utilities_language_general/rus_constants.py

import json
import spacy
import gensim
import pymorphy3
import streamlit as st
from pickle import load
from transformers import pipeline
from summarizer import Summarizer
from torch import cuda, device
device = device('cuda' if cuda.is_available else 'cpu')


@st.cache_resource
def load_morph():
    _morph = pymorphy3.MorphAnalyzer(lang='ru')
    return _morph


@st.cache_resource
def load_w2v(model):
    with st.spinner('Загружаю языковую модель'):
        if model == 'model1':
            model_path = r'language_data/model1.gz'
        else:
            model_path = r'language_data/model2.gz'
    return gensim.models.KeyedVectors.load_word2vec_format(model_path, binary=True)


@st.cache_resource
def load_spacy():
    with st.spinner('Загружаю морфо-синтаксический парсер'):
        _nlp = spacy.load('ru_core_news_lg')
    return _nlp


@st.cache_resource
def load_bert():
    with st.spinner('Загружаю языковую модель'):
        _pipeline = pipeline(task="fill-mask", model="a-v-bely/ruBert-base-finetuned-russian-moshkov-child-corpus-pro", device=device)
    return _pipeline


@st.cache_resource
def load_summarizer():
    return Summarizer()

@st.cache_resource
def load_classifiers(model):
    if model == 'model1':
        scaler_path = 'language_data/model1_no_wn_minmaxscaler.pickle'
        classifier_path = 'language_data/model1_no_wn_catboost_classifier.pickle'
    elif model == 'model2':
        scaler_path = 'language_data/model2_no_wn_minmaxscaler.pickle'
        classifier_path = 'language_data/model2_no_wn_catboost_classifier.pickle'
    else:
        scaler_path = 'language_data/model3_no_wn_minmaxscaler.pickle'
        classifier_path = 'language_data/model3_no_wn_catboost_classifier.pickle'
    with (open(scaler_path, 'rb') as f1, open(classifier_path, 'rb') as f2, open('language_data/pos_dict.pickle', 'rb') as f3):
        scaler = load(f1)
        classifier = load(f2)
        pos_dict = load(f3)
    return pos_dict, scaler, classifier

nlp = load_spacy()
morph = load_morph()
summarization = load_summarizer()
w2v_model1_path = r'model1.gz'
w2v_model2_path = r'model2.gz'

# Upload stop list
stop_list = set()
with open(r'language_data/stop_words.txt', 'r', encoding='utf-8') as read_file:
    for line in read_file:
        stop_list.add(line.strip())

# Upload minimums
a1_path, a1_target_set = r'language_data/A1_MINIMUM.txt', set()
a2_path, a2_target_set = r'language_data/A2_MINIMUM.txt', set()
b1_path, b1_target_set = r'language_data/B1_MINIMUM.txt', set()
b2_path, b2_target_set = r'language_data/B2_MINIMUM.txt', set()
c1_path, c1_target_set = r'language_data/C1_MINIMUM.txt', set()
c2_path, c2_target_set = r'language_data/C2_MINIMUM.txt', set()

minimums_paths = (a1_path, a2_path, b1_path, b2_path, c1_path, c2_path)
minimums_sets = (a1_target_set, a2_target_set, b1_target_set, b2_target_set, c1_target_set, c2_target_set)
for i in range(len(minimums_paths)):
    with open(minimums_paths[i], 'r', encoding='utf-8') as read_file:
        for line in read_file:
            minimums_sets[i].add(line.strip())

MINIMUM_SETS = {
    'A1': (a1_target_set, a1_target_set),
    'A2': (a2_target_set, a2_target_set.union(a1_target_set)),
    'B1': (b1_target_set, b1_target_set.union(a2_target_set)),
    'B2': (b2_target_set, b2_target_set.union(b1_target_set)),
    'C1': (c1_target_set, c1_target_set.union(b2_target_set)),
    'C2': (c2_target_set, c2_target_set.union(c1_target_set)),
    'Без уровня': (None, None)
}

LEVEL_NUMBERS = {'A1': 1, 'A2': 2, 'B1': 3, 'B2': 4, 'C1': 5, 'C2': 6}

with open('language_data/phrases.json', 'r', encoding='utf-8') as f:
    PHRASES = set(json.load(f)['PHRASES'])

BAD_USER_TARGET_WORDS = []


COMBINE_POS = {
    'simple':
    {
        'A1': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'A2': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'B1': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'B2': {'VERB': ['AUX'], '': ['VERB'], },
        'C1': {'VERB': ['AUX'], '': ['VERB'], },
        'C2': {'VERB': ['AUX'], '': ['VERB'], },
        'Без уровня': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], }
    },
    'phrase': 
    {
        'A1': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'A2': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'B1': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], },
        'B2': {'VERB': ['AUX'], '': ['VERB'], },
        'C1': {'VERB': ['AUX'], '': ['VERB'], },
        'C2': {'VERB': ['AUX'], '': ['VERB'], },
        'Без уровня': {'VERB': ['AUX'], '': ['VERB'], 'ADV':['ADJ'], 'ADJ': ['ADV'], }
    },
}