Python CLAModel_custom Examples

Example #1

File: run_tm_model.py Project: solversa/nupic.research

        DATE_FORMAT = '%Y-%m-%d %H:%M:%S'
        predictedField = "passenger_count"
    else:
        raise RuntimeError("un recognized dataset")

    if dataSet == "nyc_taxi" or dataSet == "nyc_taxi_perturb" or dataSet == "nyc_taxi_perturb_baseline":
        modelParams = getModelParamsFromName("nyc_taxi")
    else:
        modelParams = getModelParamsFromName(dataSet)
    modelParams['modelParams']['clParams']['steps'] = str(_options.stepsAhead)
    modelParams['modelParams']['clParams']['regionName'] = classifierType

    print "Creating model from %s..." % dataSet

    # use customized CLA model
    model = CLAModel_custom(**modelParams['modelParams'])
    model.enableInference({"predictedField": predictedField})
    model.enableLearning()
    model._spLearningEnabled = True
    model._tpLearningEnabled = True

    printTPRegionParams(model._getTPRegion())

    inputData = "%s/%s.csv" % (DATA_DIR, dataSet.replace(" ", "_"))

    sensor = model._getSensorRegion()
    encoderList = sensor.getSelf().encoder.getEncoderList()
    if sensor.getSelf().disabledEncoder is not None:
        classifier_encoder = sensor.getSelf().disabledEncoder.getEncoderList()
        classifier_encoder = classifier_encoder[0]
    else:

Example #2

File: run_tm_model_compare_sdr_cla_classifier.py Project: rhyolight/nupic.research

if __name__ == "__main__":

  (_options, _args) = _getArgs()
  dataSet = _options.dataSet
  plot = _options.plot
  noise = _options.noise
  print "Noise Amount: ", noise
  DATE_FORMAT, predictedField = getDateFormatAndPredictedField(dataSet)

  modelParams = getModelParamsFromName(dataSet)
  modelParams['modelParams']['clParams']['steps'] = str(_options.stepsAhead)


  # use customized CLA model
  print "Creating model from %s..." % dataSet
  model = CLAModel_custom(**modelParams['modelParams'])
  model.enableInference({"predictedField": predictedField})
  model.enableLearning()
  model._spLearningEnabled = True
  model._tpLearningEnabled = True

  printTPRegionParams(model._getTPRegion())

  inputData = "%s/%s.csv" % (DATA_DIR, dataSet.replace(" ", "_"))

  sensor = model._getSensorRegion()
  encoderList = sensor.getSelf().encoder.getEncoderList()
  if sensor.getSelf().disabledEncoder is not None:
    classifier_encoder = sensor.getSelf().disabledEncoder.getEncoderList()
    classifier_encoder = classifier_encoder[0]
  else:

Example #3

File: run_sp_tm_model.py Project: ywcui1990/nupic.research

  trainSP = bool(_options.trainSP)
  boostStrength = _options.boostStrength

  DATE_FORMAT = '%Y-%m-%d %H:%M:%S'
  predictedField = "passenger_count"

  modelParams = getModelParamsFromName("nyc_taxi")

  modelParams['modelParams']['clParams']['steps'] = str(_options.stepsAhead)
  modelParams['modelParams']['clParams']['regionName'] = classifierType
  modelParams['modelParams']['spParams']['boostStrength'] = boostStrength

  print "Creating model from %s..." % dataSet

  # use customized CLA model
  model = CLAModel_custom(**modelParams['modelParams'])
  model.enableInference({"predictedField": predictedField})
  model.enableLearning()
  model._spLearningEnabled = bool(trainSP)
  model._tpLearningEnabled = True

  print model._spLearningEnabled
  printTPRegionParams(model._getTPRegion())

  inputData = "%s/%s.csv" % (DATA_DIR, dataSet.replace(" ", "_"))

  sensor = model._getSensorRegion()
  encoderList = sensor.getSelf().encoder.getEncoderList()
  if sensor.getSelf().disabledEncoder is not None:
    classifier_encoder = sensor.getSelf().disabledEncoder.getEncoderList()
    classifier_encoder = classifier_encoder[0]

Example #4

File: run_model.py Project: chanceraine/nupic.research

  if dataSet == "rec-center-hourly":
    DATE_FORMAT = "%m/%d/%y %H:%M" # '7/2/10 0:00'
    predictedField = "kw_energy_consumption"
  elif dataSet == "nyc_taxi" or dataSet == "nyc_taxi_perturb":
    DATE_FORMAT = '%Y-%m-%d %H:%M:%S'
    predictedField = "passenger_count"
  else:
    raise RuntimeError("un recognized dataset")

  modelParams = getModelParamsFromName(dataSet)
  modelParams['modelParams']['clParams']['steps'] = str(_options.stepsAhead)

  print "Creating model from %s..." % dataSet

  # use customized CLA model
  model = CLAModel_custom(**modelParams['modelParams'])
  model.enableInference({"predictedField": predictedField})
  model.enableLearning()
  model._spLearningEnabled = True
  model._tpLearningEnabled = True

  printTPRegionParams(model._getTPRegion())

  inputData = "%s/%s.csv" % (DATA_DIR, dataSet.replace(" ", "_"))

  sensor = model._getSensorRegion()
  encoderList = sensor.getSelf().encoder.getEncoderList()
  if sensor.getSelf().disabledEncoder is not None:
    classifier_encoder = sensor.getSelf().disabledEncoder.getEncoderList()
    classifier_encoder = classifier_encoder[0]
  else: