import numpy as np
import pandas as pd
from sklearn.model_selection import KFold

df = pd.DataFrame({'num_legs': [2, 4, 8, 0], 'num_wings': [2, 0, 0, 0], 'num_specimen_seen': [10, 2, 1, 8]}, index=[0,1,2,3])

kf = KFold(n_splits=2, shuffle=True)
for train_index, val_index in kf.split(df):
    df_train, df_val = df[train_index], df[val_index]