这是数据集的一部分:

a b c result0 1 1  positive0 0 1  negative0 1 1  negative0 0 0  positiveresult = [1 if v=='positive' else 0 for v in data['result'].tolist()]Output = resultX = data["a", "b", "c"]y = np.reshape(Output, (X.shape[0], 1))

我尝试使用sklearn中的交叉验证方法来预测X数据的类别: 这部分代码是有效的:

logreg = LogisticRegression('l2')y_pred_class = cross_val_predict(logreg, X, y, cv=10, method= 'predict' ) 

但是当我想用以下代码计算一个类的概率时:

y_pred_prob = cross_val_predict(logreg, X, y, cv=10, method='predict_proba')

出现了这个错误:

index 1 is out of bounds for axis 1 with size 1

你知道问题出在哪里吗?

回答：

当你调用 method="predict" 时，你会收到一个警告:

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().return f(**kwargs)/usr/local/lib/python3.8/dist-packages/sklearn/utils/validation.py:72: 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().return f(**kwargs)

如果你遵循这个警告，它将解决 method="predict_proba" 中的错误。你只需要更改这一行

y = np.reshape(Output, (X.shape[0], 1))

为

y = np.reshape(Output, (X.shape[0],))

或者甚至

y = np.array(result)

或者根本不用列表解析，继续使用pandas:

y = data["result"].replace({"positive": 1, "negative": 0})