PCA+mnist_PCA降维；KNN分类；mnist手写体_pypcaminist_K._python_MNIST降维_

import numpy as np import struct from sklearn.decomposition import PCA from keras.datasets import mnist (train_data_ori, train_label), (test_data_ori, test_label) = mnist.load_data() print ("mnist data loaded") print ("original training data shape:",train_data_ori.shape) print ("original testing data shape:",test_data_ori.shape) train_data=train_data_ori.reshape(60000,784) test_data=test_data_ori.reshape(10000,784) print ("training data shape after reshape:",train_data.shape) print ("testing data shape after reshape:",test_data.shape) pca = PCA(n_components = 100) pca.fit(train_data) #fit PCA with training data instead of the whole dataset train_data_pca = pca.transform(train_data) test_data_pca = pca.transform(test_data) print("PCA completed with 100 components") print ("training data shape after PCA:",train_data_pca.shape) print ("testing data shape after PCA:",test_data_pca.shape) def KNN(test_data1,train_data_pca,train_label,k,p): subMat = train_data_pca - np.tile(test_data1,(60000,1)) subMat = np.abs(subMat) distance = subMat**p distance = np.sum(distance,axis=1) distance = distance**(1.0/p) distanceIndex = np.argsort(distance) classCount = [0,0,0,0,0,0,0,0,0,0] for i in range(k): label = train_label[distanceIndex[i]] classCount[label] = classCount[label] + 1 return np.argmax(classCount) def test(k, p): print("testing with K= %d and lp norm p=%d" % (k, p)) m, n = np.shape(test_data_pca) correctCount = 0 M = np.zeros((10, 10), int) for i in range(m): test_data1 = test_data_pca[i, :] predict_label = KNN(test_data1, train_data_pca, train_label, k, p) true_label = test_label[i] M[true_label][predict_label] += 1 # print("predict：%d,true:%d" % (predict_label,true_label)) if true_label == predict_label: correctCount += 1 print("The accuracy is: %f" % (float(correctCount) / m)) print("Confusion matrix:", M) test(3, 2)