def main(mode='test', question=None, answers=None):
"""
This function is used to train, predict or test
Args:
mode (str): train/preddict/test
question (str): this contains the question
answers (list): this contains list of answers in string format
Returns:
index (integer): index of the most likely answer
"""
# get the train and predict model model
vocabulary = Vocabulary("./data/vocab_all.txt")
embedding_file = "./data/word2vec_100_dim.embeddings"
qa_model = QAModel()
train_model, predict_model = qa_model.get_bilstm_model(
embedding_file, len(vocabulary))
epoch = 1
if mode == 'train':
for i in range(epoch):
print('Training epoch', i)
# load training data
qa_data = QAData()
questions, good_answers, bad_answers = qa_data.get_training_data()
# train the model
Y = np.zeros(shape=(questions.shape[0], ))
train_model.fit([questions, good_answers, bad_answers],
Y,
epochs=1,
batch_size=64,
validation_split=0.1,
verbose=1)
# save the trained model
train_model.save_weights('model/train_weights_epoch_' +
str(epoch) + '.h5',
overwrite=True)
predict_model.save_weights('model/predict_weights_epoch_' +
str(epoch) + '.h5',
overwrite=True)
elif mode == 'predict':
# load the evaluation data
data = pickle.load(open("./data/dev.pkl", 'rb'))
random.shuffle(data)
# load weights from trained model
qa_data = QAData()
predict_model.load_weights('model/lstm_predict_weights_epoch_1.h5')
c = 0
c1 = 0
for i, d in enumerate(data):
print(i, len(data))
# pad the data and get it in desired format
indices, answers, question = qa_data.process_data(d)
# get the similarity score
sims = predict_model.predict([question, answers])
n_good = len(d['good'])
max_r = np.argmax(sims)
max_n = np.argmax(sims[:n_good])
r = rankdata(sims, method='max')
c += 1 if max_r == max_n else 0
c1 += 1 / float(r[max_r] - r[max_n] + 1)
precision = c / float(len(data))
mrr = c1 / float(len(data))
print("Precision", precision)
print("MRR", mrr)
elif mode == 'test':
# question and answers come from params
qa_data = QAData()
answers, question = qa_data.process_test_data(question, answers)
# load weights from the trained model
predict_model.load_weights('model/lstm_predict_weights_epoch_1.h5')
# get similarity score
sims = predict_model.predict([question, answers])
max_r = np.argmax(sims)
return max_r
def main(mode='test'):
# get the train and predict model model
vocabulary = Vocabulary("./data/vocab_all.txt")
embedding_file = "./data/word2vec_100_dim.embeddings"
qa_model = QAModel()
train_model, predict_model = qa_model.get_lstm_cnn_model(embedding_file, len(vocabulary))
epo = 100
if mode == 'train':
# load training data
qa_data = QAData()
questions, good_answers, bad_answers = qa_data.get_training_data()
callbacks = [EarlyStopping(monitor='val_loss', patience=20),
ModelCheckpoint(filepath='best_model.h5', monitor='val_loss', save_best_only=True)]
# train the model
Y = np.zeros(shape=(questions.shape[0],))
train_model.fit([questions, good_answers, bad_answers], Y, epochs=epo, batch_size=64, validation_split=0.1,
verbose=1, callbacks=callbacks)
# save the trained model
# train_model.save_weights('model/train_weights_epoch_' + str(epo) + '.h5', overwrite=True)
model = keras.models.load_model('best_model.h5')
model.save_weights('model/best_weights_epoch_' + str(epo) + '.h5', overwrite=True)
predict_model.save_weights('model/predict_weights_epoch_' + str(epo) + '.h5', overwrite=True)
elif mode == 'predict':
# load the evaluation data
data = pickle.load(open("./data/dev.pkl",'rb'))
random.shuffle(data)
# load weights from trained model
qa_data = QAData()
model_filenames = ['model/best_model.h5', 'model/predict_weights_epoch_' + str(epo) + '.h5']
for model_name in model_filenames:
predict_model.load_weights(model_name)
c = 0
c1 = 0
for i, d in enumerate(data):
if i%100 == 0:
print(i, len(data))
# pad the data and get it in desired format
indices, answers, question = qa_data.process_data(d)
# get the similarity score
sims = predict_model.predict([question, answers])
n_good = len(d['good'])
max_r = np.argmax(sims)
max_n = np.argmax(sims[:n_good])
r = rankdata(sims, method='max')
c += 1 if max_r == max_n else 0
c1 += 1 / float(r[max_r] - r[max_n] + 1)
precision = c / float(len(data))
mrr = c1 / float(len(data))
print(f'Results for: model: {model_name}')
print("Precision", precision)
print("MRR", mrr)
# predict_model.layers[2].layers[10].get_output_at(1), predict_model.layers[2].layers[11].output,
# predict_model.layers[2].layers[11].output, predict_model.layers[2].layers[13].get_output_at(0),
# predict_model.layers[2].layers[13].get_output_at(1), predict_model.layers[2].layers[14].output]
layer_outputs = [predict_model.layers[2].layers[13].get_output_at(0)]#, predict_model.layers[2].layers[13].get_output_at(1), predict_model.layers[2].layers[14].output]
act_model = Model(inputs = predict_model.inputs, outputs=layer_outputs)
data = pickle.load(open("./data/dev.pkl",'rb'))
print("Total data length", len(data))
qa_data = QAData()
random.shuffle(data)
for i,d in enumerate(data):
print("i",i)
indices, answers, question = qa_data.process_data(d)
#print("indices", indices)
# print("answers", answers.shape)
#print("question", question.shape)
print("Input:", d)
sims = predict_model.predict([question, answers])
#print("sims", sims)
n_good = len(d['good'])
max_r = np.argmax(sims)
max_n = np.argmax(sims[:n_good])
if max_r == max_n:
print("Correct")
else:
print("Wrong")
lo = act_model.predict([question, answers])
#print("lo", lo)
def main(mode='train',
question=None,
answers=None,
epochs=2,
batch_size=32,
validation_split=0.1,
model_name='baseline'):
"""
This function is used to train, predict or test
Args:
mode (str): train/preddict/test
question (str): this contains the question
answers (list): this contains list of answers in string format
Returns:
index (integer): index of the most likely answer
"""
# get the train and predict model model
if mode == 'train':
# baseline model
train_model, prediction_model = get_baseline_model()
train_model.summary()
train(train_model,
prediction_model,
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
# small model
small_train_model, small_prediction_model = get_small_model()
small_train_model.summary()
train(small_train_model,
small_prediction_model,
model_name='small',
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
# larger model
larger_train_model, larger_prediction_model = get_larger_model()
larger_train_model.summary()
train(larger_train_model,
larger_prediction_model,
model_name='larger',
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
elif mode == 'predict':
# load the evaluation data
data = []
with open('data/test.json') as read_file:
data = json.load(read_file)
random.shuffle(data)
qa_data = QAData()
# create model from json model's architecture saved
# logger.info(f'Loading models architecture: model/model_architecture_{model_name}.json')
logger.info(f'Creating predict model: {model_name}')
#with open(f'model/model_architecture_{model_name}.json', 'r') as read_file:
# json_string = read_file.read()
#predict_model = model_from_json(json_string)
predict_model = None
if model_name == 'small':
_, predict_model = get_small_model()
elif model_name == 'larger':
_, predict_model = get_larger_model()
else:
_, predict_model = get_baseline_model()
# load weights
logger.info(
f'Loading model weigths: model/train_weights_{model_name}.h5')
predict_model.load_weights(f'model/train_weights_{model_name}.h5')
c = 0
c1 = 0
for i, d in enumerate(data):
print(i, len(data))
# pad the data and get it in desired format
answers, question = qa_data.process_data(d)
# get the similarity score
sims = predict_model.predict([question, answers])
n_good = len(d['good'])
max_r = np.argmax(sims)
max_n = np.argmax(sims[:n_good])
r = rankdata(sims, method='max')
c += 1 if max_r == max_n else 0
c1 += 1 / float(r[max_r] - r[max_n] + 1)
precision = c / float(len(data))
mrr = c1 / float(len(data))
print("Precision", precision)
print("MRR", mrr)
elif mode == 'test':
# question and answers come from params
qa_data = QAData()
answers, question = qa_data.process_test_data(question, answers)
# create model from json model's architecture saved
logger.info(
f'Loading models architecture: model/model_architecture_{model_name}.json'
)
json_string = ''
with open(f'model/model_architecture_{model_name}.json',
'r') as read_file:
json_string = read_file.read()
predict_model = model_from_json(json_string)
# load weights
logger.info(
f'Loading model weigths: model/train_weights_{model_name}.h5')
predict_model.load_weights(f'model/train_weights_{model_name}.h5')
# get similarity score
sims = predict_model.predict([question, answers])
max_r = np.argmax(sims)
return max_r