Create train_model.py

train_model.py

@@ -0,0 +1,39 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+import joblib
+
+# URL to the Excel dataset on Hugging Face
+data_url = "https://huggingface.co/datasets/leadingbridge/flat/resolve/main/NorthPoint30.xlsx"
+
+# Load dataset
+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)
+
+# Define features and target variable
+feature_names = ['District', 'Longitude', 'Latitude', 'Floor', 'Unit', 'Area', 'Year', 'WeekNumber']
+X = df[feature_names]
+y = df['PriceInMillion']
+
+# Train/test split
+X_train, _, y_train, _ = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train a fixed-parameter RandomForest (no grid search)
+model = RandomForestRegressor(
+    n_estimators=100,
+    max_depth=6,
+    max_features='sqrt',
+    random_state=42
+)
+model.fit(X_train, y_train)
+
+# Save model and feature list
+joblib.dump({"model": model, "features": feature_names}, "model.pkl")
+print("✅ Model trained and saved to model.pkl")