def extract_tokens_from_file(self, responses, input_filename, n, token_dict):
Y = fh.read_csv(input_filename)
rids = Y.index
dataset = fh.get_basename(input_filename)
for rid in rids:
if rid in responses:
text = responses[rid].lower()
text = text.lstrip()
text = text.rstrip()
tokens = []
sentences = tokenizer.split_sentences(text)
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, n)
#sent_tokens = [t.rstrip('`"\'') if re.search('[a-z]', t) else t for t in sent_tokens]
#sent_tokens = [t.lstrip('`"\'') if re.search('[a-z]', t) else t for t in sent_tokens]
tokens = tokens + sent_tokens
tokens = [self.get_prefix() + t for t in tokens]
if self.params['source'] != 'normalized':
tokens = [t + '_<' + self.params['source'] + '>' for t in tokens]
if self.params['append_dataset']:
tokens = [t + '_' + dataset for t in tokens]
token_dict[rid] = tokens
else:
token_dict[rid] = []
def extract_tokens_from_text(self, data, items_to_load, doc_index=None):
token_dict = {}
for key in items_to_load:
if doc_index is not None:
doc_key = doc_index[key]['filename']
else:
doc_key = key
text = data[doc_key]
if self.lower:
text = text.lower()
text = text.lstrip()
text = text.rstrip()
if self.replace_num is not None:
text = re.sub('\d', self.replace_num, text)
tokens = []
sentences = text.split('\n')
if doc_index is None:
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, self.n, replace_numbers=False)
tokens = tokens + sent_tokens
elif 'sentences' not in doc_index[key]:
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, self.n, replace_numbers=False)
tokens = tokens + sent_tokens
else:
for i in doc_index[key]['sentences']:
s = sentences[int(i)]
sent_tokens = tokenizer.make_ngrams(s, self.n, replace_numbers=False)
tokens = tokens + sent_tokens
tokens = [self.get_prefix() + t for t in tokens]
token_dict[key] = tokens
return token_dict
def extract_tokens_from_text(self, data):
token_dict = {}
for key, text in data.items():
text = text.lower()
text = text.lstrip()
text = text.rstrip()
tokens = []
sentences = tokenizer.split_sentences(text)
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, self.n)
tokens = tokens + sent_tokens
tokens = [self.get_prefix() + t for t in tokens]
token_dict[key] = tokens
return token_dict
def extract_tokens_from_file(self, data, n):
token_dict = {}
for key, text in data.items():
text = text.lower()
text = text.lstrip()
text = text.rstrip()
tokens = []
sentences = tokenizer.split_sentences(text)
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, n)
tokens = tokens + sent_tokens
tokens = [self.get_prefix() + t for t in tokens]
token_dict[key] = tokens
return token_dict
def extract_tokens_from_file(self, responses, input_filename, n, cluster_dict, token_dict):
Y = fh.read_csv(input_filename)
rids = Y.index
for rid in rids:
text = responses[rid].lower()
text = text.lstrip()
text = text.rstrip()
tokens = []
sentences = tokenizer.split_sentences(text)
for s in sentences:
sent_tokens = tokenizer.make_ngrams(s, n)
sent_tokens = [t.rstrip('`"\'') if re.search('[a-z]', t) else t for t in sent_tokens]
sent_tokens = [t.lstrip('`"\'') if re.search('[a-z]', t) else t for t in sent_tokens]
sent_tokens = sent_tokens + ['__ENDS__']
tokens = tokens + sent_tokens
tokens = [self.get_prefix() + cluster_dict[t] for t in tokens if t in cluster_dict]
token_dict[rid] = tokens
