决策树识别MNIST数据集

I. 决策树基本原理

关于决策树的基本原理可以参考我之前写的一篇文章：决策树与随机森林(从入门到精通)

II. 数据处理

导入torchvision.datasets.MNIST数据集：

def load_data():
    dataset_train = torchvision.datasets.MNIST(root='./data/', train=True, transform=transforms.ToTensor())
    dataset_test = torchvision.datasets.MNIST(root='./data/', train=False, transform=transforms.ToTensor())
    data_train = dataset_train.data
    X_train = data_train.numpy()
    X_test = dataset_test.data.numpy()
    X_train = np.reshape(X_train, (60000, 784))
    X_test = np.reshape(X_test, (10000, 784))
    Y_train = dataset_train.targets.numpy()
    Y_test = dataset_test.targets.numpy()

    return X_train, Y_train, X_test, Y_test

训练集中含有60000条数据，测试集中含有10000条数据。任意输出一条数据：

print(X_train[0], Y_train[0])

结果为：

[  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
   0   0   0   0   0   0   0   0   3  18  18  18 126 136 175  26 166 255
 247 127   0   0   0   0   0   0   0   0   0   0   0   0  30  36  94 154
 170 253 253 253 253 253 225 172...] 5

x是一个维度为784的一维数组，y是标签。

III. 决策树

if __name__ == '__main__':
    train_x, train_y, test_x, test_y = load_data()
    model = DecisionTreeClassifier()
    model.fit(train_x, train_y)
    score = model.score(test_x, test_y)
    print('accuracy:', score)

结果：

在MNIST数据集上，决策树效果不如KNN。