Random forest classifier for car accidents

random_forests_car_accidents.py

def train_random_forest():
	le = preprocessing.LabelEncoder()
	le.fit(dataset['Cause'])
	dataset['Cause'] = le.transform(dataset['Cause'])

	le.fit(dataset['Severity'])
	dataset['Severity'] = le.transform(dataset['Severity'])
	print(le.classes_)

	X = dataset[['Cause', 'Weekday', 'Year', 'Month', 'Point of accident']]
	y = dataset['Severity']
	X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

	clf = RandomForestClassifier(n_estimators=100)

	clf.fit(X_train,y_train)
	y_pred = clf.predict(X_test)
	print("Accuracy:",metrics.accuracy_score(y_test, y_pred))