def processFile(self, file_path_and_name):
try:
f = open(file_path_and_name, 'r')
text_0 = f.read()
text_1 = re.search(r"<TEXT>.*</TEXT>", text_0, re.DOTALL)
text_1 = re.sub("<TEXT>\n", "", text_1.group(0))
text_1 = re.sub("\n</TEXT>", "", text_1)
text_1 = re.sub("<P>", "", text_1)
text_1 = re.sub("</P>", "", text_1)
text_1 = re.sub("\n", " ", text_1)
text_1 = re.sub("\"", "\"", text_1)
text_1 = re.sub("''", "\"", text_1)
text_1 = re.sub("``", "\"", text_1)
text_1 = re.sub(" +", " ", text_1)
text_1 = re.sub(" _ ", "", text_1)
text_1 = re.sub(r"\(AP\) _", " ", text_1)
text_1 = re.sub("&\w+;", " ", text_1)
sent_tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
lines = sent_tokenizer.tokenize(text_1.strip())
index = lines[0].find("--")
if index != -1:
lines[0] = lines[0][index + 2:]
index = lines[0].find(" _ ")
if index != -1:
lines[0] = lines[0][index + 3:]
sentences = []
for sent in lines:
sent = sent.strip()
OG_sent = sent[:]
sent = sent.lower()
line = nltk.word_tokenize(sent)
stemmed_sentence = [porter.stem(word) for word in line]
stemmed_sentence = list(filter(lambda x: x != '.' and x != '`' and x != ',' and x != '_' and x != ';'
and x != '(' and x != ')' and x.find('&') == -1
and x != '?' and x != "'" and x != '!' and x != '''"'''
and x != '``' and x != '--' and x != ':'
and x != "''" and x != "'s", stemmed_sentence))
# stemmed_sentence = [word for word in stemmed_sentence if word not in stopwords.words('english')]
if (len(stemmed_sentence) <= 4):
continue
if stemmed_sentence:
sentences.append(Sentence(file_path_and_name, stemmed_sentence, OG_sent))
return sentences
except IOError:
print('Oops! File not found', file_path_and_name)
return [Sentence(file_path_and_name, [], [])]
def _read_file(src_file):
data = []
lemma_count = {}
total_samples = 0
src = open(src_file, "rt", encoding="utf-8")
# init lists
words = []
lemma_words = []
is_prep = []
tree = []
for row in src:
if row == "\n":
# create sentence object
data.append(Sentence(words, lemma_words, is_prep, tree))
# init lists
words = []
lemma_words = []
is_prep = []
tree = []
continue
# read file
tree_id, word, lemma, _, pos, _, parent_idx, context, _, _ = row.split()
total_samples += 1
lemma_count[lemma] = lemma_count.get(lemma, 0) + 1
# fill list with relevant data from the file
words.append(word)
lemma_words.append(lemma)
is_prep.append(True if pos in PREP else False)
tree.append((int(parent_idx) - 1, context))
return total_samples, lemma_count, data
def buildQuery(self, sentences, TF_IDF_w, n):
scores = list(TF_IDF_w.keys())
scores.sort(reverse=True)
i = 0
j = 0
queryWords = []
while (i < n):
words = TF_IDF_w[scores[j]]
for word in words:
queryWords.append(word)
i = i + 1
if (i > n):
break
j = j + 1
return Sentence("query", queryWords, queryWords)
def sentence2vec(self, sentence):
sentence = Sentence(sentence, self.seg)
vec_bow = self.dictionary.doc2bow(sentence.get_cuted_sentence())
return self.model[vec_bow]
def set_sentences(self, sentences):
self.sentences = []
for i in range(0, len(sentences)):
self.sentences.append(Sentence(sentences[i], self.seg, i))
