def eval_rus():
simlex = read_files.read_simlex_rus_file()
wordsim = read_files.read_wordsim_rus_file()
wn = WikiWordnet()
"""
#evaluation of wordnet
matches = 0
for key,value in wordsim.items():
synset = wn.get_synsets(key)
for syn in synset:
for w in syn.get_words():
word = w.lemma()
if value == word:
matches = matches + 1
"""
#evaluation of word vectors
word_vectors = api.load('word2vec-ruscorpora-300')
matches1 = 0
matches2 = 0
matches3 = 0
matches4 = 0
for key, value in simlex.items():
try:
sim_words3 = word_vectors.most_similar(key + '_NOUN', topn=3)
sim_words10 = word_vectors.most_similar(key + '_NOUN', topn=10)
except:
try:
sim_words3 = word_vectors.most_similar(key + '_VERB', topn=3)
sim_words10 = word_vectors.most_similar(key + '_VERB', topn=10)
except:
try:
sim_words3 = word_vectors.most_similar(key + '_ADJ',
topn=3)
sim_words10 = word_vectors.most_similar(key + '_ADJ',
topn=10)
except:
continue
#print(sim_words10)
for word in sim_words3:
if word[0].split('_')[0] == value:
matches1 = matches1 + 1
for word in sim_words10:
if word[0].split('_')[0] == value:
matches2 = matches2 + 1
for key, value in wordsim.items():
try:
sim_words3 = word_vectors.most_similar(key + '_NOUN', topn=3)
sim_words10 = word_vectors.most_similar(key + '_NOUN', topn=10)
except:
try:
sim_words3 = word_vectors.most_similar(key + '_VERB', topn=3)
sim_words10 = word_vectors.most_similar(key + '_VERB', topn=10)
except:
try:
sim_words3 = word_vectors.most_similar(key + '_ADJ',
topn=3)
sim_words10 = word_vectors.most_similar(key + '_ADJ',
topn=10)
except:
continue
for word in sim_words3:
if word[0].split('_')[0] == value:
matches3 = matches3 + 1
for word in sim_words10:
if word[0].split('_')[0] == value:
matches4 = matches4 + 1
return [matches1, matches2, matches3, matches4]
# -*- coding: utf-8 -*-
import pymorphy2
import nltk
import copy
from wiki_ru_wordnet import WikiWordnet
wikiwordnet = WikiWordnet()
morph = pymorphy2.MorphAnalyzer()
################
def synonymscheck(inlist, keylist):
corrans = 0 #Correct Answers (Верные соответствия)
for i in inlist:
synsets = wikiwordnet.get_synsets(i)
for n in wikiwordnet.get_synsets(keylist[inlist.index(i)]):
if n in synsets:
corrans += 1
print(corrans, '/3')
else:
pass
###############
def getlemma(inlist):
corrans = 0 #Correct Answers (Верные соответствия)
for i in inlist:
synsets = wikiwordnet.get_synsets(i)
for synset in wikiwordnet.get_synsets(i):
print(synset)
for word in synset.get_words():