1>>> 2.5 * np.random.randn(2, 4) + 3
2array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], #random
3 [ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) #random
4
1# train test split
2df = pd.read_csv('file_location')
3mask = np.random.rand(len(df)) < 0.8
4train = df[mask]
5test = df[~mask]