用pybrain构建BP神经网络

pybrain是一个python关于构建神经网络的包，
官方文档：http://pybrain.org/docs/index.html

安装：

$ git clone git://github.com/pybrain/pybrain.git$ python setup.py install

以sklearn作为辅助构建BP神经网络并保存，可二次读取使用。

建立BP回归模型

#coding:utf-8'''env:    python 2.7    pybrain 0.3.3    sklearn 0.18.1'''from pybrain.structure import FeedForwardNetworkfrom pybrain.structure import LinearLayer, TanhLayer, FullConnectionfrom pybrain.supervised.trainers import BackpropTrainerfrom pybrain.datasets import SupervisedDataSetfrom pybrain.tools.customxml.networkwriter import NetworkWriterfrom pybrain.tools.customxml.networkreader import NetworkReaderfrom sklearn.datasets import load_bostonfrom sklearn.preprocessing import MinMaxScalerfrom sklearn.externals import joblib#从sklearn数据集中读取用来模拟的数据boston = load_boston()x = boston.datay = boston.target.reshape(-1,1)#直接采用不打乱的方式进行7:3分离训练集和测试集per = int(len(x) * 0.7)#对数据进行归一化处理（一般来说使用Sigmoid时一定要归一化）sx = MinMaxScaler()sy = MinMaxScaler()xTrain = x[:per]xTrain = sx.fit_transform(xTrain)yTrain = y[:per]yTrain = sy.fit_transform(yTrain)xTest = x[per:]xTest = sx.transform(xTest)yTest = y[per:]yTest = sy.transform(yTest)#初始化前馈神经网络fnn = FeedForwardNetwork()#构建输入层，隐藏层和输出层，一般隐藏层为3-5层，不宜过多inLayer = LinearLayer(x.shape[1], 'inLayer')hiddenLayer = TanhLayer(3, 'hiddenLayer')outLayer = LinearLayer(1, 'outLayer')#将构建的输出层、隐藏层、输出层加入到fnn中fnn.addInputModule(inLayer)fnn.addModule(hiddenLayer)fnn.addOutputModule(outLayer)#对各层之间建立完全连接in_to_hidden = FullConnection(inLayer, hiddenLayer)hidden_to_out = FullConnection(hiddenLayer, outLayer)#与fnn建立连接fnn.addConnection(in_to_hidden)fnn.addConnection(hidden_to_out)fnn.sortModules()#初始化监督数据集DS = SupervisedDataSet(x.shape[1],1)#将训练的数据及标签加入到DS中for i in range(len(xTrain)):    DS.addSample(xTrain[i],yTrain[i])#采用BP进行训练，训练至收敛，最大训练次数为1000trainer = BackpropTrainer(fnn, DS, learningrate=0.01, verbose=True)trainer.trainUntilConvergence(maxEpochs=1000)#在测试集上对其效果做验证values = []for x in xTest:    values.append(sy.inverse_transform(fnn.activate(x))[0])#计算RMSE (Root Mean Squared Error)均方差sum(map(lambda x: x ** 0.5,map(lambda x,y: pow(x-y,2), boston.target[per:], values))) / float(len(xTest))#将训练数据进行保存NetworkWriter.writeToFile(fnn, 'pathName.xml')joblib.dump(sx, 'sx.pkl', compress=3)joblib.dump(sy, 'sy.pkl', compress=3)#将保存的数据读取fnn = NetworkReader.readFrom('pathName.xml')sx = joblib.load('sx.pkl')sy = joblib.load('sy.pkl')

建立BP分类模型

# coding: utf-8from collections import Counterfrom pybrain.structure import FeedForwardNetworkfrom pybrain.structure import (LinearLayer,                               TanhLayer,                               FullConnection,                               )from pybrain.supervised.trainers import BackpropTrainerfrom pybrain.datasets import ClassificationDataSetfrom sklearn.datasets import load_irisfrom sklearn.preprocessing import MinMaxScalerdef generateDS(input_, out, num, xtrain, ytrain):    alldata = ClassificationDataSet(input_, out, nb_classes=num)    for x, y in zip(xtrain, ytrain):        alldata.addSample(x, y)    #这里有坑，解决方案如下，参考为：http://stackoverflow.com/questions/27887936/attributeerror-using-pybrain-splitwithportion-object-type-changed/30869317#30869317    tstdata_temp, trndata_temp = alldata.splitWithProportion(.3)    tstdata = ClassificationDataSet(input_, out, nb_classes=num)    for n in xrange(tstdata_temp.getLength()):        tstdata.addSample(*[tstdata_temp.getSample(n)[i] for i in range(2)])    trndata = ClassificationDataSet(input_, out, nb_classes=num)    for n in xrange(trndata_temp.getLength()):        trndata.addSample(*[trndata_temp.getSample(n)[i] for i in range(2)])    trndata._convertToOneOfMany()    tstdata._convertToOneOfMany()    return trndata, tstdatadef buildBP(input_, hidden, output, trndata):    fnn = FeedForwardNetwork()    inLayer = LinearLayer(input_, 'inLayer')    hidden0 = TanhLayer(hidden, 'hiddenLayer')    outLayer = LinearLayer(output, 'outLayer')    fnn.addInputModule(inLayer)    fnn.addModule(hidden0)    fnn.addOutputModule(outLayer)    in_to_hidden = FullConnection(inLayer, hidden0)    hidden_to_out = FullConnection(hidden0, outLayer)    fnn.addConnection(in_to_hidden)    fnn.addConnection(hidden_to_out)    fnn.sortModules()    trainer = BackpropTrainer(fnn, trndata, verbose=True, learningrate=.01)    trainer.trainUntilConvergence(maxEpochs=1000)    return fnndef result(data, fnn, char='test'):    value = 0    length = data.getLength()    for i in xrange(length):        predict = fnn.activate(data.getSample(i)[0]).argmax()        real = data.getSample(i)[1].argmax()        #print predict, real        if predict == real:            value += 1    print ('%s'%char).center(60, '*')    print 'accuracy:  %s' % (value / float(length))if __name__ == '__main__':    iris = load_iris()    x, y = iris.data, iris.target    scaler = MinMaxScaler()    x_train = scaler.fit_transform(x)    #print x_train[:10]    input_ = x_train.shape[1]    out = 3    num = len(Counter(y).keys())    trndata, tstdata = generateDS(input_, 1, num,  x_train, y)    fnn = buildBP(input_, 3, out, trndata)    result(tstdata, fnn)    result(trndata, fnn, 'train')

输出的total error 等详情就不放这了，主要是用来观察是否正在收敛，若减少速度过快可以适当减小learningrate ，若减少速度过慢可以适当增加 learningrate ，这里设置的隐层个数为1,隐藏层神经元个数为3，可以多试几个。
可以看到最终在训练集上分类正确效果可以达到97%，测试集效果可以达到93%，可以继续调整参数，不过这里是为了示例，所以就点到为止了。

多说几句，pybrain虽然用起来确实挺好用，但是官方文档真的很随意，用起来各种踩坑，跟着文档做都能出错，不过因为目前还没找到更好的对BP支持比较详细的第三方库，目前只能一步步踩坑了。

这里留下_convertToOneOfMany() 时遇到的坑的解决方案stackoverflow