通过机器学习svm、ranforest等方法实现AD、heart、WDBC等病例数据集的分类任务：

mode = input(‘请输入数据集名称：’)

if mode == “AD”:

data = scipy.io.loadmat(‘AD.mat’)

X1 = data[‘xtrain’]

Y1 = data[‘ytrain’]

X2 = data[‘xtest’]

Y2 = data[‘ytest’]

​

X_train, Y_train, X_test, Y_test = divide_dataset(X1, Y1, X2, Y2)

print(‘start svm training…’)

svm_accuracy = SVM_MODEL(X_train,Y_train,X_test,Y_test)

​

print(‘start ranforest training…’)

rf_accuracy = RF_MODEL(X_train,Y_train,X_test,Y_test)

​

​

plt.axis(‘off’)

rowLabels = [‘svm：’, ‘随机森林：’] # 表格行名

col_labels = [‘最高准确率’]

cellText = [[‘{:.2f}%’.format(svm_accuracy)], [‘{:.2f}%’.format(rf_accuracy)]] # 表格每一行数据

table = plt.table(cellText=cellText, rowLabels=rowLabels, loc=‘center’, cellLoc=‘center’, rowLoc=‘center’)

table.auto_set_font_size(False)

table.set_fontsize(10) # 字体大小

table.scale(1, 1.5) # 表格缩放

​

row_labels = [‘svm：’, ‘随机森林：’]

col_labels = [‘最高准确率’]

table_vals = [[‘{}%’.format(svm_accuracy100)], [‘{}%’.format(rf_accuracy100)]]  #

row_colors = [‘gold’]

my_table = plt.table(cellText=table_vals, colWidths=[0.3]*3,

rowLabels=row_labels, colLabels=col_labels,   loc=‘center’, cellLoc=‘center’, rowLoc=‘center’)