def blending():
# saved = True if args.saved != 0 else False
saved = args.saved
test_file1 = ROOT_DIR + "/data/test.txt"
test_file2 = ROOT_DIR + "/data/test_predict_aspect_ensemble.txt"
test_texts, test_aspects = load_ab_test(test_file1, test_file2)
# print(test_aspects)
word2index = pickle.load(open(ROOT_DIR + "/data/vocabulary.pkl", 'rb'))
f_dict = ROOT_DIR + "/dataset/polarity.json"
polarity_list, polarity_dict = parse_json(f_dict)
f_dict2 = ROOT_DIR + "/dataset/attribute.json"
attr_list, attr_dict = parse_json(f_dict2)
paths = args.test_dir.split('#')
models_files = []
for path in paths:
models_files.append([
os.path.join(path, f) for f in os.listdir(path)
if os.path.isfile(os.path.join(path, f))
])
test_data = Data3((test_texts, None, test_aspects),
word2index,
polarity_dict,
args,
target_dict=attr_dict)
if args.use_elmo != 0:
test_elmo = load_elmo(test_texts)
test_data.add_feature(test_elmo)
x_test = []
for dir, checkpoints_per_model in zip(paths, models_files):
print(dir, checkpoints_per_model)
if saved == 1:
oof_test = load_oof_test(dir)
else:
clfs = checkpoints_per_model
oof_test = get_oof_test(clfs, test_data)
x_test.append(oof_test)
x_test = np.stack(x_test, axis=1)
print(x_test)
print(x_test.shape)
test_predict = np.mean(x_test, axis=1)
fw = codecs.open(ROOT_DIR + "/data/test_predict_polarity_ensemble.txt",
'w',
encoding='utf-8')
for j, prob in enumerate(test_predict):
polarity = np.argmax(prob) - 1
fw.write(test_aspects[j] + ',' + str(polarity) + '\n')
time_stamp = time.asctime().replace(':', '_').split()
fw.close()
shutil.copy2(
ROOT_DIR + "/data/test_predict_polarity_ensemble.txt", ROOT_DIR +
"/data/backup/test_predict_polarity_ensemble_%s.txt" % time_stamp)
def test():
# model = Classifier()
test_file1 = ROOT_DIR + "/attribute_level/data/attribute_test.txt"
test_file2 = ROOT_DIR + "/attribute_level/test_predict.txt"
test_texts, test_aspects = load_ab_test(test_file1, test_file2)
f_w2v = ROOT_DIR + "/embedding/embedding_all_merge_300.txt"
W, word2index = load_w2v(f_w2v)
f_dict1 = ROOT_DIR + "/dataset/polarity.json"
f_dict2 = ROOT_DIR + "/dataset/attribute.json"
polarity_list, polarity_dict = parse_json(f_dict1)
attr_list, attr_dict = parse_json(f_dict2)
assert len(test_texts) == len(test_aspects)
files = ["checkpoint_HEAT_0.7189.pt", "checkpoint_HEAT_0.7062.pt"]
predicts = []
for check_point in files:
predict = []
classifier = torch.load(check_point)
for text, aspect in zip(test_texts, test_aspects):
if aspect != '':
if aspect is None:
print("error")
test_data = Data3(([text], [None], [aspect]),
word2index,
polarity_dict,
args,
target_dict=attr_dict)
test_predict = train_single.predict(classifier, test_data,
args)
assert len(test_predict) == 1
polarity = str(test_predict[0].item() - 1)
else:
print(aspect)
print(text)
polarity = '0'
# fw.write(aspect+','+polarity+'\n')
predict.append(aspect + ',' + polarity)
predicts.append(predict)
print(len(predicts))
print(len(predicts[0]))
fw = codecs.open("test_predict_polarity_ensemble.txt",
'w',
encoding='utf-8')
for j in range(len(predicts[0])):
votes = [predicts[i][j] for i in range(len(predicts))]
voted = Counter(votes).most_common(1)
fw.write(voted + '\n')
def stacking():
# saved = True if args.saved != 0 else False
saved = args.saved
f_train = ROOT_DIR + "/data/train.txt"
test_file1 = ROOT_DIR + "/data/test.txt"
test_file2 = ROOT_DIR + "/data/test_predict_aspect_ensemble.txt"
test_texts, test_aspects = load_ab_test(test_file1, test_file2)
# print(test_aspects)
fo = load_abp_raw(f_train)
word2index = pickle.load(open(ROOT_DIR + "/data/vocabulary.pkl", 'rb'))
f_dict = ROOT_DIR + "/dataset/polarity.json"
polarity_list, polarity_dict = parse_json(f_dict)
f_dict2 = ROOT_DIR + "/dataset/attribute.json"
attr_list, attr_dict = parse_json(f_dict2)
paths = args.test_dir.split('#')
models_files = []
for path in paths:
path = BASE_DIR + '/' + path
models_files.append([
os.path.join(path, f) for f in os.listdir(path)
if os.path.isfile(os.path.join(path, f))
])
test_data = Data3((test_texts, None, test_aspects),
word2index,
polarity_dict,
args,
target_dict=attr_dict)
if args.use_elmo != 0:
test_elmo = load_elmo(test_texts)
test_data.add_feature(test_elmo)
x_train = []
y_train = []
x_test = []
for dir, checkpoints_per_model in zip(paths, models_files):
print(dir, checkpoints_per_model)
dir = BASE_DIR + '/' + dir
if saved == 1:
oof_train, oof_train_y, oof_test = load_oof_dir(dir)
else:
print(checkpoints_per_model)
NFOLDS = len(checkpoints_per_model)
print(NFOLDS)
# assert NFOLDS == args.folds
clfs = [None for i in range(NFOLDS)]
for cp in checkpoints_per_model:
fold = int(cp.replace('_', '.').split('.')[-2])
clfs[fold - 1] = cp
if saved == 2:
oof_train, oof_train_y, oof_test = load_oof(
clfs,
fo,
test_data,
word2index,
polarity_dict=polarity_dict,
attr_dict=attr_dict)
elif saved == 3:
oof_train, oof_train_y, oof_test = load_oof3(
clfs,
fo,
test_data,
word2index,
polarity_dict=polarity_dict,
attr_dict=attr_dict)
elif saved == 0:
oof_train, oof_train_y, oof_test = get_oof(
clfs,
fo,
test_data,
word2index,
polarity_dict=polarity_dict,
attr_dict=attr_dict)
else:
print("saved error, [0:3]")
exit(-1)
x_train.append(oof_train)
oof_train_y = oof_train_y.reshape(oof_train_y.shape[0], )
if y_train == []:
y_train = oof_train_y
else:
assert (y_train == oof_train_y).all()
x_test.append(oof_test)
x_train = np.concatenate(x_train, axis=1)
x_test = np.concatenate(x_test, axis=1)
y_train = np.asarray(y_train).reshape((len(y_train), ))
meta_clf = LogisticRegression()
meta_clf.fit(x_train, y_train)
test_predict = meta_clf.predict_proba(x_test)
fw = codecs.open(ROOT_DIR + "/data/test_predict_polarity_ensemble.txt",
'w',
encoding='utf-8')
for j, prob in enumerate(test_predict):
polarity = np.argmax(prob) - 1
fw.write(test_aspects[j] + ',' + str(polarity) + '\n')
time_stamp = time.asctime().replace(':', '_').split()
fw.close()
shutil.copy2(
ROOT_DIR + "/data/test_predict_polarity_ensemble.txt", ROOT_DIR +
"/data/backup/test_predict_polarity_ensemble_%s.txt" % time_stamp)