen, 3 = South Horizons, 4 = Whampoa Garden)'),
+         gr.Number(label='Longitude'),
+         gr.Number(label='Latitude'),
+         gr.Dropdown(choices=list(range(1, 71)), label='Floor'),
+         gr.Dropdown(choices=list(range(1, 31)), label='Unit (e.g., A=1, B=2, C=3, ...)'),
+         gr.Slider(minimum=137, maximum=5000, step=1, label='Area (in sq. feet)'),
+         gr.Dropdown(choices=[2024, 2025], label='Year'),
+         gr.Dropdown(choices=list(range(1, 53)), label='Week Number')
+    ],
+    outputs=gr.Textbox(label='Price Prediction'),
+    title="PROPERTY PRICE PREDICTION TOOL (Larry Pang Final Year Project)",
+    description="Predict the price of a new property based on District, Longitude, Latitude, Floor, Unit, Area, Year, and Week Number."
+)
+
+if __name__ == "__main__":
+    iface.launch()