def handle_data():
if request.method == 'POST':
return render_template("search.html")
if request.method == 'GET':
query = request.args.get('content')
model = NLPModel()
clf_path = 'lib/models/SentimentClassifier.pkl'
with open(clf_path, 'rb') as f:
model.clf = pickle.load(f)
vec_path = 'lib/models/TFIDFVectorizer.pkl'
with open(vec_path, 'rb') as f:
model.vectorizer = pickle.load(f)
user_query = query
uq_vectorized = model.vectorizer_transform(np.array([user_query]))
prediction = model.predict(uq_vectorized)
# print(prediction)
pred_proba = model.predict_proba(uq_vectorized)
confidence = round(pred_proba[0], 3)
print(prediction,confidence)
if prediction == 0:
filename = 'cry.jpg'
return send_file(filename, mimetype='image/jpg')
else:
filename = 'smile.jpg'
return send_file(filename, mimetype='image/jpg')
char2idx, idx2char, configs.vocabulary_length = load_vocabulary(configs.vocabulary_path, configs.data_path, configs.tokenize_as_morph)
input = " ".join(sys.argv[1:])
print(input)
predict_input_enc, predict_input_enc_length = enc_processing([input], char2idx, configs.max_sequence_length, configs.tokenize_as_morph)
predict_output_dec, predict_output_dec_length = dec_output_processing([""], char2idx, configs.max_sequence_length, configs.tokenize_as_morph)
predict_target_dec = dec_target_processing([""], char2idx, configs.max_sequence_length, configs.tokenize_as_morph)
model = NLPModel(configs)
if os.path.exists(configs.f_name):
model.load_model(configs.f_name)
for i in range(configs.max_sequence_length):
if i > 0:
predict_output_dec, predict_output_decLength = dec_output_processing([answer], char2idx, configs.max_sequence_length, configs.tokenize_as_morph)
predict_target_dec = dec_target_processing([answer], char2idx, configs.max_sequence_length, configs.tokenize_as_morph)
# 예측을 하는 부분이다.
dataset_test = dataset_process(predict_input_enc, predict_output_dec, predict_target_dec, 1)
for (feature, _) in dataset_test.take(1):
predictions = model.predict(feature)
answer, finished = pred_next_string(predictions.numpy(), idx2char)
if finished:
break
# 예측한 값을 인지 할 수 있도록
# 텍스트로 변경하는 부분이다.
print("answer: ", answer)
def main():
configs = Config()
data_out_path = os.path.join(os.getcwd(), './out')
os.makedirs(data_out_path, exist_ok=True)
# 데이터를 통한 사전 구성 한다.
char2idx, idx2char, configs.vocabulary_length = load_vocabulary(
configs.vocabulary_path, configs.data_path, configs.tokenize_as_morph)
# 훈련 데이터와 테스트 데이터를 가져온다.
train_input, train_label, eval_input, eval_label = load_data(
configs.data_path)
# 훈련셋 인코딩 만드는 부분이다.
train_input_enc, train_input_enc_length = enc_processing(
train_input, char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 훈련셋 디코딩 입력 부분 만드는 부분이다.
train_output_dec, train_output_dec_length = dec_output_processing(
train_label, char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 훈련셋 디코딩 출력 부분 만드는 부분이다.
train_target_dec = dec_target_processing(train_label, char2idx,
configs.max_sequence_length,
configs.tokenize_as_morph)
# 평가셋 인코딩 만드는 부분이다.
eval_input_enc, eval_input_enc_length = enc_processing(
eval_input, char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 평가셋 인코딩 만드는 부분이다.
eval_output_dec, eval_output_dec_length = dec_output_processing(
eval_label, char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 평가셋 인코딩 만드는 부분이다.
eval_target_dec = dec_target_processing(eval_label, char2idx,
configs.max_sequence_length,
configs.tokenize_as_morph)
dataset_train = dataset_process(train_input_enc, train_output_dec,
train_target_dec, configs.batch_size)
dataset_eval = dataset_process(eval_input_enc, eval_output_dec,
eval_target_dec, configs.batch_size)
model = NLPModel(configs)
if os.path.exists(configs.f_name):
model.load_model(configs.f_name)
for i, (features,
labels) in enumerate(dataset_train.take(configs.train_steps)):
model.train(features, labels)
if i % 200 == 0:
model.save_model(configs.f_name)
predict_input_enc, predic_input_enc_length = enc_processing(
["가끔 궁금해"], char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 학습 과정이 아니므로 디코딩 입력은
# 존재하지 않는다.(구조를 맞추기 위해 넣는다.)
predict_output_dec, predic_output_decLength = dec_output_processing(
[""], char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 학습 과정이 아니므로 디코딩 출력 부분도
# 존재하지 않는다.(구조를 맞추기 위해 넣는다.)
predict_target_dec = dec_target_processing(
[""], char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
for i in range(configs.max_sequence_length):
if i > 0:
predict_output_dec, _ = dec_output_processing(
[answer], char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
predict_target_dec = dec_target_processing(
[answer], char2idx, configs.max_sequence_length,
configs.tokenize_as_morph)
# 예측을 하는 부분이다.
dataset_test = dataset_process(predict_input_enc,
predict_output_dec,
predict_target_dec, 1)
for (feature, _) in dataset_test.take(1):
predictions = model.predict(feature)
answer, finished = pred_next_string(predictions.numpy(),
idx2char)
if finished:
break
# 예측한 값을 인지 할 수 있도록
# 텍스트로 변경하는 부분이다.
print("answer: ", answer)
