说明：数据集 ex2data1.txt是吴恩达机器学习的作业的数据集。
# -*-coding:utf-8-*-
import matplotlib.pyplot as plt
import numpy as np
import pandas as pdclass Logitstic_Regression:def __init__(self, learning_rate=0.01, num_iterations=75000, threshold=0.5):self.learning_rate = learning_rateself.num_iterations = num_iterationsself.threshold = thresholdself.weights = Noneself.bias = Nonedef fit(self,X,y):#初始化参数num_samples,num_features=X.shapeself.weights=np.zeros((num_features,1))self.bias=0#梯度下降for i in range(self.num_iterations):#计算梯度linear_model=X @ self.weights+self.biasy_pred=self._sigmoid(linear_model)loss=(y_pred)-ydw=(1/num_samples) * (X.T @ (loss))db=(1/num_samples) * np.sum(loss)#updata W and bself.weights -= self.learning_rate*dwself.bias -= self.learning_rate*dbdef predict(self,X):#X必须是二维的，尺寸（m*2）linear_model=X @ self.weights +self.biasy_pred=self._sigmoid(linear_model)y_pred_class=[1 if i>self.thredshold else 0 for i in y_pred]return np.array(y_pred_class)def _sigmoid(self,x):return 1/(1+np.exp(-x))def draw(self,X, y):fig, ax = plt.subplots(figsize=(12, 8))ax.scatter(X[np.where(y == 1), 0], X[np.where(y == 1), 1], color="blue", s=30, marker="o")ax.scatter(X[np.where(y == 0), 0], X[np.where(y == 0), 1], color="green", s=30, marker="x")drawx2= ( 0-self.bias-X[:,0] * self.weights[0,0] ) / self.weights[1,0]ax.plot(X[:, 0], drawx2 , color="black")plt.show()
def loadData():df=pd.read_csv("ex2data1.txt",sep=",",header=None)data=np.array(df.values)# print(type(data))# print(data)#X是二维的，(m,2)，y是二维的(m,1)X=data[:,0:2]y=data[:,2:3]# print(X)# print(y)return X,yif __name__=="__main__":X,y=loadData()model=Logitstic_Regression()model.fit(X,y)print(model.weights)print(model.bias)model.draw(X,y)运行结果：
