Split Dataset in Paddle #DeepLearning

split_dataset.py

import numpy as np
from sklearn.model_selection import train_test_split

# load filepath to list X, labels to list y

# test_size appoints the ratio(0,1), random_state gives the random seed 
X_train, X_test, y_train, y_test = train_test_split(
	 X, y, test_size=0.33, random_state=42)
     
# define dataset class, pass two lists in