当前位置：首页 > news >正文

机器学习逻辑回归实战

news 2025/8/12 10:38:57

解决分类的一种模型

逻辑回归预测考试通过

基于examdata.csv数据，建立逻辑回归模型预测Exam1=75，Exam2=60时
该同学在Exam3时passed or failed

import pandas as pd
import numpy as npdata = pd.read_csv('examdata.csv')
data.head()

在这里插入图片描述

#可视化
%matplotlib inline
from matplotlib import pyplot as pltfig1 = plt.figure()
plt.scatter(data.loc[:,'Exam1'],data.loc[:,'Exam2'])
plt.title('Exam1-Exam2')
plt.xlabel('Exam1')
plt.ylabel('Exam2')
plt.show()

在这里插入图片描述

mask = data.loc[:,'Pass'] == 1
print(mask) # print(~mask) 取反

在这里插入图片描述

fig2 = plt.figure()
passed = plt.scatter(data.loc[:,'Eaxm1'][mask],data.loc[:,'Exam2'][mask])
failed = plt.scatter(data.loc[:,'Exam1'][~mask],data.loc[:,'Exam2'][~mask])
plt.title('Exam1-Exam2')
plt.xlabel('Exam1')
plt.ylabel('Exam2')
plt.legend((passed,failed),('passed','failed'))
plt.show()

在这里插入图片描述

#定义X，y
X = data.drop(['Pass'],axis=1)
y = data.loc[:,'Pass']
X1 = data.loc[:,'Exam1']
X2 = data.loc[:,'Exam2']# 逻辑回归训练模型
from sklearn.linear_model import LogisticRegression
LR = LogisticRegression()
LR.fit(X,y)#预测结果和评估模型表现
y_predict = LR.predict(X)
print(y_predict)from sklean.metrics import accuracy_score
accuracy = accuracy_score(y,y_predict)
print(accuracy)# 预测结果 exam1=70 exam2=65
y_test = LR.predict([[70,65]])
print('passed' if y_test==1 else 'failed')

获取边界函数
在这里插入图片描述

# 获取模型参数
LR.coef_
LR.intercept_theta0 = LR.intercept
theta1,theta2 = LR.coef_[0][0],LR.coef_[0][1]
print(theta0,theta1,theta2)

在这里插入图片描述

X2_new = -(theta0+theta1*X1)/theta2
fig3 = plt.figure()
passed = plt.scatter(data.loc(:,'Exam1')[mask],data.loc[:'Exam2'][mask])
failed = plt.scatter(data.loc[:,'Exam1'][~mask],data.loc[:'Exam2'][~mask])
plt.plot(X1,X2_new) # 根据边界线可以得出，准确率并不高
plt.title('Exam1-Exam2')
plt.xlabel('Exam1')
plt.ylabel('Exam2')
plt.legend((passed,failed),('passed','failed'))
plt.show()

在这里插入图片描述

建立二阶边界，提高模型准确度

X1_2 = X1*X1 #平方
X2_2 = X2*X2
X1_X2 = X1*X2
print(X1,X1_2)X_new = {'X1':X1,'X2':X2,'X1_2':X1_2,'X2_2':X2_2,'X1_X2':X1_X2}
X_new = pd.DataFrame(X_new)
print(X_new)

在这里插入图片描述

# 模型训练
LR2 = LogisticRegression()
LR2.fig(X_new,y)y2_predict = LR2.predict(X_new)
accuracy2 = accuracy_score(y,y2_predict)
print(accuracy2) # 1.0    预测结果最优

#先排序
X1_new = X1.sort_values()
print(X1,X1_new)theta0 = LR2.intercept
theta1,theta2,theta3,theta4,theta5 = LR2.coef_[0][0],LR2.coef_[0][1],LR2.coef_[0][2],LR2.coef_[0][3],LR2.coef_[0][4]
a = theta4
b = theta5*X1_new+theta2
c = theta0+theta1*X1_new+theta3*X1_new*X1_new
X2_new_boundary = (-b+np.sqrt(b*b-4*a*c))/(2*a)fig4 = plt.figure()
plt.plot(X1_new,X2_new_boundary)
plt.show()

在这里插入图片描述

芯片检测

#加载数据
import pandas as pd
import numpy as np
data = pd.read_csv('chip_test.csv')
data.head()

在这里插入图片描述

#清洗数据，去掉pass列
mask = data.loc[:,'pass'] == 1
print(~mask)

在这里插入图片描述

#可视化
%matplotlib inline
from matplotlib import pyplot as pltfig1 = plt.figure()
passed = plt.scatter(data.loc[:,'test1'][mask],data.loc[:,'test2'][mask])
failed = plt.scatter(ata.loc[:,'test1'][~mask],data.loc[:,'test2'][~mask])
plt.title('test1-test2')
plt.xlabel('test1')
plt.ylabel('test2')
plt.legend((passed,failed),('passed','failed'))
plt.show()

在这里插入图片描述

#生成新数据
X = data.drop(['pass'],axis=1)
y = data.loc[:,'pass']
X1 = data.loc[:,'test1']
X2 = data.loc[:,'test2']
X1.head()X1_2 = X1*X1
X2_X2 = X2*X2
X1_X2 = X1*X2
X_new = {'X1':X1,'X2':X2,'X1_2':X1_2,'X2_2':X2_2,'X1_X2':X1_X2}
X_new = pd.DataFrame(X_new)
print(X_new)

在这里插入图片描述

#训练模型
from sklearn.linear_model import LogisticRegression
LR2 = LogisticRegression()
LR2.fit(X_new,y)#预测
from sklearn.metrics import accuracy_score
y2_predict = LR2.predict(X_new)
accuracy2 = accuracy_score(y,y2_predict)
print(accuracy2)

#定义函数
def f(x):a = theta4b = theta5*x+theta2c = theta0+theta1*x+theta3*x*xX2_new_boundary1 = (-b+np.sqrt(b*b-4*a*c))/(2*a)X2_new_boundary2 = (-b-np.sqrt(b*b-4*a*c))/(2*a)return X2_new_boundary1,X2_new_boundary2

X2_new_boundary1 = []
X2_new_boundary2 = []
for x in X1_new:X2_new_boundary1.append(f(x)[0])X2_new_boundary2.append(f(x)[1])
print(X2_new_boundary1,X2_new_boundary2)