def demo(readLocation="../data/sensor_data/late_small.dat"):
import dataio
oData = dataio.loadData(readLocation)
val = bestCorrelation(oData.data, offsetMax=3, offsetMin=1)
neighbors = createNeighbors(val)
oData.correlation = val
oData.neighbors = neighbors
dataio.saveData(readLocation, oData)
def demo(readLocation = "../data/sensor_data/late_small.dat"):
import dataio
oData = dataio.loadData(readLocation)
val = bestCorrelation(oData.data, offsetMax = 3, offsetMin = 1)
neighbors = createNeighbors(val)
oData.correlation = val
oData.neighbors = neighbors
dataio.saveData(readLocation, oData)
import bbdata
if __name__ == "__main__":
readLocation = "../data/old_sensor_data_raw/"
writeLocation = "../data/sensor_data/ss.dat"
startTime = "2008-02-15 00:00:00"
endTime = "2008-02-25 23:59:59"
sensors = [53, 52, 51, 50, 44]
validDays = [1, 3, 5]
data, start, end = bbparser.rawDataToBinaryExtended(readLocation, \
#bbparser.allSensors, \
sensors, \
startTime, endTime, \
validDays = validDays, \
verbose = True)
sTime = time.ctime(start)
eTime = time.ctime(end)
print "Data made. Size is " + str(data.shape)
print "Time goes from " + str(sTime) + " to " + str(eTime)
tmpData = bbdata.Dataset(data)
tmpData.startTime = sTime
tmpData.endTime = eTime
dataio.saveData(writeLocation, tmpData)
#directories.append("detectionsOct2007")
#directories.append("detectionsNov2007")
#directories.append("detectionsDec2007")
#directories.append("detectionsJan2008")
#directories.append("detectionsFeb2008")
#directories.append("detectionsMar2008")
#directories.append("detectionsApr2008")
directories.append("detectionsJan2008-Mar2008")
#directories.append("detectionsSep2007-Dec2007")
for i in range(1, 11):
for j in range(0, 5):
sensors.append(i*10 + j)
print "Sensors:" + str(len(sensors))
tdMatrix = calculateTDMatrix(readLoc, startTime, endTime, interval, directories, sensors)
print tdMatrix
oData = None
try:
oData = dataio.loadData(fileLoc)
except:
oData = bbdata.Dataset(None)
oData.tdMatrix = tdMatrix
dataio.saveData(fileLoc, oData)
scores = [0, 0]
entropys = [0, 0]
for i in range(2, 26):
print "Models:" + str(i)
bestScore = -1
bestModels = []
bestData = []
bestOut = []
for j in range(2):
suppress.suppress(2)
bm, bd, out = markov_anneal.train(sData, i, states, obs, \
iterations = 9, outliers = False, voidOutput = False)
suppress.restore(2)
mea = markov_anneal.modelErrorAverage(bm, bd, obs)
entropy = markov_anneal.assignedDataEntropy(bd, out)
score = (2**(sum(mea)/(len(mea) * 1.0)))*entropy
if bestScore == -1 or score < bestScore:
bestScore = score
bestEnt = entropy
print " best score:" + str(bestScore) + " best entropy:" + str(bestEnt)
scores.append(bestScore)
entropys.append(bestEnt)
oData.scores = scores
oData.entropys = entropys
dataio.saveData(readLocation, oData)
entropys = [0, 0]
for i in range(2, 26):
print "Models:" + str(i)
bestScore = -1
bestModels = []
bestData = []
bestOut = []
for j in range(2):
suppress.suppress(2)
bm, bd, out = markov_anneal.train(sData, i, states, obs, \
iterations = 9, outliers = False, voidOutput = False)
suppress.restore(2)
mea = markov_anneal.modelErrorAverage(bm, bd, obs)
entropy = markov_anneal.assignedDataEntropy(bd, out)
score = (2**(sum(mea) / (len(mea) * 1.0))) * entropy
if bestScore == -1 or score < bestScore:
bestScore = score
bestEnt = entropy
print " best score:" + str(bestScore) + " best entropy:" + str(
bestEnt)
scores.append(bestScore)
entropys.append(bestEnt)
oData.scores = scores
oData.entropys = entropys
dataio.saveData(readLocation, oData)
#directories.append("detectionsOct2007")
#directories.append("detectionsNov2007")
#directories.append("detectionsDec2007")
#directories.append("detectionsJan2008")
#directories.append("detectionsFeb2008")
#directories.append("detectionsMar2008")
#directories.append("detectionsApr2008")
directories.append("detectionsJan2008-Mar2008")
#directories.append("detectionsSep2007-Dec2007")
for i in range(1, 11):
for j in range(0, 5):
sensors.append(i * 10 + j)
print "Sensors:" + str(len(sensors))
tdMatrix = calculateTDMatrix(readLoc, startTime, endTime, interval,
directories, sensors)
print tdMatrix
oData = None
try:
oData = dataio.loadData(fileLoc)
except:
oData = bbdata.Dataset(None)
oData.tdMatrix = tdMatrix
dataio.saveData(fileLoc, oData)
Simple program that should only need to be run once for each data run.
Takes data from a given location and calls all necessary functions to
prepare the data for being run with different hmm trails.
"""
import dataio
import bbdata
calcCombineData = True
calcCompressedData = True
combineAmount = 2
readLocation = "../data/sensor_data/ss.dat"
writeLocation = "../data/sensor_data/ss.dat"
if __name__ == "__main__":
oData = dataio.loadData(readLocation)
oData.ad = oData.data
if calcCombineData:
print "Calculating combine data with size of " + str(combineAmount)
averagedData = bbdata.combineData(oData.data, combineAmount)
oData.ad = averagedData
dataio.saveData(writeLocation, oData)
if calcCompressedData:
print "Calculating compressed data."
compressedData = bbdata.compressData(oData.ad)
oData.cd = compressedData
dataio.saveData(writeLocation, oData)
import correlation
import bbdata
if __name__ == "__main__":
readLocation = "../data/old_sensor_data_raw/"
writeLocation = "../data/sensor_data/ss.dat"
startTime = "2008-02-15 00:00:00"
endTime = "2008-02-25 23:59:59"
sensors = [53, 52, 51, 50, 44]
validDays = [1, 3, 5]
data, start, end = bbparser.rawDataToBinaryExtended(readLocation, \
#bbparser.allSensors, \
sensors, \
startTime, endTime, \
validDays = validDays, \
verbose = True)
sTime = time.ctime(start)
eTime = time.ctime(end)
print "Data made. Size is " + str(data.shape)
print "Time goes from " + str(sTime) + " to " + str(eTime)
tmpData = bbdata.Dataset(data)
tmpData.startTime = sTime
tmpData.endTime = eTime
dataio.saveData(writeLocation, tmpData)
def save(self):
dataio.saveData()
return "Data Saved"
data[i * readings:i * readings + readings, :] = tmpData
return data
if __name__ == "__main__":
dist = []
saveLocation = "../data/generated/small.dat"
sensors = 5
readings = 250
#dist.append(Distribution(nLoiter = 20, \
# mLoiter = 5, \
# stdLoiter = 0))
dist.append(Distribution(nWalkLeft = 20, \
mWalkLeft = 5, \
stdWalkLeft = 0))
dist.append(Distribution(nWalkRight = 20, \
mWalkRight = 5, \
stdWalkRight = 0))
data = combineData(dist, readings, sensors)
tmpData = bbdata.Dataset(data)
dataio.saveData(saveLocation, tmpData)
visualizer.drawData(data)
print "Generated image."
for d in validDays:
print "Day " + str(d)
print " Getting data."
#Iterate over all valid days.
cd, td = bbdata.comp(st, et, \
vDays = [d], \
comp = compress, \
sens = sensors)
print " Splitting."
#Get the split calculation finished.
sData = markov_anneal.splitActivityMax(cd, td, splitLen)
print " Calculating."
sigma = IntegerRange(0, 2**len(sensors))
val, counts = analysis.ratio(sData.values(), models, sigma)
tdMatrix.append(counts)
#Save output matrix.
foo = bbdata.Dataset(None)
foo.tdMatrix = numpy.array(tdMatrix)
dataio.saveData(writeLocation, foo)
return data
if __name__ == "__main__":
dist = []
saveLocation = "../data/generated/small.dat"
sensors = 5
readings = 250
#dist.append(Distribution(nLoiter = 20, \
# mLoiter = 5, \
# stdLoiter = 0))
dist.append(Distribution(nWalkLeft = 20, \
mWalkLeft = 5, \
stdWalkLeft = 0))
dist.append(Distribution(nWalkRight = 20, \
mWalkRight = 5, \
stdWalkRight = 0))
data = combineData(dist, readings, sensors)
tmpData = bbdata.Dataset(data)
dataio.saveData(saveLocation, tmpData)
visualizer.drawData(data)
print "Generated image."