def calc():
# Separating texts on sentences
text = centralize_texts.run()
tokenized_text = sent_tokenize(text)
# Separating sentences on words
tokenized_word_arr = []
for sentence in tokenized_text:
tokenized_word = word_tokenize(sentence)
tokenized_word_arr.append(tokenized_word)
# Searching dialog signs in words
stop_words = ['а', 'б', 'в', 'г', 'д', 'е', 'ё', 'ж', 'з', 'и', 'й', 'к', 'л', 'м', 'н', 'о', 'п', 'р', 'с', 'т',
'у', 'ф', 'х', 'ц', 'ч', 'ш', 'щ', 'ъ', 'ы', 'ь', 'э', 'ю', 'я']
dialogs = []
for sentence in tokenized_word_arr:
if sentence[0] == '-' or sentence[0] == '–' or sentence[0] == '—':
if sentence[1][0] not in stop_words:
dialogs.append(sentence)
# Calculating a relative indicator
relative_indicator = round(len(dialogs) * 100 / text__word.calc(), 2)
# Calculating the result
return relative_indicator
def calc():
# Coping data from the other function
text = centralize_texts.run().lower()
tokenized_text = sent_tokenize(text)
tokenized_word_arr = []
for sentence in tokenized_text:
tokenized_word = word_tokenize(sentence)
tokenized_word_arr.append(tokenized_word)
# Deleting punctuation signs
tokenizer = RegexpTokenizer(r'\w+')
text_without_punctuation_signs = tokenizer.tokenize(text)
# Deleting stop-words
stop_words = stopwords.words('russian')
stop_words.extend(['не', 'это', 'что', 'именно', 'эта', 'лишь', 'очень', 'либо', 'или', 'ru', 'которые', 'конец',
'которая', 'который', 'ибо', 'см', 'n', 'например', 'является', '', 'а', 'б', 'в', 'г', 'д', 'е',
'ё', 'ж', 'з', 'и', 'й', 'к', 'л', 'м', 'н', 'о', 'п', 'р', 'с', 'т', 'у', 'ф', 'х', 'ц', 'ч',
'ш', 'щ', 'ъ', 'ы', 'ь', 'э', 'ю', 'я'])
filtered_sent = []
for word in text_without_punctuation_signs:
if word not in stop_words:
filtered_sent.append(word)
def calc():
# Coping data from the other function
text = centralize_texts.run().lower()
tokenized_text = sent_tokenize(text)
tokenized_word_arr = []
for sentence in tokenized_text:
tokenized_word = word_tokenize(sentence)
tokenized_word_arr.append(tokenized_word)
# Deleting punctuation signs
tokenizer = RegexpTokenizer(r'\w+')
text_without_punctuation_signs = tokenizer.tokenize(text)
# Deleting stop-words
stop_words = stopwords.words('russian')
stop_words.extend(['не', 'это', 'что', 'именно', 'эта', 'лишь', 'очень', 'либо', 'или', 'ru', 'которые', 'конец',
'которая', 'который', 'ибо', 'см', 'n', 'например', 'является', '1', '2', '3', '4', '5', '6',
'7', '8', '9', '0', '', 'а', 'б', 'в', 'г', 'д', 'е', 'ё', 'ж', 'з', 'и', 'й', 'к', 'л', 'м',
'н', 'о', 'п', 'р', 'с', 'т', 'у', 'ф', 'х', 'ц', 'ч', 'ш', 'щ', 'ъ', 'ы', 'ь', 'э', 'ю', 'я'])
filtered_sent = []
for w in text_without_punctuation_signs:
if w not in stop_words:
filtered_sent.append(w)
# Searching adjectives in the text
adjectives = []
for word in filtered_sent:
if word[len(word) - 2] == 'а' and word[len(word) - 1] == 'я' \
or word[len(word) - 2] == 'о' and word[len(word) - 1] == 'е'\
or word[len(word) - 2] == 'е' and word[len(word) - 1] == 'е'\
or word[len(word) - 2] == 'о' and word[len(word) - 1] == 'й'\
or word[len(word) - 2] == 'ы' and word[len(word) - 1] == 'е'\
or word[len(word) - 2] == 'и' and word[len(word) - 1] == 'е'\
or word[len(word) - 2] == 'ы' and word[len(word) - 1] == 'й':
adjectives.append(word)
# Deleting conjunctions
for word in adjectives:
if word[0] == 'к' and word[1] == 'о' and word[2] == 'т' and word[3] == 'о' and word[4] == 'р' \
or word[0] == 'к' and word[1] == 'а' and word[2] == 'к':
adjectives.remove(word)
# Calculating a relative indicator
relative_indicator = round(len(adjectives) * 100 / text__word.calc(), 2)
# Calculating the result
return relative_indicator
def calc(analysed_word):
# Adding the text
text = centralize_texts.run().lower()
# Deleting punctuation signs
tokenizer = RegexpTokenizer(r'\w+')
text_without_punctuation_signs = tokenizer.tokenize(text)
# Deleting stop-words
stop_words = stopwords.words('russian')
stop_words.extend([
'не', 'это', 'что', 'именно', 'эта', 'лишь', 'очень', 'либо', 'или',
'ru', 'которые', 'которая', 'который', 'ибо', 'см', 'n', 'например',
'является', '1', '2', '3', '4', '5', '6', '7', '8', '9', '0', '', 'а',
'б', 'в', 'г', 'д', 'е', 'ё', 'ж', 'з', 'и', 'й', 'к', 'л', 'м', 'н',
'о', 'п', 'р', 'с', 'т', 'у', 'ф', 'х', 'ц', 'ч', 'ш', 'щ', 'ъ', 'ы',
'ь', 'э', 'ю', 'я'
])
filtered_sent = []
for word in text_without_punctuation_signs:
if word not in stop_words:
filtered_sent.append(word)
# Calculating TOP-words
fdist = FreqDist(filtered_sent)
top_words = fdist.most_common(1000)
# Calculating frequency of the marker word
returned_result = ''
for word in top_words:
word_value = word[0]
word_freq = word[1]
if word_value == analysed_word:
returned_result = word_freq
if returned_result == '':
returned_result = 'The word is not find'
# Calculating a relative indicator of the marker word
relative_indicator = 0
if returned_result != 'The word is not find':
relative_indicator = returned_result * 100 / text__word.calc()
# Calculating the result
return round(relative_indicator, 3)
def calc():
# Coping data from the other function
text = centralize_texts.run()
tokenized_text = sent_tokenize(text)
tokenized_word_arr = []
for sentence in tokenized_text:
tokenized_word = word_tokenize(sentence)
tokenized_word_arr.append(tokenized_word)
# Deleting punctuation signs
tokenizer = RegexpTokenizer(r'\w+')
text_without_punctuation_signs = tokenizer.tokenize(text)
# Calculating the result
return len(text_without_punctuation_signs)
def adding():
# Coping data from the other function
text = centralize_texts.run()
tokenized_text = sent_tokenize(text)
tokenized_word_arr = []
for sentence in tokenized_text:
tokenized_word = word_tokenize(sentence)
tokenized_word_arr.append(tokenized_word)
tokenized_word_arr_without_tokenized = ''
for word in tokenized_word_arr:
tokenized_word_arr_without_tokenized += (word + ' ')
# Returning the result
return tokenized_word_arr_without_tokenized
def calc():
text = centralize_texts.run()
tokenized_text = sent_tokenize(text)
return len(tokenized_text)
from private_apps.AI_fiction_or_scientific.modules.additional_indicators import text__word
from private_apps.AI_fiction_or_scientific.modules.additional_indicators import text__sign_abs
from private_apps.AI_fiction_or_scientific.modules.main_indicators import text__sign_rel
from private_apps.AI_fiction_or_scientific.modules.main_indicators import sentence__word
from private_apps.AI_fiction_or_scientific.modules.main_indicators import word__letter
from private_apps.AI_fiction_or_scientific.modules.main_indicators import text__adjective
from private_apps.AI_fiction_or_scientific.modules.main_indicators import text__number
from private_apps.AI_fiction_or_scientific.modules.main_indicators import text__dialog
from private_apps.AI_fiction_or_scientific.modules.main_indicators import text__marker
from private_apps.AI_fiction_or_scientific.modules.results import result_recorder
from private_apps.AI_fiction_or_scientific.modules.results.result_calculator import result_generator
# 1. CENTRALIZING FEW TEXTS
centralize_texts.run()
# 2. GETTING MAIN AND ADDITIONAL ANALYSIS INDICATORS
print('РЕЗУЛЬТАТ АНАЛИЗА')
# 2.1. Getting sentences number in text(s)
print('1. Количество предложений: ' + str(text__sentence.calc()) +
' ед./текс.')
# 2.2. Getting words number in text(s)
print('2. Количество слов: ' + str(text__word.calc()) + ' ед./текс.')
# 2.3. Getting punctuation signs number in text(s)
print('3. Абсолютное число знаков препинания: ' + str(text__sign_abs.calc()) +
' ед./текс.')