Python RandomDistributedScalarEncoder.encodeIntoArray方法代码示例

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
 def testVerbosity(self):
     """
 Test that nothing is printed out when verbosity=0
 """
     _stdout = sys.stdout
     sys.stdout = _stringio = StringIO()
     encoder = RandomDistributedScalarEncoder(name="mv", resolution=1.0, verbosity=0)
     output = numpy.zeros(encoder.getWidth(), dtype=defaultDtype)
     encoder.encodeIntoArray(23.0, output)
     encoder.getBucketIndices(23.0)
     sys.stdout = _stdout
     self.assertEqual(len(_stringio.getvalue()), 0, "zero verbosity doesn't lead to zero output")

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
  def runSimpleSequence(self, resets, repetitions=1):
    scalarEncoder = RandomDistributedScalarEncoder(0.88, n=2048, w=41)

    instances = self._createInstances(cellsPerColumn=32)
    times = [0.0] * len(self.contestants)

    duration = 10000 * repetitions
    increment = 4
    sequenceLength = 25
    sequence = (i % (sequenceLength * 4)
                for i in xrange(0, duration * increment, increment))
    t = 0

    encodedValue = numpy.zeros(2048, dtype=numpy.int32)

    for value in sequence:
      scalarEncoder.encodeIntoArray(value, output=encodedValue)
      activeBits = encodedValue.nonzero()[0]

      for i in xrange(len(self.contestants)):
        tmInstance = instances[i]
        computeFn = self.contestants[i][2]

        if resets:
          if value == 0:
            tmInstance.reset()

        start = time.clock()
        computeFn(tmInstance, encodedValue, activeBits)
        times[i] += time.clock() - start

      printProgressBar(t, duration, 50)
      t += 1

    clearProgressBar(50)

    results = []
    for i in xrange(len(self.contestants)):
      name = self.contestants[i][3]
      results.append((name,
                      times[i],))

    return results

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
  def runHotgym(self, cellsPerColumn, repetitions=1):
    scalarEncoder = RandomDistributedScalarEncoder(0.88, n=2048, w=41)

    instances = self._createInstances(cellsPerColumn=cellsPerColumn)
    times = [0.0] * len(self.contestants)

    t = 0
    duration = HOTGYM_LENGTH * repetitions

    for _ in xrange(repetitions):
      with open(HOTGYM_PATH) as fin:
        reader = csv.reader(fin)
        reader.next()
        reader.next()
        reader.next()

        encodedValue = numpy.zeros(2048, dtype=numpy.uint32)

        for timeStr, valueStr in reader:
          value = float(valueStr)
          scalarEncoder.encodeIntoArray(value, output=encodedValue)
          activeBits = encodedValue.nonzero()[0]

          for i in xrange(len(self.contestants)):
            tmInstance = instances[i]
            computeFn = self.contestants[i][2]

            start = time.clock()
            computeFn(tmInstance, encodedValue, activeBits)
            times[i] += time.clock() - start

          printProgressBar(t, duration, 50)
          t += 1

    clearProgressBar(50)

    results = []
    for i in xrange(len(self.contestants)):
      name = self.contestants[i][3]
      results.append((name,
                      times[i],))

    return results

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]

#.........这里部分代码省略.........
      "cellsPerColumn": self.cellsPerColumn,
      "columnDimensions": (self.numColumns,),
      "initialPermanence": 0.24,
      "maxSegmentsPerCell": 128,
      "maxSynapsesPerSegment": 128,
      "minThreshold": 13,
      "maxNewSynapseCount": 31,
      "permanenceDecrement": 0.008,
      "permanenceIncrement": 0.04,
      "seed": 1960,
    }
    self.tm = TemporalMemory(**self.tmParams)

    # Sanity
    if self.runSanity:
      self.sanity = sanity.SPTMInstance(self.sp, self.tm)


  def handleRecord(self, scalarValue, label=None, skipEncoding=False,
                   learningMode=True):
    """Process one record."""

    if self.runSanity:
      self.sanity.waitForUserContinue()

    # Encode the input data record if it hasn't already been encoded.
    if not skipEncoding:
      self.encodeValue(scalarValue)

    # Run the encoded data through the spatial pooler
    self.sp.compute(self.encoderOutput, learningMode, self.spOutput)
    self.spOutputNZ = self.spOutput.nonzero()[0]

    # WARNING: this needs to happen here, before the TM runs.
    self.previouslyPredictiveCells = self.tm.getPredictiveCells()

    # Run SP output through temporal memory
    self.tm.compute(self.spOutputNZ)
    self.predictedActiveCells = _computePredictedActiveCells(
      self.tm.getActiveCells(), self.previouslyPredictiveCells)

    # Anomaly score
    self.anomalyScore = _computeAnomalyScore(self.spOutputNZ,
                                             self.previouslyPredictiveCells,
                                             self.cellsPerColumn)

    # Run Sanity
    if self.runSanity:
      self.sanity.appendTimestep(self.getEncoderOutputNZ(),
                                 self.getSpOutputNZ(),
                                 self.previouslyPredictiveCells,
                                 {
                                   'value': scalarValue,
                                   'label':label
                                   })


  def encodeValue(self, scalarValue):
    self.encoder.encodeIntoArray(scalarValue, self.encoderOutput)


  def getEncoderResolution(self):
    """
    Compute the Random Distributed Scalar Encoder (RDSE) resolution. It's 
    calculated from the data min and max, specific to the data stream.
    """
    if self.inputMin is None or self.inputMax is None:
      return self.defaultEncoderResolution
    else:
      rangePadding = abs(self.inputMax - self.inputMin) * 0.2
      minVal = self.inputMin - rangePadding
      maxVal = (self.inputMax + rangePadding
                if self.inputMin != self.inputMax
                else self.inputMin + 1)
      numBuckets = 130.0
      return max(self.defaultEncoderResolution, (maxVal - minVal) / numBuckets)


  def getEncoderOutputNZ(self):
    return self.encoderOutput.nonzero()[0]


  def getSpOutputNZ(self):
    return self.spOutputNZ


  def getTmPredictiveCellsNZ(self):
    return self.tm.getPredictiveCells()


  def getTmActiveCellsNZ(self):
    return self.tm.getActiveCells()


  def getTmPredictedActiveCellsNZ(self):
    return self.predictedActiveCells


  def getRawAnomalyScore(self):
    return self.anomalyScore

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
class NumentaTMLowLevelDetector(AnomalyDetector):
  """The 'numentaTM' detector, but not using the CLAModel or network API """
  def __init__(self, *args, **kwargs):
    super(NumentaTMLowLevelDetector, self).__init__(*args, **kwargs)

    self.valueEncoder = None
    self.encodedValue = None
    self.timestampEncoder = None
    self.encodedTimestamp = None
    self.sp = None
    self.spOutput = None
    self.tm = None
    self.anomalyLikelihood = None

    # Set this to False if you want to get results based on raw scores
    # without using AnomalyLikelihood. This will give worse results, but
    # useful for checking the efficacy of AnomalyLikelihood. You will need
    # to re-optimize the thresholds when running with this setting.
    self.useLikelihood = True


  def getAdditionalHeaders(self):
    """Returns a list of strings."""
    return ["raw_score"]


  def initialize(self):

    # Initialize the RDSE with a resolution; calculated from the data min and
    # max, the resolution is specific to the data stream.
    rangePadding = abs(self.inputMax - self.inputMin) * 0.2
    minVal = self.inputMin - rangePadding
    maxVal = (self.inputMax + rangePadding
              if self.inputMin != self.inputMax
              else self.inputMin + 1)
    numBuckets = 130.0
    resolution = max(0.001, (maxVal - minVal) / numBuckets)
    self.valueEncoder = RandomDistributedScalarEncoder(resolution, seed=42)
    self.encodedValue = np.zeros(self.valueEncoder.getWidth(),
                                 dtype=np.uint32)

    # Initialize the timestamp encoder
    self.timestampEncoder = DateEncoder(timeOfDay=(21, 9.49, ))
    self.encodedTimestamp = np.zeros(self.timestampEncoder.getWidth(),
                                     dtype=np.uint32)

    inputWidth = (self.timestampEncoder.getWidth() +
                  self.valueEncoder.getWidth())

    self.sp = SpatialPooler(**{
      "globalInhibition": True,
      "columnDimensions": [2048],
      "inputDimensions": [inputWidth],
      "potentialRadius": inputWidth,
      "numActiveColumnsPerInhArea": 40,
      "seed": 1956,
      "potentialPct": 0.8,
      "boostStrength": 0.0,
      "synPermActiveInc": 0.003,
      "synPermConnected": 0.2,
      "synPermInactiveDec": 0.0005,
    })
    self.spOutput = np.zeros(2048, dtype=np.float32)

    self.tm = TemporalMemory(**{
      "activationThreshold": 20,
      "cellsPerColumn": 32,
      "columnDimensions": (2048,),
      "initialPermanence": 0.24,
      "maxSegmentsPerCell": 128,
      "maxSynapsesPerSegment": 128,
      "minThreshold": 13,
      "maxNewSynapseCount": 31,
      "permanenceDecrement": 0.008,
      "permanenceIncrement": 0.04,
      "seed": 1960,
    })

    if self.useLikelihood:
      learningPeriod = math.floor(self.probationaryPeriod / 2.0)
      self.anomalyLikelihood = anomaly_likelihood.AnomalyLikelihood(
        claLearningPeriod=learningPeriod,
        estimationSamples=self.probationaryPeriod - learningPeriod,
        reestimationPeriod=100
      )


  def handleRecord(self, inputData):
    """Returns a tuple (anomalyScore, rawScore)."""

    # Encode the input data record
    self.valueEncoder.encodeIntoArray(
        inputData["value"], self.encodedValue)
    self.timestampEncoder.encodeIntoArray(
        inputData["timestamp"], self.encodedTimestamp)

    # Run the encoded data through the spatial pooler
    self.sp.compute(np.concatenate((self.encodedTimestamp,
                                    self.encodedValue,)),
                    True, self.spOutput)
#.........这里部分代码省略.........

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
def runHotgym(numRecords):
  with open(_PARAMS_PATH, "r") as f:
    modelParams = yaml.safe_load(f)["modelParams"]
    enParams = modelParams["sensorParams"]["encoders"]
    spParams = modelParams["spParams"]
    tmParams = modelParams["tmParams"]

  timeOfDayEncoder = DateEncoder(
    timeOfDay=enParams["timestamp_timeOfDay"]["timeOfDay"])
  weekendEncoder = DateEncoder(
    weekend=enParams["timestamp_weekend"]["weekend"])
  scalarEncoder = RandomDistributedScalarEncoder(
    enParams["consumption"]["resolution"])

  encodingWidth = (timeOfDayEncoder.getWidth()
                   + weekendEncoder.getWidth()
                   + scalarEncoder.getWidth())

  sp = SpatialPooler(
    inputDimensions=(encodingWidth,),
    columnDimensions=(spParams["columnCount"],),
    potentialPct=spParams["potentialPct"],
    potentialRadius=encodingWidth,
    globalInhibition=spParams["globalInhibition"],
    localAreaDensity=spParams["localAreaDensity"],
    numActiveColumnsPerInhArea=spParams["numActiveColumnsPerInhArea"],
    synPermInactiveDec=spParams["synPermInactiveDec"],
    synPermActiveInc=spParams["synPermActiveInc"],
    synPermConnected=spParams["synPermConnected"],
    boostStrength=spParams["boostStrength"],
    seed=spParams["seed"],
    wrapAround=True
  )

  tm = TemporalMemory(
    columnDimensions=(tmParams["columnCount"],),
    cellsPerColumn=tmParams["cellsPerColumn"],
    activationThreshold=tmParams["activationThreshold"],
    initialPermanence=tmParams["initialPerm"],
    connectedPermanence=spParams["synPermConnected"],
    minThreshold=tmParams["minThreshold"],
    maxNewSynapseCount=tmParams["newSynapseCount"],
    permanenceIncrement=tmParams["permanenceInc"],
    permanenceDecrement=tmParams["permanenceDec"],
    predictedSegmentDecrement=0.0,
    maxSegmentsPerCell=tmParams["maxSegmentsPerCell"],
    maxSynapsesPerSegment=tmParams["maxSynapsesPerSegment"],
    seed=tmParams["seed"]
  )

  classifier = SDRClassifierFactory.create()
  results = []
  with open(_INPUT_FILE_PATH, "r") as fin:
    reader = csv.reader(fin)
    headers = reader.next()
    reader.next()
    reader.next()

    for count, record in enumerate(reader):

      if count >= numRecords: break

      # Convert data string into Python date object.
      dateString = datetime.datetime.strptime(record[0], "%m/%d/%y %H:%M")
      # Convert data value string into float.
      consumption = float(record[1])

      # To encode, we need to provide zero-filled numpy arrays for the encoders
      # to populate.
      timeOfDayBits = numpy.zeros(timeOfDayEncoder.getWidth())
      weekendBits = numpy.zeros(weekendEncoder.getWidth())
      consumptionBits = numpy.zeros(scalarEncoder.getWidth())

      # Now we call the encoders to create bit representations for each value.
      timeOfDayEncoder.encodeIntoArray(dateString, timeOfDayBits)
      weekendEncoder.encodeIntoArray(dateString, weekendBits)
      scalarEncoder.encodeIntoArray(consumption, consumptionBits)

      # Concatenate all these encodings into one large encoding for Spatial
      # Pooling.
      encoding = numpy.concatenate(
        [timeOfDayBits, weekendBits, consumptionBits]
      )

      # Create an array to represent active columns, all initially zero. This
      # will be populated by the compute method below. It must have the same
      # dimensions as the Spatial Pooler.
      activeColumns = numpy.zeros(spParams["columnCount"])

      # Execute Spatial Pooling algorithm over input space.
      sp.compute(encoding, True, activeColumns)
      activeColumnIndices = numpy.nonzero(activeColumns)[0]

      # Execute Temporal Memory algorithm over active mini-columns.
      tm.compute(activeColumnIndices, learn=True)

      activeCells = tm.getActiveCells()

      # Get the bucket info for this input value for classification.
      bucketIdx = scalarEncoder.getBucketIndices(consumption)[0]
#.........这里部分代码省略.........

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
class DistalTimestamps1CellPerColumnDetector(AnomalyDetector):
  """The 'numenta' detector, with the following changes:

  - Use pure Temporal Memory, not the classic TP that uses backtracking.
  - Don't spatial pool the timestamp. Pass it in as distal input.
  - 1 cell per column.
  - Use w=41 in the scalar encoding, rather than w=21, to make up for the
    lost timestamp input to the spatial pooler.
  """
  def __init__(self, *args, **kwargs):
    super(DistalTimestamps1CellPerColumnDetector, self).__init__(*args,
                                                                 **kwargs)

    self.valueEncoder = None
    self.encodedValue = None
    self.timestampEncoder = None
    self.encodedTimestamp = None
    self.activeExternalCells = []
    self.prevActiveExternalCells = []
    self.sp = None
    self.spOutput = None
    self.etm = None
    self.anomalyLikelihood = None


  def getAdditionalHeaders(self):
    """Returns a list of strings."""
    return ["raw_score"]


  def initialize(self):
    rangePadding = abs(self.inputMax - self.inputMin) * 0.2
    minVal = self.inputMin - rangePadding
    maxVal = (self.inputMax + rangePadding
              if self.inputMin != self.inputMax
              else self.inputMin + 1)
    numBuckets = 130.0
    resolution = max(0.001, (maxVal - minVal) / numBuckets)
    self.valueEncoder = RandomDistributedScalarEncoder(resolution,
                                                       w=41,
                                                       seed=42)
    self.encodedValue = np.zeros(self.valueEncoder.getWidth(),
                                 dtype=np.uint32)

    self.timestampEncoder = DateEncoder(timeOfDay=(21,9.49,))
    self.encodedTimestamp = np.zeros(self.timestampEncoder.getWidth(),
                                     dtype=np.uint32)

    inputWidth = self.valueEncoder.getWidth()

    self.sp = SpatialPooler(**{
      "globalInhibition": True,
      "columnDimensions": [2048],
      "inputDimensions": [inputWidth],
      "potentialRadius": inputWidth,
      "numActiveColumnsPerInhArea": 40,
      "seed": 1956,
      "potentialPct": 0.8,
      "boostStrength": 0.0,
      "synPermActiveInc": 0.003,
      "synPermConnected": 0.2,
      "synPermInactiveDec": 0.0005,
    })
    self.spOutput = np.zeros(2048, dtype=np.float32)

    self.etm = ExtendedTemporalMemory(**{
      "activationThreshold": 13,
      "cellsPerColumn": 1,
      "columnDimensions": (2048,),
      "basalInputDimensions": (self.timestampEncoder.getWidth(),),
      "initialPermanence": 0.21,
      "maxSegmentsPerCell": 128,
      "maxSynapsesPerSegment": 32,
      "minThreshold": 10,
      "maxNewSynapseCount": 20,
      "permanenceDecrement": 0.1,
      "permanenceIncrement": 0.1,
      "seed": 1960,
      "checkInputs": False,
    })

    learningPeriod = math.floor(self.probationaryPeriod / 2.0)
    self.anomalyLikelihood = anomaly_likelihood.AnomalyLikelihood(
      claLearningPeriod=learningPeriod,
      estimationSamples=self.probationaryPeriod - learningPeriod,
      reestimationPeriod=100
    )


  def handleRecord(self, inputData):
    """Returns a tuple (anomalyScore, rawScore)."""

    self.valueEncoder.encodeIntoArray(inputData["value"],
                                      self.encodedValue)

    self.timestampEncoder.encodeIntoArray(inputData["timestamp"],
                                          self.encodedTimestamp)
    self.prevActiveExternalCells = self.activeExternalCells
    self.activeExternalCells = self.encodedTimestamp.nonzero()[0]

#.........这里部分代码省略.........

# 需要导入模块: from nupic.encoders.random_distributed_scalar import RandomDistributedScalarEncoder [as 别名]
# 或者: from nupic.encoders.random_distributed_scalar.RandomDistributedScalarEncoder import encodeIntoArray [as 别名]
def runHotgym(numRecords):
  with open(_PARAMS_PATH, "r") as f:
    modelParams = yaml.safe_load(f)["modelParams"]
    enParams = modelParams["sensorParams"]["encoders"]
    spParams = modelParams["spParams"]
    tmParams = modelParams["tmParams"]

  timeOfDayEncoder = DateEncoder(
    timeOfDay=enParams["timestamp_timeOfDay"]["timeOfDay"])
  weekendEncoder = DateEncoder(
    weekend=enParams["timestamp_weekend"]["weekend"])
  scalarEncoder = RandomDistributedScalarEncoder(
    enParams["consumption"]["resolution"])

  encodingWidth = (timeOfDayEncoder.getWidth()
                   + weekendEncoder.getWidth()
                   + scalarEncoder.getWidth())

  sp = SpatialPooler(
    # How large the input encoding will be.
    inputDimensions=(encodingWidth),
    # How many mini-columns will be in the Spatial Pooler.
    columnDimensions=(spParams["columnCount"]),
    # What percent of the columns"s receptive field is available for potential
    # synapses?
    potentialPct=spParams["potentialPct"],
    # This means that the input space has no topology.
    globalInhibition=spParams["globalInhibition"],
    localAreaDensity=spParams["localAreaDensity"],
    # Roughly 2%, giving that there is only one inhibition area because we have
    # turned on globalInhibition (40 / 2048 = 0.0195)
    numActiveColumnsPerInhArea=spParams["numActiveColumnsPerInhArea"],
    # How quickly synapses grow and degrade.
    synPermInactiveDec=spParams["synPermInactiveDec"],
    synPermActiveInc=spParams["synPermActiveInc"],
    synPermConnected=spParams["synPermConnected"],
    # boostStrength controls the strength of boosting. Boosting encourages
    # efficient usage of SP columns.
    boostStrength=spParams["boostStrength"],
    # Random number generator seed.
    seed=spParams["seed"],
    # TODO: is this useful?
    # Determines if inputs at the beginning and end of an input dimension should
    # be considered neighbors when mapping columns to inputs.
    wrapAround=False
  )

  tm = TemporalMemory(
    # Must be the same dimensions as the SP
    columnDimensions=(tmParams["columnCount"],),
    # How many cells in each mini-column.
    cellsPerColumn=tmParams["cellsPerColumn"],
    # A segment is active if it has >= activationThreshold connected synapses
    # that are active due to infActiveState
    activationThreshold=tmParams["activationThreshold"],
    initialPermanence=tmParams["initialPerm"],
    # TODO: This comes from the SP params, is this normal
    connectedPermanence=spParams["synPermConnected"],
    # Minimum number of active synapses for a segment to be considered during
    # search for the best-matching segments.
    minThreshold=tmParams["minThreshold"],
    # The max number of synapses added to a segment during learning
    maxNewSynapseCount=tmParams["newSynapseCount"],
    permanenceIncrement=tmParams["permanenceInc"],
    permanenceDecrement=tmParams["permanenceDec"],
    predictedSegmentDecrement=0.0,
    maxSegmentsPerCell=tmParams["maxSegmentsPerCell"],
    maxSynapsesPerSegment=tmParams["maxSynapsesPerSegment"],
    seed=tmParams["seed"]
  )

  classifier = SDRClassifierFactory.create()
  results = []
  with open(_INPUT_FILE_PATH, "r") as fin:
    reader = csv.reader(fin)
    headers = reader.next()
    reader.next()
    reader.next()

    for count, record in enumerate(reader):

      if count >= numRecords: break

      # Convert data string into Python date object.
      dateString = datetime.datetime.strptime(record[0], "%m/%d/%y %H:%M")
      # Convert data value string into float.
      consumption = float(record[1])

      # To encode, we need to provide zero-filled numpy arrays for the encoders
      # to populate.
      timeOfDayBits = numpy.zeros(timeOfDayEncoder.getWidth())
      weekendBits = numpy.zeros(weekendEncoder.getWidth())
      consumptionBits = numpy.zeros(scalarEncoder.getWidth())

      # Now we call the encoders create bit representations for each value.
      timeOfDayEncoder.encodeIntoArray(dateString, timeOfDayBits)
      weekendEncoder.encodeIntoArray(dateString, weekendBits)
      scalarEncoder.encodeIntoArray(consumption, consumptionBits)

      # Concatenate all these encodings into one large encoding for Spatial
#.........这里部分代码省略.........