机器学习作业之混淆矩阵

 

from sklearn.model_selection import cross_val_predict
import pandas as pd
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import numpy as np
df = pd.read_excel(r'D:\Machine Learning\35\hunxiao.xls')
y_train=df['real_labels'].tolist()
y_train_pre=df['pre_labels'].tolist()
#构建混淆矩阵
conf_mx=confusion_matrix(y_train,y_train_pre)
plt.matshow(conf_mx,cmap=plt.cm.Purples)
plt.show()

 

#将混淆矩阵中的每个值除以相应类中的数量，比较的就是错误率
row_sums=conf_mx.sum(axis=1,keepdims=True)
norm_conf_mx=conf_mx/row_sums
np.fill_diagonal(norm_conf_mx,0)
plt.matshow(norm_conf_mx,cmap=plt.cm.Purples)
plt.show()
# 所有的分类 label
labels = list(set(y_train_pre))

 

import itertools
# 绘制混淆矩阵
def plot_confusion_matrix(cm, classes, normalize=False, title='Normalized confusion matrix', cmap=plt.cm.Purples):
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    print(cm)
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()#侧边的颜色带
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, format(cm[i, j], fmt),
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")
    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

plot_confusion_matrix(conf_mx,labels,normalize=True,title='Normalized confusion matrix 35RenXuan')