Question

我正在尝试使用不同的技术对数据进行分类。我清理了数据集，然后也对输入组件进行了标准化和缩放，以查找任何差异。当我尝试执行以下支持向量机时，出现以下错误。

我的代码：

def svm(x,x_std,x_minmax,y):
    ##Support Vector Machines, seeks a line that separates two classes. The
    ##data instances that are closest to the line are called support vectors

    res_w1 = pd.DataFrame()
    res_w2 = pd.DataFrame()
    res_w3 = pd.DataFrame()

    #model and regression
    kfold = KFold(n_splits=10,random_state=7)
    model = SVC(gamma='scale')

    #reesults for original
    #results for original input component
    results=cross_val_score(model,x,y,cv=kfold)
    print(f'Support Vector Machines - Accuracy {results.mean()*100:.3f}% std {results.std()*100:3f}')

    #results for the standarized input components
    results_std=cross_val_score(model,x_std,y,cv=kfold)
    print(f'Support Vector Machines (-1..1) - Accuaracy {results_std.mean()*100:.3f})% std {results_std.std()*100:3f}')

    #results for the rescaled input components
    results_minmax = cross_val_score(model,x_minmax,y,cv=kfold)
    print(f'Support Vector Machines (0..1) - Accuaracy {results_minmax.mean()*100:.3f})% std {results_minmax.std()*100:3f}')

    res_w1['Res']=results
    res_w1['Type']='SVM'
    res_w2['Res']=results_std
    res_w2['Type']='SVM -1..1'
    res_w3['Res']=results
    res_w3['Type']='SVM 0..1'

    resall5=pd.concat([resall,res_w1,res_w2,res_w3], ignore_index=True)

    return

-> 207个结果= cross_val_score（model，x，y，cv = kfold）

ValueError：类的数量必须大于一；一堂课

尝试使用支持向量机进行分类时出现值错误

0 个答案: