def initialize(self):
"""Initialize all the relevant objects for the run."""
self.corpus = Corpus(self.dataDir)
self.corpusLabel = CorpusLabel(path=self.labelPath, corpus=self.corpus)
with open(self.profilesPath) as p:
self.profiles = json.load(p)
def main(args):
if not args.absolutePaths:
dataDir = os.path.join(root, args.dataDir)
labelDir = os.path.join(root, args.labelDir)
else:
dataDir = args.dataDir
labelDir = args.labelDir
# The following params are used in NAB scoring, but defined here because they
# impact the labeling process -- i.e. windows cannot exist in the probationary
# period.
windowSize = 0.10
probationaryPercent = 0.15
print "Getting Corpus"
corpus = Corpus(dataDir)
print "Creating LabelCombiner"
labelCombiner = LabelCombiner(labelDir, corpus,
args.threshold, windowSize,
probationaryPercent, args.verbosity)
print "Combining Labels"
labelCombiner.combine()
print "Writing combined labels files"
labelCombiner.write(args.combinedLabelsPath, args.combinedWindowsPath)
print "Attempting to load objects as a test"
corpusLabel = CorpusLabel(args.combinedWindowsPath, corpus)
corpusLabel.validateLabels()
print "Successfully combined labels!"
print "Resulting windows stored in:", args.combinedWindowsPath
def main(args):
if not args.absolutePaths:
args.labelDir = os.path.join(root, args.labelDir)
args.dataDir = os.path.join(root, args.dataDir)
args.destDir = os.path.join(root, args.destDir)
if not checkInputs(args):
return
corpus = Corpus(args.dataDir)
corpusLabel = CorpusLabel(args.labelDir, corpus=corpus)
corpusLabel.getEverything()
columnData = {}
for relativePath in corpusLabel.labels.keys():
columnData[relativePath] = pandas.Series(
corpusLabel.labels[relativePath]["label"])
corpus.addColumn("label", columnData)
corpus.copy(newRoot=args.destDir)
print "Done adding labels!"
def main(args):
if args.create:
createApplication()
if args.start:
startApplication()
if args.stop:
stopApplication()
if args.file:
corpus = Corpus(args.data)
labels = CorpusLabel(path=args.labels, corpus=corpus)
streamFile(corpus, labels, args.results, args.file)
if args.stream:
corpus = Corpus(args.data)
labels = CorpusLabel(path=args.labels, corpus=corpus)
streamAll(corpus, labels, args.results)
if args.delete:
deleteApplication()
