"ValueError: y should be a 1d array, got an array of shape (3, 4) instead." While using fit() from sklearn

Question

我输入：

import numpy as np
from sklearn.linear_model import LogisticRegression
label_list = np.array([1,2,3])
label_list = label_list.reshape(-1,1)
feature_matrix = np.array([[0,0,1,1],[0,1,0,1],[1,0,0,1]])
model = LogisticRegression()
model.fit(label_list,feature_matrix)

然后我的控制台输出：

ValueError: y should be a 1d array, got an array of shape (3, 4) instead.

我该如何解决？我是初学者。请说清楚。

Answer 1

根据示例代码，我了解到 label_list 是“目标向量”（y），feature_matrix 是 X 矩阵。

所以，正确的用法应该是：

 model.fit(feature_matrix, label_list)

此外，您无法重塑 label_list:

label_list = label_list.reshape(-1,1)

因为 model.fit() 需要一个形状为 (n_samples,) 的向量，而你给出的向量形状为 (n_samples, 1).

总而言之，您的代码应如下所示：

import numpy as np
from sklearn.linear_model import LogisticRegression
label_list = np.array([1,2,3])
feature_matrix = np.array([[0,0,1,1],[0,1,0,1],[1,0,0,1]])
model = LogisticRegression()
model.fit(feature_matrix, label_list)

"ValueError: y should be a 1d array, got an array of shape (3, 4) instead." While using fit() from sklearn

"ValueError: y should be a 1d array, got an array of shape (3, 4) instead." While using fit() from sklearn

python

scikit-learn

logistic-regression