def cross_validate(result_file, root_dir, folds, read_func, sent_num):
if os.path.isfile(result_file):
os.system('rm ' + result_file)
print 'cross-validation started'
for i, fold in enumerate(folds):
print 'fold %d/%d started' % (i+1, len(folds))
# read test
test = read_func(root_dir, fold, sent_num, local_idx = True, full_info = True)
# read train
train_files = reduce(lambda a,b: a+b, folds[:i] + folds[i+1:])
train = read_func(root_dir, train_files, sent_num)
# open result file
fw = open(result_file, 'ab')
# train and compute
count = 1
for key in test.iterkeys():
lm = NgramModel(3, train[key])
for s in test[key]:
if len(s[-1]) > 0:
e = lm.entropy(s[-1])
# s[0] is xml id
# s[1] is div index
# key is global index
# s[2] is turn index
# s[3] is local index
fw.write(','.join(map(str, (s[0], s[1], key, s[2], s[3], e))) + '\n')
# print progress
sys.stdout.write('\rkey = %d/%d done' % (count, len(test)))
sys.stdout.flush()
count += 1
print 'fold %d/%d done' % (i+1, len(folds))
def get_similarity(q, idx, tf_idf):
COUNT_WORDS_IN_TEXT = 100
urls_for_sim = set()
for info in tf_idf:
weight = info[0]
ds2_lst = info[1]
for ds in ds2_lst:
urls_for_sim.add(ds.text_id)
rank_lm = []
est = lambda fdist, bins: LidstoneProbDist(fdist, 0.2)
q_sequence = wordpunct_tokenize(q)
for text_id in urls_for_sim:
text = ds.text
sequence = wordpunct_tokenize(text)
lm = NgramModel(3, sequence, estimator=est)
ds.weight = lm.entropy(q_sequence)
# if len(ds.text) > COUNT_WORDS_IN_TEXT:
rank_lm += [ds]
return sorted(rank_lm, key=lambda ds: ds.weight)
SAMPLE_SENTS_NUM = 100
for fold_idx, fold in enumerate(folds): # takes 37 min
# print progress
print 'fold %d/%d started' % (fold_idx + 1, len(folds))
# read test sents
test_sents = read_firstN_sents(cur,
fold,
SAMPLE_SENTS_NUM,
include_loc=True)
# read the train sents
train_convIDs = reduce(lambda a, b: a + b,
folds[:fold_idx] + folds[fold_idx + 1:])
train_sents = read_firstN_sents(cur, train_convIDs, SAMPLE_SENTS_NUM)
# open the file to write the results
fw = open(res_file_name, 'ab')
# train and compute
key_count = 1
for key in test_sents.iterkeys():
lm = NgramModel(3, train_sents[key])
for s in test_sents[key]:
e = lm.entropy(s[2])
fw.write(','.join((str(s[0]), str(key), str(s[1]), str(e))) +
'\n')
# print progress
sys.stdout.write('\rkey = %d/%d done' %
(key_count, len(test_sents)))
sys.stdout.flush()
key_count += 1
# print progress
print '\nfold %d/%d done\n' % (fold_idx + 1, len(folds))
# $$
# P(X_i|X_{i-1},..,X_{i-n+1})
# $$
# <codecell>
from nltk.model.ngram import NgramModel
from nltk.probability import WittenBellProbDist, LidstoneProbDist
train_words = brown.words()[:-500]
test_words = brown.words()[-500:]
lm = NgramModel(2, train_words, lambda fd, b: LidstoneProbDist(fd, 0.2))
# <codecell>
lm.entropy(test_words)
# <markdowncell>
# ### Counting
#
# For example, how many words in a corpus are not in WordNet?
# <codecell>
from nltk.corpus import wordnet
from nltk.probability import ConditionalFreqDist
cfd = ConditionalFreqDist(
(pos, len(wordnet.synsets(word)) > 0) for word,pos in treebank.tagged_words()
)
folds = tmp
# remove the existing result file
res_file_name = 'results_swbd_nltk_CV.txt'
if os.path.isfile(res_file_name):
os.system('rm ' + res_file_name)
SAMPLE_SENTS_NUM = 100
for fold_idx, fold in enumerate(folds): # takes 37 min
# print progress
print 'fold %d/%d started' % (fold_idx+1, len(folds))
# read test sents
test_sents = read_firstN_sents(cur, fold, SAMPLE_SENTS_NUM, include_loc = True)
# read the train sents
train_convIDs = reduce(lambda a,b: a+b, folds[:fold_idx] + folds[fold_idx+1:])
train_sents = read_firstN_sents(cur, train_convIDs, SAMPLE_SENTS_NUM)
# open the file to write the results
fw = open(res_file_name, 'ab')
# train and compute
key_count = 1
for key in test_sents.iterkeys():
lm = NgramModel(3, train_sents[key])
for s in test_sents[key]:
e = lm.entropy(s[2])
fw.write(','.join((str(s[0]), str(key), str(s[1]), str(e))) + '\n')
# print progress
sys.stdout.write('\rkey = %d/%d done' % (key_count, len(test_sents)))
sys.stdout.flush()
key_count += 1
# print progress
print '\nfold %d/%d done\n' % (fold_idx+1, len(folds))
