optparser.add_option('-o',
'--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
inFile = sys.stdin
elif options.input is not None:
inFile = ioFile.dataFromFile(options.input)
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = "arxiv-category_dict.pkl"
elif options.output is not None:
outFile = options.output
data_iterator = inFile
category_dict = {}
for line in data_iterator:
line = line.rstrip('\n')
line = line.split('\t')
category_dict[line[0]] = line[1]
ioFile.save_object(category_dict, outFile)
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
fname = sys.stdin
elif options.input is not None:
fname = options.input
else:
print 'No filename(.pkl) specified, system with exit\n'
sys.exit('System will exit')
if options.num is None:
n_all_term = sys.stdin
elif options.num is not None:
n_all_term = int(options.num)
else:
print 'No number of conversion specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = 'convert_prob.pkl'
elif options.output is not None:
outFile = options.output
prob = ioFile.load_object(fname)
convert_prob = convertProb(prob, n_all_term)
#print convert_prob.shape
ioFile.save_object(convert_prob, outFile)
if __name__ == "__main__":
optparser = OptionParser()
optparser.add_option('-f', '--inputFile',
dest='input',
help='fileName',
default=None)
optparser.add_option('-o', '--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
fname = sys.stdin
elif options.input is not None:
fname = options.input
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = 'prob.pkl'
elif options.output is not None:
outFile = options.output
prob = readProb(fname)
ioFile.save_object(prob, outFile)
default=None)
optparser.add_option('-o', '--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
inFile = sys.stdin
elif options.input is not None:
inFile = ioFile.dataFromFile(options.input)
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = "arxiv-category_dict.pkl"
elif options.output is not None:
outFile = options.output
data_iterator = inFile
category_dict = {}
for line in data_iterator:
line = line.rstrip('\n')
line = line.split('\t')
category_dict[line[0]] = line[1]
ioFile.save_object(category_dict, outFile)
optparser = OptionParser()
optparser.add_option('-f',
'--inputFile',
dest='input',
help='filename containing xml',
default=None)
optparser.add_option('-o',
'--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
fname = sys.stdin
elif options.input is not None:
fname = (options.input)
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = "acm-class_dict.pkl"
elif options.output is not None:
outFile = options.output
acm_class_dict = acmClassification(fname)
ioFile.save_object(acm_class_dict, outFile)
optparser.add_option('-f', '--inputFile',
dest='input',
help='filename containing xml',
default=None)
optparser.add_option('-o', '--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
fname = sys.stdin
elif options.input is not None:
fname = (options.input)
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = "acm-class_dict.pkl"
elif options.output is not None:
outFile = options.output
acm_class_dict = acmClassification(fname)
ioFile.save_object(acm_class_dict, outFile)
fname_f = sys.stdin
elif options.input_f is not None:
fname_f = options.input_f
else:
print 'No filename(.pkl) specified, system with exit\n'
sys.exit('System will exit')
if options.input_g is None:
fname_g = sys.stdin
elif options.input_g is not None:
fname_g = options.input_g
else:
print 'No filename(.pkl) specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = 'distance.pkl'
elif options.output is not None:
outFile = options.output
prob_f = ioFile.load_object(fname_f)
prob_g = ioFile.load_object(fname_g)
all_distance, count = distanceBetweenTwoYears(prob_f, prob_g)
print count, len(all_distance)
ioFile.save_object(all_distance, outFile)
if options.prob is None:
inFile = sys.stdin
elif options.prob is not None:
inFile = options.prob
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.vocabulary is not None:
fname = options.vocabulary
all_term = allTerm(fname)
else:
fname = None
all_term = None
if options.output is None:
outFile = 'topic.pkl'
elif options.output is not None:
outFile = options.output
prob = ioFile.load_object(inFile)
all_topic = []
nTopic, nTerm = prob.shape
for i in range(0, nTopic):
topic = topNTerm(5, prob[i, :].reshape(nTerm, 1), 1, all_term)
all_topic.append(topic)
ioFile.save_object(all_topic, outFile)
else:
print 'Name of the category is incorrect, system with exit\n'
sys.exit('System will exit')
if options.clf is None:
print 'No class filename specified, system with exit\n'
sys.exit('System will exit')
elif options.clf is not None:
classDir = options.clf
if options.clf_dict is None:
print 'No class-dict filename specified, system with exit\n'
sys.exit('System will exit')
elif options.clf_dict is not None:
clf_dict = ioFile.load_object(options.clf_dict)
if options.output is None:
if fun == 0:
outFile = "class_topic_arxiv-category.pkl"
elif fun == 1:
outFile = "class_topic_acm-class.pkl"
elif options.output is not None:
outFile = options.output
all_clf_topic = topicOfClassificationForAllYear(probDir, modelDir, classDir, clf_dict, fun)
ioFile.save_object(all_clf_topic, outFile)
if __name__ == "__main__":
optparser = OptionParser()
optparser.add_option('-f',
'--inputFile',
dest='input',
help='fileName',
default=None)
optparser.add_option('-o',
'--outputFile',
dest='output',
help='fileName',
default=None)
(options, args) = optparser.parse_args()
if options.input is None:
fname = sys.stdin
elif options.input is not None:
fname = options.input
else:
print 'No filename specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = 'prob.pkl'
elif options.output is not None:
outFile = options.output
prob = readProb(fname)
ioFile.save_object(prob, outFile)
if options.input_f is None:
fname_f = sys.stdin
elif options.input_f is not None:
fname_f = options.input_f
else:
print 'No filename(.pkl) specified, system with exit\n'
sys.exit('System will exit')
if options.input_g is None:
fname_g = sys.stdin
elif options.input_g is not None:
fname_g = options.input_g
else:
print 'No filename(.pkl) specified, system with exit\n'
sys.exit('System will exit')
if options.output is None:
outFile = 'distance.pkl'
elif options.output is not None:
outFile = options.output
prob_f = ioFile.load_object(fname_f)
prob_g = ioFile.load_object(fname_g)
all_distance, count = distanceBetweenTwoYears(prob_f, prob_g)
print count, len(all_distance)
ioFile.save_object(all_distance, outFile)