def __init__(self, histogram_type, lowerBounding=False, logger=None):
self.initialized = False
self.HistogramType = histogram_type
self.lowerBounding = lowerBounding
self.MUSE_Bool = False
logger.Log(self.__dict__, level=0)
self.logger = logger
self.sfa = SFA(histogram_type,
LB=self.lowerBounding,
logger=self.logger)
def createWords(self, samples):
if self.signature == None:
self.signature = SFA("EQUI_DEPTH")
self.signature.fitWindowing(samples, self.windowLength, self.maxF, self.symbols, self.normMean,True)
words = []
for i in range(samples["Samples"]):
sfaWords = self.signature.transformWindowing(samples[i])
words_small = []
for word in sfaWords:
words_small.append(self.createWord(word, self.maxF, int2byte(self.symbols)))
words.append(words_small)
return words
def createWords(self, samples, index, bar=None):
if self.signature[index] == None:
self.signature[index] = SFA("INFORMATION_GAIN", True, False)
self.signature[index].fitWindowing(samples,
self.windowLengths[index],
self.maxF, self.symbols,
self.normMean, False)
# self.signature[index].printBins()
words = []
for i in range(samples["Samples"]):
words.append(self.signature[index].transformWindowingInt(
samples[i], self.maxF))
self.words[index] = words
if bar != None:
bar.update(index)
def createWords(self, samples, index, data):
if self.signature[index] == None:
self.signature[index] = [None for _ in range(samples['Dimensions'])]
for i in range(samples['Dimensions']):
self.signature[index][i] = SFA(self.histogramType, self.lowerBounding, logger = self.logger, mftUseMaxOrMin=False)
self.signature[index][i].mv_fitWindowing(samples, self.windowLengths[index], self.maxF, self.alphabetSize, self.normMean, self.lowerBounding, dim = i)
self.signature[index][i].printBins(self.logger)
words = []
for m in range(samples["Samples"]):
for n in range(samples["Dimensions"]):
if len(samples[m][n].data) >= self.windowLengths[index]:
words.append(self.signature[index][n].transformWindowingInt(samples[m][n], self.maxF))
else:
words.append([])
self.logger.Log("Generating %s Words for Norm=%s and Window=%s" % (data, self.normMean, self.windowLengths[index]))
self.words[index] = words
def lookup(self, windowLength, wordLength, symbols, sequence, val):
normMean = True
key = (windowLength, wordLength, symbols)
if key not in self.sfa:
sfa = SFA("EQUI_DEPTH")
sfa.fitWindowing(self.raw, windowLength, wordLength, symbols,
normMean, True)
self.sfa[key] = []
for i in range(self.raw["Samples"]):
sfa_sr = []
wordList = sfa.transformWindowing(self.raw[i])
for word in wordList:
sfa_sr.append(self.sfaToDWord(word, symbols))
#print(str(i) + "-th transformed time series SFA word " + "\t" + sfaToWordList(wordList))
self.sfa[key].append(sfa_sr)
for i in range(self.raw["Samples"]):
for j in range(len(self.sfa[key][i])):
if sequence in self.sfa[key][i][j]:
self.acscores[i, j:(j + windowLength)] += val
def createWords(self, samples, index, bar=None):
if self.signature[index] == None:
self.signature[index] = SFA(self.histogramType, False,
self.lowerBounding, False)
self.signature[index].mv_fitWindowing(samples,
self.windowLengths[index],
self.maxF, self.alphabetSize,
self.normMean, False)
# self.signature[index].printBins()
words = []
for m in range(samples["Samples"]):
for n in range(samples["Dimensions"]):
if len(samples[m][n].data) >= self.windowLengths[index]:
words.append(self.signature[index].transformWindowingInt(
samples[m][n], self.maxF))
else:
words.append([])
self.words[index] = words
if bar != None:
bar.update(index)
def sfaToWord(word):
word_string = ""
for w in word:
word_string += chr(w + 97)
return word_string
def sfaToWordList(wordList):
list_string = ""
for word in wordList:
list_string += sfaToWord(word)
list_string += "; "
return list_string
train, test, train_labels, test_labels = load("CBF", "\t")
sfa = SFA("EQUI_DEPTH")
sfa.fitWindowing(train, train_labels, windowLength, wordLength, symbols,
normMean, True)
sfa.printBins()
for i in range(test.shape[0]):
wordList = sfa.transformWindowing(test.iloc[i, :])
print(
str(i) + "-th transformed time series SFA word " + "\t" +
sfaToWordList(wordList))
(FIXED_PARAMETERS['dataset'], scoreShotgunEnsemble))
if FIXED_PARAMETERS['test'] == 'Shotgun':
logger.Log("Test: Shotgun")
from src.classification.ShotgunClassifier import *
shotgun = ShotgunClassifier(FIXED_PARAMETERS, logger)
scoreShotgun = shotgun.eval(train, test)[0]
logger.Log("%s: %s" % (FIXED_PARAMETERS['dataset'], scoreShotgun))
##=========================================================================================
## SFA Word Tests
##=========================================================================================
if FIXED_PARAMETERS['test'] == 'SFAWordTest':
logger.Log("Test: SFAWordTest")
from src.transformation.SFA import *
sfa = SFA(FIXED_PARAMETERS["histogram_type"], logger=logger)
sfa.fitTransform(train, FIXED_PARAMETERS['wordLength'],
FIXED_PARAMETERS['symbols'],
FIXED_PARAMETERS['normMean'])
logger.Log(sfa.__dict__)
for i in range(test["Samples"]):
wordList = sfa.transform2(test[i].data, "null", str_return=True)
logger.Log("%s-th transformed TEST time series SFA word \t %s " %
(i, wordList))
if FIXED_PARAMETERS['test'] == 'SFAWordWindowingTest':
logger.Log("Test: SFAWordWindowingTest")
from src.transformation.SFA import *
sfa = SFA(FIXED_PARAMETERS["histogram_type"], logger=logger)