PCA在手写体MNIST数据集上做实验，对于很好地理解PCA工具的作用非常明显。
比如：数字9的不同识别体。
具体代码如下：
import os
import struct
import numpy as np
import matplotlib.pyplot as plt
def load_mnist(path, kind='train'):
"""Load MNIST data from `path`"""
labels_path = os.path.join(path,'%s-labels.idx1-ubyte'%kind)
print(labels_path)
#train-labels.idx1-ubyte
images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind)
print(images_path)
#train-images.idx3-ubyte
with open(labels_path, 'rb') as lbpath:
magic,n = struct.unpack('>II',lbpath.read(8))
labels = np.fromfile(lbpath,dtype=np.uint8)
with open(images_path, 'rb') as imgpath:
magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))
images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)
return images, labels
#-----------------------------------------------------------------------------
X_train,y_train=load_mnist("d:\\")
print(shape(X_train),shape(y_train))
X_test,y_test=load_mnist("d:\\",kind="t10k")
print(shape(X_test),shape(y_test))
def Plt_numberfrom0to10():
import matplotlib.pyplot as plt
fig, ax = plt.subplots(nrows=2,ncols=5,sharex=True,sharey=True, )
ax = ax.flatten()
for i in range(10):
img = X_train[y_train == i][0].reshape(28, 28)
ax[i].imshow(img, cmap='Greys', interpolation='nearest')
ax[0].set_xticks([])
ax[0].set_yticks([])
plt.tight_layout()
plt.show()
def Plt_number(t):
import matplotlib.pyplot as plt
fig, ax = plt.subplots(nrows=5,ncols=5,sharex=True,sharey=True, )
ax = ax.flatten()
for i in range(25):
img = X_train[y_train == t][i].reshape(28, 28)
ax[i].imshow(img, cmap='Greys', interpolation='nearest')
ax[0].set_xticks([])
ax[0].set_yticks([])
plt.tight_layout()
plt.show()
Plt_numberfrom0to10()
for i in range(10):
Plt_number(i)
def main(X_train,y_train,X_test,y_test):
import numpy as np
# from sklearn.datasets import fetch_mldata
#mnist=fetch_mldata("MNIST original")
#print(mnist)
X_train=np.array(X_train,dtype=float)
y_train=np.array(y_train,dtype=float)
X_test=np.array(X_test,dtype=float)
y_test=np.array(y_test,dtype=float)
print(y_train)
main(X_train,y_train,X_test,y_test)
from sklearn.neighbors import KNeighborsClassifier
knn_clf=KNeighborsClassifier()
knn_clf.fit(X_train,y_train)
print("normal:",knn_clf.score(X_test,y_test))
