def complexRun(plot = True):
dataLength = 200
actLength = 13
numActivities = 1
actSize = 0.5
actStd = 0.05
backStd = 0.1
minWindowLen = 2
maxWindowLen = 8
backMean = 0.0
#Create simple gaussian noise
data = [random.gauss(backMean, backStd) for i in range(dataLength)]
acts = pybb.data.generateActivities1d(10, actLength, actSize, actStd, aType = 2)
#Make testing data
sacts = pybb.data.generateActivities1d(numActivities, actLength, actSize, actStd, aType = 2)
starts = []
for s in sacts:
#Pick a random spot
start = int((dataLength - actLength) * random.random())
starts.append(start)
for i in range(len(s)):
data[start + i] = s[i]
m, mdata, mout = khmm.train(acts.tolist(), 1, actLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++",
verbose = False)
model = []
model.append(gaussian.Gaussian(backMean, backStd))
model.append(m[0])
bf = BayesianForecast(model)
bf.setStd(0, backStd)
bf.setStd(1, actStd)
#fdata, probs, windowLens = bf.forecast(data, windowLen = minWindowLen, ftype = "best")
fdata, probs, windowLens, models = bf.windowForecast(data, \
minWindow = minWindowLen, \
maxWindow = maxWindowLen, \
ftype = "best")
if plot:
mpl.subplot(211)
xdata = range(len(data))
mpl.plot(xdata, data, 'k', alpha = 0.5, linewidth = 2)
mpl.plot(xdata, fdata, 'r', alpha = 0.5)
mpl.xlim([0, len(data) - 1])
mpl.subplot(212)
xdata = range(actLength)
for s in sacts:
mpl.plot(xdata, s, 'k', alpha = 0.5)
mpl.xlim([0, actLength - 1])
return data, starts, fdata, probs, bf, windowLens, models
def complexRun(plot=True):
dataLength = 200
actLength = 13
numActivities = 1
actSize = 0.5
actStd = 0.05
backStd = 0.1
minWindowLen = 2
maxWindowLen = 8
backMean = 0.0
#Create simple gaussian noise
data = [random.gauss(backMean, backStd) for i in range(dataLength)]
acts = pybb.data.generateActivities1d(10,
actLength,
actSize,
actStd,
aType=2)
#Make testing data
sacts = pybb.data.generateActivities1d(numActivities,
actLength,
actSize,
actStd,
aType=2)
starts = []
for s in sacts:
#Pick a random spot
start = int((dataLength - actLength) * random.random())
starts.append(start)
for i in range(len(s)):
data[start + i] = s[i]
m, mdata, mout = khmm.train(acts.tolist(), 1, actLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++",
verbose = False)
model = []
model.append(gaussian.Gaussian(backMean, backStd))
model.append(m[0])
bf = BayesianForecast(model)
bf.setStd(0, backStd)
bf.setStd(1, actStd)
#fdata, probs, windowLens = bf.forecast(data, windowLen = minWindowLen, ftype = "best")
fdata, probs, windowLens, models = bf.windowForecast(data, \
minWindow = minWindowLen, \
maxWindow = maxWindowLen, \
ftype = "best")
if plot:
mpl.subplot(211)
xdata = range(len(data))
mpl.plot(xdata, data, 'k', alpha=0.5, linewidth=2)
mpl.plot(xdata, fdata, 'r', alpha=0.5)
mpl.xlim([0, len(data) - 1])
mpl.subplot(212)
xdata = range(actLength)
for s in sacts:
mpl.plot(xdata, s, 'k', alpha=0.5)
mpl.xlim([0, actLength - 1])
return data, starts, fdata, probs, bf, windowLens, models
pybb.data.parseEvents(fData, sunTimes, eventTimes)
#Get just the broncos residual 9-15
resEventData = []
for r in resSData:
resEventData.append(r[9:17])
#Convert to list
tmp = np.array(resEventData)
resEventData = tmp.tolist()
resEventData = pybb.data.stripZero(resEventData, threshold=6)
#Train HMM
m, mdata, mout = khmm.train(resEventData, 1, actLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++",
verbose = False)
mase = analysis.mase(sunData1d, fData1d)
mape = analysis.mape(sunData1d, fData1d)
print "Mean Mase:", mase
print "Mean Mape:", mape
#Setup forecast
model = []
model.append(gaussian.Gaussian(resData.mean(), resData.std()))
#model.append(gaussian.Gaussian(0, resData.std()))
model.append(m[0])
bf = bayesianforecast.BayesianForecast(model)
mpl.subplot(211)
xdata = range(periodLength)
for d in data:
mpl.plot(xdata, d, 'k', alpha = 0.3)
mpl.xlim([0, periodLength - 1])
#Residuals
mpl.subplot(212)
xdata = range(activityLength)
for a in act:
mpl.plot(xdata, a, 'k', alpha = 0.3)
mpl.xlim([0, activityLength - 1])
#Train Models
model, mdata, mout = khmm.train(act.tolist(), numModels, activityLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++")
model.append(gaussian.Gaussian(0, res1d.std()))
"""
#Perform a simple forecast for one dataelement.
#Start with simply two periods
sdata = res1d[(acts[0][0] - 2) * periodLength:(acts[0][0]) * periodLength]
#Forecast all points along sdata
bf = bayesian.BayesianForecast(model)
bf.setStd(0, res1d.std())
bf.setStd(1, res1d.std())
windowLen = 5
bfData = []
mpl.subplot(211)
xdata = range(periodLength)
for d in data:
mpl.plot(xdata, d, 'k', alpha=0.3)
mpl.xlim([0, periodLength - 1])
#Residuals
mpl.subplot(212)
xdata = range(activityLength)
for a in act:
mpl.plot(xdata, a, 'k', alpha=0.3)
mpl.xlim([0, activityLength - 1])
#Train Models
model, mdata, mout = khmm.train(act.tolist(), numModels, activityLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++")
model.append(gaussian.Gaussian(0, res1d.std()))
"""
#Perform a simple forecast for one dataelement.
#Start with simply two periods
sdata = res1d[(acts[0][0] - 2) * periodLength:(acts[0][0]) * periodLength]
#Forecast all points along sdata
bf = bayesian.BayesianForecast(model)
bf.setStd(0, res1d.std())
bf.setStd(1, res1d.std())
windowLen = 5
bfData = []
scores.append(a)
return scores
def findFit(data, models):
index = []
for d in data:
index.append(bestFit(d, models))
return index
if __name__ == "__main__":
data = sampleMany(200, 8, atype = 0)
data += sampleMany(200, 8, atype = 1)
m, d, o = khmm.train(data, 2, 8, iterations = 10, outliers = False, \
clustering = "kmeans++")
res = findFit(data, m)
counts = [0, 0]
for r in range(len(data)):
i = r / len(data) / 2
counts[i] += res[r]
print counts
print "This should print out something close to 200, 0 or 0, 200"
#Get just the broncos residual 9-15
resEventData = []
for r in resSData:
resEventData.append(r[9:17])
#Convert to list
tmp = np.array(resEventData)
resEventData = tmp.tolist()
resEventData = pybb.data.stripZero(resEventData, threshold = 6)
#Train HMM
m, mdata, mout = khmm.train(resEventData, 1, actLength, \
iterations = 20, outliers = False, \
clustering = "kmeans++",
verbose = False)
mase = analysis.mase(sunData1d, fData1d)
mape = analysis.mape(sunData1d, fData1d)
print "Mean Mase:", mase
print "Mean Mape:", mape
#Setup forecast
model = []
model.append(gaussian.Gaussian(resData.mean(), resData.std()))
#model.append(gaussian.Gaussian(0, resData.std()))
model.append(m[0])