In [10]:
from sklearn.datasets import fetch_mldata
import os
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
In [4]:
# load data
mnist = fetch_mldata('MNIST original')
In [5]:
mnist
Out[5]:
{'COL_NAMES': ['label', 'data'],
'DESCR': 'mldata.org dataset: mnist-original',
'data': array([[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
...,
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0]], dtype=uint8),
'target': array([0., 0., 0., ..., 9., 9., 9.])}
In [6]:
dir(mnist)
Out[6]:
['COL_NAMES', 'DESCR', 'data', 'target']
In [7]:
X, y = mnist['data'], mnist['target']
In [8]:
print(X.shape)
print(y.shape)
(70000, 784)
(70000,)
In [11]:
# assign a random image
some_digit = X[np.random.randint(0,X.shape[0],1)]
In [12]:
Out[12]:
array([[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 32, 109, 109, 110, 233, 232, 109, 63, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 73, 252, 252, 253, 252, 252, 252, 238, 217, 114,
73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 73, 252, 252, 253, 252, 252, 252, 253,
252, 252, 252, 37, 5, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 31, 108, 108, 108, 108, 108,
190, 170, 252, 252, 252, 253, 35, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 42, 159, 252, 253, 252, 71, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 26, 221, 253, 252, 206, 31,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 27, 221, 253, 252,
252, 108, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 37, 252,
253, 252, 252, 108, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 145, 255, 253, 253, 108, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 32, 237, 253, 252, 252, 108, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 140, 252, 253, 252, 226, 31, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 181, 252, 253, 252, 132, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 63, 110, 109, 109, 109, 110, 150, 253, 253, 255, 222, 41,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
32, 115, 217, 237, 253, 252, 252, 252, 253, 252, 252, 252, 253,
242, 62, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 32,
58, 181, 211, 252, 252, 252, 253, 252, 252, 252, 253, 252, 252,
252, 253, 252, 98, 16, 0, 0, 0, 0, 0, 0, 0, 0,
63, 237, 252, 252, 252, 252, 252, 252, 253, 252, 252, 252, 253,
252, 252, 252, 253, 252, 252, 190, 0, 0, 0, 0, 0, 0,
0, 0, 255, 253, 253, 253, 253, 253, 253, 253, 255, 253, 253,
253, 255, 253, 175, 207, 255, 253, 253, 253, 0, 0, 0, 0,
0, 0, 0, 0, 253, 252, 252, 252, 252, 252, 252, 252, 253,
252, 252, 252, 119, 35, 10, 20, 35, 180, 252, 252, 0, 0,
0, 0, 0, 0, 0, 0, 149, 252, 252, 252, 252, 252, 252,
252, 253, 220, 112, 71, 0, 0, 0, 0, 0, 21, 71, 154,
0, 0, 0, 0, 0, 0, 0, 0, 47, 232, 252, 252, 252,
252, 148, 108, 108, 15, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0]], dtype=uint8)
In [ ]:
Content source: jaabberwocky/jaabberwocky.github.io
Similar notebooks: