def call_matlab(stat, m, kappa):
assert(m is not None and kappa is not None)
outdirname = 'output/{}.m{}.kappa{}.matlab.out'.format(complete_path(stat)[:-1].rsplit('/',1)[1] , m, kappa)
if not os.path.exists(outdirname): os.makedirs(outdirname)
commandstr = matlab + ' -nojvm -nodisplay -nosplash -r ' + '\"approx_cca(\'' + stat + '\',' + str(m) + ',' + str(kappa) + ',\'' + outdirname + '\')\"'
os.system(commandstr)
say('Postprocessing to sort rows by frequency...')
wordmap = read_wordmap(os.path.join(stat, 'wordmap'))
freqmap = read_freqmap(os.path.join(stat, 'X'))
sorted_indices = [pair[0] for pair in sorted([(i, freqmap[i]) for i in wordmap], key=lambda x:x[1], reverse=True)]
lines = open(os.path.join(outdirname, 'Ur')).readlines()
with open(os.path.join(outdirname, 'Ur'), 'wb') as outf:
for i in sorted_indices: write_row(outf, freqmap[i], wordmap[i], lines[i].split())
return outdirname
def call_matlab(stat, m, kappa):
assert(m is not None and kappa is not None)
outdirname = 'output/{}.m{}.kappa{}.matlab.out'.format(complete_path(stat)[:-1].rsplit('/',1)[1] , m, kappa)
if not os.path.exists(outdirname): os.makedirs(outdirname)
commandstr = matlab + ' -nojvm -nodisplay -nosplash -r ' + '\"approx_cca(\'' + stat + '\',' + str(m) + ',' + str(kappa) + ',\'' + outdirname + '\')\"'
os.system(commandstr)
say('Postprocessing to sort rows by frequency...')
wordmap = read_wordmap(os.path.join(stat, 'wordmap'))
freqmap = read_freqmap(os.path.join(stat, 'X'))
sorted_indices = [pair[0] for pair in sorted([(i, freqmap[i]) for i in wordmap], key=lambda x:x[1], reverse=True)]
lines = open(os.path.join(outdirname, 'Ur')).readlines()
with open(os.path.join(outdirname, 'Ur'), 'wb') as outf:
for i in sorted_indices: write_row(outf, freqmap[i], wordmap[i], lines[i].split())
return outdirname
def get_stat(self, stat):
self.stat = complete_path(stat)
XYstats = self.stat + 'XY'
Xstats = self.stat + 'X'
Ystats = self.stat + 'Y'
assert(os.path.isfile(XYstats) and
os.path.isfile(Xstats) and
os.path.isfile(Ystats))
say('XYstats: {}'.format(XYstats))
say('Xstats: {}'.format(Xstats))
say('Ystats: {}'.format(Ystats))
self.wordmap = {}
wordmapf = self.stat + 'wordmap'
with open(wordmapf) as f:
for line in f:
toks = line.split()
self.wordmap[int(toks[0])-1] = toks[1]
pickle_file = self.stat + 'pickle'
if os.path.isfile(pickle_file):
with open(pickle_file) as f:
self.countXY, self.countX, self.countY, self.num_samples = \
cPickle.load(f)
return
self.countXY = Counter()
self.countX = Counter()
self.countY = Counter()
self.num_samples = 0.
num_lines = wc_l(XYstats)
linenum = 0
with open(XYstats) as f:
for line in f:
linenum += 1
toks = line.split()
x, y, count = int(toks[0])-1, int(toks[1])-1, int(toks[2])
self.countXY[x, y] = count
if linenum % 1000 is 0:
inline_print('Processing line %i of %i' %
(linenum, num_lines))
with open(Xstats) as f:
for line in f:
toks = line.split()
x, count = int(toks[0])-1, int(toks[1])
self.countX[x] = count
self.num_samples += count
with open(Ystats) as f:
for line in f:
toks = line.split()
y, count = int(toks[0])-1, int(toks[1])
self.countY[y] = count
inline_print('\nConstructing matrices\n')
self.countXY = csc_matrix((self.countXY.values(),
zip(*self.countXY.keys())),
shape=(len(self.countX), len(self.countY)))
self.countX = array([self.countX[i] for i in range(len(self.countX))])
self.countY = array([self.countY[i] for i in range(len(self.countY))])
with open(pickle_file, 'wb') as outf:
cPickle.dump((self.countXY, self.countX, self.countY,
self.num_samples), outf,
protocol=cPickle.HIGHEST_PROTOCOL)
def get_stat(self, stat):
self.stat = complete_path(stat)
XYstats = self.stat + 'XY'
Xstats = self.stat + 'X'
Ystats = self.stat + 'Y'
assert(os.path.isfile(XYstats) and
os.path.isfile(Xstats) and
os.path.isfile(Ystats))
say('XYstats: {}'.format(XYstats))
say('Xstats: {}'.format(Xstats))
say('Ystats: {}'.format(Ystats))
self.wordmap = {}
wordmapf = self.stat + 'wordmap'
with open(wordmapf) as f:
for line in f:
toks = line.split()
self.wordmap[int(toks[0])-1] = toks[1]
pickle_file = self.stat + 'pickle'
if os.path.isfile(pickle_file):
with open(pickle_file) as f:
self.countXY, self.countX, self.countY, self.num_samples = \
cPickle.load(f)
return
self.countXY = Counter()
self.countX = Counter()
self.countY = Counter()
self.num_samples = 0.
num_lines = wc_l(XYstats)
linenum = 0
with open(XYstats) as f:
for line in f:
linenum += 1
toks = line.split()
x, y, count = int(toks[0])-1, int(toks[1])-1, int(toks[2])
self.countXY[x, y] = count
if linenum % 1000 is 0:
inline_print('Processing line %i of %i' %
(linenum, num_lines))
with open(Xstats) as f:
for line in f:
toks = line.split()
x, count = int(toks[0])-1, int(toks[1])
self.countX[x] = count
self.num_samples += count
with open(Ystats) as f:
for line in f:
toks = line.split()
y, count = int(toks[0])-1, int(toks[1])
self.countY[y] = count
inline_print('\nConstructing matrices\n')
self.countXY = csc_matrix((self.countXY.values(),
zip(*self.countXY.keys())),
shape=(len(self.countX), len(self.countY)))
self.countX = array([self.countX[i] for i in range(len(self.countX))])
self.countY = array([self.countY[i] for i in range(len(self.countY))])
with open(pickle_file, 'wb') as outf:
cPickle.dump((self.countXY, self.countX, self.countY,
self.num_samples), outf,
protocol=cPickle.HIGHEST_PROTOCOL)
