python - 从头开始进行交叉验证

Question

我在 Stack Overflow 上找到了这个函数定义:

def fold_i_of_k(dataset, i, k):
    n = len(dataset)
    return len(dataset[n*(i-1)//k:n*i//k])


# this is my code below

#Constants
FOLD_I = 1
FOLD_K =10

#Creating 10 folds
counter = 1
s=0
total_ac = 0
while counter!=FOLD_K+1:
    print("Fold ",counter)
    fold = fold_i_of_k(dataset,counter,10)
    d_fold = dataset[s:s + fold]
    #print(d_fold.index.values)
    #print(d_fold.iloc[1:3,0:2])
    d_test = d_fold
    X_test = d_test.iloc[:,0:11]
    y_test = d_test.iloc[:,11:12]
    d_train = dataset.drop(dataset.index[s:s+fold])
    X_train = d_train.iloc[:,0:11]
    y_train = d_train.iloc[:,11:12]
    ##print(dataset)
    ##print(d_fold)
    ##print(d_train)
    ##print(d_test)
    ##print(len(X_train))
    ##print(len(y_train))
    ##print(X_test)
    ##print(y_test)
    #print(fold)
    X_train = X_train.as_matrix()
    X_train = preprocessing.scale(X_train)

    y_train = y_train.as_matrix()

    X_test = X_test.as_matrix()
    X_test = preprocessing.scale(X_test)

    y_test = y_test.as_matrix()

    #l1 = len(y_train)
    #np.reshape(y_train, l1)
    #print(y_train)
    from numpy import array
    #l = len(y_test)
    #np.reshape(y_test, l)
    #print(y_test)

    data.reshape((data.shape[0], 1))

    y_train = array(y_train)
    print(y_train.shape)
    lr = LogisticRegression()
    lr.fit(X_train,y_train)
    #lr_pred = lr.predict(X_test)
    #ac = accuracy_score(y_test,lr_pred)
    #print(ac)
    ##print(classification_report(y_test,lr_pred))

    total_ac = total_ac + ac
    s = s + fold 
    counter= counter+1

total_ac = total_ac / FOLD_K
print("Cross validation accuracy is: ",total_ac)`

我收到以下错误:

/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:578: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().

y = column_or_1d(y, warn=True)

如何修复它？

Answer 1

y_train.ravel() 解决了问题。