利用python 内置的digits 数据进行 数字识别
# 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,metrics import numpy as np import matplotlib.pyplot as plt digits = 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)) #true classifier = 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()
上4个图是训练的时候画的,下面4个是预测的(前4张图)