错误框中的混淆矩阵值

Question

我为混淆矩阵编写了一个代码，以便比较在线文档后的两个数字列表，当我认为我得到了很好的结果时，我注意到这些值的位置很奇怪。首先，这是我正在使用的代码：

## Classification report and confusion matrix
import numpy as np
def evaluate_pred(y_true, y_pred):

    y_test = np.array(y_true) 
    y_predict = np.array(y_pred)

    target_names = ['Empty', 'Human', 'Dog', 'Dog&Human']
    labels_names = [0,1,2,3] 

    print(classification_report(y_test, y_predict,labels=labels_names, target_names=target_names))  

    cm = confusion_matrix(y_test, y_predict,labels=labels_names, normalize='pred')
    cm2 = confusion_matrix(y_test, y_predict,labels=labels_names)

    disp = ConfusionMatrixDisplay(confusion_matrix=cm,display_labels=target_names)
    disp = disp.plot(cmap=plt.cm.Blues,values_format='g')

    disp2 = ConfusionMatrixDisplay(confusion_matrix=cm2,display_labels=target_names)
    disp2 = disp2.plot(cmap=plt.cm.Blues,values_format='g')

    plt.show()

在给它两个列表（标签和预测）之后，我得到了以下结果（下面是归一化矩阵），但是正如你所看到的，每个类的行应该加起来就是总数，但是，它的列。我尝试了不同的东西，但我仍然无法修复它。我缺少一些东西，但我无法弄清楚。非常感谢您的帮助。

Answer 1

这有帮助吗？

完整示例：

import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.utils.multiclass import unique_labels

# import some data to play with
iris = datasets.load_iris()
X = iris.data
y = np.repeat(np.arange(0,10),15)
class_names = np.array(['1', '2', '3', '4', '5','6','7','8','9','10'])

# Split the data into a training set and a test set
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

# Run classifier, using a model that is too regularized (C too low) to see
# the impact on the results
classifier = svm.SVC(kernel='linear', C=0.01)
y_pred = classifier.fit(X_train, y_train).predict(X_test)


def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    if not title:
        if normalize:
            title = 'Normalized confusion matrix'
        else:
            title = 'Confusion matrix, without normalization'

    # Compute confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    # Only use the labels that appear in the data
    classes = classes[unique_labels(y_true, y_pred)]
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    print(cm)

    fig, ax = plt.subplots()
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # We want to show all ticks...
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           # ... and label them with the respective list entries
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")

    # Loop over data dimensions and create text annotations.
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", va="center",
                    color="white" if cm[i, j] > thresh else "black")
    fig.tight_layout()
    plt.xlim(-0.5, len(np.unique(y))-0.5)
    plt.ylim(len(np.unique(y))-0.5, -0.5)
    return ax


np.set_printoptions(precision=2)

# Plot non-normalized confusion matrix
plot_confusion_matrix(y_test, y_pred, classes=class_names,
                      title='Confusion matrix, without normalization')

# Plot normalized confusion matrix
plot_confusion_matrix(y_test, y_pred, classes=class_names, normalize=True,
                      title='Normalized confusion matrix')

plt.show()

Answer 2

我只需要使用normalize='true' 而不是normalize='pred' 来解决问题。似乎将值设置为pred 会考虑每列的总数，然后根据该值计算百分比。