In [1]:

    

from cltk.corpus.utils.formatter import assemble_phi5_author_filepaths
from cltk.corpus.utils.formatter import assemble_tlg_author_filepaths
from cltk.corpus.utils.formatter import phi5_plaintext_cleanup
from cltk.corpus.utils.formatter import tlg_plaintext_cleanup
from cltk.stem.latin.j_v import JVReplacer
from cltk.stem.lemma import LemmaReplacer
from cltk.stop.greek.stops import STOPS_LIST as greek_stops
from cltk.stop.latin.stops import STOPS_LIST as latin_stops
from nltk.tokenize.punkt import PunktLanguageVars
from cltk.tokenize.sentence import TokenizeSentence
from gensim.models import Word2Vec
import os


    

In [2]:

    

model_path = os.path.expanduser('~/cltk_data/user_data/word2vec_phi_lemma.model')
model = Word2Vec.load(model_path)


    

In [3]:

    

#vocab = model.vocab
vocab = model.vocab


    

In [10]:

    

path = os.path.expanduser('~/cltk_data/user_data/latin_word2vec_most_sims.txt')
# empty file if exists
if os.path.exists(path):
    with open(path, 'w') as fo:
        fo.write('')

for x in vocab:
    syn_list = []
    pairs = model.most_similar(x)
    for k,v in pairs:
        if v > 0.50:
            syn_list.append(k)

    if syn_list:
        with open(path, 'a') as fo:
            line = x + '\t' + str(syn_list) + '\n'
            fo.write(line)


    

In [ ]: