def runDataset(dataset):
"""
Runs through the dataset given for anomaly detection
"""
# set model parameters, csv path, and output csv/plot
if (dataset == 0):
model_par = machine_model_params
csv_path = "./data/machine_temperature_system_failure.csv"
outputCSVFile = nupic_output.NuPICFileOutput(
["Machine_Temp_Sys_Failure_OUTPUT_CSV"])
outputPlotFile = nupic_output.NuPICPlotOutput(
["Machine_Temp_Sys_Failure_OUTPUT_PLOT"])
elif (dataset == 1):
model_par = twitter_model_params
csv_path = "./data/Twitter_volume_GOOG.csv"
outputCSVFile = nupic_output.NuPICFileOutput(
["Twitter_Volume_Google_OUTPUT_CSV"])
outputPlotFile = nupic_output.NuPICPlotOutput(
["Twitter_Volume_Google_OUTPUT_PLOT"])
else:
print("No specified dataset, error will occur")
model_params = None
# create model
model = createModel(model_par)
#run model
runModel(model, csv_path, outputCSVFile, outputPlotFile)
def runModel(model):
inputFile = open("rec-center-hourly.csv", "rb")
csvReader = csv.reader(inputFile)
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
output = nupic_output.NuPICPlotOutput(['REC center'])
counter = 0
for row in csvReader:
counter += 1
if (counter % 100 == 0):
print("Read %i lines", counter)
timestamp = datetime.datetime.strptime(row[0], DATE_FORMAT)
consumption = float(row[1])
result = model.run({
"timestamp": timestamp,
"kw_energy_consumption": consumption
})
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([timestamp], [consumption], [prediction])
inputFile.close()
output.close()
def runIoThroughNupic(inputData, model, gymName, plot):
inputFile = open(inputData, "rb")
csvReader = csv.reader(inputFile)
# skip header rows
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput([gymName])
else:
output = nupic_output.NuPICFileOutput([gymName])
counter = 0
for row in csvReader:
counter += 1
if (counter % 100 == 0):
print "Read %i lines..." % counter
timestamp = datetime.datetime.strptime(row[0], DATE_FORMAT)
consumption = float(row[1])
result = model.run({
"timestamp": timestamp,
"kw_energy_consumption": consumption
})
if plot:
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([timestamp], [consumption], [prediction])
inputFile.close()
output.close()
def runIoThroughNupic(inputPath, model, modelName, plot=False):
with open(inputPath, "rb") as inputFile:
csvReader = csv.reader(inputFile)
# skip header rows
headers = csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput(modelName)
else:
output = nupic_output.NuPICFileOutput(modelName, path="data")
counter = 0
for row in csvReader:
assert len(row) == len(headers)
counter += 1
if (counter % 100 == 0):
print "Read %i lines..." % counter
row = [float(row[0])] + [int(val) for val in row[1:]]
input_row = dict(zip(headers, row))
result = model.run(input_row)
if plot:
seconds = input_row["seconds"]
actual = input_row[PREDICTED_BUCKET]
shifter.shift(result)
predicted = result.inferences["multiStepBestPredictions"][1]
output.write([seconds], [actual], [predicted])
else:
output.write(input_row, result)
output.close()
def runEEGAnomaly():
# Create Model
model = createModel()
model.enableInference({'predictedField': 'ch0','predictedField': 'ch1'})
# Load data
mat = scipy.io.loadmat(_DATA_FILE)
data = mat['data']
seconds = mat['seconds']
# plotting stuff?
output = nupic_output.NuPICPlotOutput(["ch0","ch1"])
#for i,t in data,seconds:
for i, t in zip(data, seconds):
#modelInput = dict(zip('ch1', i[0]))
modelInput = {'ch0':i[0],'ch1':i[1]}
result = model.run(modelInput)
#anomalyScore = result.inferences['anomalyScore']
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([t[0],t[0]],[i[0],i[1]],[prediction,prediction])
#if anomalyScore > _ANOMALY_THRESHOLD:
# _LOGGER.info("Anomaly detected. Anomaly score: %f.", anomalyScore)
print "Anomaly scores have been written to",_OUTPUT_PATH
def runModel(model, file_name):
'''
Run predictions with a given model.
Args:
model: Opf model.
'''
input_file = open(file_name, "rb")
csv_reader = csv.reader(input_file)
csv_reader.next()
csv_reader.next()
csv_reader.next()
shifter = InferenceShifter()
output = nupic_output.NuPICPlotOutput("Sine", show_anomaly_score=True)
for row in csv_reader:
angle = float(row[0])
sine = float(row[1])
result = model.run({"angle": angle, "sine": sine})
result = shifter.shift(result)
inference = result.inferences['multiStepBestPredictions'][1]
anomaly_score = result.inferences['anomalyScore']
output.write(sine, inference, anomaly_score)
input_file.close()
output.close()
def run_io_through_nupic(input_data, model, file_name, plot, print_results):
input_file = open(input_data, "rb")
csv_reader = csv.reader(input_file)
# skip header rows
csv_reader.next()
csv_reader.next()
csv_reader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput([file_name])
else:
output = nupic_output.NuPICFileOutput([file_name])
metrics_manager = MetricsManager(_METRIC_SPECS, model.getFieldInfo(),
model.getInferenceType())
counter = 0
timestamp = None
consumption = None
result = None
for row in csv_reader:
counter += 1
timestamp = datetime.datetime.strptime(row[1], DATE_FORMAT)
consumption = int(row[2])
amount = float(row[0])
result = model.run({
"amount": amount,
"date": timestamp,
"tte": consumption
})
result.metrics = metrics_manager.update(result)
if counter % 100 == 0 or counter % 384 == 0:
print "Read %i lines..." % counter
print ("After %i records, rmse=%f" % (counter,
result.metrics["multiStepBestPredictions:multiStep:"
"errorMetric='rmse':steps=1:window=1000:"
"field=tte"]))
if plot:
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([timestamp], [consumption], [prediction])
if print_results:
print("date:", timestamp.strftime("%y-%m-%d"), "actual:", consumption, "predicted:", prediction)
if plot and counter % 20 == 0:
output.refresh_gui()
#if plot and counter % 1000 == 0:
# break
input_file.close()
output.close()
def run(numRecords):
'''
Run the Hot Gym example.
'''
# Create a data source for the network.
dataSource = FileRecordStream(streamID=_INPUT_FILE_PATH)
numRecords = min(numRecords, dataSource.getDataRowCount())
network = createNetwork(dataSource)
network.regions["sensor"].getSelf().predictedField = "sine"
# Set predicted field
network.regions["sensor"].setParameter("predictedField", "sine")
# Enable learning for all regions.
network.regions["SP"].setParameter("learningMode", 1)
network.regions["TM"].setParameter("learningMode", 1)
network.regions["classifier"].setParameter("learningMode", 1)
# Enable inference for all regions.
network.regions["SP"].setParameter("inferenceMode", 1)
network.regions["TM"].setParameter("inferenceMode", 1)
network.regions["classifier"].setParameter("inferenceMode", 1)
results = []
N = 1 # Run the network, N iterations at a time.
output = nupic_output.NuPICPlotOutput("Sine", show_anomaly_score=True)
for iteration in range(0, numRecords, N):
network.run(N)
sine = network.regions["sensor"].getOutputData("sourceOut")[0]
predictionResults = getPredictionResults(network, "classifier")
oneStep = predictionResults[1]["predictedValue"]
oneStepConfidence = predictionResults[1]["predictionConfidence"]
fiveStep = predictionResults[10]["predictedValue"]
fiveStepConfidence = predictionResults[10]["predictionConfidence"]
result = (oneStep, oneStepConfidence * 100, fiveStep,
fiveStepConfidence * 100)
print "1-step: {:16} ({:4.4}%)\t 10-step: {:16} ({:4.4}%)".format(
*result)
results.append(result)
output.write(sine, oneStep, 0)
output.close()
return results
def runIoThroughNupic(inputData, model, name, plot):
inputFile = open(inputData, "rb")
csvReader = csv.reader(inputFile)
# skip header rows
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if len(plot) == 0:
for field in SWARM_DESCRIPTION["includedFields"]:
plot.append(field["fieldName"])
output = nupic_output.NuPICFileOutput(name, plot)
else:
output = nupic_output.NuPICPlotOutput(name, plot)
metricsManager = MetricsManager(_METRIC_SPECS, model.getFieldInfo(),
model.getInferenceType())
counter = 0
for row in csvReader:
counter += 1
data = {}
fldCounter = 0
for field in SWARM_DESCRIPTION["includedFields"]:
data[field["fieldName"]] = translate_data(field["fieldType"], row[fldCounter])
fldCounter += 1
result = model.run(data)
result.metrics = metricsManager.update(result)
if options.verbose is not None and counter % 100 == 0:
print "Read %i lines..." % counter
print ("After %i records, 1-step altMAPE=%f" % (counter,
result.metrics["multiStepBestPredictions:multiStep:"
"errorMetric='altMAPE':steps=1:window=1000:"
"field="+PREDICTED_FIELD]))
if plot:
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
vals = []
for field in plot:
vals.append(data[field])
output.write(vals, prediction)
inputFile.close()
output.close()
def runIoThroughNupic(inputData, model, gymName, plot):
inputFile = open(inputData, "rb")
csvReader = csv.reader(inputFile)
# skip header rows
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput([gymName])
else:
output = nupic_output.NuPICFileOutput([gymName])
metricsManager = MetricsManager(_METRIC_SPECS, model.getFieldInfo(),
model.getInferenceType())
counter = 0
for row in csvReader:
counter += 1
timestamp = datetime.datetime.strptime(row[0], DATE_FORMAT)
consumption = float(row[1])
result = model.run({
"timestamp": timestamp,
"kw_energy_consumption": consumption
})
result.metrics = metricsManager.update(result)
if counter % 100 == 0:
print "Read %i lines..." % counter
print("After %i records, 1-step altMAPE=%f" %
(counter,
result.metrics["multiStepBestPredictions:multiStep:"
"errorMetric='altMAPE':steps=1:window=1000:"
"field=kw_energy_consumption"]))
if plot:
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([timestamp], [consumption], [prediction])
if plot and counter % 20 == 0:
output.refreshGUI()
inputFile.close()
output.close()
def runIoThroughNupic(inputData, model, dataName, plot):
inputFile = open(inputData, "rU")
csvReader = csv.reader(inputFile)
# skip header rows
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput([dataName])
else:
output = nupic_output.NuPICFileOutput([dataName])
metricsManager = MetricsManager(_METRIC_SPECS, model.getFieldInfo(),
model.getInferenceType())
counter = 0
for row in csvReader:
counter += 1
y = float(row[0])
result = model.run({"y": y})
result.metrics = metricsManager.update(result)
if counter % 100 == 0:
print "Read %i lines..." % counter
print(
"After %i records, 1-step nrmse=%f", counter,
result.metrics["multiStepBestPredictions:multiStep:"
"errorMetric='nrmse':steps=1:window=1000000:"
"field=y"])
if plot:
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([0], [y], [prediction])
inputFile.close()
output.close()
def runIoThroughNupic(inputData, model, modelName, plot):
inputFile = open(inputData, "rb")
csvReader = csv.reader(inputFile)
# skip header rows
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
if plot:
output = nupic_output.NuPICPlotOutput([modelName])
else:
output = nupic_output.NuPICFileOutput([modelName])
counter = 0
for row in csvReader:
counter += 1
if (counter % 100 == 0):
print "Read %i lines..." % counter
#timestamp = datetime.datetime.strptime(row[0], DATE_FORMAT)
#consumption = float(row[1])
subject=row[0]
verb=row[1]
obj=row[2]
result = model.run({
"subject": subject,
"verb": verb,
"object":obj
})
if plot:
result = shifter.shift(result)
print "result: " + repr(result.inferences["multiStepBestPredictions"])
prediction = result.inferences["multiStepBestPredictions"][1]
output.write([subject], [verb], [obj], [prediction])
inputFile.close()
output.close()
def runModel(model):
predictions = []
inputFilePath = "RKIGTData.csv"
inputFile = open(inputFilePath, 'rb')
csvReader = csv.reader(inputFile)
# Skip header
csvReader.next()
csvReader.next()
csvReader.next()
shifter = InferenceShifter()
output = nupic_output.NuPICPlotOutput(["rki_faelle"])
counter = 0
for row in csvReader:
counter += 1
if (counter % 100 == 0):
print("Read %i lines ..." % counter)
time.sleep(1)
timestamp = datetime.datetime.strptime(row[0], DATE_FORMAT)
grippe = float(row[1])
flu = float(row[2])
faelle = float(row[3])
result = model.run({
"wstday": timestamp,
"Grippe": grippe,
"Influenza": flu,
"faelle": faelle
})
result = shifter.shift(result)
prediction = result.inferences["multiStepBestPredictions"][1]
output.write(
str(timestamp) + ',' + str(faelle) + ',' + str(prediction) + '\n')
#output.write([timestamp], [faelle], [prediction])
inputFile.close()
output.close()
