机器学习：LR逻辑回归（实战）

import numpy as np import random from sklearn.linear_model import LogisticRegression """ 函数说明：sigmoid函数 Parameters： inX - 数据 Returns： sigmoid函数 """ def sigmoid(inX): return 1.0 / (1 + np.exp(-inX)) #函数说明：随机梯度上升算法 def stocGradAscent1(dataMatrix, classLabels, numIter=150): # 返回dataMatrix的大小。m为行数,n为列数。 m, n = np.shape(dataMatrix) # 参数初始化 weights = np.ones(n) for j in range(numIter): dataIndex = list(range(m)) for i in range(m): # 降低alpha的大小，每次减小1/(j+i)。 alpha = 4 / (1.0 + j + i) + 0.01 # 随机选取样本 randIndex = int(random.uniform(0, len(dataIndex))) # 选择随机选取的一个样本，计算h h = sigmoid(sum(dataMatrix[randIndex] * weights)) # 计算误差 error = classLabels[randIndex] - h # 更新回归系数 weights = weights + alpha * error * dataMatrix[randIndex] # 删除已经使用的样本 del (dataIndex[randIndex]) return weights """ #函数说明：梯度上升算法 Parameters： dataMatIn - 数据集 classLabels - 数据标签 Returns： weights.getA() - 求得的权重数组（最优参数） """ def gradAscent(dataMatIn, classLabels): # 转换成numpy的mat dataMatrix = np.mat(dataMatIn) # 转换成numpy的mat,并进行转置 labelMat = np.mat(classLabels).transpose() # 返回dataMatrix的大小。m为行数,n为列数。 m, n = np.shape(dataMatrix) # 移动步长,也就是学习速率,控制更新的幅度。 alpha = 0.001 # 最大迭代次数 maxCycles = 500 weights = np.ones((n,1)) for k in range(maxCycles): # 梯度上升矢量化公式 # g(X)=h(theta) = theta * X h = sigmoid(dataMatrix * weights) error = labelMat - h # theta = theta + alpha * X^T(y - g(X)) weights = weights + alpha * dataMatrix.transpose() * error return weights.getA() #函数说明：使用Python写的Logistic分类器做预测 def colicTest(): # 打开训练集 frTrain = open('horseColicTraining.txt') # 打开测试集 frTest = open('horseColicTest.txt') # 训练数据集 trainingSet = [] # 训练集标签 trainingLabels = [] # 遍历所有训练集 for line in frTrain.readlines(): # 去除空格，并以'\t'分割 currLine = line.strip().split('\t') lineArr = [] for i in range(len(currLine) - 1): lineArr.append(float(currLine[i])) trainingSet.append(lineArr) trainingLabels.append(float(currLine[-1])) # trainWeights = gradAscent(np.array(trainingSet), trainingLabels, 500) # 使用梯度上升训练 trainWeights = gradAscent(np.array(trainingSet), trainingLabels) errorCount = 0 numTestVec = 0.0 for line in frTest: numTestVec += 1.0 currLine = line.strip().split('\t') lineArr = [] for i in range(len(currLine) - 1): lineArr.append(float(currLine[i])) # if int(classifyVector(np.array(lineArr), trainWeights)) != int(currLine[-1]): # 改进的梯度上升算法 if int(classifyVector(np.array(lineArr), trainWeights[:, 0])) != int(currLine[-1]): errorCount += 1 errorRate = (float(errorCount) / numTestVec) * 100 print("测试集合错误率为： %.2f%%" % errorRate) """ 函数说明：分类函数 Parameters: inX - 特征向量 weights - 回归系数 returns: 分类结果 """ def classifyVector(inX, weights): prob = sigmoid(sum(inX * weights)) if prob > 0.5: return 1.0 else: return 0.0 #函数说明：使用sklearn构件Logistic回归分类 def colicSklearn(): # 打开训练集 frTrain = open('horseColicTraining.txt') # 打开测试集 frTest = open('horseColicTest.txt') # 训练集和标签 trainingSet = [] trainingLabels = [] # 测试集和标签 testSet = [] testLabels = [] # 遍历训练集 for line in frTrain.readlines(): currLine = line.strip().split('\t') lineArr = [] for i in range(len(currLine) - 1): lineArr.append(float(currLine[i])) trainingSet.append(lineArr) trainingLabels.append(float(currLine[-1])) # 遍历测试集 for line in frTest.readlines(): currLine = line.strip().split('\t') lineArr = [] for i in range(len(currLine) - 1): lineArr.append(float(currLine[i])) testSet.append(lineArr) testLabels.append(float(currLine[-1])) # sklearn中的分类器 classifier = LogisticRegression(solver='sag', max_iter=5000).fit(trainingSet, trainingLabels) test_accurcy = classifier.score(testSet, testLabels) * 100 print('正确率:%f%%' % test_accurcy) if __name__ == '__main__': colicSklearn() if __name__ == '__main__': # 梯度上升算法测试 # colicTest() # sklearn中的分类器 colicSklearn()