In [1]: import numpy as np import pandas as pd from sklearn.model_selection import train_test_split mush = pd.read_csv('../../data/mushroom.csv', header=None) mush.head() Out[1]: 0 1 2 3 4 5 6 7 8 9 ... 13 14 15 16 17 18 19 20 21 22 0 p x s n t p f c n k ... s w w p w o p k s u 1 e x s y t a f c b k ... s w w p w o p n n g 2 e b s w t l f c b n ... s w w p w o p n n m 3 p x y w t p f c n n ... s..