Question

我正在尝试对我的模型使用Kfold交叉价值，但这样做时会出现此错误。我知道KFold只接受1D数组，但即使将长度输入转换为数组，它也会给我这个问题。

from sklearn.ensemble import ExtraTreesClassifier, RandomForestClassifier
from sklearn.cross_validation import train_test_split
from sklearn.cross_validation import KFold

if __name__ == "__main__":
  np.random.seed(1335)

  verbose = True
  shuffle = False
  n_folds = 5

  y = np.array(y)

  if shuffle: 
    idx = np.random.permutation(y.size)
    X_train = X_train[idx]
    y = y[idx]

  skf = KFold(y, n_folds) 

  models = [RandomForestClassifier(n_estimators=100, n_jobs=-1, criterion='gini'),ExtraTreesClassifier(n_estimators=100, n_jobs=-1, criterion='entropy')]

  print("Stacking in progress")
  A = []
  for j, clf in enumerate(models):
     print(j, clf)

     for i, (itrain, itest) in enumerate(skf):
        print("Fold :", i)
        x_train = X_train[itrain]
        x_test = X_train[itest]
        y_train = y[itrain]
        y_test = y[itest]
        print(x_train.shape, x_test.shape)

        print(len(x_train), len(x_test))

        clf.fit(x_train, y_train)
        pred = clf.predict_proba(x_test)
        A.append(pred)

我收到“skf = KFold(y, n_folds)”行的错误。任何有关这方面的帮助将不胜感激。

Answer 1

从its doc开始，KFold()不会指望y作为输入，而只会指望拆分数（n_folds）。

获得KFold的实例后，执行myKfold.split(x)（x作为所有输入数据）以获取迭代器，产生列车和测试索引。从sklearn doc粘贴的示例副本：

>>> from sklearn.model_selection import KFold
>>> X = np.array([[1, 2], [3, 4], [1, 2], [3, 4]])
>>> y = np.array([1, 2, 3, 4])
>>> kf = KFold(n_splits=2)
>>> kf.get_n_splits(X)
2
>>> print(kf)  
KFold(n_splits=2, random_state=None, shuffle=False)
>>> for train_index, test_index in kf.split(X):
...    print("TRAIN:", train_index, "TEST:", test_index)
...    X_train, X_test = X[train_index], X[test_index]
...    y_train, y_test = y[train_index], y[test_index]
TRAIN: [2 3] TEST: [0 1]
TRAIN: [0 1] TEST: [2 3]

TypeError：使用Kfold交叉验证时，只能将length-1数组转换为Python标量

1 个答案: