def _cross_train(self, fold_sz):
rid2shard = ST.random_shardlize(fold_sz, len(self._train_xs), load=True)
precision = 0
for fid,sd in rid2shard.items():
tmp_train_xs = [self._train_xs[i] for i in sd]
tmp_train_ys = [self._train_ys[i] for i in sd]
test_set = [(self._feature_encoding(self._train_xs[i]), self._train_ys[i]) for i in sd]
classifier = self._train(tmp_train_xs, tmp_train_ys)
p = classify.accuracy(classifier, test_set)
linfo('maxent classifier precision: %.4f' % p)
precision += p
linfo('average maxent classifier precision: %.4f' % precision/fold_sz)
def _train(self, shard_sz=10, cross_validation=True):
#print self._ngrams_config
linfo('begin train classifier')
st = time.time()
rid2shard = ST.random_shardlize(shard_sz,
len(self._train_xs),
load=True,
path=self.rand_path)
#rid2word_info = {}
#total_word2cnt = BayesClassifier.Word2Cnt()
rid2tag_cnt, rid2word_presence = {}, {}
total_word2presence = BayesClassifier.Word2Cnt()
total_tag2cnt = {"P": 0, "N": 0, "O": 0}
for rid in range(1, shard_sz + 1):
shard = rid2shard[rid]
#rid2word_info[rid]
rid2tag_cnt[rid], rid2word_presence[rid] = self._cal_shard2info(
shard)
#for tag, w2c in rid2word_info[rid].items():
# for w, c in w2c.items():
# total_word2cnt[tag].setdefault(w, 0)
# total_word2cnt[tag][w] += c
for tag, w2p in rid2word_presence[rid].items():
for w, c in w2p.items():
total_word2presence[tag].setdefault(w, 0)
total_word2presence[tag][w] += c
for tag, cnt in rid2tag_cnt[rid].items():
total_tag2cnt[tag] += cnt
#self._debug_bigram(total_word2presence)
self._prune(total_word2presence, rid2word_presence, total_tag2cnt)
self.total_w2c, self.total_t2c = total_word2presence, total_tag2cnt
linfo(self.total_t2c)
#cross_validation
if cross_validation:
linfo('beign cross validation')
p, r, f = self._cross_train(total_word2presence, rid2word_presence,
total_tag2cnt, rid2tag_cnt, shard_sz,
rid2shard)
linfo(
'Classifier METRIC trained-precision: %.4f. recall: %.4f.f-value:%.4f. train cost used: %.2f'
% (p, r, f, time.time() - st))
else:
linfo('beign train and test with manually tagged data set')
p, r, f = self._all_train(total_word2presence, total_tag2cnt)
linfo(
'Manually Tag Data Classifier METRIC trained-precision: %.4f. recall: %.4f.f-value:%.4f. train cost used: %.2f'
% (p, r, f, time.time() - st))
def _train(self, shard_sz=10, cross_validation=True):
#print self._ngrams_config
linfo('begin train classifier')
st = time.time()
rid2shard = ST.random_shardlize(shard_sz, len(self._train_xs), load=True, path=self.rand_path)
#rid2word_info = {}
#total_word2cnt = BayesClassifier.Word2Cnt()
rid2tag_cnt, rid2word_presence = {}, {}
total_word2presence = BayesClassifier.Word2Cnt()
total_tag2cnt = {"P":0,"N":0,"O":0}
for rid in range(1, shard_sz+1):
shard = rid2shard[rid]
#rid2word_info[rid]
rid2tag_cnt[rid], rid2word_presence[rid] = self._cal_shard2info(shard)
#for tag, w2c in rid2word_info[rid].items():
# for w, c in w2c.items():
# total_word2cnt[tag].setdefault(w, 0)
# total_word2cnt[tag][w] += c
for tag, w2p in rid2word_presence[rid].items():
for w, c in w2p.items():
total_word2presence[tag].setdefault(w, 0)
total_word2presence[tag][w] += c
for tag, cnt in rid2tag_cnt[rid].items():
total_tag2cnt[tag] += cnt
#self._debug_bigram(total_word2presence)
self._prune(total_word2presence, rid2word_presence, total_tag2cnt)
self.total_w2c, self.total_t2c = total_word2presence, total_tag2cnt
linfo(self.total_t2c)
#cross_validation
if cross_validation:
linfo('beign cross validation')
p, r, f= self._cross_train(total_word2presence, rid2word_presence, total_tag2cnt, rid2tag_cnt, shard_sz, rid2shard)
linfo('Classifier METRIC trained-precision: %.4f. recall: %.4f.f-value:%.4f. train cost used: %.2f' % (p , r , f, time.time()- st))
else:
linfo('beign train and test with manually tagged data set')
p, r, f = self._all_train(total_word2presence, total_tag2cnt)
linfo('Manually Tag Data Classifier METRIC trained-precision: %.4f. recall: %.4f.f-value:%.4f. train cost used: %.2f' % (p , r , f , time.time()- st))
