def main(): x = 10 y = 10 steps = 10000 history = [] world = np.array([i for i in xrange(625)]) world.resize((25, 25)) sp = SpatialPooler( inputDimensions=(625, ), columnDimensions=(25, ), potentialRadius=625, numActiveColumnsPerInhArea=1, ) output = np.zeros((25, ), dtype=np.uint32) for _ in xrange(steps): active = getActive(world, x, y) assert len(active) == 25, "{}, {}: {}".format(x, y, active) activeInput = np.zeros((625, ), dtype=np.uint32) for v in active: activeInput[v] = 1 history.append(active) sp.compute(activeInput, True, output) x, y = getNewLocation(x, y, 25, 2, False) for i in xrange(25): permanence = np.zeros((625, )) sp.getPermanence(i, permanence) plt.imshow(permanence.reshape((25, 25)), cmap="hot", interpolation="nearest") plt.show()
def create_sp(self): sp = SpatialPooler( # How large the input encoding will be. inputDimensions=(len(self.encoding[0])), # 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) return sp
def test_whether_is_the_same_as_spatial_pooler(self): """ Naive reality check for the encoding function of the lateral pooler implementation. """ n = 1024 m = 784 d = 100 w = 20 X = np.random.randint(0, 2, size=(m, d)) Y_nup = np.zeros((n, d)) Y_lat = np.zeros((n, d)) params_nup = { "inputDimensions": [m, 1], "columnDimensions": [n, 1], "potentialRadius": n, "potentialPct": 1.0, "globalInhibition": True, "localAreaDensity": -1.0, "numActiveColumnsPerInhArea": w, "stimulusThreshold": 0, "synPermInactiveDec": 0.05, "synPermActiveInc": 0.1, "synPermConnected": 0.5, "minPctOverlapDutyCycle": 0.001, "dutyCyclePeriod": 1000, "boostStrength": 100.0, "seed": 1936 } params_lat = params_nup.copy() params_lat["lateralLearningRate"] = 0.0 params_lat["enforceDesiredWeight"] = False sp_nup = SpatialPooler(**params_nup) sp_lat = LateralPooler(**params_lat) for t in range(d): sp_nup.compute(X[:, t], False, Y_nup[:, t]) sp_lat.compute(X[:, t], False, Y_lat[:, t]) self.assertTrue(np.all(Y_nup == Y_lat), "Produces wrong output even without learning.") for t in range(d): sp_nup.compute(X[:, t], True, Y_nup[:, t]) sp_lat.compute(X[:, t], True, Y_lat[:, t]) self.assertTrue(np.all(Y_nup == Y_lat), "Wrong outputs, something diverges during learning.") W_nup = get_W(sp_nup) W_lat = get_W(sp_lat) self.assertTrue( np.all(W_nup == W_lat), "Wrong synaptic weights, something diverges during learning.")
def init_imgs(write_output): #problems = parse_images.get_problems(folder_name) folder_name = 'Data/raw' problems = [] for sub_folder in os.listdir(folder_name): f = os.path.join(folder_name, sub_folder) problems += parse_images.get_problems(f) print(len(problems)) for problem in problems: problem['Input'] = problem['Input'].reshape((3, -1)) problem['Output'] = problem['Output'].reshape((6, -1)) # dimenstions num_cols1 = len(problems[0]['Input'][0]) tm_cols = num_cols1 layers = [] if not write_output: num_cols2 = num_cols1 / 2 num_cols3 = num_cols2 / 2 sp1 = SpatialPooler(inputDimensions=(num_cols1, ), columnDimensions=(num_cols2, ), numActiveColumnsPerInhArea=-1, localAreaDensity=0.05) sp2 = SpatialPooler(inputDimensions=(num_cols2, ), columnDimensions=(num_cols3, ), numActiveColumnsPerInhArea=-1, localAreaDensity=0.05) tm_cols = num_cols3 layers = [(sp1, sp_compute), (sp2, sp_compute)] bckTM = BTM(numberOfCols=tm_cols, cellsPerColumn=10, initialPerm=0.5, connectedPerm=0.5, minThreshold=10, newSynapseCount=10, activationThreshold=10, pamLength=10) layers += [(bckTM, bk_tm_compute)] return (layers, problems)
def definir_SP(SIZE_ENCODER_): """ retorna a classe sp """ N_COLUMNS= 2048 sp = SpatialPooler( inputDimensions = (SIZE_ENCODER_,), columnDimensions = ( N_COLUMNS,), # in this case we will use 2048 mini-columns distributed in a "linear array" ... potentialRadius = SIZE_ENCODER_, # i set the potential radius of each mini-column as the whole ... #input space potentialPct = 0.8, # how many bits on the input space that should have some permanence with each mini-column ## attention: having a permanence value doesn't mean that it will be connected, to be connected the "connection... ## force" / permanence needs to be higher than the threshold. globalInhibition = True, # means that the winning columns are selected in the neighborhood, though in this code... #we're dealing as if all the columns are neigbhors with one another localAreaDensity = -1.0, numActiveColumnsPerInhArea = NUM_ACTIVE_COLUMNS, stimulusThreshold = 0, ##Well, if we set the number of active columns per input, than there is no need to set an stimulusThreshold ##First = because the simulusTHreshold will be already set as the sum of permanences of the 40th column...@@NEED TO CHECK ##any other mini-column with less than it won't be active on this input synPermInactiveDec = 0.0005, #if a column is active, the off (that aren't 1 in input) bits which it is connected ... # will have a decrement on the "synapse force"/permance @@ synPermActiveInc = 0.003,#if a column is active, the on (that are 1 in input) bits which it is connected ... # will have a increment on the "synapse force"/permance @@ synPermConnected = 0.2, #how much the "strength" of the connection between the on bit and the mini-column ... #needs to be for they to be connected. @@ # @@ what needs to be checked is if the bits with synPermConnected < 0.1 will decrement ou increment when a column ... # is active - but i think they will increment minPctOverlapDutyCycle = 0.001, # number between 0 and 1.0, used to set a floor on how often a column #...should have at least stimulusThreshold active inputs dutyCyclePeriod = 100, # how many "inputs seen" this should happen boostStrength = 0.01, seed = 47, spVerbosity = 0, wrapAround = False ) return sp
def main(): # cluster similar inputs together in SDR space s = SpatialPooler() print(type(s)) # powerful sequence memory in SDR space t = TemporalMemory() print(type(t)) # computes rolling Gaussian based on raw anomaly scores and then their # likelihood a = AnomalyLikelihood() print(type(a)) # temporally groups active cell sets from TM u = UnionTemporalPooler() print(type(u)) # learning pairings of Union representations and labeled classes c = SDRClassifier() print(type(c))
def runTrial(ww, numColumns, potentialPct, inc, dec, mpo, dutyCycle, boost, steps, rr, spW, stimulusThreshold, connected, stepSize, jumpProb, directionStability): ws = ww ** 2 x = 10 y = 10 locationHeatmap = np.zeros((ww, ww)) history = [] world = np.array([i for i in xrange(ws)]) world.resize((ww, ww)) sp = SpatialPooler( inputDimensions=(ws,), columnDimensions=(numColumns,), potentialRadius=ws, potentialPct=potentialPct, numActiveColumnsPerInhArea=spW, stimulusThreshold=stimulusThreshold, synPermActiveInc=inc, synPermInactiveDec=dec, synPermConnected=connected, minPctOverlapDutyCycle=mpo, dutyCyclePeriod=dutyCycle, boostStrength=boost, seed=1936, globalInhibition=True, ) output = np.zeros((numColumns,), dtype=np.uint32) direction = 0 for i in xrange(steps): locationHeatmap[x][y] += 1 active = getActive(world, ww, x, y, rr) history.append(active) activeInput = np.zeros((ws,), dtype=np.uint32) for v in active: activeInput[v] = 1 sp.compute(activeInput, True, output) x, y, direction = getNewLocation(x, y, ww, rr, wrap=True, locationHeatmap=locationHeatmap, stepSize=stepSize, jumpProb=jumpProb, direction=direction, directionStability=directionStability) if (i + 1) % 100 == 0: saveImage(history, ws, ww, numColumns, locationHeatmap, potentialPct, inc, dec, mpo, dutyCycle, boost, rr, spW, i+1, sp) saveImage(history, ws, ww, numColumns, locationHeatmap, potentialPct, inc, dec, mpo, dutyCycle, boost, rr, spW, steps, sp)
def main(): x = 10 y = 10 steps = 10000 world = np.array([i for i in xrange(625)]) world.resize((25, 25)) spInputSize = 21 * 21 sp = SpatialPooler( inputDimensions=(spInputSize, ), columnDimensions=(25, ), potentialRadius=spInputSize, numActiveColumnsPerInhArea=1, synPermActiveInc=0.1, synPermInactiveDec=0.5, boostStrength=1.0, ) csFields = generateCenterSurroundFields() output = np.zeros((25, ), dtype=np.uint32) for _ in xrange(steps): active = getActive(world, x, y) assert len(active) == 25, "{}, {}: {}".format(x, y, active) activeInput = np.zeros((625, ), dtype=np.uint32) for v in active: activeInput[v] = 1 centerSurround = processCenterSurround(csFields, activeInput) print centerSurround sp.compute(centerSurround, True, output) x, y = getNewLocation(x, y, 25, 2, False) for i in xrange(25): permanence = np.zeros((spInputSize, )) sp.getPermanence(i, permanence) plt.imshow(permanence.reshape((21, 21)), cmap="hot", interpolation="nearest") plt.show()
def toString(self): print("sentenceNum: " + self.id) print("startIdx " + self.startIdx) print("startIdx " + self.endIdx) print("anomalyScore " + self.anomalyScore) # parameters for the spatial pooler and temporal memory networks, only tm_only is used sp_layer1 = SpatialPooler(inputDimensions=(128, 128), columnDimensions=(64, 64), potentialPct=0.1, potentialRadius=5, globalInhibition=False, localAreaDensity=0.1, numActiveColumnsPerInhArea=3, synPermInactiveDec=0.5, synPermActiveInc=0.02, synPermConnected=0.90, boostStrength=0.0, wrapAround=False) tm_only = TemporalMemory( inputDimensions=(4096, ), columnDimensions=(4096, ), cellsPerColumn=5, newSynapseCount=15, activationThreshold=15, initialPermanence=0.7, connectedPermanence=0.8, minThreshold=8,
# Pick a combination of parameter values parameters.nextCombination() #parameters.nextRandomCombination() synPermConn = parameters.getValue("synPermConn") synPermDec = synPermConn * parameters.getValue("synPermDecFrac") synPermInc = synPermConn * parameters.getValue("synPermIncFrac") # Instantiate our spatial pooler sp = SpatialPooler( inputDimensions=(32, 32), # Size of image patch columnDimensions=(32, 32), potentialRadius=10000, # Ensures 100% potential pool potentialPct=0.8, globalInhibition=True, localAreaDensity=-1, # Using numActiveColumnsPerInhArea numActiveColumnsPerInhArea=64, # All input activity can contribute to feature output stimulusThreshold=0, synPermInactiveDec=synPermDec, synPermActiveInc=synPermInc, synPermConnected=synPermConn, boostStrength=1.0, seed=1956, # The seed that Grok uses spVerbosity=1) # Instantiate the spatial pooler test bench. tb = VisionTestBench(sp) # Instantiate the classifier clf = KNNClassifier() # Train the spatial pooler on trainingVectors.
now = datetime.datetime.strptime(lines, "%Y-%m-%d %H:%M:%S") print "now = ", de.encode(now) cpt += 1 categories = ('info', 'error', 'warning') encoder = CategoryEncoder(w=3, categoryList=categories, forced=True) info = encoder.encode("info") error = encoder.encode("error") warning = encoder.encode("warning") #print "info = ", info #print "error = ", error #print "warning = ", warning sp = SpatialPooler(inputDimensions=(len(info), ), columnDimensions=(3, ), potentialRadius=15, numActiveColumnsPerInhArea=1, globalInhibition=True, synPermActiveInc=0.03, potentialPct=1.0) import numpy for column in xrange(3): connected = numpy.zeros((len(info), ), dtype="int") sp.getConnectedSynapses(column, connected) print connected output = numpy.zeros((3, ), dtype="int") sp.compute(info, learn=True, activeArray=output) print output output = numpy.zeros((3, ), dtype="int") sp.compute(error, learn=True, activeArray=output)
def __init__(self, columnCount, InputEncoderParams, toL4ConnectorParamsI, toL4ConnectorParamsII, toL5ConnectorParams, toD1ConnectorParams, toD2ConnectorParams, L4Params, L5Params, k, D1Params, D2Params): self.columnCount = columnCount self.toL4ConnectorParamsI = toL4ConnectorParamsI self.toL4ConnectorParamsII = toL4ConnectorParamsII self.toL5ConnectorParams = toL5ConnectorParams self.toD1ConnectorParams = toD1ConnectorParams self.toD2ConnectorParams = toD2ConnectorParams self.L4Params = L4Params self.L5Params = L5Params self.k = k self.D1Params = D1Params self.D2Params = D2Params self.learning = False #encoder from nupic.encoders import MultiEncoder self.InputEncoder = MultiEncoder() self.InputEncoder.addMultipleEncoders(InputEncoderParams) print "Encoder Online" #spatialPoolers from nupic.algorithms.spatial_pooler import SpatialPooler self.toL4ConnectorI = SpatialPooler( inputDimensions=(toL4ConnectorParamsI["inputDimensions"], ), columnDimensions=(columnCount, ), potentialPct=toL4ConnectorParamsI["potentialPct"], globalInhibition=toL4ConnectorParamsI["globalInhibition"], localAreaDensity=toL4ConnectorParamsI["localAreaDensity"], numActiveColumnsPerInhArea=toL4ConnectorParamsI[ "numActiveColumnsPerInhArea"], synPermInactiveDec=toL4ConnectorParamsI["synPermInactiveDec"], synPermActiveInc=toL4ConnectorParamsI["synPermActiveInc"], synPermConnected=toL4ConnectorParamsI["synPermConnected"], boostStrength=toL4ConnectorParamsI["boostStrength"], seed=toL4ConnectorParamsI["seed"], wrapAround=toL4ConnectorParamsI["wrapAround"]) #this part sucks self.toL4ConnectorII = SpatialPooler( inputDimensions=(columnCount * 3, ), columnDimensions=(columnCount, ), potentialPct=toL4ConnectorParamsII["potentialPct"], globalInhibition=toL4ConnectorParamsII["globalInhibition"], localAreaDensity=toL4ConnectorParamsII["localAreaDensity"], numActiveColumnsPerInhArea=toL4ConnectorParamsII[ "numActiveColumnsPerInhArea"], synPermInactiveDec=toL4ConnectorParamsII["synPermInactiveDec"], synPermActiveInc=toL4ConnectorParamsII["synPermActiveInc"], synPermConnected=toL4ConnectorParamsII["synPermConnected"], boostStrength=toL4ConnectorParamsII["boostStrength"], seed=toL4ConnectorParamsII["seed"], wrapAround=toL4ConnectorParamsII["wrapAround"]) print "toL4Connector Online" self.toL5Connector = SpatialPooler( inputDimensions=(columnCount, ), columnDimensions=(columnCount, ), potentialPct=toL5ConnectorParams["potentialPct"], globalInhibition=toL5ConnectorParams["globalInhibition"], localAreaDensity=toL5ConnectorParams["localAreaDensity"], numActiveColumnsPerInhArea=toL5ConnectorParams[ "numActiveColumnsPerInhArea"], synPermInactiveDec=toL5ConnectorParams["synPermInactiveDec"], synPermActiveInc=toL5ConnectorParams["synPermActiveInc"], synPermConnected=toL5ConnectorParams["synPermConnected"], boostStrength=toL5ConnectorParams["boostStrength"], seed=toL5ConnectorParams["seed"], wrapAround=toL5ConnectorParams["wrapAround"]) print "toL5Connector Online" self.toD1Connector = SpatialPooler( inputDimensions=(columnCount, ), columnDimensions=(columnCount, ), potentialPct=toD1ConnectorParams["potentialPct"], globalInhibition=toD1ConnectorParams["globalInhibition"], localAreaDensity=toD1ConnectorParams["localAreaDensity"], numActiveColumnsPerInhArea=toD1ConnectorParams[ "numActiveColumnsPerInhArea"], synPermInactiveDec=toD1ConnectorParams["synPermInactiveDec"], synPermActiveInc=toD1ConnectorParams["synPermActiveInc"], synPermConnected=toD1ConnectorParams["synPermConnected"], boostStrength=toD1ConnectorParams["boostStrength"], seed=toD1ConnectorParams["seed"], wrapAround=toD1ConnectorParams["wrapAround"]) print "toD1Connector Online" self.toD2Connector = SpatialPooler( inputDimensions=(columnCount, ), columnDimensions=(columnCount, ), potentialPct=toD2ConnectorParams["potentialPct"], globalInhibition=toD2ConnectorParams["globalInhibition"], localAreaDensity=toD2ConnectorParams["localAreaDensity"], numActiveColumnsPerInhArea=toD2ConnectorParams[ "numActiveColumnsPerInhArea"], synPermInactiveDec=toD2ConnectorParams["synPermInactiveDec"], synPermActiveInc=toD2ConnectorParams["synPermActiveInc"], synPermConnected=toD2ConnectorParams["synPermConnected"], boostStrength=toD2ConnectorParams["boostStrength"], seed=toD2ConnectorParams["seed"], wrapAround=toD2ConnectorParams["wrapAround"]) print "toD2Connector Online" #HTM Layers from nupic.algorithms.temporal_memory import TemporalMemory self.L4ActiveColumns = numpy.zeros(self.columnCount, dtype=int) self.L4 = TemporalMemory( columnDimensions=(columnCount, ), seed=42, ) print "L4 Online" self.L5ActiveColumns = numpy.zeros(self.columnCount, dtype=int) self.L5 = TemporalMemory( columnDimensions=(columnCount, ), seed=42, ) print "L5 Online" self.D1ActiveColumns = numpy.zeros(self.columnCount, dtype=int) self.D1 = TemporalMemory( columnDimensions=(columnCount, ), seed=42, initialPermanence=0.21, connectedPermanence=0.5, ) print "D1 Online" self.D2ActiveColumns = numpy.zeros(self.columnCount, dtype=int) self.D2 = TemporalMemory( columnDimensions=(columnCount, ), seed=42, initialPermanence=0.21, connectedPermanence=0.5, ) print "D2 Online"
if __name__ == "__main__": # Get training images and convert them to vectors. trainingImages, trainingTags = dataset_readers.getImagesAndTags( trainingDataset) trainingVectors = encoder.imagesToVectors(trainingImages) # Instantiate the python spatial pooler sp = SpatialPooler( inputDimensions=32**2, # Size of image patch columnDimensions=16, # Number of potential features potentialRadius=10000, # Ensures 100% potential pool potentialPct=1, # Neurons can connect to 100% of input globalInhibition=True, localAreaDensity=-1, # Using numActiveColumnsPerInhArea #localAreaDensity=0.02, # one percent of columns active at a time #numActiveColumnsPerInhArea=-1, # Using percentage instead numActiveColumnsPerInhArea=1, # Only one feature active at a time # All input activity can contribute to feature output stimulusThreshold=0, synPermInactiveDec=0.3, synPermActiveInc=0.3, synPermConnected=0.3, # Connected threshold boostStrength=2, seed=1956, # The seed that Grok uses spVerbosity=1) # Instantiate the spatial pooler test bench. tb = VisionTestBench(sp) # Instantiate the classifier clf = exactMatch()
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 HTM_AD( Data='Test', vars={'value': ['num']}, prec_param=5, pooler_out=2024, # Number of columns of the pooler output cell_col=5, # HTM cells per column W=72, # Window parameter W_prim=5, # Local window for anomaly detection likelihood eps=1e-6, # to Avoid by zero divisions athreshold=0.95): """ This function performs HTM based anomaly detection on a time series provided :param Data: :param vars: Possible values: num, tod, weekend :param prec_param: A parameter that defines how much precision the number encoder has The encoder precision depends on the variability of the data, The real precision is computed taking into account both the precision parameter and data std A high precision might mean a high error at predicting the variable value in noisy variables :param pooler_out: Number of columns of the pooler output :param cell_col: HTM cells per column :param W: Window parameter :param W_prim: Local window for anomaly detection likelihood :param eps: to Avoid by zero divisions :param athreshold: To classify based on anomaly likelihood whether there is an anomaly or not :return: The Data + 3 columns Anomaly: indicates the error of within the value predicted by the HTM network Anomaly_likelihood: indicates the likelihood of the data into being anomalous Anomaly_flag: classifies the data in anomalous vs non anomalous """ if Data == 'Test': # If there is not data available, simply loads the temperature benchmark dataset # Import data Data = pd.read_csv('anomaly_API/Data/sample.csv', parse_dates=True, index_col='timestamp') Data = Data.resample('H').bfill().interpolate() TODE = DateEncoder(timeOfDay=(21, 1)) WENDE = DateEncoder(weekend=21) var_encoders = set() # Spatial Pooler Parameters for x in vars: for y in vars[x]: if y == 'num': exec( "RDSE_" + x + " = RandomDistributedScalarEncoder(resolution=Data['" + x + "'].std()/prec_param)", locals(), globals()) var_encoders.add(Encoder(x, ["RDSE_" + x])) elif y == 'weekend': var_encoders.add(Encoder(x, ["WENDE"])) elif y == 'tod': var_encoders.add(Encoder(x, ["TODE"])) else: return {"error": "Variable encoder type is not recognized "} encoder_width = 0 # Computes encoder width for x in var_encoders: for y in x.encoders: exec("s = " + y + ".getWidth()", locals(), globals()) encoder_width += s SP = SpatialPooler( inputDimensions=encoder_width, columnDimensions=pooler_out, potentialPct=0.8, globalInhibition=True, numActiveColumnsPerInhArea=pooler_out // 50, # Gets 2% of the total area boostStrength=1.0, wrapAround=False) TM = TemporalMemory(columnDimensions=(pooler_out, ), cellsPerColumn=cell_col) Data['Anomaly'] = 0.0 Data['Anomaly_Likelihood'] = 0.0 # Train Spatial Pooler print("Spatial pooler learning") start = time.time() active_columns = np.zeros(pooler_out) for x in range(len(Data)): encoder = multiencode(var_encoders, Data, x) SP.compute(encoder, True, active_columns) end = time.time() print(end - start) # Temporal pooler print("Temporal pooler learning") start = time.time() A_score = np.zeros(len(Data)) for x in range(len(Data)): encoder = multiencode(var_encoders, Data, x) SP.compute(encoder, False, active_columns) col_index = active_columns.nonzero()[0] TM.compute(col_index, learn=True) if x > 0: inter = set(col_index).intersection(Prev_pred_col) inter_l = len(inter) active_l = len(col_index) A_score[x] = 1 - (inter_l / active_l) Data.iat[x, -2] = A_score[x] Prev_pred_col = list( set(x // cell_col for x in TM.getPredictiveCells())) end = time.time() print(end - start) AL_score = np.zeros(len(Data)) # Computes the likelihood of the anomaly for x in range(len(Data)): if x > 0: W_vec = A_score[max(0, x - W):x] W_prim_vec = A_score[max(0, x - W_prim):x] AL_score[x] = 1 - 2 * norm.sf( abs(np.mean(W_vec) - np.mean(W_prim_vec)) / max(np.std(W_vec), eps)) Data.iat[x, -1] = AL_score[x] Data['Anomaly_flag'] = athreshold < Data['Anomaly_Likelihood'] return Data
def testSP(): """ Run a SP test """ elemSize = 400 numSet = 42 addNear = True numRecords = 2 wantPlot = True poolPct = 0.5 itr = 1 doLearn = True while numRecords < 3: # Setup a SP sp = SpatialPooler(columnDimensions=(2048, 1), inputDimensions=(1, elemSize), potentialRadius=elemSize / 2, numActiveColumnsPerInhArea=40, spVerbosity=0, stimulusThreshold=0, seed=1, potentialPct=poolPct, globalInhibition=True) # Generate inputs using rand() inputs = generateRandomInput(numRecords, elemSize, numSet) if addNear: # Append similar entries (distance of 1) appendInputWithNSimilarValues(inputs, 42) inputSize = len(inputs) print('Num random records = %d, inputs to process %d' % (numRecords, inputSize)) # Run a number of iterations, with learning on or off, # retrieve results from the last iteration only outputs = np.zeros((inputSize, 2048)) numIter = 1 if doLearn: numIter = itr for iter in range(numIter): for i in range(inputSize): time.sleep(0.001) if iter == numIter - 1: # TODO: See https://github.com/numenta/nupic/issues/2072 sp.compute(inputs[i], learn=doLearn, activeArray=outputs[i]) #print outputs[i].sum(), outputs[i] else: # TODO: See https://github.com/numenta/nupic/issues/2072 output = np.zeros(2048) sp.compute(inputs[i], learn=doLearn, activeArray=output) # Build a plot from the generated input and output and display it distribMatrix = generatePlot(outputs, inputs) # If we don't want a plot, just continue if wantPlot: plt.imshow(distribMatrix, origin='lower', interpolation="nearest") plt.ylabel('SP (2048/40) distance in %') plt.xlabel('Input (400/42) distance in %') title = 'SP distribution' if doLearn: title += ', leaning ON' else: title += ', learning OFF' title += ', inputs = %d' % len(inputs) title += ', iterations = %d' % numIter title += ', poolPct =%f' % poolPct plt.suptitle(title, fontsize=12) plt.show() #plt.savefig(os.path.join('~/Desktop/ExperimentResults/videos5', '%s' % numRecords)) #plt.clf() numRecords += 1 return
def testSPFile(): """ Run test on the data file - the file has records previously encoded. """ spSize = 2048 spSet = 40 poolPct = 0.5 pattern = [50, 1000] doLearn = True PLOT_PRECISION = 100.0 distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1)) inputs = [] #file = open('~/Desktop/ExperimentResults/sampleArtificial.csv', 'rb') #elemSize = 400 #numSet = 42 #file = open('~/Desktop/ExperimentResults/sampleDataBasilOneField.csv', 'rb') #elemSize = 499 #numSet = 7 outdir = '~/Desktop/ExperimentResults/Basil100x21' inputFile = outdir + '.csv' file = open(inputFile, 'rb') elemSize = 100 numSet = 21 reader = csv.reader(file) for row in reader: input = np.array(list(map(float, row)), dtype=realDType) if len(input.nonzero()[0]) != numSet: continue inputs.append(input.copy()) file.close() # Setup a SP sp = SpatialPooler(columnDimensions=(spSize, 1), inputDimensions=(1, elemSize), potentialRadius=elemSize / 2, numActiveColumnsPerInhArea=spSet, spVerbosity=0, stimulusThreshold=0, synPermConnected=0.10, seed=1, potentialPct=poolPct, globalInhibition=True) cleanPlot = False doLearn = False print('Finished reading file, inputs/outputs to process =', len(inputs)) size = len(inputs) for iter in range(100): print('Iteration', iter) # Learn if iter != 0: for learnRecs in range(pattern[0]): # TODO: See https://github.com/numenta/nupic/issues/2072 ind = np.random.random_integers(0, size - 1, 1)[0] sp.compute(inputs[ind], learn=True, activeArray=outputs[ind]) # Test for _ in range(pattern[1]): rand1 = np.random.random_integers(0, size - 1, 1)[0] rand2 = np.random.random_integers(0, size - 1, 1)[0] sp.compute(inputs[rand1], learn=False, activeArray=output1) sp.compute(inputs[rand2], learn=False, activeArray=output2) outDist = (abs(output1 - output2) > 0.1) intOutDist = int(outDist.sum() / 2 + 0.1) inDist = (abs(inputs[rand1] - inputs[rand2]) > 0.1) intInDist = int(inDist.sum() / 2 + 0.1) if intInDist != numSet or intOutDist != spSet: print(rand1, rand2, '-', intInDist, intOutDist) x = int(PLOT_PRECISION * intOutDist / spSet) y = int(PLOT_PRECISION * intInDist / numSet) if distribMatrix[x, y] < 0.1: distribMatrix[x, y] = 3 else: if distribMatrix[x, y] < 10: distribMatrix[x, y] += 1 if True: plt.imshow(distribMatrix, origin='lower', interpolation="nearest") plt.ylabel('SP (%d/%d) distance in pct' % (spSize, spSet)) plt.xlabel('Input (%d/%d) distance in pct' % (elemSize, numSet)) title = 'SP distribution' title += ', iter = %d' % iter title += ', Pct =%f' % poolPct plt.suptitle(title, fontsize=12) #plt.savefig(os.path.join('~/Desktop/ExperimentResults/videosArtData', '%s' % iter)) plt.savefig(os.path.join(outdir, '%s' % iter)) plt.clf() distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1))
def testSPNew(): """ New version of the test""" elemSize = 400 numSet = 42 addNear = True numRecords = 1000 wantPlot = False poolPct = 0.5 itr = 5 pattern = [60, 1000] doLearn = True start = 1 learnIter = 0 noLearnIter = 0 numLearns = 0 numTests = 0 numIter = 1 numGroups = 1000 PLOT_PRECISION = 100.0 distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1)) inputs = generateRandomInput(numGroups, elemSize, numSet) # Setup a SP sp = SpatialPooler(columnDimensions=(2048, 1), inputDimensions=(1, elemSize), potentialRadius=elemSize / 2, numActiveColumnsPerInhArea=40, spVerbosity=0, stimulusThreshold=0, synPermConnected=0.12, seed=1, potentialPct=poolPct, globalInhibition=True) cleanPlot = False for i in range(numRecords): input1 = getRandomWithMods(inputs, 4) if i % 2 == 0: input2 = getRandomWithMods(inputs, 4) else: input2 = input1.copy() input2 = modifyBits(input2, 21) inDist = (abs(input1 - input2) > 0.1) intInDist = int(inDist.sum() / 2 + 0.1) #print intInDist if start == 0: doLearn = True learnIter += 1 if learnIter == pattern[start]: numLearns += 1 start = 1 noLearnIter = 0 elif start == 1: doLearn = False noLearnIter += 1 if noLearnIter == pattern[start]: numTests += 1 start = 0 learnIter = 0 cleanPlot = True # TODO: See https://github.com/numenta/nupic/issues/2072 sp.compute(input1, learn=doLearn, activeArray=output1) sp.compute(input2, learn=doLearn, activeArray=output2) time.sleep(0.001) outDist = (abs(output1 - output2) > 0.1) intOutDist = int(outDist.sum() / 2 + 0.1) if not doLearn and intOutDist < 2 and intInDist > 10: """ sp.spVerbosity = 10 # TODO: See https://github.com/numenta/nupic/issues/2072 sp.compute(input1, learn=doLearn, activeArray=output1) sp.compute(input2, learn=doLearn, activeArray=output2) sp.spVerbosity = 0 print 'Elements has very small SP distance: %d' % intOutDist print output1.nonzero() print output2.nonzero() print sp._firingBoostFactors[output1.nonzero()[0]] print sp._synPermBoostFactors[output1.nonzero()[0]] print 'Input elements distance is %d' % intInDist print input1.nonzero() print input2.nonzero() sys.stdin.readline() """ if not doLearn: x = int(PLOT_PRECISION * intOutDist / 40.0) y = int(PLOT_PRECISION * intInDist / 42.0) if distribMatrix[x, y] < 0.1: distribMatrix[x, y] = 3 else: if distribMatrix[x, y] < 10: distribMatrix[x, y] += 1 #print i # If we don't want a plot, just continue if wantPlot and cleanPlot: plt.imshow(distribMatrix, origin='lower', interpolation="nearest") plt.ylabel('SP (2048/40) distance in %') plt.xlabel('Input (400/42) distance in %') title = 'SP distribution' #if doLearn: # title += ', leaning ON' #else: # title += ', learning OFF' title += ', learn sets = %d' % numLearns title += ', test sets = %d' % numTests title += ', iter = %d' % numIter title += ', groups = %d' % numGroups title += ', Pct =%f' % poolPct plt.suptitle(title, fontsize=12) #plt.show() plt.savefig( os.path.join('~/Desktop/ExperimentResults/videosNew', '%s' % i)) plt.clf() distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1)) cleanPlot = False
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"], # Potential radius should be set to the input size if there is global # inhibition. potentialRadius=encodingWidth, # 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=True) 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
# minval=0, # maxval=100) #consumeEncoder = AdaptiveScalarEncoder( # n=400, # w=21) consumeEncoder = SimHashDistributedScalarEncoder(n=400, w=21, resolution=0.25) encodingWidth = (timeOfDayEncoder.getWidth() + weekendEncoder.getWidth() + consumeEncoder.getWidth()) classifier = SDRClassifierFactory.create() sp = SpatialPooler(inputDimensions=(encodingWidth, ), columnDimensions=(COL_WIDTH), potentialPct=0.85, potentialRadius=encodingWidth, globalInhibition=True, localAreaDensity=-1.0, numActiveColumnsPerInhArea=40, synPermInactiveDec=0.005, synPermActiveInc=0.04, synPermConnected=0.1, boostStrength=3.0, seed=1956, wrapAround=False) tm = TemporalMemory(columnDimensions=(COL_WIDTH, ), cellsPerColumn=32, activationThreshold=16, initialPermanence=0.21, connectedPermanence=0.5, minThreshold=12, maxNewSynapseCount=20, permanenceIncrement=0.1, permanenceDecrement=0.1,
def initialize(self): # Keep track of value range for spatial anomaly detection. self.minVal = None self.maxVal = None # Time of day encoder self.timeOfDayEncoder = DateEncoder(timeOfDay=(21, 9.49), name='time_enc') # RDSE encoder for the time series value. minResolution = 0.001 rangePadding = abs(self.inputMax - self.inputMin) * 0.2 minVal = self.inputMin - rangePadding maxVal = self.inputMax + rangePadding numBuckets = 130 resolution = max(minResolution, (maxVal - minVal) / numBuckets) self.value_enc = RandomDistributedScalarEncoder(resolution=resolution, name='value_rdse') # Spatial Pooler. encodingWidth = self.timeOfDayEncoder.getWidth( ) + self.value_enc.getWidth() self.sp = SpatialPooler( inputDimensions=(encodingWidth, ), columnDimensions=(2048, ), potentialPct=0.8, potentialRadius=encodingWidth, globalInhibition=1, numActiveColumnsPerInhArea=40, synPermInactiveDec=0.0005, synPermActiveInc=0.003, synPermConnected=0.2, boostStrength=0.0, seed=1956, wrapAround=True, ) self.tm = TemporalMemory( columnDimensions=(2048, ), cellsPerColumn=32, activationThreshold=20, initialPermanence=.5, # Increased to connectedPermanence. connectedPermanence=.5, minThreshold=13, maxNewSynapseCount=31, permanenceIncrement=0.04, permanenceDecrement=0.008, predictedSegmentDecrement=0.001, maxSegmentsPerCell=128, maxSynapsesPerSegment= 128, # Changed meaning. Also see connections.topology[2] seed=1993, ) # Initialize the anomaly likelihood object numentaLearningPeriod = int(math.floor(self.probationaryPeriod / 2.0)) self.anomalyLikelihood = anomaly_likelihood.AnomalyLikelihood( learningPeriod=numentaLearningPeriod, estimationSamples=self.probationaryPeriod - numentaLearningPeriod, reestimationPeriod=100, ) self.age = 0
def _runLearnInference(self, n=30, w=15, columnDimensions=2048, numActiveColumnsPerInhArea=40, spSeed=1951, spVerbosity=0, numTrainingRecords=100, seed=42): # Instantiate two identical spatial pooler. One will be used only for # learning. The other will be trained with identical records, but with # random inference calls thrown in spLearnOnly = SpatialPooler( columnDimensions=(columnDimensions, 1), inputDimensions=(1, n), potentialRadius=n / 2, numActiveColumnsPerInhArea=numActiveColumnsPerInhArea, spVerbosity=spVerbosity, seed=spSeed, synPermInactiveDec=0.01, synPermActiveInc=0.2, synPermConnected=0.11, ) spLearnInfer = SpatialPooler( columnDimensions=(columnDimensions, 1), inputDimensions=(1, n), potentialRadius=n / 2, numActiveColumnsPerInhArea=numActiveColumnsPerInhArea, spVerbosity=spVerbosity, seed=spSeed, synPermInactiveDec=0.01, synPermActiveInc=0.2, synPermConnected=0.11, ) random.seed(seed) np.random.seed(seed) # Build up training set with numTrainingRecords patterns inputs = [] # holds post-encoded input patterns for i in xrange(numTrainingRecords): inputVector = np.zeros(n, dtype=realDType) inputVector[random.sample(xrange(n), w)] = 1 inputs.append(inputVector) # Train each SP with identical inputs startTime = time.time() random.seed(seed) np.random.seed(seed) for i in xrange(numTrainingRecords): if spVerbosity > 0: print "Input #%d" % i # TODO: See https://github.com/numenta/nupic/issues/2072 encodedInput = inputs[i] decodedOutput = np.zeros(columnDimensions) spLearnOnly.compute(encodedInput, learn=True, activeArray=decodedOutput) random.seed(seed) np.random.seed(seed) for i in xrange(numTrainingRecords): if spVerbosity > 0: print "Input #%d" % i # TODO: See https://github.com/numenta/nupic/issues/2072 encodedInput = inputs[i] decodedOutput = np.zeros(columnDimensions) spLearnInfer.compute(encodedInput, learn=True, activeArray=decodedOutput) print "\nElapsed time: %.2f seconds\n" % (time.time() - startTime) # Test that both SP"s are identical by checking learning stats # A more in depth test would check all the coincidences, duty cycles, etc. # ala tpDiff # Edit: spDiff has been written as an in depth tester of the spatial pooler learnOnlyStats = spLearnOnly.getLearningStats() learnInferStats = spLearnInfer.getLearningStats() success = True # Check that the two spatial poolers are equivalent after the same training. success = success and spDiff(spLearnInfer, spLearnOnly) self.assertTrue(success) # Make sure that the pickled and loaded SPs are equivalent. spPickle = pickle.dumps(spLearnOnly, protocol=0) spLearnOnlyLoaded = pickle.loads(spPickle) success = success and spDiff(spLearnOnly, spLearnOnlyLoaded) self.assertTrue(success) for k in learnOnlyStats.keys(): if learnOnlyStats[k] != learnInferStats[k]: success = False print "Stat", k, "is different:", learnOnlyStats[ k], learnInferStats[k] self.assertTrue(success) if success: print "Test succeeded"
import numpy as np from tqdm import tqdm from nupic.encoders.scalar import ScalarEncoder from nupic.algorithms.spatial_pooler import SpatialPooler from nupic.algorithms.temporal_memory import TemporalMemory from nupic.algorithms.sdr_classifier import SDRClassifier N = 900 x = np.sin(np.arange(N) * 2 * np.pi / 30.0) inputDimensions = (256, ) columnDimensions = (512, ) encoder = ScalarEncoder(21, -1.0, 1.0, n=inputDimensions[0]) sp = SpatialPooler(inputDimensions=inputDimensions, columnDimensions=columnDimensions, globalInhibition=True, numActiveColumnsPerInhArea=21) tm = TemporalMemory(columnDimensions=columnDimensions) c = SDRClassifier(steps=[1], alpha=0.1, actValueAlpha=0.1, verbosity=0) x_true = x[1:] x_predict = np.zeros(len(x) - 1) for i, xi in tqdm(enumerate(x[:-1])): encoded = encoder.encode(xi) bucketIdx = np.where(encoded > 0)[0][0] spd = np.zeros(columnDimensions[0]) sp.compute(encoded, True, spd) active_indices = np.where(spd > 0)[0] tm.compute(active_indices)
# Spatial Pooler Parameters var_encoders = {Encoder('value', ['RDSE'])} # Encoder('_index', ['TODE'])} encoder_width = 0 for x in var_encoders: for y in x.encoders: exec("s = " + y + ".getWidth()") encoder_width += s SP = SpatialPooler( inputDimensions=encoder_width, columnDimensions=pooler_out, potentialPct=0.8, globalInhibition=True, numActiveColumnsPerInhArea=pooler_out // 50, # Gets 2% of the total area boostStrength=1.0, wrapAround=False) TM = TemporalMemory(columnDimensions=(pooler_out, ), cellsPerColumn=cell_col) # Train Spatial Pooler start = time.time() active_columns = np.zeros(pooler_out) print("Spatial pooler learning") for x in range(len(Data)): encoder = multiencode(var_encoders, Data, x) # e_val = RDSE.encode(Data['value'][x])
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 testInhibition(self): """ Test if the firing number of coincidences after inhibition equals spatial pooler numActiveColumnsPerInhArea. """ # Miscellaneous variables: # n, w: n, w of encoders # inputLen: Length of binary input # synPermConnected: Spatial pooler synPermConnected # synPermActiveInc: Spatial pooler synPermActiveInc # connectPct: Initial connect percentage of permanences # columnDimensions: Number of spatial pooler coincidences # numActiveColumnsPerInhArea: Spatial pooler numActiveColumnsPerInhArea # stimulusThreshold: Spatial pooler stimulusThreshold # spSeed: Spatial pooler for initial permanences # stimulusThresholdInh: Parameter for inhibition, default value 0.00001 # kDutyCycleFactor: kDutyCycleFactor for dutyCycleTieBreaker in # Inhibition # spVerbosity: Verbosity to print other sp initial parameters # testIter: Testing iterations n = 100 w = 15 inputLen = 300 columnDimensions = 2048 numActiveColumnsPerInhArea = 40 stimulusThreshold = 0 spSeed = 1956 stimulusThresholdInh = 0.00001 kDutyCycleFactor = 0.01 spVerbosity = 0 testIter = 100 spTest = SpatialPooler( columnDimensions=(columnDimensions, 1), inputDimensions=(1, inputLen), potentialRadius=inputLen / 2, numActiveColumnsPerInhArea=numActiveColumnsPerInhArea, spVerbosity=spVerbosity, stimulusThreshold=stimulusThreshold, seed=spSeed) initialPermanence = spTest._initialPermanence() spTest._masterPotentialM, spTest._masterPermanenceM = ( spTest._makeMasterCoincidences(spTest.numCloneMasters, spTest._coincRFShape, spTest.potentialPct, initialPermanence, spTest.random)) spTest._updateInhibitionObj() boostFactors = numpy.ones(columnDimensions) for i in range(testIter): spTest._iterNum = i # random binary input input_ = numpy.zeros((1, inputLen)) nonzero = numpy.random.random(inputLen) input_[0][numpy.where(nonzero < float(w) / float(n))] = 1 # overlap step spTest._computeOverlapsFP( input_, stimulusThreshold=spTest.stimulusThreshold) spTest._overlaps *= boostFactors onCellIndices = numpy.where(spTest._overlaps > 0) spTest._onCells.fill(0) spTest._onCells[onCellIndices] = 1 denseOn = spTest._onCells # update _dutyCycleBeforeInh spTest.dutyCyclePeriod = min(i + 1, 1000) spTest._dutyCycleBeforeInh = ( (spTest.dutyCyclePeriod - 1) * spTest._dutyCycleBeforeInh + denseOn) / spTest.dutyCyclePeriod dutyCycleTieBreaker = spTest._dutyCycleAfterInh.copy() dutyCycleTieBreaker *= kDutyCycleFactor # inhibition step numOn = spTest._inhibitionObj.compute( spTest._overlaps + dutyCycleTieBreaker, spTest._onCellIndices, stimulusThresholdInh, # stimulusThresholdInh max(spTest._overlaps) / 1000, # addToWinners ) # update _dutyCycleAfterInh spTest._onCells.fill(0) onCellIndices = spTest._onCellIndices[0:numOn] spTest._onCells[onCellIndices] = 1 denseOn = spTest._onCells spTest._dutyCycleAfterInh = ( ((spTest.dutyCyclePeriod - 1) * spTest._dutyCycleAfterInh + denseOn) / spTest.dutyCyclePeriod) # learning step spTest._adaptSynapses(onCellIndices, [], input_) # update boostFactor spTest._updateBoostFactors() boostFactors = spTest._firingBoostFactors # update dutyCycle and boost if ((spTest._iterNum + 1) % 50) == 0: spTest._updateInhibitionObj() spTest._updateMinDutyCycles(spTest._dutyCycleBeforeInh, spTest.minPctDutyCycleBeforeInh, spTest._minDutyCycleBeforeInh) spTest._updateMinDutyCycles(spTest._dutyCycleAfterInh, spTest.minPctDutyCycleAfterInh, spTest._minDutyCycleAfterInh) # test numOn and spTest.numActiveColumnsPerInhArea self.assertEqual( numOn, spTest.numActiveColumnsPerInhArea, "Error at input %s, actual numOn are: %i, " "numActivePerInhAre is: %s" % (i, numOn, numActiveColumnsPerInhArea))