Create random_forest.py

random_forest.py

@@ -0,0 +1,39 @@
+import json
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import r2_score
+import joblib # Import joblib for saving the model
+
+try:
+    with open('./data.json', 'r') as f:
+        data = json.load(f)
+except FileNotFoundError:
+    print("Error: 'data.json' not found. Please ensure the file is in the same directory as this script.")
+    exit()
+
+df = pd.DataFrame.from_dict(data, orient='index')
+df[['latitude', 'longitude']] = pd.DataFrame(df['middle_point'].tolist(), index=df.index)
+df.drop('middle_point', axis=1, inplace=True)
+df = df[df['price'] > 1.0]
+
+features = ['area', 'dis', 'type', 'latitude', 'longitude']
+target = 'price'
+X = df[features]
+y = df[target]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+print(f"Data loaded. Training model on {len(X_train)} samples...")
+
+model = RandomForestRegressor(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+print("Model training complete.")
+
+y_pred = model.predict(X_test)
+r2 = r2_score(y_test, y_pred)
+print(f"Model R-squared on test data: {r2:.4f}")
+
+
+model_filename = 'random_forest_model.joblib'
+joblib.dump(model, model_filename)
+print(f"\nModel saved successfully as '{model_filename}'")