Python datasets.SequentialDataSet类代码示例

def main():
	generated_data = [0 for i in range(10000)]
	rate, data = get_data_from_wav("../../data/natabhairavi_violin.wav")
	data = data[1000:190000]
	print("Got wav")
	ds = SequentialDataSet(1, 1)
	for sample, next_sample in zip(data, cycle(data[1:])):
	    ds.addSample(sample, next_sample)

	net = buildNetwork(1, 5, 1, 
                   hiddenclass=LSTMLayer, outputbias=False, recurrent=True)

	trainer = RPropMinusTrainer(net, dataset=ds)
	train_errors = [] # save errors for plotting later
	EPOCHS_PER_CYCLE = 5
	CYCLES = 10
	EPOCHS = EPOCHS_PER_CYCLE * CYCLES
	for i in xrange(CYCLES):
	    trainer.trainEpochs(EPOCHS_PER_CYCLE)
	    train_errors.append(trainer.testOnData())
	    epoch = (i+1) * EPOCHS_PER_CYCLE
	    print("\r epoch {}/{}".format(epoch, EPOCHS), end="")
	    stdout.flush()

	# predict new values
	old_sample = [100]

	for i in xrange(500000):
		new_sample = net.activate(old_sample)
		old_sample = new_sample
		generated_data[i] = new_sample[0]
		print(new_sample)
	
	wavfile.write("../../output/test.wav", rate, np.array(generated_data))

  def train(self, params):
    n = params['encoding_num']
    net = buildNetwork(n, params['num_cells'], n,
                       hiddenclass=LSTMLayer,
                       bias=True,
                       outputbias=params['output_bias'],
                       recurrent=True)
    net.reset()

    ds = SequentialDataSet(n, n)
    trainer = RPropMinusTrainer(net, dataset=ds)

    history = self.window(self.history, params)
    resets = self.window(self.resets, params)

    for i in xrange(1, len(history)):
      if not resets[i-1]:
        ds.addSample(self.encoder.encode(history[i-1]),
                     self.encoder.encode(history[i]))
      if resets[i]:
        ds.newSequence()

    if len(history) > 1:
      trainer.trainEpochs(params['num_epochs'])
      net.reset()

    for i in xrange(len(history) - 1):
      symbol = history[i]
      output = self.net.activate(self.encoder.encode(symbol))
      predictions = self.encoder.classify(output, num=params['num_predictions'])

      if resets[i]:
        net.reset()

    return net

def visulizeDataSet(network, data, seqno, in_labels, out_labels):

    seq = data.getSequence(seqno)
    tmpDs = SequentialDataSet(data.indim, data.outdim)
    tmpDs.newSequence()

    for i in xrange(data.getSequenceLength(seqno)):
        tmpDs.addSample(seq[0][i], seq[1][i])

    nplots = len(in_labels) + len(out_labels)

    for i in range(len(in_labels)):
        p = PL.subplot(nplots, 1, i + 1)
        p.clear()
        p.plot(tmpDs['input'][:, i])
        p.set_ylabel(in_labels[i])

    for i in range(len(out_labels)):
        p = PL.subplot(nplots, 1, i + 1 + len(in_labels))
        p.clear()

        output = ModuleValidator.calculateModuleOutput(network, tmpDs)

        p.plot(tmpDs['target'][:, i], label='train')
        p.plot(output[:, i], label='sim')

        p.legend()
        p.set_ylabel(out_labels[i])

  def train(self, params):
    """
    Train LSTM network on buffered dataset history
    After training, run LSTM on history[:-1] to get the state correct
    :param params:
    :return:
    """
    if params['reset_every_training']:
      n = params['encoding_num']
      self.net = buildNetwork(n, params['num_cells'], n,
                               hiddenclass=LSTMLayer,
                               bias=True,
                               outputbias=params['output_bias'],
                               recurrent=True)
      self.net.reset()

    # prepare training dataset
    ds = SequentialDataSet(params['encoding_num'], params['encoding_num'])
    history = self.window(self.history, params)
    resets = self.window(self.resets, params)

    for i in xrange(1, len(history)):
      if not resets[i - 1]:
        ds.addSample(self.encoder.encode(history[i - 1]),
                     self.encoder.encode(history[i]))
      if resets[i]:
        ds.newSequence()

    print "Train LSTM network on buffered dataset of length ", len(history)
    if params['num_epochs'] > 1:
      trainer = RPropMinusTrainer(self.net,
                                  dataset=ds,
                                  verbose=params['verbosity'] > 0)

      if len(history) > 1:
        trainer.trainEpochs(params['num_epochs'])

      # run network on buffered dataset after training to get the state right
      self.net.reset()
      for i in xrange(len(history) - 1):
        symbol = history[i]
        output = self.net.activate(self.encoder.encode(symbol))
        self.encoder.classify(output, num=params['num_predictions'])

        if resets[i]:
          self.net.reset()
    else:
      self.trainer.setData(ds)
      self.trainer.train()

      # run network on buffered dataset after training to get the state right
      self.net.reset()
      for i in xrange(len(history) - 1):
        symbol = history[i]
        output = self.net.activate(self.encoder.encode(symbol))
        self.encoder.classify(output, num=params['num_predictions'])

        if resets[i]:
          self.net.reset()

 def create_data(self, inputs, targets):
     data = SequentialDataSet(inputs, targets)
     for i in xrange(0, len(self.dataframe) - 1):
         data.newSequence()
         ins = self.dataframe.ix[i].values
         target = self.dataframe.ix[i + 1].values[0]
         data.appendLinked(ins, target)
     self.data = data

def create_train_set (consumption):
    #create train/test set
	global active_max 
	ds = SequentialDataSet(1, 1)
	consumption_data = normalize (consumption) 
	active_max = max(consumption_data[1],active_max)
	consumption = consumption_data[0]

	size = len (consumption)
	for i in range(0, size-1):
		ds.addSample(consumption[i], consumption[i+1])	

	return ds 

def train(d, cycles=100, epochs_per_cycle=7):
    ds = SequentialDataSet(1, 1)
    net = buildNetwork(1, 5, 1, hiddenclass=LSTMLayer, outputbias=False, recurrent=False)

    for sample, next_sample in zip(d, cycle(d[1:])):
        ds.addSample(sample, next_sample)

    trainer = RPropMinusTrainer(net, dataset=ds)
    train_errors = []  # save errors for plotting later
    for i in xrange(cycles):
        trainer.trainEpochs(epochs_per_cycle)
        train_errors.append(trainer.testOnData())
        stdout.flush()

    return net, train_errors

 def __init__(self, net, task, valueNetwork=None, **args):
     self.net = net
     self.task = task
     self.setArgs(**args)
     if self.valueLearningRate == None:
         self.valueLearningRate = self.learningRate
     if self.valueMomentum == None:
         self.valueMomentum = self.momentum        
     if self.supervisedPlotting:
         from pylab import ion
         ion() 
     
     # adaptive temperature:
     self.tau = 1.
     
     # prepare the datasets to be used
     self.weightedDs = ImportanceDataSet(self.task.outdim, self.task.indim)
     self.rawDs = ReinforcementDataSet(self.task.outdim, self.task.indim)
     self.valueDs = SequentialDataSet(self.task.outdim, 1)
     
     # prepare the supervised trainers
     self.bp = BackpropTrainer(self.net, self.weightedDs, self.learningRate,
                               self.momentum, verbose=False,
                               batchlearning=True)            
     
     # CHECKME: outsource
     self.vnet = valueNetwork
     if valueNetwork != None:
         self.vbp = BackpropTrainer(self.vnet, self.valueDs, self.valueLearningRate,
                                    self.valueMomentum, verbose=self.verbose)
         
     # keep information:
     self.totalSteps = 0
     self.totalEpisodes = 0

  def __init__(self, ds): 
    self.alldata = SequentialDataSet(ds.num_features, 1)
    # Now add the samples to the data set.
    idx = 1
    self.alldata.newSequence()
    for sample in ds.all_moves:
      self.alldata.addSample(sample.get_features(), [ds.get_classes().index(sample.class_)])
      idx += 1
      if (idx%6 == 0): 
        self.alldata.newSequence()
     

    self.tstdata, self.trndata = self.alldata.splitWithProportion(0.25)
    #print "Number of training patterns: ", len(self.trndata)
    #print "Input and output dimensions: ", self.trndata.indim, self.trndata.outdim
    #print "First sample (input, target, class):"
    #print self.trndata['input'][0], self.trndata['target'][0], self.trndata['class'][0]
    # 5 hidden layers.  
    self.rnn = buildNetwork(self.trndata.indim,
                            3, 
                            self.trndata.outdim,  
                            hiddenclass=LSTMLayer, 
                            outclass=SigmoidLayer, 
                            recurrent=True)
 
    self.rnn.randomize()
    self.trainer = BackpropTrainer(self.nn, dataset=self.trndata, momentum=0.1, verbose=True, weightdecay=0.01)

def create_train_set (open_price, close_price):
	global open_max
	global close_max 
	ds = SequentialDataSet(1, 1)
	open_data = normalize (open_price) 
	close_data = normalize (close_price) 
	open_max = open_data[1]
	close_max = close_data[1]
	open_price = open_data[0]
	close_price = close_data[0]

	size = len (open_price)
	for i in range(0, size):
		ds.addSample(open_price[i], close_price[i])	

	return ds 

    def __init__(self):
        SequentialDataSet.__init__(self, 1,1)

        self.newSequence()
        self.addSample([-1], [-1])
        self.addSample([1], [1])
        self.addSample([1], [-1])

        self.newSequence()
        self.addSample([1], [1])
        self.addSample([1], [-1])

        self.newSequence()
        self.addSample([1], [1])
        self.addSample([1], [-1])
        self.addSample([1], [1])
        self.addSample([1], [-1])
        self.addSample([1], [1])
        self.addSample([1], [-1])
        self.addSample([1], [1])
        self.addSample([1], [-1])
        self.addSample([1], [1])
        self.addSample([1], [-1])

        self.newSequence()
        self.addSample([1], [1])
        self.addSample([1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([1], [1])
        self.addSample([-1], [1])
        self.addSample([-1], [1])
        self.addSample([-1], [1])
        self.addSample([-1], [1])
        self.addSample([-1], [1])

        self.newSequence()
        self.addSample([-1], [-1])
        self.addSample([-1], [-1])
        self.addSample([1], [1])

    def __init__(self):
        SequentialDataSet.__init__(self, 0, 1)

        self.newSequence()
        self.addSample([],[0])
        self.addSample([],[1])
        self.addSample([],[0])
        self.addSample([],[1])
        self.addSample([],[0])
        self.addSample([],[1])

        self.newSequence()
        self.addSample([],[0])
        self.addSample([],[1])
        self.addSample([],[0])
        self.addSample([],[1])
        self.addSample([],[0])
        self.addSample([],[1])

    def __init__(self, inp, target, nb_classes=0, class_labels=None):
        """Initialize an empty dataset.

        `inp` is used to specify the dimensionality of the input. While the
        number of targets is given by implicitly by the training samples, it can
        also be set explicity by `nb_classes`. To give the classes names, supply
        an iterable of strings as `class_labels`."""
        # FIXME: hard to keep nClasses synchronized if appendLinked() etc. is used.
        SequentialDataSet.__init__(self, inp, target)
        # we want integer class numbers as targets
        self.convertField('target', int)
        if len(self) > 0:
            # calculate class histogram, if we already have data
            self.calculateStatistics()
        self.nClasses = nb_classes
        self.class_labels = list(range(self.nClasses)) if class_labels is None else class_labels
        # copy classes (targets may be changed into other representation)
        self.setField('class', self.getField('target'))

def getPyBrainDataSetScalarEncoder(sequence, nTrain, encoderInput, encoderOutput,
                                   predictionStep=1, useTimeOfDay=True, useDayOfWeek=True):
  """
  Use scalar encoder for the data
  :param sequence:
  :param nTrain:
  :param predictionStep:
  :param useTimeOfDay:
  :param useDayOfWeek:
  :return:
  """
  print "generate a pybrain dataset of sequences"
  print "the training data contains ", str(nTrain-predictionStep), "records"

  if encoderInput is None:
    inDim = 1 + int(useTimeOfDay) + int(useDayOfWeek)
  else:
    inDim = encoderInput.n + int(useTimeOfDay) + int(useDayOfWeek)

  if encoderOutput is None:
    outDim = 1
  else:
    outDim = encoderOutput.n

  ds = SequentialDataSet(inDim, outDim)
  if useTimeOfDay:
    print "include time of day as input field"
  if useDayOfWeek:
    print "include day of week as input field"

  for i in xrange(nTrain-predictionStep):

    sample = getSingleSample(i, sequence, useTimeOfDay, useDayOfWeek)

    if encoderOutput is None:
      dataSDROutput = [sequence['normdata'][i+predictionStep]]
    else:
      dataSDROutput = encoderOutput.encode(sequence['data'][i+predictionStep])


    ds.addSample(sample, dataSDROutput)

  return ds

  def train(self, params, verbose=False):

    if params['reset_every_training']:
      if verbose:
        print 'create lstm network'

      random.seed(6)
      if params['output_encoding'] == None:
        self.net = buildNetwork(self.nDimInput, params['num_cells'], self.nDimOutput,
                           hiddenclass=LSTMLayer, bias=True, outputbias=True, recurrent=True)
      elif params['output_encoding'] == 'likelihood':
        self.net = buildNetwork(self.nDimInput, params['num_cells'], self.nDimOutput,
                           hiddenclass=LSTMLayer, bias=True, outclass=SigmoidLayer, recurrent=True)

    self.net.reset()

    ds = SequentialDataSet(self.nDimInput, self.nDimOutput)
    networkInput = self.window(self.networkInput, params)
    targetPrediction = self.window(self.targetPrediction, params)

    # prepare a training data-set using the history
    for i in xrange(len(networkInput)):
      ds.addSample(self.inputEncoder.encode(networkInput[i]),
                   self.outputEncoder.encode(targetPrediction[i]))

    if params['num_epochs'] > 1:
      trainer = RPropMinusTrainer(self.net, dataset=ds, verbose=verbose)

      if verbose:
        print " train LSTM on ", len(ds), " records for ", params['num_epochs'], " epochs "

      if len(networkInput) > 1:
        trainer.trainEpochs(params['num_epochs'])

    else:
      self.trainer.setData(ds)
      self.trainer.train()

    # run through the training dataset to get the lstm network state right
    self.net.reset()
    for i in xrange(len(networkInput)):
      self.net.activate(ds.getSample(i)[0])