版权声明:转载请声明转自Juanlyjack https://blog.csdn.net/m0_38088359/article/details/82052263
LogisticRegression
梯度上升及决策边界代码实现
时间原因,暂时先敲这两部分,模型准确率后期完善。
import numpy as np
def loadDataSet(file_name):
dataMat = [] #创建数据列表
labelMat = [] #创建标签列表
fr = open(file_name) #打开文件
for line in fr.readlines(): #逐行读取
lineArr = line.strip().split() #去回车,放入列表
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) #添加数据
labelMat.append(int(lineArr[2])) #添加标签
fr.close() #关闭文件
return dataMat, labelMat #返回
def sigmoid(inX):
return 1.0/(1+np.exp(-inX))
def gradAscent(dataMat,Labels,alpha=0.001):
dataMatrix = np.mat(dataMat)
labelsMat = np.mat(Labels).transpose()
m, n = np.shape(dataMatrix) #返回dataMatrix的大小。m为行数,n为列数。
alpha = alpha #学习速率,控制更新的幅度。
maxCycles = 500 #最大迭代次数
weights = np.ones((n,1))
for i in range(maxCycles):
H = sigmoid(dataMatrix * weights) #梯度上升矢量化公式
error = labelsMat - H
weights = weights + alpha * dataMatrix.transpose() * error
return weights
def DecisionBoundary():
dataMat, labelMat = loadDataSet() #加载数据集
dataArr = np.array(dataMat) #转换成numpy的array数组
n = np.shape(dataMat)[0] #数据个数
xcord1 = []; ycord1 = [] #正样本
xcord2 = []; ycord2 = [] #负样本
for i in range(n): #根据数据集标签进行分类
if int(labelMat[i]) == 1:
xcord1.append(dataArr[i,1]); ycord1.append(dataArr[i,2]) #1为正样本
else:
xcord2.append(dataArr[i,1]); ycord2.append(dataArr[i,2]) #0为负样本
print("正样本:{}".format(xcord1,ycord1))
print("负样本:{}".format(xcord2,ycord2))
if __name__ == '__main__':
dataMat, labelMat = loadDataSet(file_name)
weights = gradAscent(dataMat, labelMat)
DecisionBoundary()