Label encoder

label_encode.py

def clean_data(train,test):
	obj_cols = [] #list to store columns that have been read as objects
	for col in train.columns:
		if train[col].dtype==object:
			obj_cols.append(col)
	preprocessor = preprocessing.LabelEncoder()	
	
	for col in obj_cols:
		preprocessor.fit(list(train[col].values) + list(test[col].values))
		train[col] = preprocessor.transform(list(train[col].values))
		test[col] = preprocessor.transform(list(test[col].values))	

	return train,test