def testMapBucketIndexToNonZeroBits(self):
"""
Test that mapBucketIndexToNonZeroBits works and that max buckets and
clipping are handled properly.
"""
enc = RandomDistributedScalarEncoder(resolution=1.0, w=11, n=150)
# Set a low number of max buckets
enc._initializeBucketMap(10, None)
enc.encode(0.0)
enc.encode(-7.0)
enc.encode(7.0)
self.assertEqual(len(enc.bucketMap), enc._maxBuckets,
"_maxBuckets exceeded")
self.assertTrue(
(enc.mapBucketIndexToNonZeroBits(-1) == enc.bucketMap[0]).all(),
"mapBucketIndexToNonZeroBits did not handle negative index")
self.assertTrue(
(enc.mapBucketIndexToNonZeroBits(1000) == enc.bucketMap[9]).all(),
"mapBucketIndexToNonZeroBits did not handle negative index")
e23 = enc.encode(23.0)
e6 = enc.encode(6)
self.assertEqual((e23 == e6).sum(), enc.getWidth(),
"Values not clipped correctly during encoding")
e_8 = enc.encode(-8)
e_7 = enc.encode(-7)
self.assertEqual((e_8 == e_7).sum(), enc.getWidth(),
"Values not clipped correctly during encoding")
self.assertEqual(enc.getBucketIndices(-8)[0], 0,
"getBucketIndices returned negative bucket index")
self.assertEqual(enc.getBucketIndices(23)[0], enc._maxBuckets-1,
"getBucketIndices returned bucket index that is too large")
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")
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")
def testEncoding(self):
"""
Test basic encoding functionality. Create encodings without crashing and
check they contain the correct number of on and off bits. Check some
encodings for expected overlap. Test that encodings for old values don't
change once we generate new buckets.
"""
# Initialize with non-default parameters and encode with a number close to
# the offset
encoder = RandomDistributedScalarEncoder(name="encoder",
resolution=1.0,
w=23,
n=500,
offset=0.0)
e0 = encoder.encode(-0.1)
self.assertEqual(e0.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e0.size, 500, "Width of the vector is incorrect")
self.assertEqual(
encoder.getBucketIndices(0.0)[0], encoder._maxBuckets / 2,
"Offset doesn't correspond to middle bucket")
self.assertEqual(len(encoder.bucketMap), 1,
"Number of buckets is not 1")
# Encode with a number that is resolution away from offset. Now we should
# have two buckets and this encoding should be one bit away from e0
e1 = encoder.encode(1.0)
self.assertEqual(len(encoder.bucketMap), 2,
"Number of buckets is not 2")
self.assertEqual(e1.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e1.size, 500, "Width of the vector is incorrect")
self.assertEqual(computeOverlap(e0, e1), 22,
"Overlap is not equal to w-1")
# Encode with a number that is resolution*w away from offset. Now we should
# have many buckets and this encoding should have very little overlap with
# e0
e25 = encoder.encode(25.0)
self.assertGreater(len(encoder.bucketMap), 23,
"Number of buckets is not 2")
self.assertEqual(e25.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e25.size, 500, "Width of the vector is incorrect")
self.assertLess(computeOverlap(e0, e25), 4, "Overlap is too high")
# Test encoding consistency. The encodings for previous numbers
# shouldn't change even though we have added additional buckets
self.assertTrue(
numpy.array_equal(e0, encoder.encode(-0.1)),
"Encodings are not consistent - they have changed after new buckets "
"have been created")
self.assertTrue(
numpy.array_equal(e1, encoder.encode(1.0)),
"Encodings are not consistent - they have changed after new buckets "
"have been created")
def testMapBucketIndexToNonZeroBits(self):
"""
Test that mapBucketIndexToNonZeroBits works and that max buckets and
clipping are handled properly.
"""
encoder = RandomDistributedScalarEncoder(resolution=1.0, w=11, n=150)
# Set a low number of max buckets
encoder._initializeBucketMap(10, None)
encoder.encode(0.0)
encoder.encode(-7.0)
encoder.encode(7.0)
self.assertEqual(len(encoder.bucketMap), encoder._maxBuckets,
"_maxBuckets exceeded")
self.assertTrue(
numpy.array_equal(encoder.mapBucketIndexToNonZeroBits(-1),
encoder.bucketMap[0]),
"mapBucketIndexToNonZeroBits did not handle negative"
" index")
self.assertTrue(
numpy.array_equal(encoder.mapBucketIndexToNonZeroBits(1000),
encoder.bucketMap[9]),
"mapBucketIndexToNonZeroBits did not handle negative index")
e23 = encoder.encode(23.0)
e6 = encoder.encode(6)
self.assertEqual((e23 == e6).sum(), encoder.getWidth(),
"Values not clipped correctly during encoding")
ep8 = encoder.encode(-8)
ep7 = encoder.encode(-7)
self.assertEqual((ep8 == ep7).sum(), encoder.getWidth(),
"Values not clipped correctly during encoding")
self.assertEqual(
encoder.getBucketIndices(-8)[0], 0,
"getBucketIndices returned negative bucket index")
self.assertEqual(
encoder.getBucketIndices(23)[0], encoder._maxBuckets - 1,
"getBucketIndices returned bucket index that is too"
" large")
def testEncoding(self):
"""
Test basic encoding functionality. Create encodings without crashing and
check they contain the correct number of on and off bits. Check some
encodings for expected overlap. Test that encodings for old values don't
change once we generate new buckets.
"""
# Initialize with non-default parameters and encode with a number close to
# the offset
enc = RandomDistributedScalarEncoder(name='enc', resolution=1.0, w=23,
n=500, offset = 0.0)
e0 = enc.encode(-0.1)
self.assertEqual(e0.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e0.size, 500, "Width of the vector is incorrect")
self.assertEqual(enc.getBucketIndices(0.0)[0], enc._maxBuckets / 2,
"Offset doesn't correspond to middle bucket")
self.assertEqual(len(enc.bucketMap), 1, "Number of buckets is not 1")
# Encode with a number that is resolution away from offset. Now we should
# have two buckets and this encoding should be one bit away from e0
e1 = enc.encode(1.0)
self.assertEqual(len(enc.bucketMap), 2, "Number of buckets is not 2")
self.assertEqual(e1.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e1.size, 500, "Width of the vector is incorrect")
self.assertEqual(computeOverlap(e0, e1), 22,
"Overlap is not equal to w-1")
# Encode with a number that is resolution*w away from offset. Now we should
# have many buckets and this encoding should have very little overlap with
# e0
e25 = enc.encode(25.0)
self.assertGreater(len(enc.bucketMap), 23, "Number of buckets is not 2")
self.assertEqual(e25.sum(), 23, "Number of on bits is incorrect")
self.assertEqual(e25.size, 500, "Width of the vector is incorrect")
self.assertLess(computeOverlap(e0, e25), 4,
"Overlap is too high")
# Test encoding consistency. The encodings for previous numbers
# shouldn't change even though we have added additional buckets
self.assertEqual((e0 == enc.encode(-0.1)).sum(), 500,
"Encodings are not consistent - they have changed after new buckets "
"have been created")
self.assertEqual((e1 == enc.encode(1.0)).sum(), 500,
"Encodings are not consistent - they have changed after new buckets "
"have been created")
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"]
scalarEncoder = RandomDistributedScalarEncoder(
enParams["consumption"]["resolution"])
scalarEncoder2 = RandomDistributedScalarEncoder(
enParams["consumption2"]["resolution"])
encodingWidth = (scalarEncoder.getWidth() + scalarEncoder2.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()
output = output_anomaly_generic_v1.NuPICFileOutput(_FILE_NAME)
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.
prediction = float(record[1])
prediction2 = float(record[2])
# To encode, we need to provide zero-filled numpy arrays for the encoders
# to populate.
consumptionBits = numpy.zeros(scalarEncoder.getWidth())
consumptionBits2 = numpy.zeros(scalarEncoder2.getWidth())
# Now we call the encoders to create bit representations for each value.
scalarEncoder.encodeIntoArray(prediction, consumptionBits)
scalarEncoder2.encodeIntoArray(prediction2, consumptionBits2)
# Concatenate all these encodings into one large encoding for Spatial
# Pooling.
encoding = numpy.concatenate([consumptionBits, consumptionBits2])
# 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(prediction)[0]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": prediction
},
learn=True,
infer=True)
# Print the best prediction for 1 step out.
oneStepConfidence, oneStep = sorted(zip(
classifierResult[1], classifierResult["actualValues"]),
reverse=True)[0]
# print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
# results.append([oneStep, oneStepConfidence * 100, None, None])
results.append(
[record[0], prediction, oneStep, oneStepConfidence * 100])
output.write(record[0], prediction, oneStep,
oneStepConfidence * 100)
output.close()
return results
def runHotgym():
timeOfDayEncoder = DateEncoder(timeOfDay=(21,1))
weekendEncoder = DateEncoder(weekend=21)
scalarEncoder = RandomDistributedScalarEncoder(0.88)
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=(2048),
# What percent of the columns's receptive field is available for potential
# synapses?
potentialPct=0.85,
# This means that the input space has no topology.
globalInhibition=True,
localAreaDensity=-1.0,
# Roughly 2%, giving that there is only one inhibition area because we have
# turned on globalInhibition (40 / 2048 = 0.0195)
numActiveColumnsPerInhArea=40.0,
# How quickly synapses grow and degrade.
synPermInactiveDec=0.005,
synPermActiveInc=0.04,
synPermConnected=0.1,
# boostStrength controls the strength of boosting. Boosting encourages
# efficient usage of SP columns.
boostStrength=3.0,
# Random number generator seed.
seed=1956,
# 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=(2048, ),
# How many cells in each mini-column.
cellsPerColumn=32,
# A segment is active if it has >= activationThreshold connected synapses
# that are active due to infActiveState
activationThreshold=16,
initialPermanence=0.21,
connectedPermanence=0.5,
# Minimum number of active synapses for a segment to be considered during
# search for the best-matching segments.
minThreshold=12,
# The max number of synapses added to a segment during learning
maxNewSynapseCount=20,
permanenceIncrement=0.1,
permanenceDecrement=0.1,
predictedSegmentDecrement=0.0,
maxSegmentsPerCell=128,
maxSynapsesPerSegment=32,
seed=1960
)
classifier = SDRClassifierFactory.create()
with open (_INPUT_FILE_PATH) as fin:
reader = csv.reader(fin)
headers = reader.next()
reader.next()
reader.next()
for count, record in enumerate(reader):
# 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
# 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(2048)
# 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]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(
recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": consumption
},
learn=True,
infer=True
)
# Print the best prediction for 1 step out.
probability, value = sorted(
zip(classifierResult[1], classifierResult["actualValues"]),
reverse=True
)[0]
print("1-step: {:16} ({:4.4}%)".format(value, probability * 100))
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
# 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]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(
recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": consumption
},
learn=True,
infer=True
)
# Print the best prediction for 1 step out.
oneStepConfidence, oneStep = sorted(
zip(classifierResult[1], classifierResult["actualValues"]),
reverse=True
)[0]
print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
results.append([oneStep, oneStepConfidence * 100, None, None])
return results
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]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(
recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": consumption
},
learn=True,
infer=True
)
# Print the best prediction for 1 step out.
oneStepConfidence, oneStep = sorted(
zip(classifierResult[1], classifierResult["actualValues"]),
reverse=True
)[0]
print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
results.append([oneStep, oneStepConfidence * 100, None, None])
return results
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"])
CtEncoder = RandomDistributedScalarEncoder(enParams["Ct"]["resolution"])
ZIP_10467Encoder = RandomDistributedScalarEncoder(
enParams["ZIP_10467"]["resolution"])
# ZIP_10462Encoder = RandomDistributedScalarEncoder(enParams["ZIP_10462"]["resolution"])
# ZIP_10475Encoder = RandomDistributedScalarEncoder(enParams["ZIP_10475"]["resolution"])
# ZIP_10466Encoder = RandomDistributedScalarEncoder(enParams["ZIP_10466"]["resolution"])
# ZIP_10469Encoder = RandomDistributedScalarEncoder(enParams["ZIP_10469"]["resolution"])
# DEPT_11Encoder = RandomDistributedScalarEncoder(enParams["DEPT_11"]["resolution"])
# DEPT_24Encoder = RandomDistributedScalarEncoder(enParams["DEPT_24"]["resolution"])
# DEPT_41Encoder = RandomDistributedScalarEncoder(enParams["DEPT_41"]["resolution"])
# DEPT_34Encoder = RandomDistributedScalarEncoder(enParams["DEPT_34"]["resolution"])
# DEPT_31Encoder = RandomDistributedScalarEncoder(enParams["DEPT_31"]["resolution"])
# DEPT_60Encoder = RandomDistributedScalarEncoder(enParams["DEPT_60"]["resolution"])
# AGE_0_9Encoder = RandomDistributedScalarEncoder(enParams["AGE_0_9"]["resolution"])
# AGE_10_19Encoder = RandomDistributedScalarEncoder(enParams["AGE_10_19"]["resolution"])
# AGE_20_29Encoder = RandomDistributedScalarEncoder(enParams["AGE_20_29"]["resolution"])
# AGE_30_39Encoder = RandomDistributedScalarEncoder(enParams["AGE_30_39"]["resolution"])
# AGE_40_49Encoder = RandomDistributedScalarEncoder(enParams["AGE_40_49"]["resolution"])
# AGE_50_59Encoder = RandomDistributedScalarEncoder(enParams["AGE_50_59"]["resolution"])
# AGE_60_69Encoder = RandomDistributedScalarEncoder(enParams["AGE_60_69"]["resolution"])
# AGE_70_79Encoder = RandomDistributedScalarEncoder(enParams["AGE_70_79"]["resolution"])
# AGE_80_89Encoder = RandomDistributedScalarEncoder(enParams["AGE_80_89"]["resolution"])
# AGE_90_99Encoder = RandomDistributedScalarEncoder(enParams["AGE_90_99"]["resolution"])
# DIST_1_7Encoder = RandomDistributedScalarEncoder(enParams["DIST_1_7"]["resolution"])
# DIST_8_14Encoder = RandomDistributedScalarEncoder(enParams["DIST_8_14"]["resolution"])
# DIST_15_21Encoder = RandomDistributedScalarEncoder(enParams["DIST_15_21"]["resolution"])
# DIST_22_28Encoder = RandomDistributedScalarEncoder(enParams["DIST_22_28"]["resolution"])
# DIST_29_35Encoder = RandomDistributedScalarEncoder(enParams["DIST_29_35"]["resolution"])
# DIST_36_42Encoder = RandomDistributedScalarEncoder(enParams["DIST_36_42"]["resolution"])
# DIST_43_49Encoder = RandomDistributedScalarEncoder(enParams["DIST_43_49"]["resolution"])
# DIST_50_56Encoder = RandomDistributedScalarEncoder(enParams["DIST_50_56"]["resolution"])
# DIST_57_63Encoder = RandomDistributedScalarEncoder(enParams["DIST_57_63"]["resolution"])
# DIST_64_70Encoder = RandomDistributedScalarEncoder(enParams["DIST_64_70"]["resolution"])
encodingWidth = (timeOfDayEncoder.getWidth() + weekendEncoder.getWidth() +
CtEncoder.getWidth() * 2)
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()
output = output_anomaly_generic_v1.NuPICFileOutput(_FILE_NAME)
for count, record in enumerate(reader):
if count >= numRecords: break
# Convert data string into Python date object.
dateString = datetime.datetime.strptime(record[0],
"%Y-%m-%d %H:%M:%S")
# Convert data value string into float.
Ct = float(record[1])
ZIP_10467 = float(record[2])
# ZIP_10462 = float(record[3])
# ZIP_10475 = float(record[4])
# ZIP_10466 = float(record[5])
# ZIP_10469 = float(record[6])
# DEPT_11 = float(record[7])
# DEPT_24 = float(record[8])
# DEPT_41 = float(record[9])
# DEPT_34 = float(record[10])
# DEPT_31 = float(record[11])
# DEPT_60 = float(record[12])
# AGE_0_9 = float(record[13])
# AGE_10_19 = float(record[14])
# AGE_20_29 = float(record[15])
# AGE_30_39 = float(record[16])
# AGE_40_49 = float(record[17])
# AGE_50_59 = float(record[18])
# AGE_60_69 = float(record[19])
# AGE_70_79 = float(record[20])
# AGE_80_89 = float(record[21])
# AGE_90_99 = float(record[22])
# DIST_1_7 = float(record[23])
# DIST_8_14 = float(record[24])
# DIST_15_21 = float(record[25])
# DIST_22_28 = float(record[26])
# DIST_29_35 = float(record[27])
# DIST_36_42 = float(record[28])
# DIST_43_49 = float(record[29])
# DIST_50_56 = float(record[30])
# DIST_57_63 = float(record[31])
# DIST_64_70 = float(record[31])
# 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())
CtBits = numpy.zeros(CtEncoder.getWidth())
ZIP_10467Bits = numpy.zeros(ZIP_10467Encoder.getWidth())
# ZIP_10462Bits = numpy.zeros(ZIP_10462Encoder.getWidth())
# ZIP_10475Bits = numpy.zeros(ZIP_10475Encoder.getWidth())
# ZIP_10466Bits = numpy.zeros(ZIP_10466Encoder.getWidth())
# ZIP_10469Bits = numpy.zeros(ZIP_10469Encoder.getWidth())
# DEPT_11Bits = numpy.zeros(DEPT_11Encoder.getWidth())
# DEPT_24Bits = numpy.zeros(DEPT_24Encoder.getWidth())
# DEPT_41Bits = numpy.zeros(DEPT_41Encoder.getWidth())
# DEPT_34Bits = numpy.zeros(DEPT_34Encoder.getWidth())
# DEPT_31Bits = numpy.zeros(DEPT_31Encoder.getWidth())
# DEPT_60Bits = numpy.zeros(DEPT_60Encoder.getWidth())
# AGE_0_9Bits = numpy.zeros(AGE_0_9Encoder.getWidth())
# AGE_10_19Bits = numpy.zeros(AGE_10_19Encoder.getWidth())
# AGE_20_29Bits = numpy.zeros(AGE_20_29Encoder.getWidth())
# AGE_30_39Bits = numpy.zeros(AGE_30_39Encoder.getWidth())
# AGE_40_49Bits = numpy.zeros(AGE_40_49Encoder.getWidth())
# AGE_50_59Bits = numpy.zeros(AGE_50_59Encoder.getWidth())
# AGE_60_69Bits = numpy.zeros(AGE_60_69Encoder.getWidth())
# AGE_70_79Bits = numpy.zeros(AGE_70_79Encoder.getWidth())
# AGE_80_89Bits = numpy.zeros(AGE_80_89Encoder.getWidth())
# AGE_90_99Bits = numpy.zeros(AGE_90_99Encoder.getWidth())
# DIST_1_7Bits = numpy.zeros(DIST_1_7Encoder.getWidth())
# DIST_8_14Bits = numpy.zeros(DIST_8_14Encoder.getWidth())
# DIST_15_21Bits = numpy.zeros(DIST_15_21Encoder.getWidth())
# DIST_22_28Bits = numpy.zeros(DIST_22_28Encoder.getWidth())
# DIST_29_35Bits = numpy.zeros(DIST_29_35Encoder.getWidth())
# DIST_36_42Bits = numpy.zeros(DIST_36_42Encoder.getWidth())
# DIST_43_49Bits = numpy.zeros(DIST_43_49Encoder.getWidth())
# DIST_50_56Bits = numpy.zeros(DIST_50_56Encoder.getWidth())
# DIST_57_63Bits = numpy.zeros(DIST_57_63Encoder.getWidth())
# DIST_64_70Bits = numpy.zeros(DIST_64_70Encoder.getWidth())
# Now we call the encoders to create bit representations for each value.
timeOfDayEncoder.encodeIntoArray(dateString, timeOfDayBits)
weekendEncoder.encodeIntoArray(dateString, weekendBits)
CtEncoder.encodeIntoArray(Ct, CtBits)
ZIP_10467Encoder.encodeIntoArray(ZIP_10467, ZIP_10467Bits)
# ZIP_10462Encoder.encodeIntoArray(ZIP_10462, ZIP_10462Bits)
# ZIP_10475Encoder.encodeIntoArray(ZIP_10475, ZIP_10475Bits)
# ZIP_10466Encoder.encodeIntoArray(ZIP_10466, ZIP_10466Bits)
# ZIP_10469Encoder.encodeIntoArray(ZIP_10469, ZIP_10469Bits)
# DEPT_11Encoder.encodeIntoArray(DEPT_11, DEPT_11Bits)
# DEPT_24Encoder.encodeIntoArray(DEPT_24, DEPT_24Bits)
# DEPT_41Encoder.encodeIntoArray(DEPT_41, DEPT_41Bits)
# DEPT_34Encoder.encodeIntoArray(DEPT_34, DEPT_34Bits)
# DEPT_31Encoder.encodeIntoArray(DEPT_31, DEPT_31Bits)
# DEPT_60Encoder.encodeIntoArray(DEPT_60, DEPT_60Bits)
# AGE_0_9Encoder.encodeIntoArray(AGE_0_9, AGE_0_9Bits)
# AGE_10_19Encoder.encodeIntoArray(AGE_10_19, AGE_10_19Bits)
# AGE_20_29Encoder.encodeIntoArray(AGE_20_29, AGE_20_29Bits)
# AGE_30_39Encoder.encodeIntoArray(AGE_30_39, AGE_30_39Bits)
# AGE_40_49Encoder.encodeIntoArray(AGE_40_49, AGE_40_49Bits)
# AGE_50_59Encoder.encodeIntoArray(AGE_50_59, AGE_50_59Bits)
# AGE_60_69Encoder.encodeIntoArray(AGE_60_69, AGE_60_69Bits)
# AGE_70_79Encoder.encodeIntoArray(AGE_70_79, AGE_70_79Bits)
# AGE_80_89Encoder.encodeIntoArray(AGE_80_89, AGE_80_89Bits)
# AGE_90_99Encoder.encodeIntoArray(AGE_90_99, AGE_90_99Bits)
# DIST_1_7Encoder.encodeIntoArray(DIST_1_7, DIST_1_7Bits)
# DIST_8_14Encoder.encodeIntoArray(DIST_8_14, DIST_8_14Bits)
# DIST_15_21Encoder.encodeIntoArray(DIST_15_21, DIST_15_21Bits)
# DIST_22_28Encoder.encodeIntoArray(DIST_22_28, DIST_22_28Bits)
# DIST_29_35Encoder.encodeIntoArray(DIST_29_35, DIST_29_35Bits)
# DIST_36_42Encoder.encodeIntoArray(DIST_36_42, DIST_36_42Bits)
# DIST_43_49Encoder.encodeIntoArray(DIST_43_49, DIST_43_49Bits)
# DIST_50_56Encoder.encodeIntoArray(DIST_50_56, DIST_50_56Bits)
# DIST_57_63Encoder.encodeIntoArray(DIST_57_63, DIST_57_63Bits)
# DIST_64_70Encoder.encodeIntoArray(DIST_64_70, DIST_64_70Bits)
# Concatenate all these encodings into one large encoding for Spatial
# Pooling.
encoding = numpy.concatenate(
[timeOfDayBits, weekendBits, CtBits, ZIP_10467Bits])
# encoding = numpy.concatenate(
# [timeOfDayBits, weekendBits, CtBits,
# ZIP_10467Bits, ZIP_10462Bits, ZIP_10475Bits, ZIP_10466Bits, ZIP_10469Bits,
# DEPT_11Bits, DEPT_24Bits, DEPT_41Bits, DEPT_34Bits, DEPT_31Bits,
# DEPT_60Bits, AGE_0_9Bits, AGE_10_19Bits, AGE_20_29Bits, AGE_30_39Bits,
# AGE_40_49Bits, AGE_50_59Bits, AGE_60_69Bits, AGE_70_79Bits, AGE_80_89Bits,
# AGE_90_99Bits, DIST_1_7Bits, DIST_8_14Bits, DIST_15_21Bits, DIST_22_28Bits,
# DIST_29_35Bits, DIST_36_42Bits, DIST_43_49Bits, DIST_50_56Bits, DIST_57_63Bits,
# DIST_64_70Bits])
# 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 = CtEncoder.getBucketIndices(Ct)[0]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": Ct
},
learn=True,
infer=True)
# Print the best prediction for 1 step out.
oneStepConfidence, oneStep = sorted(zip(
classifierResult[1], classifierResult["actualValues"]),
reverse=True)[0]
# print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
# results.append([oneStep, oneStepConfidence * 100, None, None])
results.append([record[0], Ct, oneStep, oneStepConfidence * 100])
output.write(record[0], Ct, oneStep, oneStepConfidence * 100)
output.close()
return results
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
# 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]
# Run classifier to translate active cells back to scalar value.
classifierResult = classifier.compute(
recordNum=count,
patternNZ=activeCells,
classification={
"bucketIdx": bucketIdx,
"actValue": consumption
},
learn=True,
infer=True
)
# Print the best prediction for 1 step out.
oneStepConfidence, oneStep = sorted(
zip(classifierResult[1], classifierResult["actualValues"]),
reverse=True
)[0]
print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
results.append([oneStep, oneStepConfidence * 100, None, None])
return results