PYTHON

np random array

# uniform distribution over [0, 1)
np.random.rand(3, 3)
# [[0.20966286 0.72581506 0.78926387]
#  [0.85719525 0.00163033 0.45001818]
#  [0.17630303 0.40184026 0.89585902]]

# discrete uniform distribution in [0, 10)
np.random.randint(0, 10, size=[3,3])
# [[6 8 4]
#  [1 3 3]
#  [6 9 7]]

# normal distribution around 5 with standard deviation of 2
np.random.normal(5, 2, size=[3,3])
# [[3.8768528  5.73747086 3.63564872]
#  [5.49814587 2.62757122 3.61948982]
#  [3.36409537 7.86431236 5.16509868]]

np.random

np.random.rand(3,2)
array([[ 0.14022471,  0.96360618],  #random
       [ 0.37601032,  0.25528411],  #random
       [ 0.49313049,  0.94909878]]) #random

np.random.randn()

>>> 2.5 * np.random.randn(2, 4) + 3
array([[-4.49401501,  4.00950034, -1.81814867,  7.29718677],  #random
       [ 0.39924804,  4.68456316,  4.99394529,  4.84057254]]) #random

np.random.rand()

# train test split
df = pd.read_csv('file_location')
mask = np.random.rand(len(df)) < 0.8
train  = df[mask]
test = df[~mask]