Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,75 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+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
+
+# URL to the Excel dataset on Hugging Face
+data_url = "https://huggingface.co/datasets/leadingbridge/flat/resolve/main/NorthPoint30.xlsx"
+
+@st.cache_resource
+def load_and_train_model():
+    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)
+
+    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.")
+
+    feature_names = ['District', 'Longitude', 'Latitude', 'Floor', 'Unit', 'Area', 'Year', 'WeekNumber']
+    X = df[feature_names]
+    y = df['PriceInMillion']
+
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    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)
+
+    model = rf_grid.best_estimator_
+    return model, feature_names
+
+@st.cache_data
+def predict_price(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 main():
+    st.title("PROPERTY PRICE PREDICTION TOOL (Streamlit Version)")
+    st.markdown("Predict the price of a new property based on District, Longitude, Latitude, Floor, Unit, Area, Year, and Week Number.")
+
+    model, feature_names = load_and_train_model()
+
+    district = st.selectbox("District (1 = Taikoo Shing, 2 = Mei Foo Sun Chuen, 3 = South Horizons, 4 = Whampoa Garden)", list(range(1, 9)))
+    longitude = st.number_input("Longitude", value=114.200)
+    latitude = st.number_input("Latitude", value=22.300)
+    floor = st.selectbox("Floor", list(range(1, 71)))
+    unit = st.selectbox("Unit (e.g., A=1, B=2, C=3, ...)", list(range(1, 31)))
+    area = st.slider("Area (in sq. feet)", min_value=137, max_value=5000, value=300)
+    year = st.selectbox("Year", [2024, 2025])
+    weeknumber = st.selectbox("Week Number", list(range(1, 53)))
+
+    if st.button("Predict"):
+        new_data = [district, longitude, latitude, floor, unit, area, year, weeknumber]
+        prediction = predict_price(model, feature_names, new_data)
+        st.success(f"🏠 Estimated Price: **${prediction:,.2f} Million**")
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+if __name__ == "__main__":
+    main()