def sim_ox_wn_defi_WDS_via_defi_of_curr_main_syn(word):
dict_vectors_wn = WordnetParseDefinition.get_dict_vectors_synsets_for_word(word)
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(dict_vectors_wn)
dict_vectors_wn_defi = WordnetParseDefinition.get_vectors_defi_for_word(word)
(keys_wn_defi, vectors_wn_defi) = Util.get_keys_values_of_dict(dict_vectors_wn_defi)
definitions = OxfordParser.get_definitions_of_word(word)
m2d_sim = [[0 for x in range(len(definitions))] for x in range(len(vectors_wn))]
for i in range(len(vectors_wn)):
vector_wn = vectors_wn[i]
vector_wn_defi = vectors_wn_defi[i]
dict_vectors_ox = OxParseDefinition.get_dict_vectors_synsets_for_word(word, vector_wn_defi)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(dict_vectors_ox)
for j in range(len(vectors_ox)):
vector_ox = vectors_ox[j]
m2d_sim[i][j] = sim_2_vector(vector_ox, vector_wn)
cal_sim_ngrams(word)
return m2d_sim
def sim_ox_wn_value_main_synsets(word):
dict_vectors_wn = WordnetParseDefinition.get_dict_vectors_value_for(word)
synsets_wn = WordnetHandler.get_synsets_for_word(word,'n')
dict_vectors_ox = OxParseDefinition.get_vectors_value_for_word(word, synsets_wn)
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(dict_vectors_wn)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(dict_vectors_ox)
m2d_sim_defi_temp = sim_ox_wn_defi_WDS_via_main_syns(word)
DebugHandler.print_2d_matrix(m2d_sim_defi_temp)
m2d_sim_defi = [[0 for x in range(len(vectors_wn))] for x in range(len(vectors_ox))]
for i in range(len(vectors_wn)):
for j in range(len(vectors_ox)):
m2d_sim_defi[j][i] = m2d_sim_defi_temp[i][j]
m2d_sim = [[0 for x in range(len(vectors_ox))] for x in range(len(vectors_wn))]
for i in range(len(vectors_wn)):
vector_wn = vectors_wn[i]
print vector_wn
for j in range(len(vectors_ox)):
vector_ox = vectors_ox[j]
cosine = spatial.distance.cosine(m2d_sim_defi[j], vector_wn)
m2d_sim[i][j] = cosine
print "\n"
for j in range(len(vectors_ox)):
vector_ox = vectors_ox[j]
print vector_ox
return m2d_sim
def sim_ox_wn_defi_WDS_via_main_syns(word):
dict_vectors_wn = WordnetParseDefinition.get_dict_vectors_synsets_for_word(word)
synsets_wn = WordnetHandler.get_synsets_for_word(word,'n')
dict_vectors_ox = OxParseDefinition.get_dict_vectors_synsets_for_word(word, synsets_wn)
#
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(dict_vectors_wn)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(dict_vectors_ox)
#
m2d_sim = sim_wn_ox_vector(vectors_ox, vectors_wn)
#
cal_sim_ngrams(word)
# write to file
# # - - - - - - - - - - - - - - - - - - - - - - - - -
# for i in range(len(keys_wn)):
# m2d_sim[i].insert(0,keys_wn[i]);
# # - - - - - - - - - - - - - - - - - - - - - - - - -
# # row
# row_dict = [];
# row_dict.append(word);
# for i in range(len(keys_ox)):
# row_dict.append(keys_ox[i].encode('utf8'));
# # - - - - - - - - - - - - - - - - - - - - - - - - -
# filename = 'Results/vector_definition/' + word + '.csv'
# FileProcess.append_to_excel_file(filename, row_dict, m2d_sim)
# # - - - - - - - - - - - - - - - - - - - - - - - - -
return m2d_sim
def sim_ox_wn_defi_WDS_via_1_main_syn(word): dict_vectors_wn = WordnetParseDefinition.get_dict_vectors_synsets_for_word(word) synsets_wn = WordnetHandler.get_synsets_for_word(word,'n') dict_vectors_ox = OxParseDefinition.get_dict_vectors_synsets_for_word(word, synsets_wn) (keys_wn, vectors_wn) = Util.get_keys_values_of_dict(dict_vectors_wn) (keys_ox, vectors_ox) = Util.get_keys_values_of_dict(dict_vectors_ox) m2d_sim = sim_wn_ox_vector(vectors_ox, vectors_wn) return m2d_sim
def sim_ox_wn_defi_WDS_via_main_syns_for_reduce(synsets_wn, status_synsets_wn, word):
dict_vectors_wn = WordnetParseDefinition.get_dict_vectores_synsets_for_synsets(synsets_wn)
synsets_reduce_wn = list(synsets_wn)
for i in reversed(range(len(synsets_reduce_wn))):
if status_synsets_wn[i] == 0:
del synsets_reduce_wn[i]
dict_vectors_ox = OxParseDefinition.get_dict_vectors_synsets_for_word(word, synsets_reduce_wn)
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(dict_vectors_wn)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(dict_vectors_ox)
m2d_sim = sim_wn_ox_vector_reduce(vectors_ox, vectors_wn, status_synsets_wn)
return m2d_sim
def sim_ox_wn_defi_WDS_via_align_all(word):
words_wn = WordnetParseDefinition.get_dict_vectors_words_for_word(word)
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(words_wn)
words_ox = OxParseDefinition.get_dict_vectors_word_for_word(word)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(words_ox)
m2d_sim = [[0 for x in range(len(keys_ox))] for x in range(len(keys_wn))]
for i in range(len(keys_wn)):
vector_wn = vectors_wn[i]
words_ox = []
for j in range(len(keys_ox)):
words_ox += vectors_ox[j]
synsets_wn = WordnetHandler.get_nearest_synsets_words_words_order(vector_wn, words_ox)
for j in range(len(keys_ox)):
synsets_ox = WordnetHandler.get_nearest_synsets_words_synsets_order(vectors_ox[j], synsets_wn)
m2d_sim[i][j] = sim_2_vector(synsets_wn, synsets_ox)
cal_sim_ngrams(word)
return m2d_sim
def sim_ox_wn_defi_WDS_via_align(word):
words_wn = WordnetParseDefinition.get_dict_vectors_words_for_word(word)
(keys_wn, vectors_wn) = Util.get_keys_values_of_dict(words_wn)
words_ox = OxParseDefinition.get_dict_vectors_word_for_word(word)
(keys_ox, vectors_ox) = Util.get_keys_values_of_dict(words_ox)
synsets_wn = WordnetHandler.get_synsets_for_word(word, 'n')
m2d_sim = [[0 for x in range(len(keys_ox))] for x in range(len(keys_wn))]
for i in range(len(keys_wn)):
vector_wn = vectors_wn[i]
synset_wn = synsets_wn[i]
for j in range(len(keys_ox)):
vector_ox = vectors_ox[j]
m2d_sim[i][j] = WordnetHandler.sim_for_words_words_no_order(vector_ox, vector_wn, synset_wn)
# (vector_1, vector_2) = WordnetHandler.get_nearest_synsets_words_words_noorder(vector_ox, vector_wn)
# m2d_sim[i][j] = sim_2_vector(vector_1, vector_2)
cal_sim_ngrams(word)
return m2d_sim
def cal_sim_ngrams(word):
dict_gloss_wn = WordnetParseDefinition.get_gloss_for_jacc(word)
(key_wn, wn_gloss) = Util.get_keys_values_of_dict(dict_gloss_wn)
ox_gloss = OxfordParser.get_definitions_of_word_for_jacc(word)
cal_n_grams_sim(word, wn_gloss, ox_gloss, 2)
cal_n_grams_sim(word, wn_gloss, ox_gloss, 3)
cal_n_grams_sim(word, wn_gloss, ox_gloss, 4)
for i in range(len(wn_gloss)):
wn_gloss[i] = wn_gloss[i].replace(word, "")
for i in range(len(ox_gloss)):
ox_gloss[i] = ox_gloss[i].replace(word, "")
cal_jacc_sim(word, wn_gloss, ox_gloss)