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 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))
class BOSS():
def __init__(self, maxF, maxS, windowLength, normMean):
self.maxF = maxF
self.symbols = maxS
self.windowLength = windowLength
self.normMean = normMean
self.signature = None
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)
# self.signature.printBins()
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 createWord(self, numbers, maxF, bits):
shortsPerLong = int(round(60 / bits))
to = min([len(numbers), maxF])
b = 0
s = 0
shiftOffset = 1
for i in range(s, (min(to, shortsPerLong + s))):
shift = 1
for j in range(bits):
if (numbers[i] & shift) != 0:
b |= shiftOffset
shiftOffset <<= 1
shift <<= 1
limit = 2147483647
total = 2147483647 + 2147483648
while b > limit:
b = b - total - 1
return b
def createBagOfPattern(self, words, samples, f):
bagOfPatterns = []
usedBits = int2byte(self.symbols)
mask = (1 << (usedBits * f)) - 1
for j in range(len(words)):
BOP = {}
lastWord = -9223372036854775808
for offset in range(len(words[j])):
word = words[j][offset] & mask
if word != lastWord:
if word in BOP.keys():
BOP[word] += 1
else:
BOP[word] = 1
lastWord = word
bagOfPatterns.append(BOP)
return bagOfPatterns
def int2byte(self, number):
log = 0
if (number & 0xffff0000) != 0:
number >>= 16
log = 16
if number >= 256:
number >>= 8
log += 8
if number >= 16:
number >>= 4
log += 4
if number >= 4:
number >>= 2
log += 2
return log + (number >> 1)
def bag2dict(self, bag):
bag_dict = []
for list in bag:
new_dict = {}
for element in list:
if element in new_dict.keys():
new_dict[element] += 1
else:
new_dict[element] = 1
bag_dict.append(new_dict)
return bag_dict
class BOSSVS():
def __init__(self, maxF, maxS, windowLength, normMean, logger = None):
self.maxF = maxF
self.symbols = maxS
self.windowLength = windowLength
self.normMean = normMean
self.signature = None
logger.Log(self.__dict__, level = 0)
self.logger = logger
def createWords(self, samples):
if self.signature == None:
self.signature = SFA("EQUI_DEPTH", logger = self.logger)
self.signature.fitWindowing(samples, self.windowLength, self.maxF, self.symbols, self.normMean,True)
self.signature.printBins(self.logger)
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 createWord(self, numbers, maxF, bits):
shortsPerLong = int(round(60 / bits))
to = min([len(numbers), maxF])
b = 0
s = 0
shiftOffset = 1
for i in range(s, (min(to, shortsPerLong + s))):
shift = 1
for j in range(bits):
if (numbers[i] & shift) != 0:
b |= shiftOffset
shiftOffset <<= 1
shift <<= 1
limit = 2147483647
total = 2147483647 + 2147483648
while b > limit:
b = b - total - 1
return b
def createBagOfPattern(self, words, samples, f):
bagOfPatterns = []
usedBits = int2byte(self.symbols)
mask = (1 << (usedBits * f)) - 1
for j in range(len(words)):
BOP = BagOfBigrams(samples[j].label)# {}
lastWord = -9223372036854775808
for offset in range(len(words[j])):
word = words[j][offset] & mask
if word != lastWord:
if word in BOP.bob.keys():
BOP.bob[word] += 1
else:
BOP.bob[word] = 1
lastWord = word
bagOfPatterns.append(BOP)
return bagOfPatterns
def createTfIdf(self, bagOfPatterns, sampleIndices, uniqueLabels, labels):
matrix = {}
for label in uniqueLabels:
matrix[label] = {}
for j in sampleIndices:
label = labels[j]
for key, value in bagOfPatterns[j].bob.items():
matrix[label][key] = matrix[label][key] + value if key in matrix[label].keys() else value
wordInClassFreq = {}
for key, value in matrix.items():
for key2, value2 in matrix[key].items():
wordInClassFreq[key2] = wordInClassFreq[key2] + 1 if key2 in wordInClassFreq.keys() else 1
for key, value in matrix.items():
tfIDFs = matrix[key]
for key2, value2 in tfIDFs.items():
wordCount = wordInClassFreq.get(key2)
if (value2 > 0) & (len(uniqueLabels) != wordCount):
tfValue = 1. + math.log10(value2)
idfValue = math.log10(1. + len(uniqueLabels) / wordCount)
tfIdf = tfValue / idfValue
tfIDFs[key2] = tfIdf
else:
tfIDFs[key2] = 0.
matrix[key] = tfIDFs
matrix = self.normalizeTfIdf(matrix)
return matrix
def normalizeTfIdf(self, classStatistics):
for key, values in classStatistics.items():
squareSum = 0.
for key2, value2 in classStatistics[key].items():
squareSum += value2 ** 2
squareRoot = math.sqrt(squareSum)
if squareRoot > 0:
for key2, value2 in classStatistics[key].items():
classStatistics[key][key2] /= squareRoot
return classStatistics
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)
sfa.fitWindowing(train, FIXED_PARAMETERS['windowLength'],
FIXED_PARAMETERS['wordLength'],
FIXED_PARAMETERS['symbols'],
FIXED_PARAMETERS['normMean'], True)
logger.Log(sfa.__dict__)
for i in range(test["Samples"]):
wordList = sfa.transformWindowing(test[i], str_return=True)
logger.Log("%s-th transformed time series SFA word \t %s " %
(i, wordList))
except:
logger.Log("Test and Dataset combo entered is not available")