utilities_language_general/esp_constants.py

import json
import spacy
import gensim
import streamlit as st
from transformers import pipeline


@st.cache_resource
def load_w2v(model_path):
    _w2v_model = gensim.models.KeyedVectors.load_word2vec_format(model_path, binary=True)
    return _w2v_model


@st.cache_resource
def load_spacy():
    _nlp = spacy.load('es_core_news_lg')
    return _nlp


@st.cache_resource
def load_bert():
    return pipeline("fill-mask", model="a-v-white/bert-base-spanish-wwm-cased-finetuned-literature-pro")


nlp = load_spacy()
news_model_path = r'news_phrases_s300_cw10_mc50_w4_negative5-075_mean_e10_notshr.bin.gz'
all_model_path = r'ALL_annot_all_pos_spell_g_h_new_phrases_s300_cw10_mc100_w4_negative5-075_mean_e10_shr.bin.gz'
lit_model_path = r'LITERATURA_annot_all_pos_spell_g_h_phrases_s300_cw10_mc50_w4_negative_5-075_mean_e20_shr.bin.gz'

# Upload minimums
a1_path, a1_target_set = r'lexical_minimums/A1_MINIMUM.txt', set()
a2_path, a2_target_set = r'lexical_minimums/A2_MINIMUM.txt', set()
b1_path, b1_target_set = r'lexical_minimums/B1_MINIMUM.txt', set()
b2_path, b2_target_set = r'lexical_minimums/B2_MINIMUM.txt', set()
c1_path, c1_target_set = r'lexical_minimums/C1_MINIMUM.txt', set()
c2_path, c2_target_set = r'lexical_minimums/C2_MINIMUM.txt', set()
minimums_paths = (a1_path, a2_path, b1_path, b2_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())

a1_distractor_set = a1_target_set
a2_distractor_set = a2_target_set.union(a1_target_set)
b1_distractor_set = b1_target_set.union(a2_target_set)
b2_distractor_set = b2_target_set.union(b1_target_set)
c1_distractor_set = c1_target_set.union(b2_target_set)
c2_distractor_set = c2_target_set.union(c1_target_set)

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

with open('language_data/fix_irregular_lemma.json', 'r', encoding='utf-8') as f:
    FIX_LEMMA = json.load(f)

SIMILARITY_VALUES = {'A1': 1.0, 'A2': 1.0, 'B1': 1.0, 'B2': 1.0, 'C1': 1.0, 'C2': 1.0, 'Нет': 1.0}
SIMILARITY_VALUES_bert = {'A1': 1.0, 'A2': 1.0, 'B1': 1.0, 'B2': 1.0, 'C1': 1.0, 'C2': 1.0, 'Нет': 1.0}

BAD_USER_TARGET_WORDS = []