def testErrorChecks(self):
params1 = RDSE_Parameters()
params1.size = 100
params1.sparsity = .10
params1.radius = 10
R1 = RDSE(params1)
A = SDR([10, 10])
R1.encode(33, A)
# Test wrong input dimensions
B = SDR(1)
with self.assertRaises(RuntimeError):
R1.encode(3, B)
# Test invalid parameters, size == 0
params1.size = 0
with self.assertRaises(RuntimeError):
RDSE(params1)
params1.size = 100
# Test invalid parameters, activeBits == 0
params1.activeBits = 0
params1.sparsity = 0.00001 # Rounds to zero!
with self.assertRaises(RuntimeError):
RDSE(params1)
# Test missing activeBits
params2 = RDSE_Parameters()
params2.size = 100
params2.radius = 10
with self.assertRaises(RuntimeError):
RDSE(params2)
# Test missing resolution/radius
params3 = RDSE_Parameters()
params3.size = 100
params3.activeBits = 10
with self.assertRaises(RuntimeError):
RDSE(params3)
# Test too many parameters: activeBits & sparsity
params4 = RDSE_Parameters()
params4.size = 100
params4.sparsity = .6
params4.activeBits = 10
params4.radius = 4
with self.assertRaises(RuntimeError):
RDSE(params4)
# Test too many parameters: resolution & radius
params5 = RDSE_Parameters()
params5.size = 100
params5.activeBits = 10
params5.radius = 4
params5.resolution = 4
with self.assertRaises(RuntimeError):
RDSE(params5)
def testRandomOverlap(self):
""" Verify that distant values have little to no semantic similarity.
Also measure sparsity & activation frequency. """
P = RDSE_Parameters()
P.size = 2000
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
num_samples = 1000
A = SDR(R.parameters.size)
M = Metrics(A, num_samples + 1)
for i in range(num_samples):
X = i * R.parameters.radius
R.encode(X, A)
print(M)
assert (M.overlap.max() < .15)
assert (M.overlap.mean() < .10)
assert (M.sparsity.min() > R.parameters.sparsity - .01)
assert (M.sparsity.max() < R.parameters.sparsity + .01)
assert (M.sparsity.mean() > R.parameters.sparsity - .005)
assert (M.sparsity.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.min() > R.parameters.sparsity - .05)
assert (M.activationFrequency.max() < R.parameters.sparsity + .05)
assert (M.activationFrequency.mean() > R.parameters.sparsity - .005)
assert (M.activationFrequency.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.entropy() > .99)
def testAverageOverlap(self):
""" Verify that nearby values have the correct amount of semantic
similarity. Also measure sparsity & activation frequency. """
P = RDSE_Parameters()
P.size = 2000
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
A = SDR(R.parameters.size)
num_samples = 10000
M = Metrics(A, num_samples + 1)
for i in range(num_samples):
R.encode(i, A)
print(M)
assert (M.overlap.min() > (1 - 1. / R.parameters.radius) - .04)
assert (M.overlap.max() < (1 - 1. / R.parameters.radius) + .04)
assert (M.overlap.mean() > (1 - 1. / R.parameters.radius) - .001)
assert (M.overlap.mean() < (1 - 1. / R.parameters.radius) + .001)
assert (M.sparsity.min() > R.parameters.sparsity - .01)
assert (M.sparsity.max() < R.parameters.sparsity + .01)
assert (M.sparsity.mean() > R.parameters.sparsity - .005)
assert (M.sparsity.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.min() > R.parameters.sparsity - .05)
assert (M.activationFrequency.max() < R.parameters.sparsity + .05)
assert (M.activationFrequency.mean() > R.parameters.sparsity - .005)
assert (M.activationFrequency.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.entropy() > .99)
def testSeed(self):
P = RDSE_Parameters()
P.size = 1000
P.sparsity = .08
P.radius = 12
P.seed = 98
R = RDSE(P)
A = R.encode(987654)
P.seed = 99
R = RDSE(P)
B = R.encode(987654)
assert (A != B)
def testSparsityActiveBits(self):
""" Check that these arguments are equivalent. """
# Round sparsity up
P = RDSE_Parameters()
P.size = 100
P.sparsity = .0251
P.radius = 10
R = RDSE(P)
assert (R.parameters.activeBits == 3)
# Round sparsity down
P = RDSE_Parameters()
P.size = 100
P.sparsity = .0349
P.radius = 10
R = RDSE(P)
assert (R.parameters.activeBits == 3)
# Check activeBits
P = RDSE_Parameters()
P.size = 100
P.activeBits = 50 # No floating point issues here.
P.radius = 10
R = RDSE(P)
assert (R.parameters.sparsity == .5)
def testConstructor(self):
params1 = RDSE_Parameters()
params1.size = 100
params1.sparsity = .10
params1.radius = 10
R1 = RDSE(params1)
params2 = R1.parameters
params2.sparsity = 0 # Remove duplicate arguments
params2.radius = 0 # Remove duplicate arguments
R2 = RDSE(params2)
A = SDR(R1.parameters.size)
R1.encode(66, A)
B = R2.encode(66)
assert (A == B)
def testDeterminism(self):
""" Verify that the same seed always gets the same results. """
GOLD = SDR(1000)
GOLD.sparse = [
28, 47, 63, 93, 123, 124, 129, 131, 136, 140, 196, 205, 213, 239,
258, 275, 276, 286, 305, 339, 345, 350, 372, 394, 395, 443, 449,
462, 468, 471, 484, 514, 525, 557, 565, 570, 576, 585, 600, 609,
631, 632, 635, 642, 651, 683, 693, 694, 696, 699, 721, 734, 772,
790, 792, 795, 805, 806, 833, 836, 842, 846, 892, 896, 911, 914,
927, 936, 947, 953, 955, 962, 965, 989, 990, 996
]
P = RDSE_Parameters()
P.size = GOLD.size
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
A = R.encode(987654)
print(A)
assert (A == GOLD)
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"])
rdseParams = RDSE_Parameters()
rdseParams.size = 100
rdseParams.sparsity = .10
rdseParams.radius = 10
scalarEncoder = RDSE(rdseParams)
# encodingWidth = (timeOfDayEncoder.getWidth()
# + weekendEncoder.getWidth()
# + scalarEncoder.getWidth())
encodingWidth = scalarEncoder.size
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"])
results = []
with open(_INPUT_FILE_PATH, "r") as fin:
reader = csv.reader(fin)
headers = next(reader)
next(reader)
next(reader)
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.size)
consumptionBits = SDR(scalarEncoder.size)
# Now we call the encoders to create bit representations for each value.
# timeOfDayEncoder.encodeIntoArray(dateString, timeOfDayBits)
# weekendEncoder.encodeIntoArray(dateString, weekendBits)
scalarEncoder.encode(consumption, consumptionBits)
# Concatenate all these encodings into one large encoding for Spatial
# Pooling.
# encoding = numpy.concatenate(
# [timeOfDayBits, weekendBits, consumptionBits]
# )
encoding = 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"])
activeColumns = SDR(spParams["columnCount"])
encodingIn = numpy.uint32(encoding.dense)
minicolumnsOut = numpy.uint32(activeColumns.dense)
# Execute Spatial Pooling algorithm over input space.
sp.compute(encodingIn, True, minicolumnsOut)
activeColumnIndices = numpy.nonzero(minicolumnsOut)[0]
# Execute Temporal Memory algorithm over active mini-columns.
tm.compute(activeColumnIndices, learn=True)
activeCells = tm.getActiveCells()
print(len(activeCells))
results.append(activeCells)
return results