基于DNN的semi-supervised learning

半监督学习：就是通过部分有label的数据，学习得到其余没有label数据的label。

本文用的方法是 low-density separation (低密度的边界分类)中 self-training 方法；low-density separation 是按照“非黑即白”的观念进行分类。在对已有label数据建立模型时，本文采用的是DNN。整体基本步骤如下：

repeat:

1）将已有label数据带入DNN构建模型f*

2）将没有label数据带入f*预测其结果u

3）将u中满足hard-label条件的data拿出来，再带入更新f*

直到所有的unlabelled数据全都打上label

注意：对预测结果要采用hard-label重新打label，例如预测得到结果为[0.7,0.3]要变成[1,0]，再重新带入模型。实验数据还是用的Iris，贴代码：

# -*- coding: utf-8 -*-"""Created on Mon Sep 25 10:22:49 2017@author: wjw"""#基于DNN的 semi-supervised learningimport kerasimport numpy as npfrom keras.layers.core import Dense, Activation #直接import函数def readText(filePath):    lines = open(filePath,'r').readlines()    data = []    dataClass = []    for line in lines:        dataList = line.split(',')        data.append([float(dataList[0]),float(dataList[1]),float(dataList[2]),float(dataList[3])])        dataClass.append(dataList[4].split("\n")[0])       new_class = []        for name in dataClass:        if name=="Iris-setosa":            new_class.append(0)        elif name=="Iris-versicolor":            new_class.append(1)        else:            new_class.append(2)                return np.array(data),np.array(new_class)class network:    def createDnn(self):        model = keras.models.Sequential()#初始化一个神经网络        model.add(Dense(input_dim=4,output_dim=10))#Dense表示fully connected 的神经网络        model.add(Activation("sigmoid"))        model.add(Dense(output_dim=10))        model.add(Activation("sigmoid"))        model.add(Dense(output_dim=3))        model.add(Activation("softmax"))        model.compile(loss="categorical_crossentropy",optimizer="adam",metrics=["accuracy"])        #"categorical crossentropy"按照crossenrropy的方法定义损失函数        #优化方法是"adam"        return model    def low_density_seperation(classes):    for class_line in classes:        if max(class_line)>=0.7:            max_index = np.argmax(class_line)            class_line[max_index]=1            class_line[list(filter(lambda x : x != max_index, range(class_line.size)))]=0    return classes    def getTraindata():    filePath = r"E:\学习\研究生\李宏毅\data\iris.txt"    data, Class = readText(filePath)    train_index = np.random.randint(0,data.shape[0],size =int(data.shape[0]*0.2))    traindata = data[train_index]    dataClass = Class[train_index]    rest_index = list(filter(lambda x:x not in train_index,range(data.shape[0])))#filter过滤器，和map类似,将有标签的数据过滤掉    restdata = data[rest_index]    restClass = Class[rest_index]    return traindata,dataClass,restdata,restClassdef train(model,traindata,dataClass,restdata):        if len(restdata)==0:        return         model.fit(traindata,dataClass,batch_size=15,epochs=1000)#traindata是输入数据，dataclass是输出结果，对应的都是神经元    testClasses = model.predict(restdata)    testClasses = low_density_seperation(testClasses)    low_density_index = list(filter(lambda x : max(testClasses[x])==1,range(len(testClasses))))    traindata = np.vstack((traindata , restdata[low_density_index]))  # np.vstack将两个array进行纵向合并    dataClass = np.vstack((dataClass , testClasses[low_density_index])) #np.hstack 将两个array进行横向合并        rest_index = list(filter(lambda x:x not in low_density_index,range(len(restdata))))    if rest_index == '':        return     restdata = restdata[rest_index]    train(model,traindata,dataClass,restdata)    if __name__ == '__main__':    traindata,dataClass,restdata,restClass = getTraindata()    dataClass = keras.utils.to_categorical(dataClass)#装换成one-hot类型的数据比如说3就变成了[0,0,0,1]    restClass = keras.utils.to_categorical(restClass)    model = network().createDnn()    train(model,traindata,dataClass,restdata)    score = model.evaluate(np.vstack((traindata,restdata)),np.vstack((dataClass,restClass)),batch_size=20)    print(score)

差不多要进行3次递归，得到的score为：

20/155 [==>...........................] - ETA: 2s[0.22960705333980513, 0.94838709792783182]