def test():
DS = loadPybrainData()
train, test = DS.splitWithProportion(0.1)
fnn = joblib.load(PKL)
# 预测test情况
output = fnn.activateOnDataset(test)
# ann.activate(onedata)可以只对一个数据进行预测
outputs = []
target = []
count = 0
for out in output:
outs = out.argmax()
outputs.append(outs)
for tar in test['target']:
ta = tar.argmax()
target.append(ta)
for i in range(0, len(target)):
if outputs[i] == target[i]:
count += 1
right = count / len(target) #单个字符正确率
rate = (right**4)
print("分类正确率是：%.4f%%" % (rate * 100))
v = Validator()
print(u'均方和差为：', v.MSE(output,
test['target'])) #计算test的原始值和预测值的均方差和,两者格式必须相等
def nn():
DS = ClassificationDataSet(28, 1, nb_classes=4)
train = pickle.load(open('train_extracted_df.pkl', 'r'))
y = train["median_relevance"]
kfold_train_test = pickle.load(open('kfold_train_test.pkl', 'r'))
features = ['query_tokens_in_title', 'query_tokens_in_description', 'percent_query_tokens_in_description', 'percent_query_tokens_in_title', 'query_length', 'description_length', 'title_length', 'two_grams_in_q_and_t', 'two_grams_in_q_and_d', 'q_mean_of_training_relevance', 'q_median_of_training_relevance', 'avg_relevance_variance', 'average_title_1gram_similarity_1', 'average_title_2gram_similarity_1', 'average_title_1gram_similarity_2', 'average_title_2gram_similarity_2', 'average_title_1gram_similarity_3', 'average_title_2gram_similarity_3', 'average_title_1gram_similarity_4', 'average_title_2gram_similarity_4', 'average_description_1gram_similarity_1', 'average_description_2gram_similarity_1', 'average_description_2gram_similarity_2', 'average_description_1gram_similarity_2', 'average_description_1gram_similarity_3', 'average_description_2gram_similarity_3', 'average_description_1gram_similarity_4', 'average_description_2gram_similarity_4']
train = train[features]
for i in range(len(y)):
DS.addSample(train.values[i],y[i])
X = DS['input']
Y = DS['target']
dataTrain, dataTest = DS.splitWithProportion(0.8)
xTrain, yTrain = dataTrain['input'], dataTrain['target']
xTest, yTest = dataTest['input'], dataTest['target']
#fnn = RecurrentNetwork()
fnn = FeedForwardNetwork()
#fnn=buildNetwork(1,40,1,hiddenclass=TanhLayer, bias=True, outclass=SoftmaxLayer)
#fnn=buildNetwork(1,40,1,hiddenclass=LSTMLayer, bias=True, outclass=SoftmaxLayer)
inLayer = LinearLayer(28, name='inLayer')
hiddenLayer = SigmoidLayer(40, name='hiddenLayer0')
outLayer =LinearLayer(4, name='outLayer')
fnn.addInputModule(inLayer)
fnn.addModule(hiddenLayer)
fnn.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
fnn.addConnection(in_to_hidden)
fnn.addConnection(hidden_to_out)
fnn.sortModules()
trainer = BackpropTrainer(fnn, DS, verbose = True, learningrate=0.01)
#trainer.trainUntilConvergence(maxEpochs=1000)
trainer.trainEpochs(epochs=5)
prediction = fnn.activateOnDataset(dataTest)
out=[]
total_score = 0
for i in prediction:
class_index = max(xrange(len(i)), key=i.__getitem__)
out.append(class_index+1)
print str((class_index+1-yTest[class_index+1])/yTest[class_index+1])
df=pd.DataFrame(out,columns=['predict'])
df['real']=dataTest['target']
coun = 0
for i,row in df.iterrows():
if row[0]== row[1]:
coun+=1
print coun
print "df['real']", df['real'],type(df['real'][0])
print "df['predict']",df['predict'],type(df['predict'][0])
print df
v=Validator()
#v.MSE(out,dataTest['target'])
print "out",out
print "dataTest['target']",dataTest['target']
pylab.plot(tsts['input'], ctsts, c='g')
pylab.xlabel('x')
pylab.ylabel('y')
pylab.title('Neuron Number:' + str(nneuron))
pylab.grid(True)
plotname = os.path.join(plotdir, ('jpq2layers_plot' + str(iter)))
pylab.savefig(plotname)
# set-up the neural network
nneuron = 5
mom = 0.98
netname = "LSL-" + str(nneuron) + "-" + str(mom)
mv = ModuleValidator()
v = Validator()
#create the test DataSet
x = numpy.arange(0.0, 1.0 + 0.01, 0.01)
s = 0.5 + 0.4 * numpy.sin(2 * numpy.pi * x)
tsts = SupervisedDataSet(1, 1)
tsts.setField('input', x.reshape(len(x), 1))
tsts.setField('target', s.reshape(len(s), 1))
#read the train DataSet from file
trndata = SupervisedDataSet.loadFromFile(os.path.join(os.getcwd(), 'trndata'))
myneuralnet = os.path.join(os.getcwd(), 'myneuralnet.xml')
if os.path.isfile(myneuralnet):
n = NetworkReader.readFrom(myneuralnet, name=netname)
#calculate the test DataSet based on the trained Neural Network
ctsts = mv.calculateModuleOutput(n, tsts)
