sklearn split train test
import numpy as np
from sklearn.model_selection import train_test_split
X, y = np.arange(10).reshape((5, 2)), range(5)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=42)
X_train
# array([[4, 5],
# [0, 1],
# [6, 7]])
y_train
# [2, 0, 3]
X_test
# array([[2, 3],
# [8, 9]])
y_test
# [1, 4]