#定义画混淆矩阵的函数

def plot_confusion_matrix(cm, classes,title='Confusion

matrix',cmap=plt.cm.Blues):

"""

This function prints and

plots the confusion matrix.

"""

plt.imshow(cm,

interpolation='nearest', cmap=cmap)

plt.title(title)

plt.colorbar()

tick_marks =

np.arange(len(classes))

plt.xticks(tick_marks,

classes, rotation=0)

plt.yticks(tick_marks,

classes)

thresh = cm.max() / 2

for i, j in

itertools.product(range(cm.shape[0]),

range(cm.shape[1])):

plt.text(j, i, cm[i, j],

horizontalalignment="center", color="white" if cm[i, j]

> thresh else "black")

plt.tight_layout()

plt.ylabel('True label')

plt.xlabel('Predicted label')

#引入数据库

import itertools

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

#引入数据库

#混淆矩阵

lr=LogisticRegression(C=0.01,penalty='l1')

lr.fit(X_train_undersample,y_train_undersample.values.ravel())

y_pred_undersample_proba=lr.predict_proba(X_test_undersample.values)

#这里改成计算结果的概率值

# 指定阈值

thresholds =

[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]

plt.figure(figsize=(10,10))

# 将预测的概率值与阈值进行对比

j=1

for i in thresholds:

y_test_predictions_high_recall = y_pred_undersample_proba[:,1]

> i

#取大于概率的的值

#

画出3*3的子图

plt.subplot(3,3,j)

j += 1

# Compute confusion

matrix

cnf_matrix =

confusion_matrix(y_test_undersample,y_test_predictions_high_recall)

np.set_printoptions(precision=2)

#小数点后面显示2位

print("Recall metric

in the testing dataset: ",

cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

#计算recall值

# Plot

non-normalized confusion matrix

class_names =

[0,1]

plot_confusion_matrix(cnf_matrix, classes=class_names,

title='Threshold >= %s'%i)

#还有问题。