Spaces:
Runtime error
Runtime error
File size: 3,113 Bytes
0fa6542 a24f96a 0fa6542 a24f96a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
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**")
if __name__ == "__main__":
main()
|