import numpy as np
import matplotlib.pyplot as plt
import sklearn
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression
import pandas as pd
from sklearn.metrics import accuracy_score
from sklearn.metrics import mean_squared_error,r2_score


data = pd.read_csv("./examdata.csv",encoding="gbk")
data.head()
x1 = data.loc[:,"Exam1"]
x2 = data.loc[:,"Exam2"]
x3 = data.drop(['Pass'],axis=1)
y = data.loc[:,"Pass"]
mask = data.loc[:,"Pass"]==1

x11 = np.array(x1).reshape(-1,1)
x22 = np.array(x2).reshape(-1,1)

LR = LogisticRegression()
LR.fit(x3,y)
y_predict = LR.predict(x3)
y_test = LR.predict([[40,100]])
print('ok'if y_test == 1 else 'ng')
accuray = accuracy_score(y,y_predict)
print(accuray)


# t0 = LR.intercept_
# t1,t2=LR.coef_[0][0],LR.coef_[0][1]
# x2_new = -(t0+t1*x1)/t2

x1_2 = x1*x1
x2_2 = x2*x2
x1_x2 = x1*x2
##创建二阶边界函数
x_new = {'x11':x1,'x22':x2,'x1_2 ':x1_2 ,'x2_2':x2_2,'x1_x2':x1_x2}
x_new = pd.DataFrame(x_new)
print(x_new)
LR2 = LogisticRegression()
LR2.fit(x_new,y)
# print(t0)
t0 = LR2.intercept_
t1 = LR2.coef_[0][0]
t2 = LR2.coef_[0][1]
t3 = LR2.coef_[0][2]
t4 = LR2.coef_[0][3]
t5 = LR2.coef_[0][4]
print(t1,t2)
print(t3,t4,t5)
y2_predict = LR2.predict(x_new)
print(y2_predict)
accuray2 = accuracy_score(y,y2_predict)
print(accuray2)

x1_new = x1.sort_values()#排序
print(x1_new)

a = t4
b = t5*x1_new + t2
c = t0 + t1 *x1_new + t3 *x1_new*x1_new
x2_new_2 = (-b+np.sqrt(b*b-4*a*c))/(2*a)
print(x2_new_2)


fig = plt.figure()
# # plt.subplot(1,2,1)
ok = plt.scatter(x1[mask],x2[mask])
ng = plt.scatter(x1[~mask],x2[~mask])
plt.legend((ok,ng),('ok','ng'))
plt.plot(x1_new,x2_new_2)
# # plt.subplot(1,2,2)
# # plt.scatter(x1,x2,c='b',marker="s")
# # plt.xlabel("test1")
# # plt.ylabel("test2")
plt.show()

 结果展示：

数据：