python - 超过 3 个类的 Scikit-learn (sklearn) 混淆矩阵图

Question

当我使用 scikit-learn 中的代码时，我遇到了混淆矩阵问题这就是我得到的

如你所见，第一个类被剪掉了

!!!更新!!!我通过使用这些行强制它工作

    plt.xlim(-0.5, 5.5)
    plt.ylim(5.5, -0.5)

并得到这个

但我仍然想知道是否有其他方法可以使它不特定于 5 类。我已经尝试更改斧头尺寸，但没有成功

    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 = list(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()
    return ax

plot_confusion_matrix(y, y_pred, classes=[0, 1, 2, 3, 4, 5], normalize=True,
                      title='Normalized confusion matrix')

我希望盒子不会切割第一行和最后一行

Answer 1

在这种情况下，您需要设置 xlim 和 ylim，这里有一种自动方法，例如10 节课。

简单来说，您需要:

plt.xlim(-0.5, len(np.unique(y))-0.5)
plt.ylim(len(np.unique(y))-0.5, -0.5)

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()