def classify(self, doc, verbose=False):
model_file = '%ssvm_model' % self.path
if not self.feats: sbd_util.die('Incomplete model')
if not os.path.isfile(model_file):
sbd_util.die('no model [%s]' % model_file)
## testing data file
if verbose: sys.stderr.write('SVM classifying... ')
lines = []
frag = doc.frag
while frag:
if frag.label == None: svm_label = '0'
elif frag.label: svm_label = '+1'
else: svm_label = '-1'
line = '%s ' % svm_label
feats = [f + '_' + v for f, v in frag.features.items()]
svm_feats = [self.feats[f] for f in feats if f in self.feats]
svm_feats.sort(lambda x, y: x - y)
line += ' '.join(['%d:1' % x for x in svm_feats])
lines.append(line)
frag = frag.next
#print "!----!",get_open_fds()
#unused, test_file = tempfile.mkstemp()
test_file = "tmp1"
fh = open(test_file, 'w')
fh.write('\n'.join(lines) + '\n')
fh.close()
#print "!----!",get_open_fds()
#unused, pred_file = tempfile.mkstemp()
pred_file = "tmp2"
options = '-v 0'
cmd = '%s %s %s %s %s' % (SVM_CLASSIFY, options, test_file, model_file,
pred_file)
os.system(cmd)
## get predictions
total = 0
pf = open(pred_file, 'r')
#print pf
preds = map(float, pf.read().splitlines())
frag = doc.frag
while frag:
frag.pred = sbd_util.logit(preds[total])
frag = frag.next
total += 1
## clean up
pf.close()
os.remove(test_file)
os.remove(pred_file)
if verbose: sys.stderr.write('done!\n')
def classify(self, doc, verbose=False):
model_file = '%ssvm_model' %self.path
if not self.feats: sbd_util.die('Incomplete model')
if not os.path.isfile(model_file): sbd_util.die('no model [%s]' %model_file)
## testing data file
if verbose: sys.stderr.write('SVM classifying... ')
lines = []
frag = doc.frag
while frag:
if frag.label == None: svm_label = '0'
elif frag.label: svm_label = '+1'
else: svm_label = '-1'
line = '%s ' %svm_label
feats = [f+'_'+v for f,v in frag.features.items()]
svm_feats = [self.feats[f] for f in feats if f in self.feats]
svm_feats.sort(lambda x,y: x-y)
line += ' '.join(['%d:1' %x for x in svm_feats])
lines.append(line)
frag = frag.next
#print "!----!",get_open_fds()
#unused, test_file = tempfile.mkstemp()
test_file = "tmp1"
fh = open(test_file, 'w')
fh.write('\n'.join(lines) + '\n')
fh.close()
#print "!----!",get_open_fds()
#unused, pred_file = tempfile.mkstemp()
pred_file = "tmp2"
options = '-v 0'
cmd = '%s %s %s %s %s' %(SVM_CLASSIFY, options, test_file, model_file, pred_file)
os.system(cmd)
## get predictions
total = 0
pf = open(pred_file,'r')
#print pf
preds = map(float, pf.read().splitlines())
frag = doc.frag
while frag:
frag.pred = sbd_util.logit(preds[total])
frag = frag.next
total += 1
## clean up
pf.close()
os.remove(test_file)
os.remove(pred_file)
if verbose: sys.stderr.write('done!\n')
