sklearn中的模型选择和分层抽样相结合

Question

我使用scikit学习预测模型，同时使用Kfold分层采样和KNeighbors分类器。

伪数据集为：进口熊猫作为pd将numpy导入为np

data = pd.DataFrame(
    {'A' : [4,5,6,7,1,3,4,9,1,8], 'B' : [10,20,30,40,90,55,68,25,19,97],'C' : [100,50,30,89,54,23,13,67,93,84],'y' :[1,1,0,0,0,1,0,1,1,0]}).astype(np.float)
data1 = data.drop(['y'],axis = 1, inplace= False)
X = data1.as_matrix().astype(np.float)
X
y = data['y'].as_matrix().astype(np.int)
y

对于K倍分层采样，代码为：

from sklearn.cross_validation import StratifiedKFold
def stratifiedkfold_cv(X, y, clf_class, shuffle=True, n_folds=2, **kwargs):
    stratifiedk_fold = StratifiedKFold(y, n_folds=n_folds, shuffle=shuffle)
    y_pred = y.copy()
    for train_index, test_index in stratifiedk_fold:
        X_train, X_test = X[train_index], X[test_index]
        y_train = y[train_index]
        clf = clf_class(**kwargs)
        clf.fit(X_train,y_train)
        y_pred[test_index] = clf.predict(X_test)
    return y_pred 

我试图通过调整参数：n_neighbors based accurcy_score来拟合尽可能好的sklearn.neighbors，KNeighborsClassifier。代码是

from sklearn.neighbors import KNeighborsClassifier
k_range = range(1,31)
k_scores = []
for k in k_range:
    knn = KNeighborsClassifier
    y_pred = stratifiedkfold_cv(X, y,knn(n_neighbors = k))
    scores = accuracy_score(y, y_pred)
    k_scores.append(scores.mean())
print(k_scores)

但我得到的错误是：**---->7 y_pred=分层kfold_cv（X，y，knn（n_neighbors=k））---->7 clf=clf_class（**kwargs）**TypeError："KNeighborsClassifier"对象不可调用******

我相信我与定义为分层kfold_cv的函数有一些不一致。但我不知道如何修改它？

Answer 1

def accuracy(y_true,y_pred):
    return np.mean(y_true == y_pred)    
from sklearn.neighbors import KNeighborsClassifier
    k_range = range(1,31)
    k_scores = []
    for k in k_range:
        knn = KNeighborsClassifier
        print accuracy(y, stratifiedkfold_cv(X,y,KNN,n_neighbors=k))