def report(self, dset, pred):
pred = [self.tdecoder.decode(s, p) for s, p in zip(dset, pred)]
y_true = self.feat.yenc.transform(
[t for sent in dset for t in sent['y']])
y_pred = list(chain.from_iterable(pred))
yerr = np.sum(y_true != y_pred) / float(len(y_true))
# char_conmat_str = self.get_conmat_str(y_true, y_pred, self.feat.tseqenc)
lts = [sent['ts'] for sent in dset]
lts_pred = []
for sent, ipred in zip(dset, pred):
tseq_pred = self.feat.yenc.inverse_transform(ipred)
# tseqgrp_pred = get_tseqgrp(sent['wiseq'],tseq_pred)
ts_pred = self.tfunc(sent['wiseq'], tseq_pred)
lts_pred.append(ts_pred) # changed
# wacc, pre, recall, f1 = bilouEval2(lts, lts_pred)
(wacc, pre, recall, f1), conll_print = conlleval(lts, lts_pred)
logging.debug('')
logging.debug(conll_print)
# logging.debug(char_conmat_str)
# logging.debug(word_conmat_str)
logging.debug('')
return yerr, pre, recall, f1
def report(self, dset, pred, epoch, index):
pred = [self.tdecoder.decode(s, p) for s, p in zip(dset, pred)]
y_true = self.feat.yenc.transform([t for sent in dset for t in sent['y']])
y_pred = list(chain.from_iterable(pred))
print len(y_true)
print len(y_pred)
yerr = np.sum(y_true!=y_pred)/float(len(y_true))
# char_conmat_str = self.get_conmat_str(y_true, y_pred, self.feat.tseqenc)
lts = [sent['ts'] for sent in dset]
lts_pred = []
for sent, ipred in zip(dset, pred):
tseq_pred = self.feat.yenc.inverse_transform(ipred)
# tseqgrp_pred = get_tseqgrp(sent['wiseq'],tseq_pred)
ts_pred = self.tfunc(sent['wiseq'],tseq_pred)
lts_pred.append(ts_pred) # changed
# wacc, pre, recall, f1 = bilouEval2(lts, lts_pred)
# Start out File
f = open('tmp/' + index + str(epoch), 'w')
for sent1, sent2 in zip(lts, lts_pred):
for word1, word2 in zip(sent1, sent2):
f.write('x x x %s %s\n'%(word1, word2))
f.write('\n')
f.close()
# End out file
(wacc, pre, recall, f1), conll_print = conlleval(lts, lts_pred)
logging.debug('')
logging.debug(conll_print)
# logging.debug(char_conmat_str)
# logging.debug(word_conmat_str)
logging.debug('')
return yerr, pre, recall, f1
def io_ideal(dev, tst):
from score import conlleval
print 'io tagging ideal scores'
for dset, dset_str in zip((dev, tst), ('dev', 'tst')):
ts_gold = [sent['ts'] for sent in dset]
ts_pred = [encoding.any2io(sent['ts']) for sent in dset]
r1, r2 = conlleval(ts_gold, ts_pred)
print '\t'.join([dset_str] + map(str, r1))
def main():
langs = ['eng', 'deu', 'spa', 'ned', 'tr', 'cze', 'ger', 'arb0', 'ita']
# langs = ['eng', 'deu']
dsetnames = ['trn', 'dev', 'tst']
data = dict((lang,
dict((dname, dset)
for dname, dset in zip(dsetnames, get_sents(lang))))
for lang in langs)
for l in langs:
print l, sorted(set(t for sent in data[l]['trn'] for t in sent['ts']))
print
table = []
for l in langs:
table.append([
l,
sum(1 for sent in data[l]['trn']
if len(' '.join(sent['ws'])) > 500)
])
print tabulate(table)
table = []
for dname in dsetnames:
table.append([dname] + map(len, [data[l][dname] for l in langs]))
print tabulate(table, headers=['#sent'] + langs, tablefmt='latex')
print
table = []
for dname in dsetnames:
table.append(
[dname] +
[sum(len(sent['ws']) for sent in data[l][dname]) for l in langs])
print tabulate(table, headers=['#token'] + langs)
print
table = []
for dname in dsetnames:
table.append([dname] + [
float(
sum(
len([c for w in sent['ws'] for c in w])
for sent in data[l][dname])) for l in langs
])
print tabulate(table, headers=['#char'] + langs, floatfmt='.1e')
print
table = []
for l in langs:
# nchar_sents = [sum(1 for w in sent['ws']) for sent in chain(*data[l].values())]
for dname in dsetnames:
nchar_sents = [
sum(1 for w in sent['ws']) for sent in data[l][dname]
]
table.append(['{}-{}'.format(l, dname)] + [
int(f(nchar_sents)) if len(nchar_sents) else 0
for f in (np.min, np.max, np.mean, np.std)
])
table.append(['...'] * 5)
print tabulate(table,
headers=['#word per sent'] + ['min', 'max', 'mean', 'std'])
print
table = []
for l in langs:
# nchar_sents = [sum(1 for c in ' '.join(sent['ws'])) for sent in chain(*data[l].values())]
for dname in dsetnames:
nchar_sents = [
sum(1 for c in ' '.join(sent['ws'])) for sent in data[l][dname]
]
table.append(['{}-{}'.format(l, dname)] + [
int(f(nchar_sents)) if len(nchar_sents) else 0
for f in (np.min, np.max, np.mean, np.std)
])
table.append(['...'] * 5)
print tabulate(table,
headers=['#char per sent'] + ['min', 'max', 'mean', 'std'])
print
table = []
for dname in dsetnames:
table.append([dname] + [len(get_vocab(data[l][dname])) for l in langs])
print tabulate(table, headers=['size(vocab)'] + langs)
print
table = []
for l, dname in product(langs, ('dev', 'tst')):
vdst = get_vocab(data[l][dname])
vsrc = get_vocab(data[l]['trn'])
vdiff = vdst.difference(vsrc)
uperc = len(vdiff) / float(len(vdst)) * 100
cnt = Counter(w for sent in data[l][dname]
for w, t in zip(sent['ws'], sent['ts']) if t != 'O')
pperc = sum(cnt[w] for w in vdiff) / float(sum(cnt.values())) * 100
cnt = Counter(w for sent in data[l][dname] for w in sent['ws'])
cperc = sum(cnt[w] for w in vdiff) / float(sum(cnt.values())) * 100
table.append([l + '-' + dname] + [uperc, pperc, cperc])
print tabulate(table,
headers=['unk', 'unique', 'phrase', 'corpus'],
floatfmt='.2f')
table = []
for l, dname in product(langs, ('dev', 'tst')):
dset = data[l][dname]
ts_gold = [sent['ts'] for sent in dset]
ts_pred = [encoding.any2io(sent['ts']) for sent in dset]
r1, r2 = conlleval(ts_gold, ts_pred)
table.append([l + '-' + dname] + map(str, r1))
print tabulate(table, headers=['io-ideal', 'wacc', 'pre', 'rec', 'f1'])
print