def find_collocations(file_name, data, popular_word):
text_file = open(file_name, 'r')
file_content = text_file.read()
most_common_words = find_most_common_words(file_content, popular_word)
second_word = None
third_word = None
collocations = data
text_file.seek(0)
for line in text_file:
for word in line.split():
first_word = second_word
second_word = third_word
third_word = trim_word(word)
if (first_word not in most_common_words and second_word not in most_common_words) and \
(first_word and first_word[0].islower() and second_word and second_word[0].islower()):
count_collocations(collocations, stem(first_word.lower()), stem(second_word.lower()))
# dodatkowa iteracja dla ostatniego slowa
first_word = second_word
second_word = third_word
count_collocations(collocations, first_word, second_word)
collocations = find_whole_collocations_from_stems(collocations, file_content)
return collocations, most_common_words, file_content
def find_collocations(file_name, data, popular_word):
text_file = open(file_name, 'r')
file_content = text_file.read()
most_common_words = find_most_common_words(file_content, popular_word)
second_word = None
third_word = None
collocations = data
text_file.seek(0)
for line in text_file:
for word in line.split():
first_word = second_word
second_word = third_word
third_word = trim_word(word)
if (first_word not in most_common_words and second_word not in most_common_words) and \
(first_word and first_word[0].islower() and second_word and second_word[0].islower()):
count_collocations(collocations, stem(first_word.lower()),
stem(second_word.lower()))
# dodatkowa iteracja dla ostatniego slowa
first_word = second_word
second_word = third_word
count_collocations(collocations, first_word, second_word)
collocations = find_whole_collocations_from_stems(collocations,
file_content)
return collocations, most_common_words, file_content
def find_collocations(text, data, popular_word):
most_common_words = find_most_common_words(text, popular_word)
second_word = None
third_word = None
collocations = data
for word in text.split():
first_word = second_word
second_word = third_word
third_word = trim_word(word)
if (first_word not in most_common_words and second_word not in most_common_words) and \
(first_word and first_word[0].islower() and second_word and second_word[0].islower()):
count_collocations(collocations, stem(first_word.lower()),
stem(second_word.lower()))
# dodatkowa iteracja dla ostatniego slowa
first_word = second_word
second_word = third_word
count_collocations(collocations, first_word, second_word)
collocations = find_whole_collocations_from_stems(collocations, text)
return collocations, most_common_words
