使用sklearn进行mnist数据集分类

深度之眼-西瓜书课后代码

import time
import matplotlib.pyplot as plt
import numpy as np

from sklearn.datasets import fetch_openml
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import  StandardScaler
from sklearn.utils import check_random_state

print(__doc__)
t0 = time.time()
train_sample = 5000

x,y = fetch_openml('mnist_784',version=1,return_X_y=True)
random_state = check_random_state(0)#设置随机种子

permutation = random_state.permutation(x.shape[0])

x = x[permutation]
y = y[permutation]#两个进行顺序打乱
# x = x.reshape((x.shape[0],-1))

x_train,x_test,y_train,y_test = train_test_split(x, y
                                                 , train_size=train_sample
                                                 , test_size=10000)
scaler = StandardScaler()#对数据进行归一化，即对数据求方差与均值
x_train = scaler.fit_transform(x_train)#先进行拟合，再进行归一化变换
x_test = scaler.transform(x_test)#只是进行归一化变换

clf = LogisticRegression(C=50./train_sample
                         , multi_class='multinomial'
                         ,penalty='l1'
                         ,solver='saga'
                         ,tol=0.1)
clf.fit(x_train,y_train)
sparsity = np.mean(clf.coef_ == 0) * 100
score = clf.score(x_test,y_test)

print('Sparsity with L1 penalty: %.2f%%' % sparsity)#76.82%
print('Sparsity with L1 penalty {:.2f}%'.format(sparsity))#76.82%
print('Test score with L1 penalty: %.4f' % score)# 0.8287
print('Test score with L1 penalty {:.4f}'.format(score))# 0.8287

coef = clf.coef_.copy()
plt.figure(figsize=(10,5))
scale = np.abs(coef).max()
for i in range(10):
    l1_plot = plt.subplot(2, 5, i + 1)
    l1_plot.imshow(coef[i].reshape(28,28),interpolation='nearest'
                   ,cmap=plt.cm.RdBu
                   ,vmin=-scale
                   ,vmax=scale)
    l1_plot.set_xticks(())
    l1_plot.set_yticks(())
    l1_plot.set_xlabel('Class %i' % i)
plt.suptitle('Classification vector for .....')

run_time = time.time() -t0
print('Example run in %.3f s' % run_time)
plt.show()

没搞懂，里面很多函数用法都没看懂，
如果要使用fetch_openml，建议进行一下科学上网
里面同时对%和format两者输出形式进行了对比