def build_seg(self, minSize = None, plotSwitch = None):
if plotSwitch is None:
plotSwitch = False
if minSize is None:
minSize = 2
#GAP_k = self.GAP_decide_k(minSize)
# by using the K generated by GAP_decide_k statics, segment the time series again
# BUGFIX: bottomup_seg(ts=self.__ts...., should input self.__normTS!
#segTS, _, seg_fit_list, seg_symbol_list = bottomup_seg(ts=self.__ts, max_err=sys.float_info.max, init_size=minSize, k=GAP_k, PLOT_DEBUG=plotSwitch)
# GAP decide K
# segTS, _, seg_fit_list = bottomup_seg(ts=self.__normTS, max_err=sys.float_info.max, init_size=minSize, k=GAP_k, PLOT_DEBUG=plotSwitch)
# just use maximum segment error
segTS, _, seg_fit_list = bottomup_seg(ts=self.__normTS, max_err=self.__zero_thresh, init_size=minSize, k=1, PLOT_DEBUG=plotSwitch)
if plotSwitch:
plot_segts_fit(self.__normTS, seg_ts=segTS, seg_fit=seg_fit_list)
plt.show(block=False)
self.__seg_fit_list = seg_fit_list
self.__segTS = segTS
pass
def gap_uniform(lenTS, minSize = None, num_round = None):
if minSize is None:
minSize = 2
# See paper: we estimate error of segmentation by taking the mean of 10 uniformly randomly time series
if num_round is None:
num_round = 10
random.seed(time.time())
# estimate error from uniform random time series
mat = np.array([])
for i in range(num_round):
# generate uniform time series in the range of [0,1]
uniformTS = np.array([random.uniform(0,1) for _ in range(lenTS)])
# bottomUp: use initSize=2 and k=1 to iterate every possible number of segments
_, uniformSegCost, _ = bottomup_seg(ts=uniformTS, max_err=sys.float_info.max, k=1, init_size=minSize)
# the testing K must be in [1, len(uniformTS) // 2]
# assert len(uniformSegCost) == (len(uniformTS) // minSize - 1)
if not( len(uniformSegCost) == (len(uniformTS) // minSize - 1)):
print len(uniformSegCost), (len(uniformTS) // minSize - 1)
# the length of uniformSegCost
mat = mat.reshape(i, len(uniformSegCost))
mat = np.vstack([mat, np.array(uniformSegCost)])
pass
# calculate the weighted GAP and get smoothing factor GAP
mat = np.log(mat)
sk = (num_round - 1) * publib.std(mat,axis=0) / num_round * np.sqrt(1 + 1/num_round)
weightGAP = np.mean(mat, axis=0) - sk
# return num_round uniform random experiments
return weightGAP
def GAP_decide_k(self, minSize):
logger = logging.getLogger("SSSTSR_Class.GAP_decide_k")
logger.setLevel(self.__loggerLevel)
logger.addHandler(publib.console_handle)
# calculate the error of uniform random time series
uniformSegErr = gap_uniform(len(self.__normTS), minSize)
# get segmentation error of scaled time series
# TRICK: input normalize time series!
_, ts_segCost, _ = bottomup_seg(max_err=sys.float_info.max, ts=self.__normTS, k=1, init_size=minSize)
# TRICK: sometime regression is perfect matching, so ts_segCost is very tiny
# cutOffPoint = (ts_segCost > 1e-10).sum()
cutOffPoint = len(ts_segCost)
# compute gap
gap_K = np.log(ts_segCost[range(cutOffPoint)]) - uniformSegErr[range(cutOffPoint)]
# gap_K_minus = ts_segCost[range(cutOffPoint)] - uniformSegErr[range(cutOffPoint)]
# compute gap with first derivative, second derivative
gapDiff1 = -np.diff(gap_K)
gapDiff2 = -np.diff(gapDiff1)
#-----------------------------------------------------
# TRICK: the index of gapDiff2 start from 0, but it actually means 1
# GAP_K = np.argmax(gapDiff2) + 1
#-----------------------------------------------------
# TRICK: In the ideal situation, the first derivative should become zeros from the point of K
# So, we add a "nearly zero" region, that gap_1st_dev < T (T is hardcode, 0.05 is this case)
# Then, find the K after which the first derivatives are strictly "nearly zero"
# NOTE: nearlyZeroThresh is a very important internal parameter!
nearlyZeroThresh = self.__zero_thresh # TODO: find it automaticlly?
temp = (gapDiff1 >= nearlyZeroThresh)
if ((np.nonzero(temp[::-1]))[0]).size == 0:
# all gapDiff1 could be less than nearlyZeroThresh
GAP_K = GAP_K = np.argmax(gapDiff2) + 1
else:
GAP_K = len(gapDiff1) - (np.nonzero(temp[::-1]))[0][0]
#logger.info("GAP choose " + str(GAP_K) + " as the number of segments.")
# plot GAP_decide_k, 1st diff, 2nd diff curve
# self.plot_gap_curve(gap_K, gapDiff1, gapDiff2, ts_segCost, uniformSegErr)
# self.plot_gap_curve(gap_K, gapDiff1, gapDiff2, ts_segCost, uniformSegErr, gap_K_minus)
#self.plot_gap_curve(gap_K, gapDiff1, gapDiff2)
return GAP_K
