def frequency(self,
n=15,
w=7,
columnDimensions=2048,
numActiveColumnsPerInhArea=40,
stimulusThreshold=0,
spSeed=1,
spVerbosity=0,
numColors=2,
seed=42,
minVal=0,
maxVal=10,
encoder='category',
forced=True):
""" Helper function that tests whether the SP predicts the most
frequent record """
print("\nRunning SP overlap test...")
print(encoder, 'encoder,', 'Random seed:', seed, 'and', numColors,
'colors')
#Setting up SP and creating training patterns
# Instantiate Spatial Pooler
spImpl = SpatialPooler(
columnDimensions=(columnDimensions, 1),
inputDimensions=(1, n),
potentialRadius=n // 2,
numActiveColumnsPerInhArea=numActiveColumnsPerInhArea,
spVerbosity=spVerbosity,
stimulusThreshold=stimulusThreshold,
potentialPct=0.5,
seed=spSeed,
globalInhibition=True,
)
rnd.seed(seed)
numpy.random.seed(seed)
colors = []
coincs = []
reUsedCoincs = []
spOutput = []
patterns = set([])
# Setting up the encodings
if encoder == 'scalar':
enc = scalar.ScalarEncoder(
name='car',
w=w,
n=n,
minval=minVal,
maxval=maxVal,
periodic=False,
forced=True
) # forced: it's strongly recommended to use w>=21, in the example we force skip the check for readibility
for y in range(numColors):
temp = enc.encode(rnd.random() * maxVal)
colors.append(numpy.array(temp, dtype=numpy.uint32))
else:
for y in range(numColors):
sdr = numpy.zeros(n, dtype=numpy.uint32)
# Randomly setting w out of n bits to 1
sdr[rnd.sample(range(n), w)] = 1
colors.append(sdr)
# Training the sp
print('Starting to train the sp on', numColors, 'patterns')
startTime = time.time()
for i in range(numColors):
# TODO: See https://github.com/numenta/nupic/issues/2072
spInput = colors[i]
onCells = numpy.zeros(columnDimensions, dtype=numpy.uint32)
spImpl.compute(spInput, True, onCells)
spOutput.append(onCells.tolist())
activeCoincIndices = set(onCells.nonzero()[0])
# Checking if any of the active cells have been previously active
reUsed = activeCoincIndices.intersection(patterns)
if len(reUsed) == 0:
# The set of all coincidences that have won at least once
coincs.append((i, activeCoincIndices, colors[i]))
else:
reUsedCoincs.append((i, activeCoincIndices, colors[i]))
# Adding the active cells to the set of coincs that have been active at
# least once
patterns.update(activeCoincIndices)
if (i + 1) % 100 == 0:
print('Record number:', i + 1)
print("Elapsed time: %.2f seconds" % (time.time() - startTime))
print(len(reUsedCoincs), "re-used coinc(s),")
# Check if results match expectations
summ = []
for z in coincs:
summ.append(
sum([len(z[1].intersection(y[1])) for y in reUsedCoincs]))
zeros = len([x for x in summ if x == 0])
factor = max(summ) * len(summ) / sum(summ)
if len(reUsed) < 10:
self.assertLess(
factor, 41,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 41))
self.assertLess(
zeros, 0.99 * len(summ),
"\nComputed zeros: %d\nExpected Less than %d" %
(zeros, 0.99 * len(summ)))
else:
self.assertLess(
factor, 8,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 8))
self.assertLess(
zeros, 12,
"\nComputed zeros: %d\nExpected Less than %d" % (zeros, 12))
def frequency(self,
n=15,
w=7,
coincidencesShape=2048,
numActivePerInhArea=40,
stimulusThreshold=0,
spSeed=1,
spVerbosity=0,
numColors=2,
seed=42,
minVal=0,
maxVal=10,
encoder='category'):
""" Helper function that tests whether the SP predicts the most
frequent record """
print "\nRunning SP overlap test..."
print encoder, 'encoder,', 'Random seed:', seed, 'and', numColors, 'colors'
#Setting up SP and creating training patterns
# Instantiate Spatial Pooler
spImpl = FDRCSpatial2.FDRCSpatial2(
coincidencesShape=(coincidencesShape, 1),
inputShape=(1, n),
inputBorder=(n - 2) / 2,
coincInputRadius=n / 2,
numActivePerInhArea=numActivePerInhArea,
spVerbosity=spVerbosity,
stimulusThreshold=stimulusThreshold,
coincInputPoolPct=0.5,
seed=spSeed,
spReconstructionParam='dutycycle',
)
rnd.seed(seed)
numpy.random.seed(seed)
colors = []
coincs = []
reUsedCoincs = []
spOutput = []
patterns = set([])
# Setting up the encodings
if encoder == 'scalar':
enc = scalar.ScalarEncoder(name='car',
w=w,
n=n,
minval=minVal,
maxval=maxVal,
periodic=False)
for y in xrange(numColors):
temp = enc.encode(rnd.random() * maxVal)
colors.append(numpy.array(temp, dtype=realDType))
else:
for y in xrange(numColors):
sdr = numpy.zeros(n, dtype=realDType)
# Randomly setting w out of n bits to 1
sdr[rnd.sample(xrange(n), w)] = 1
colors.append(sdr)
# Training the sp
print 'Starting to train the sp on', numColors, 'patterns'
startTime = time.time()
for i in xrange(numColors):
spInput = colors[i]
onCells = spImpl.compute(spInput, learn=True, infer=False)
spOutput.append(onCells.tolist())
activeCoincIndices = set(onCells.nonzero()[0])
# Checking if any of the active cells have been previously active
reUsed = activeCoincIndices.intersection(patterns)
if len(reUsed) == 0:
# The set of all coincidences that have won at least once
coincs.append((i, activeCoincIndices, colors[i]))
else:
reUsedCoincs.append((i, activeCoincIndices, colors[i]))
# Adding the active cells to the set of coincs that have been active at
# least once
patterns.update(activeCoincIndices)
if (i + 1) % 100 == 0:
print 'Record number:', i + 1
print "Elapsed time: %.2f seconds" % (time.time() - startTime)
print len(reUsedCoincs), "re-used coinc(s),"
# Check if results match expectations
summ = []
for z in coincs:
summ.append(
sum([len(z[1].intersection(y[1])) for y in reUsedCoincs]))
zeros = len([x for x in summ if x == 0])
factor = max(summ) * len(summ) / sum(summ)
if len(reUsed) < 10:
self.assertLess(
factor, 30,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 30))
self.assertLess(
zeros, 0.99 * len(summ),
"\nComputed zeros: %d\nExpected Less than %d" %
(zeros, 0.99 * len(summ)))
else:
self.assertLess(
factor, 8,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 8))
self.assertLess(
zeros, 12,
"\nComputed zeros: %d\nExpected Less than %d" % (zeros, 12))