File model.py has 360 lines of code (exceeds 250 allowed). Consider refactoring.

Open

# -*- coding: utf-8 -*-
# Автор: Гусев Илья
# Описание: Модель PoS-теггера на основе BiLSTM.

from typing import List, Tuple

Function __iter__ has a Cognitive Complexity of 26 (exceeds 5 allowed). Consider refactoring.

Open

    def __iter__(self):
        """
        Получение очередного батча.

        :return: индексы словоформ, грамматические векторы, ответы-индексы.

• Read up
  Read up

Function __get_lemma has a Cognitive Complexity of 17 (exceeds 5 allowed). Consider refactoring.

Open

    def __get_lemma(self, word: str, pos_tag: str, gram: str, word_forms=None,
                    enable_normalization: bool=True):
        """
        Получить лемму.
        

• Read up
  Read up

Function evaluate has a Cognitive Complexity of 16 (exceeds 5 allowed). Consider refactoring.

Open

    def evaluate(self, file_names, val_idx, train_config: TrainConfig, build_config: BuildModelConfig) -> None:
        """
        Оценка на val выборке.

        :param file_names: файлы выборки.

• Read up
  Read up

Function get_sample has a Cognitive Complexity of 16 (exceeds 5 allowed). Consider refactoring.

Open

    def get_sample(sentence: List[str],
                   language: str,
                   converter,
                   morph: MorphAnalyzer,
                   grammeme_vectorizer: GrammemeVectorizer,

• Read up
  Read up

Function train has a Cognitive Complexity of 15 (exceeds 5 allowed). Consider refactoring.

Open

def train(file_names: List[str], train_config_path: str, build_config_path: str,
          language: str, embeddings_path: str=None):
    train_config = TrainConfig()
    train_config.load(train_config_path)
    if train_config.train_model_config_path is None:

• Read up
  Read up

Function convert_from_conllu has a Cognitive Complexity of 15 (exceeds 5 allowed). Consider refactoring.

Open

    def convert_from_conllu(input_filename, output_filename, with_forth_column=False, with_punct=True,
                            add_number=False):
        with open(input_filename, "r", encoding='utf-8') as r, open(output_filename, "w", encoding='utf-8') as w:
            i = 0
            for line in r:

• Read up
  Read up

Function build has a Cognitive Complexity of 13 (exceeds 5 allowed). Consider refactoring.

Open

    def build(self, config: BuildModelConfig, word_embeddings=None):
        """
        Описание модели.

        :param config: конфиг модели.

• Read up
  Read up

Function get_char_model has 10 arguments (exceeds 4 allowed). Consider refactoring.

Open

def get_char_model(

Function __normalize_for_gikrya has a Cognitive Complexity of 11 (exceeds 5 allowed). Consider refactoring.

Open

    def __normalize_for_gikrya(form):
        """
        Поучение леммы по правилам, максимально близким к тем, которые в корпусе ГИКРЯ.
        
        :param form: форма из pymorphy2.

• Read up
  Read up

Function __init__ has 9 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, language: str,

Function __init__ has a Cognitive Complexity of 10 (exceeds 5 allowed). Consider refactoring.

Open

    def __init__(self,
                 language="ru",
                 eval_model_config_path: str=None,
                 eval_model_weights_path: str=None,
                 gram_dict_input: str=None,

• Read up
  Read up

Function __build_vector has a Cognitive Complexity of 10 (exceeds 5 allowed). Consider refactoring.

Open

    def __build_vector(self, pos_tag: str, grammemes: List[str]) -> List[int]:
        """
        Построение вектора по части речи и грамматическим значениям.
        
        :param pos_tag: часть речи.

• Read up
  Read up

Function build has 27 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    def build(self, config: BuildModelConfig, word_embeddings=None):
        """
        Описание модели.

        :param config: конфиг модели.

Function __init__ has 26 lines of code (exceeds 25 allowed). Consider refactoring.

Open

    def __init__(self):
        self.use_gram = True
        self.gram_hidden_size = 30
        self.gram_dropout = 0.3

Function __init__ has 8 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self,

Function get_sample has 8 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def get_sample(sentence: List[str],

Function load_train has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

    def load_train(self, config: BuildModelConfig, model_config_path: str=None, model_weights_path: str=None):
        with open(model_config_path, "r", encoding='utf-8') as f:
            if config.use_crf:
                from keras_contrib.layers import CRF
                custom_objects = {'ReversedLSTM': ReversedLSTM, 'CRF': CRF}

• Read up
  Read up

Function shrink_w2v has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

def shrink_w2v(input_filename, border, output_filename, print_step=10000):
    vocabulary_embeddings = dict()
    all_count = 0
    correct_count = 0
    with open(input_filename, "r", encoding='utf-8', errors='ignore') as r:

• Read up
  Read up

Avoid deeply nested control flow statements.

Open

                        for index, bucket in enumerate(self.buckets):
                            if self.bucket_borders[index][0] <= len(last_sentence) < self.bucket_borders[index][1]:
                                bucket.append(last_sentence)
                            if len(bucket) >= self.batch_size:
                                yield self.__to_tensor(bucket)