一.前言
在上一篇文章中博主用逻辑回归方法解决了一个考试预测问题,这次我们依然用逻辑回归方法来解决一个芯片质量预测问题,但本次实战和上一次有所不同,本次实战中运用了以函数的方式求解边界曲线并且描绘出完整的决策边界曲线。好了,话不多说,直接进入实战环节。
二.实战
#加载数据
import pandas as pd
import numpy as np
data = pd.read_csv('chip_test.csv')
data.head() #数据预览
#添加标签
mask = data.loc[:,'pass'] == 1
print(mask)#预览
#可视化数据
%matplotlib inline
from matplotlib import pyplot as plt
fig1 = plt.figure()
passed = plt.scatter(data.loc[:,'test1'][mask],data.loc[:,'test2'][mask])
failed = plt.scatter(data.loc[:,'test1'][~mask],data.loc[:,'test2'][~mask]) #这里的~mask是取反,可以理解为0
plt.title('test1-test2')
plt.xlabel('test1')
plt.ylabel('test2')
plt.legend((passed,failed),('passed','failed'))
plt.show()
#将数据赋值给相关变量
X = data.drop(['pass'],axis=1)
y = data.loc[:,'pass']
X1 = data.loc[:,'test1']
X2 = data.loc[:,'test2']
X1.head()
#创建新数据
X1_2 = X1*X1
X2_2 = 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)
#创建并训练模型
from sklearn.linear_model import LogisticRegression
LR1 = LogisticRegression()
LR1.fit(X_new,y)
#评估模型
from sklearn.metrics import accuracy_score
y1_predict = LR1.predict(X_new)
accuracy1 = accuracy_score(y,y1_predict)
print(accuracy1)
X1_new = X1.sort_values()
theta0 = LR1.intercept_
theta1,theta2,theta3,theta4,theta5 = LR1.coef_[0][0],LR1.coef_[0][1],LR1.coef_[0][2],LR1.coef_[0][3],LR1.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)
fig2 = plt.figure()
passed=plt.scatter(data.loc[:,'test1'][mask],data.loc[:,'test2'][mask])
failed=plt.scatter(data.loc[:,'test1'][~mask],data.loc[:,'test2'][~mask])
plt.plot(X1_new,X2_new_boundary)
plt.title('test1-test2')
plt.xlabel('test1')
plt.ylabel('test2')
plt.legend((passed,failed),('passed','failed'))
plt.show()
d = np.array(b*b-4*a*c)
#d = (-b+np.sqrt(b*b-4*a*c))/(2*a)
X1_new
#print(np.array(d))
实战一中因为成绩不可以为负数,所以要舍去d,这里可以为负数,故不可舍去。
#定义一个函数f(x)
#define f(x)
def f(x):
a = theta4
b = theta5*x+theta2
c = theta0+theta1*x+theta3*x*x
X2_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
通过调用函数的方式可以直接用test1上的值去计算它对应的边界上的test2的值
X2_new_boundary1 = [] #用这两个变量来存储test1对应的边界上的test2的值
X2_new_boundary2 = []
for x in X1_new:
X2_new_boundary1.append(f(x)[0]) #所求解的第一个数值,故它的索引为0
X2_new_boundary2.append(f(x)[1]) #所求解的第二个数值,故它的索引为1
print(X2_new_boundary1,X2_new_boundary2)
fig3 = plt.figure()
passed=plt.scatter(data.loc[:,'test1'][mask],data.loc[:,'test2'][mask])
failed=plt.scatter(data.loc[:,'test1'][~mask],data.loc[:,'test2'][~mask])
plt.plot(X1_new,X2_new_boundary1)
plt.plot(X1_new,X2_new_boundary2)
plt.title('test1-test2')
plt.xlabel('test1')
plt.ylabel('test2')
plt.legend((passed,failed),('passed','failed'))
plt.show();
这里图形有缺损是因为test1它对应的边界上的test2的值之间是有间隔的
要补上图形,我们就不用原来的X1了,而是自己生成一个比较密集的X1,从而来解决这个间隔问题。观察图形可发现,最小值大概是-0.9,最大值大概是1.0多一点,所以我们从-0.9开始,每个数间隔为1/10000,数是从0到20000,这样自己生成的X1就比较密集了,也就可以补全图形了。
X1_range = [-0.9 + x/10000 for x in range(0,20000)]
X1_range = np.array(X1_range) #转换成数组
X2_new_boundary1 = []
X2_new_boundary2 = []
for x in X1_range:
X2_new_boundary1.append(f(x)[0])
X2_new_boundary2.append(f(x)[1])
# coding:utf-8
import matplotlib as mlp
mlp.rcParams['font.family'] = 'SimHei'
mlp.rcParams['axes.unicode_minus'] = False
fig4 = plt.figure()
passed=plt.scatter(data.loc[:,'test1'][mask],data.loc[:,'test2'][mask])
failed=plt.scatter(data.loc[:,'test1'][~mask],data.loc[:,'test2'][~mask])
plt.plot(X1_range,X2_new_boundary1,'r')
plt.plot(X1_range,X2_new_boundary2,'r')
plt.title('test1-test2')
plt.xlabel('测试1')
plt.ylabel('测试2')
plt.title('芯片质量预测')
plt.legend((passed,failed),('passed','failed'))
plt.show()
这样缺口就补上啦~~
ps:有些公式可以参照博主上一篇博客哦
数据集:
链接.
提取码:vflx
thanks~~