本文共 2051 字,大约阅读时间需要 6 分钟。
# The data that we are interested in is made of 8x8 images of digits, let's# have a look at the first 4 images, stored in the `images` attribute of the# dataset. If we were working from image files, we could load them using# matplotlib.pyplot.imread. Note that each image must have the same size. For these# images, we know which digit they represent: it is given in the 'target' of# the dataset.from sklearn import datasets,svm,metricsimport numpy as npimport matplotlib.pyplot as pltdigits = datasets.load_digits()images_and_labels = list(zip(digits.images,digits.target))#print(images_and_labels[0])#print(images_and_labels[0:4])#显示训练集的前4个结果for index,(image,label) in enumerate(images_and_labels[:4]): plt.subplot(2,4,index+1) plt.axis('off') plt.imshow(image,cmap=plt.cm.gray_r,interpolation='nearest') plt.title('Training :%i' %label)#样本数n_samples = len(digits.images)#print(digits.images.shape)data = digits.images.reshape((n_samples,-1)) #和 reshape(n_samples,64)效果一样 可以用下面的这条验证#print(np.all(digits.images.reshape((1797,-1))==digits.data)) #trueclassifier = svm.SVC(gamma=0.001)#对前一半样本进行训练,构建模型classifier.fit(data[:n_samples//2],digits.target[:n_samples//2])#对后半部分数据进行验证,期望的预测结果expected = digits.target[n_samples//2:]#真实的预测结果predicted = classifier.predict(data[n_samples//2:])#预测结果与真实结果进行对比,得出预测详细信息(正确率等)print("Classification report for classifier %s:\n%s\n" % (classifier, metrics.classification_report(expected, predicted)))print("Confusion matrix:\n%s" % metrics.confusion_matrix(expected, predicted))#print(predicted) 所有的预测结果#将测试数据用zip构建城dict 进行图像与预测结果的对应images_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))#对结果进行显示for index, (image, prediction) in enumerate(images_and_predictions[:4]): #只是画出了前四个 预测的结果 plt.subplot(2, 4, index + 5) #2*4的图 第index+5部分 plt.axis('off')#不显示坐标信息 #显示图片(灰色) plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest') #在图片上方显示预测结果,方便直观看出正确性 plt.title('Prediction: %i' % prediction)plt.show()