class FileReader(QWidget):
def __init__(self):
super().__init__()
self.__logger = Logger()
self.__file_dialog = QFileDialog()
self.__logger.info('FileReader was successfully initialized.',
__name__)
def _detect_encoding(self, filename):
with open(filename, 'rb') as byte_file:
byte_string = byte_file.read()
encoding = chardet.detect(byte_string)['encoding']
self.__logger.info(f"File's encoding: {encoding}", __name__)
return encoding
def get_file_content(self):
try:
filename = self.__file_dialog.getOpenFileName(
self, 'Open file', '/home')[0]
self.__logger.info(f'Filename: {filename}', __name__)
if filename:
with open(filename,
'r',
encoding=self._detect_encoding(filename)) as file:
return file.read()
except BaseException as exception:
self.__logger.error(str(exception), __name__)
class SpeechRecognizer:
def __init__(self):
# Services
self.__recognizer = sr.Recognizer()
self.__logger = Logger()
self._exceptions_handler = ExceptionsHandler()
self.__logger.info('SpeechRecognizer was successfully initialized.', __name__)
def recognize_speech(self):
while True:
try:
with sr.Microphone() as source:
speech = self.__recognizer.listen(source)
except BaseException as exception:
error_message = self._exceptions_handler.get_error_message(exception)
self.__logger.error(error_message, __name__)
return error_message
try:
text = self.__recognizer.recognize_google(speech, language="ru-RU").lower().strip()
return text
except BaseException as exception:
error_message = self._exceptions_handler.get_error_message(exception)
if isinstance(exception, sr.WaitTimeoutError):
self.__logger.warning(self._exceptions_handler.get_error_message(exception), __name__)
else:
self.__logger.error(error_message, __name__)
return error_message
class SpellChecker:
def __init__(self):
# Services
self.__logger = Logger()
self._exceptions_handler = ExceptionsHandler()
self.__logger.info('SpellChecker was successfully initialized.',
__name__)
def check_spelling(self, text):
self.__logger.info(f'Start text: {text}', __name__)
try:
response = requests.get(
'https://speller.yandex.net/services/spellservice.json/checkText',
params={
'text': text
}).json()
except BaseException as exception:
self.__logger.error(
self._exceptions_handler.get_error_message(exception),
__name__)
return text
for word in response:
text = text.replace(word['word'], word['s'][0])
self.__logger.info(f'Checked text: {text}', __name__)
return text
class DatabaseCursor:
def __init__(self):
# Services
self.__logger = Logger()
self._path_service = PathService()
self._configurator = Configurator()
self._exceptions_handler = ExceptionsHandler()
# Data
self._wd = os.getcwd()
self._request_url = None
self.databases_public_keys = None
self.__logger.info('DatabaseCursor was successfully initialized.',
__name__)
def _load_config(self):
path_to_config = os.path.join(self._path_service.path_to_configs,
'database_cursor.json')
if os.path.exists(path_to_config):
with open(path_to_config, 'r', encoding='utf-8') as file:
config = json.load(file)
self._request_url = config['request_url']
self.databases_public_keys = config['database_public_keys']
else:
self.__logger.error(
"Can't load config for DatabaseCursor (doesn't exist).",
__name__)
def __update_connection(self, ngram):
path_to_db = None
if ngram.count(' ') == 0:
path_to_db = self._path_service.get_path_to_database('unigrams.db')
elif ngram.count(' ') == 1:
path_to_db = self._path_service.get_path_to_database('bigrams.db')
elif ngram.count(' ') == 2:
path_to_db = self._path_service.get_path_to_database('trigrams.db')
if path_to_db and os.path.exists(path_to_db):
self.__logger.info(f'Connected to database: {path_to_db}',
__name__)
return sqlite3.connect(path_to_db)
else:
self.__logger.warning(f'Database lost: {path_to_db}', __name__)
self.__logger.info('Trying to download database from cloud...',
__name__)
self._configurator.download_database(path_to_db)
self.__logger.info(f'Connected to database: {path_to_db}',
__name__)
if os.path.exists(path_to_db):
return sqlite3.connect(path_to_db)
else:
self.__logger.fatal("Database doesn't exist.", __name__)
def get_entry(self, ngram):
connection = self.__update_connection(ngram)
cursor = connection.cursor()
request = ("""
SELECT * FROM 'Data' WHERE Ngram='%s'
""") % ngram
self.__logger.info(f'Request to DB: {request.strip()}', __name__)
try:
cursor.execute(request)
self.__logger.info('Request is OK.', __name__)
except BaseException as exception:
connection.close()
self.__logger.error(
self._exceptions_handler.get_error_message(exception),
__name__)
return
result = cursor.fetchone()
self.__logger.info(f'Received data: {str(result)}', __name__)
if result:
connection.close()
return result[1], result[2]
else:
connection.close()
def entry_exists(self, ngram):
connection = self.__update_connection(ngram)
cursor = connection.cursor()
request = ("""
SELECT * FROM 'Data' WHERE Ngram='%s'
""") % ngram
self.__logger.info(f'Request to DB: {request.strip()}', __name__)
try:
cursor.execute(request)
self.__logger.info('Request is OK.', __name__)
except BaseException as exception:
connection.close()
self.__logger.error(
self._exceptions_handler.get_error_message(exception),
__name__)
return
if cursor.fetchone():
connection.close()
self.__logger.info('Entry exists.', __name__)
return True
else:
connection.close()
self.__logger.info("Entry doesn't exist.", __name__)
return False
class PathService(metaclass=Singleton):
def __init__(self):
# Services
self.__logger = Logger()
# Data
self._wd = os.getcwd()
self.path_to_databases = None
self.path_to_configs = None
self._valid_classifiers = None
self._valid_model_types = None
self._valid_databases = None
self._valid_test_results_modes = None
self._valid_datasets = None
self.path_to_stop_words = None
self._path_to_main_directory = None
self.path_to_vector_model = None
self._path_to_classifier_models = None
self._path_to_test_results = None
self.configure()
self.__logger.info('PathService was successfully configured.', __name__)
def _find_main_directory(self):
max_nesting_level = 5
nesting_level = 0
while not os.getcwd().endswith('Python'):
if os.getcwd().endswith('Databases'):
os.chdir(os.path.join('..', 'Python'))
break
else:
os.chdir('..')
nesting_level += 1
if nesting_level > max_nesting_level:
self.__logger.fatal("Can't find main directory (exceeded maximum nesting level).", __name__)
exit(-1)
self._path_to_main_directory = os.getcwd()
self.path_to_configs = os.path.join(self._path_to_main_directory, 'Services', 'Configs')
self.path_to_databases = os.path.abspath(os.path.join('..', 'Databases'))
os.chdir(self._wd)
def _check_paths_existing(self):
if not os.path.exists(self.path_to_configs):
self.__logger.fatal("Directory with config files doesn't exist.", __name__)
exit(-1)
elif not os.path.exists(self.path_to_databases):
self.__logger.fatal("Directory with databases doesn't exist.", __name__)
exit(-1)
elif not os.path.exists(self._path_to_classifier_models):
self.__logger.fatal("Directory with classifier models doesn't exist.", __name__)
exit(-1)
if not os.path.exists(self.path_to_vector_model):
self.path_to_vector_model = None
self.__logger.error("Vector model doesn't exist.", __name__)
if not os.path.exists(self.path_to_stop_words):
self.path_to_stop_words = None
self.__logger.error("File with stop-words doesn't exist.", __name__)
if not os.path.exists(self._path_to_test_results):
self._path_to_test_results = None
self.__logger.warning("Directory with tests reports doesn't exist.", __name__)
def _load_config(self):
path_to_config = os.path.join(self.path_to_configs, 'path_service.json')
if not os.path.exists(path_to_config):
self.__logger.error("Can't find config-file for PathService.", __name__)
with open(path_to_config, 'r', encoding='utf-8') as file:
config = json.load(file)
self._valid_classifiers = config['valid_classifiers']
self._valid_databases = config['valid_databases']
self._valid_datasets = config['valid_datasets']
self._valid_test_results_modes = config['valid_test_results_modes']
self._valid_model_types = config['valid_model_types']
def configure(self):
self._find_main_directory()
self._load_config()
self.path_to_vector_model = os.path.join(self.path_to_databases, 'ruscorpora_upos_skipgram_300_10_2017.bin.gz')
self.path_to_stop_words = os.path.join(self._path_to_main_directory, 'Services', 'Lemmatizer',
'stop_words.json')
self._path_to_classifier_models = os.path.join(self.path_to_databases, 'Models')
self._path_to_test_results = os.path.join(self._path_to_main_directory, 'Tests', 'System', 'Reports')
self._check_paths_existing()
def get_path_to_test_results(self, mode='classifier', classifier_name='NBC'):
if classifier_name not in self._valid_classifiers:
self.__logger.warning('Got incorrect classifier name.', __name__)
classifier_name = 'NBC'
if classifier_name not in self._valid_test_results_modes:
self.__logger.warning('Got incorrect mode.', __name__)
return self._path_to_test_results
if mode.lower().strip() == 'vec_model':
return os.path.join(self._path_to_test_results, 'VectorModel')
elif mode.lower().strip() == 'classifier_main':
return os.path.join(self._path_to_test_results, '..', '..', 'MainReports', 'Classifier', classifier_name)
elif mode.lower().strip() == 'classifier':
return self._path_to_test_results
def get_path_to_model(self, model='unigrams', classifier_name='NBC'):
if classifier_name not in self._valid_classifiers:
self.__logger.warning('Got incorrect classifier name.', __name__)
classifier_name = 'NBC'
if model not in self._valid_model_types:
self.__logger.warning('Got incorrect model type.', __name__)
model = 'unigrams'
path_to_models = os.path.join(self._path_to_classifier_models, classifier_name)
if os.path.exists(path_to_models):
path_to_required_model = os.path.join(path_to_models, f'model_{model}.pkl')
return path_to_required_model
else:
self.__logger.error("Required model wasn't found.", __name__)
def get_path_to_database(self, database_name='unigrams.db'):
if database_name not in self._valid_databases:
self.__logger.warning('Got incorrect database name.', __name__)
database_name = 'unigrams.db'
path_to_database = os.path.join(self.path_to_databases, database_name)
return path_to_database
def get_path_to_dataset(self, dataset):
if dataset not in self._valid_datasets:
self.__logger.warning('Got incorrect dataset name.', __name__)
dataset = 'dataset_with_unigrams.csv'
path_to_dataset = os.path.join(self.path_to_databases, dataset)
return path_to_dataset
def set_path_to_vector_model(self, path_to_vector_model):
self.path_to_vector_model = path_to_vector_model
class NgramAnalyzer:
def __init__(self):
# Services
self._database_cursor = DatabaseCursor()
self.__logger = Logger()
self._exceptions_hanlder = ExceptionsHandler()
self._lemmatizer = Lemmatizer()
self._path_service = PathService()
self._configurator = Configurator()
self._morph_analyzer = pymorphy2.MorphAnalyzer()
# Data
self._vec_model = None
self._load_vec_model()
self.__logger.info('NgramAnalyzer was successfully initialized.', __name__)
def _load_vec_model(self):
if not self._path_service.path_to_vector_model:
self.__logger.warning("Vector model doesn't exist.", __name__)
self._configurator.download_vector_model()
self._path_service.set_path_to_vector_model(os.path.join(self._path_service.path_to_databases,
'ruscorpora_upos_skipgram_300_10_2017.bin.gz'))
self.__logger.info('Vector model was successfully downloaded.', __name__)
if self._path_service.path_to_vector_model:
self._vec_model = gensim.models.KeyedVectors.load_word2vec_format(self._path_service.path_to_vector_model,
binary=True)
else:
self.__logger.error("Vector model doesn't exist.", __name__)
def _part_of_speech_detect(self, word):
if not word:
return
part_of_speech = self._morph_analyzer.parse(word)[0].tag.POS
if part_of_speech:
if re.match(r'ADJ', part_of_speech):
return 'ADJ'
elif re.match(r'PRT', part_of_speech):
return 'PRT'
elif part_of_speech == 'INFN':
return 'VERB'
elif part_of_speech == 'ADVB' or part_of_speech == 'PRED':
return 'ADV'
elif part_of_speech == 'PRCL':
return 'PART'
return part_of_speech
@staticmethod
def _detect_ngram_type(ngram):
if not ngram:
return
if ngram.count(' ') == 0:
return 'unigram'
elif ngram.count(' ') == 1:
return 'bigram'
elif ngram.count(' ') == 2:
return 'trigram'
def _nearest_synonyms_find(self, word, topn):
if not self._vec_model or not word or topn <= 0:
return
nearest_synonyms = list()
part_of_speech = self._part_of_speech_detect(word)
ngram_type = self._detect_ngram_type(word)
if part_of_speech:
word = word + '_%s' % self._part_of_speech_detect(word)
try:
for synonym in self._vec_model.most_similar(positive=[word], topn=topn * 10):
found_synonym = self._lemmatizer.get_text_initial_form(synonym[0].split('_')[0])
if found_synonym and self._detect_ngram_type(found_synonym) == ngram_type:
nearest_synonyms.append({'word': found_synonym,
'cosine proximity': synonym[1]})
if len(nearest_synonyms) == topn:
break
except BaseException as exception:
self.__logger.warning(self._exceptions_hanlder.get_error_message(exception), __name__)
return
return nearest_synonyms
def relevant_ngram_find(self, ngram):
if not ngram:
return
self.__logger.info(f'Start ngram: {ngram}', __name__)
response = {'synonym_found': False, 'content': dict()}
if self._detect_ngram_type(ngram) == 'unigram':
synonyms_count = 10
nearest_synonyms = self._nearest_synonyms_find(ngram, synonyms_count)
if not nearest_synonyms:
return response
for nearest_synonym in nearest_synonyms:
data = self._database_cursor.get_entry(nearest_synonym['word'])
if data and data[0]:
self.__logger.info(f'Relevant ngram: {nearest_synonym["word"]}', __name__)
response['synonym_found'] = True
response['content']['synonym'] = nearest_synonym['word']
response['content']['pos_docs'] = data[0]
response['content']['neg_docs'] = data[1]
return response
return response
class Configurator(metaclass=Singleton):
def __init__(self):
# Services
self.__logger = Logger()
self._path_service = PathService()
self._exceptions_handler = ExceptionsHandler()
# Data
self._config = dict()
self._wd = os.getcwd()
self._path_to_databases = None
self._request_url = None
self._vector_model_public_key = None
self._databases_public_keys = None
self._load_public_keys()
self.__logger.info('Configurator was successfully initialized.',
__name__)
def _load_public_keys(self):
path_to_config = os.path.join(self._path_service.path_to_configs,
'configurator.json')
if os.path.exists(path_to_config):
with open(path_to_config, 'r', encoding='utf-8') as file:
config = json.load(file)
self._request_url = config['request_url']
self._vector_model_public_key = config['vector_model_public_key']
self._databases_public_keys = config['databases_public_keys']
else:
self.__logger.error(
"Can't load config for Configrurator (doesn't exist).",
__name__)
def download_database(self, path_to_db):
database_name = os.path.split(path_to_db)[1]
if database_name:
try:
download_url = requests.get(
self._request_url,
params={
'public_key':
self._databases_public_keys[database_name]
}).json()["href"]
with open(path_to_db, 'wb') as database_file:
database_file.write(requests.get(download_url).content)
self._config[path_to_db] = 'downloaded'
except BaseException as exception:
self.__logger.error(
self._exceptions_handler.get_error_message(exception),
__name__)
self._config[path_to_db] = 'error'
def download_vector_model(self):
self._path_service.set_path_to_vector_model(
os.path.join(self._path_service.path_to_databases,
'ruscorpora_upos_skipgram_300_10_2017.bin.gz'))
try:
download_url = requests.get(self._request_url,
params={
'public_key':
self._vector_model_public_key
}).json()["href"]
with open(self._path_service.path_to_vector_model,
'wb') as vec_model:
vec_model.write(requests.get(download_url).content)
self._config[
'ruscorpora_upos_skipgram_300_10_2017.bin.gz'] = 'downloaded'
except BaseException as exception:
self.__logger.error(
self._exceptions_handler.get_error_message(exception),
__name__)
self._config[
'ruscorpora_upos_skipgram_300_10_2017.bin.gz'] = 'error'
def configure_system(self):
self._config['datetime'] = str(datetime.now())
for database in ['unigrams.db', 'bigrams.db', 'trigrams.db']:
path_to_database = self._path_service.get_path_to_database(
database)
if not path_to_database or not os.path.exists(path_to_database):
self.__logger.warning('Database not found: %s' % str(database),
__name__)
self.download_database(
os.path.join(self._path_service.path_to_databases,
database))
else:
self._config[database] = 'exists'
if not self._path_service.path_to_vector_model or not os.path.exists(
self._path_service.path_to_vector_model):
self.__logger.warning('Vector model not found.', __name__)
self.download_vector_model()
else:
self._config[
'ruscorpora_upos_skipgram_300_10_2017.bin.gz'] = 'exists'
self._create_config()
def _create_config(self):
with open(os.path.join('Logs', 'config.json'), 'w',
encoding='utf-8') as config:
json.dump(self._config, config, indent=4)
class Classifier:
def __init__(self):
# Services
self.__logger = Logger()
self._path_service = PathService()
self._exceptions_handler = ExceptionsHandler()
# Data
self._container = ClassificationDataContainer()
self._possible_classifiers = ['NBC', 'LogisticRegression', 'KNN']
self.__logger.info('Classifier was successfully initialized.',
__name__)
def _load_config(self):
path_to_config = os.path.join(self._path_service.path_to_configs,
'classifier.json')
if os.path.exists(path_to_config):
with open(path_to_config, 'r', encoding='utf-8') as file:
config = json.load(file)
self._possible_classifiers = config['possible_classifiers']
else:
self.__logger.error("Can't load Classifier configuration.",
__name__)
def customize(self,
unigrams_weight,
bigrams_weight,
trigrams_weight,
classifier_name='NBC'):
self._container.clear()
if classifier_name in self._possible_classifiers:
self._container.classifiers['name'] = classifier_name
else:
self._container.classifiers['name'] = 'NBC'
self.__logger.error('Got unknown classifier, set default (NBC).',
__name__)
self._container.weights['unigrams'] = unigrams_weight
self._container.weights['bigrams'] = bigrams_weight
self._container.weights['trigrams'] = trigrams_weight
try:
if self._container.weights['unigrams']:
self._container.classifiers['unigrams'] = joblib.load(
self._path_service.get_path_to_model(
'unigrams', self._container.classifiers['name']))
if self._container.weights['bigrams']:
self._container.classifiers['bigrams'] = joblib.load(
self._path_service.get_path_to_model(
'bigrams', self._container.classifiers['name']))
if self._container.weights['trigrams']:
self._container.classifiers['trigrams'] = joblib.load(
self._path_service.get_path_to_model(
'trigrams', self._container.classifiers['name']))
self.__logger.info('Models were successfully loaded.', __name__)
self.__logger.info('Classifier was successfully configured.',
__name__)
except BaseException as exception:
self.__logger.fatal(
self._exceptions_handler.get_error_message(exception),
__name__)
def _predict_tonal_by_unigrams(self):
self._container.tonalities['unigrams'] = self._container.classifiers[
'unigrams'].predict(self._container.weights['unigrams'])[0]
self._container.probabilities['unigrams'] = max(
self._container.classifiers['unigrams'].predict_proba(
self._container.weights['unigrams'])[0])
self.__logger.info(
f'Unigrams tonal: {self._container.tonalities["unigrams"]}',
__name__)
self.__logger.info(
f'Unigrams probability: {self._container.probabilities["unigrams"]}',
__name__)
def _predict_tonal_by_unigrams_bigrams(self):
self._container.tonalities['bigrams'] = self._container.classifiers[
'bigrams'].predict([[
self._container.weights['unigrams'],
self._container.weights['bigrams']
]])[0]
self._container.probabilities['bigrams'] = max(
self._container.classifiers['bigrams'].predict_proba([[
self._container.weights['unigrams'],
self._container.weights['bigrams']
]])[0])
self.__logger.info(
f'Bigrams tonal: {self._container.tonalities["bigrams"]}',
__name__)
self.__logger.info(
f'Bigrams probability: {self._container.probabilities["bigrams"]}',
__name__)
def _predict_tonal_by_unigrams_bigrams_trigrams(self):
self._container.tonalities['trigrams'] = self._container.classifiers[
'trigrams'].predict([[
self._container.weights['unigrams'],
self._container.weights['bigrams'],
self._container.weights['trigrams']
]])[0]
self._container.probabilities['trigrams'] = max(
self._container.classifiers['trigrams'].predict_proba([[
self._container.weights['unigrams'],
self._container.weights['bigrams'],
self._container.weights['trigrams']
]])[0])
self.__logger.info(
f'Trigrams tonal: {self._container.tonalities["trigrams"]}',
__name__)
self.__logger.info(
f'Trigrams probability: {self._container.probabilities["trigrams"]}',
__name__)
def _predict_intermediate_tonalities(self):
threads = list()
if self._container.weights['unigrams']:
threads.append(
Thread(target=self._predict_tonal_by_unigrams, args=()))
if self._container.weights['bigrams']:
threads.append(
Thread(target=self._predict_tonal_by_unigrams_bigrams,
args=()))
if self._container.weights['trigrams']:
threads.append(
Thread(target=self._predict_tonal_by_unigrams_bigrams_trigrams,
args=()))
for thread in threads:
thread.start()
for thread in threads:
while thread.is_alive():
time.sleep(0.1)
thread.join()
def _select_final_tonal(self):
if self._container.tonalities['unigrams'] and self._container.tonalities['bigrams'] and \
self._container.tonalities['trigrams']:
if self._container.tonalities[
'unigrams'] == self._container.tonalities['bigrams']:
self._container.tonalities[
'final'] = self._container.tonalities['unigrams']
self._container.probabilities['final'] = max(
self._container.probabilities['unigrams'],
self._container.probabilities['bigrams'])
elif self._container.tonalities[
'unigrams'] == self._container.tonalities['trigrams']:
self._container.tonalities[
'final'] = self._container.tonalities['unigrams']
self._container.probabilities['final'] = max(
self._container.probabilities['unigrams'],
self._container.probabilities['trigrams'])
elif self._container.tonalities[
'bigrams'] == self._container.tonalities['trigrams']:
self._container.tonalities[
'final'] = self._container.tonalities['bigrams']
self._container.probabilities['final'] = max(
self._container.probabilities['bigrams'],
self._container.probabilities['trigrams'])
elif self._container.tonalities[
'unigrams'] and self._container.tonalities['bigrams']:
if self._container.tonalities[
'unigrams'] != self._container.tonalities['bigrams']:
if self._container.probabilities[
'unigrams'] >= self._container.probabilities['bigrams']:
self._container.tonalities[
'final'] = self._container.tonalities['unigrams']
self._container.probabilities[
'final'] = self._container.probabilities['unigrams']
else:
self._container.tonalities[
'final'] = self._container.tonalities['bigrams']
self._container.probabilities[
'final'] = self._container.probabilities['bigrams']
elif self._container.tonalities[
'unigrams'] == self._container.tonalities['bigrams']:
self._container.tonalities[
'final'] = self._container.tonalities['unigrams']
self._container.probabilities['final'] = max(
self._container.probabilities['bigrams'],
self._container.probabilities['unigrams'])
elif self._container.tonalities['unigrams']:
self._container.tonalities['final'] = self._container.tonalities[
'unigrams']
self._container.probabilities[
'final'] = self._container.probabilities['unigrams']
def predict_tonal(self):
self._predict_intermediate_tonalities()
self._select_final_tonal()
self.__logger.info(
f'Final tonal: {self._container.tonalities["final"]}', __name__)
self.__logger.info(
f'Final probability: {self._container.probabilities["final"]}',
__name__)
return self._container.tonalities[
'final'], self._container.probabilities['final']