统计学习方法读书笔记5-感知机代码实现

文章目录

1.感知机代码实现

1.感知机代码实现

# 随机梯度下降 import time import numpy as np # 显示进度条 from tqdm import tqdm # mnist数据集将数据集做一个首尾拼接，28*28=784 def loaddata(filename): """ 加载mnist数据集 :param filename: 要加载的数据集路径 :return: list形式的数据集及标签 """ print('start to read data') # 存放数据 dataArr = [] labelArr = [] # 打开文件 fr = open(filename, 'r') # 将文件进行按行读取 for line in tqdm(fr.readlines()): # 将读取后的每一行按切割符切割，并返回字段列表 curline = line.strip().split(',') # 存放标记 # Mnsit有0-9是个标记，由于是二分类任务，所以将>=5的作为1，<5为-1 if int(curline[0]) >= 5: labelArr.append(1) else: labelArr.append(-1) # 归一化-遍历每一行除了第一个元素外的所有元素，并归一化 # 列表推导式 dataArr.append([int(num) / 255 for num in curline[1:]]) # 返回data和label return dataArr, labelArr def perceptron(dataArr, labelArr, iter=50): """ 感知机训练过程 :param dataArr: 训练集的数据 :param labelArr: 训练集的标签 :param iter: 迭代次数 :return: 训练好的w和b """ print('strat to train') # 将数据转换成矩阵形式，矩阵可以并行计算，方便运算 dataMat = np.mat(dataArr) # 将标签转换成矩阵后，在进行转置 # 转置是因为运算中需要单独取label中的某一个元素 labelMat = np.mat(labelArr).T # 获取数据矩阵的shape,m*n m, n = np.shape(dataMat) # 创建初始权重w，初始值全为0。 w = np.zeros((1, n)) # 初始化偏置b为0 b = 0 # 初始化步长η，即学习率，控制梯度下降速率 η = 0.001 # 迭代计算 for k in range(iter): # 采用随机梯度下降-计算一个样本，就针对该样本做一个梯度下降 for i in range(m): # 获取当前样本的向量及标签 xi = dataMat[i] yi = labelMat[i] # 判断是否为误分类样本，如果为误分类样本，则进行梯度更新 # 误分类样本特征:-1 * yi * (w * xi.T + b) >= 0 if -1 * yi * (w * xi.T + b) >= 0: w = w + η * yi * xi b = b + η * yi # 打印训练进度 print('Round %d : %d training' % (k, iter)) return w, b def model_test(dataArr, labelArr, w, b): """ 测试准确率 :param dataArr:测试数据集 :param labelArr: 测试标签 :param w: 权重 :param b: 偏置 :return: 测试集的准确率 """ print('start to test') dataMat = np.mat(dataArr) labelMat = np.mat(labelArr).T m, n = np.shape(dataMat) errornum = 0 for i in range(m): xi = dataMat[i] yi = labelMat[i] result = -yi * (w * xi.T + b) # 如果result >= 0,说明被错误分类 if result >= 0: errornum += 1 # 正确率 = 1 - 错误率 accurRate = 1 - (errornum / m) return accurRate if __name__ == '__main__': # 获取当前时间 start = time.time() # 加载数据集 trainData, trainLabel = loaddata('data/mnist_train.csv') testData, testLabel = loaddata('data/mnist_test.csv') # 获取训练后的权重 w, b = perceptron(trainData, trainLabel) # 进行测试获得准确率 accurRate = model_test(testData, testLabel, w, b) # 获取当前时间，作为结束时间 end = time.time() # 显示正确率 print('accuracy rate is:', accurRate) # 显示用时时长 print('time span:', end - start) start to read data 100%|██████████| 60000/60000 [00:11<00:00, 5247.08it/s] start to read data 100%|██████████| 10000/10000 [00:01<00:00, 5326.08it/s] strat to train Round 0 : 50 training Round 1 : 50 training Round 2 : 50 training Round 3 : 50 training Round 4 : 50 training Round 5 : 50 training Round 6 : 50 training Round 7 : 50 training Round 8 : 50 training Round 9 : 50 training Round 10 : 50 training Round 11 : 50 training Round 12 : 50 training Round 13 : 50 training Round 14 : 50 training Round 15 : 50 training Round 16 : 50 training Round 17 : 50 training Round 18 : 50 training Round 19 : 50 training Round 20 : 50 training Round 21 : 50 training Round 22 : 50 training Round 23 : 50 training Round 24 : 50 training Round 25 : 50 training Round 26 : 50 training Round 27 : 50 training Round 28 : 50 training Round 29 : 50 training Round 30 : 50 training Round 31 : 50 training Round 32 : 50 training Round 33 : 50 training Round 34 : 50 training Round 35 : 50 training Round 36 : 50 training Round 37 : 50 training Round 38 : 50 training Round 39 : 50 training Round 40 : 50 training Round 41 : 50 training Round 42 : 50 training Round 43 : 50 training Round 44 : 50 training Round 45 : 50 training Round 46 : 50 training Round 47 : 50 training Round 48 : 50 training Round 49 : 50 training start to test accuracy rate is: 0.8141 time span: 111.59057807922363