并排绘制多个混淆矩阵

Question

我刚来这地方。这是我的第一个问题，希望得到专家的解答。我有 5 个分类器模型，我正在尝试绘制它们的混淆矩阵。

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
import collections

classifiers = {
    "Naive Bayes": GaussianNB(),
    "LogisiticRegression": LogisticRegression(),
    "KNearest": KNeighborsClassifier(),
    "Support Vector Classifier": SVC(),
    "DecisionTreeClassifier": DecisionTreeClassifier(),
}

进而

from sklearn.metrics import confusion_matrix
for key, classifier in classifiers.items(): 
    y_pred = classifier.fit(X_train, y_train).predict(X_test)
    cf_matrix=confusion_matrix(y_test, y_pred)
    print(cf_matrix)

这给了我

现在我尝试用下面的代码绘制它们，但图中没有显示数据。

fig, axn = plt.subplots(1,5, sharex=True, sharey=True)
cbar_ax = fig.add_axes([.91, .3, .03, .4])

for i, ax in enumerate(axn.flat):
    sns.heatmap(cf_matrix, ax=ax,
                cbar=i == 0,
                vmin=0, vmax=1,
                cbar_ax=None if i else cbar_ax)

fig.tight_layout(rect=[0, 0, .9, 1])

有人可以帮我完成这件事吗？

Answer 1

sklearn提供绘图功能confusion_matrix。有两种方法可以做到这一点，

• 绘图混淆矩阵

• 混淆矩阵显示

我在这里使用了第二种方法，因为第一种方法中删除颜色条非常冗长（有多个颜色条看起来非常混乱）。

import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
from sklearn.datasets import load_iris
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier

classifiers = {
    "Naive Bayes": GaussianNB(),
    "LogisiticRegression": LogisticRegression(),
    "KNearest": KNeighborsClassifier(),
    "Support Vector Classifier": SVC(),
    "DecisionTreeClassifier": DecisionTreeClassifier(),
}


iris = load_iris()
X, y = iris.data, iris.target

X_train, X_test, y_train, y_test = train_test_split(X, y)


f, axes = plt.subplots(1, 5, figsize=(20, 5), sharey='row')

for i, (key, classifier) in enumerate(classifiers.items()):
    y_pred = classifier.fit(X_train, y_train).predict(X_test)
    cf_matrix = confusion_matrix(y_test, y_pred)
    disp = ConfusionMatrixDisplay(cf_matrix,
                                  display_labels=iris.target_names)
    disp.plot(ax=axes[i], xticks_rotation=45)
    disp.ax_.set_title(key)
    disp.im_.colorbar.remove()
    disp.ax_.set_xlabel('')
    if i!=0:
        disp.ax_.set_ylabel('')

f.text(0.4, 0.1, 'Predicted label', ha='left')
plt.subplots_adjust(wspace=0.40, hspace=0.1)


f.colorbar(disp.im_, ax=axes)
plt.show()