def generic_predict(p_or_n, tokenized_sents, vocab, clf, use_lstm):
'''
generic_predict()
Train a model that works for both prose and nonprose
@param p_or_n. A string that indicates "prose", "nonprose", or "all"
@param tokenized_sents. A list of sentences, where each sentence is tokenized
into words
@param vocab. A dictionary mapping word tokens to numeric indices.
@param clf. An encoding of the trained keras model.
@param use_lstm. Bool indicating whether clf is a CRF or LSTM.
'''
# If nothing to predict, skip actual prediction
if len(tokenized_sents) == 0:
print '\tnothing to predict ' + p_or_n
return []
print '\tvectorizing words ' + p_or_n
if use_lstm:
# vectorize tokenized sentences
X = []
for sent in tokenized_sents:
id_seq = []
for w in sent:
if w in vocab:
id_seq.append(vocab[w])
else:
id_seq.append(vocab['oov'])
X.append(id_seq)
else:
# vectorize validation X
text_features = extract_features(tokenized_sents)
flat_X_feats = vocab.transform(flatten(text_features))
X = reconstruct_list(flat_X_feats, save_list_structure(text_features))
print '\tpredicting labels ' + p_or_n
# Predict labels
if use_lstm:
predictions = keras_ml.predict(clf, X)
else:
predictions = crf.predict(clf, X)
# Format labels from output
return predictions
def generic_predict(p_or_n, tokenized_sents, vocab, clf, use_lstm,
hyperparams):
'''
generic_predict()
Train a model that works for both prose and nonprose
@param p_or_n. A string that indicates "prose", "nonprose", or "all"
@param tokenized_sents. A list of sentences, where each sentence is tokenized
into words
@param vocab. A dictionary mapping word tokens to numeric indices.
@param clf. An encoding of the trained keras model.
@param use_lstm. Bool indicating whether clf is a CRF or LSTM.
'''
# use_lstm=self._use_lstm
if use_lstm:
#parameters=hd.load_parameters_from_file("LSTM_parameters.txt")
parameters['use_pretrained_model'] = True
#model_folder="./models/NN_models"
predictions = []
sys.stdout.write('\n use_lstm \n')
dataset = Exp.Dataset()
fictional_labels = copy.deepcopy(tokenized_sents)
for idx, x in enumerate(fictional_labels):
for val_id, value in enumerate(x):
fictional_labels[idx][val_id] = 'O'
Datasets_tokens = {}
Datasets_labels = {}
Datasets_tokens['deploy'] = tokenized_sents
Datasets_labels['deploy'] = fictional_labels
token_to_vector = dataset.load_dataset(
Datasets_tokens,
Datasets_labels,
"",
parameters,
token_to_vector=tokens_to_vec,
pretrained_dataset=pretrained_dataset)
print(dataset.token_indices.keys())
parameters['Feature_vector_length'] = dataset.feature_vector_size
parameters['use_features_before_final_lstm'] = False
dataset.update_dataset("", ['deploy'], Datasets_tokens,
Datasets_labels)
del Datasets_tokens
del Datasets_labels
#model=current_model
model = entity_model.EntityLSTM(dataset, parameters)
os.mkdir(parameters['conll_like_result_folder'])
test_temp = os.path.join(parameters['conll_like_result_folder'],
'test/')
train_temp = os.path.join(parameters['conll_like_result_folder'],
'train/')
valid_temp = os.path.join(parameters['conll_like_result_folder'],
'valid/')
os.mkdir(test_temp)
os.mkdir(train_temp)
os.mkdir(valid_temp)
sess = tf.Session()
with sess.as_default():
#model=entity_model.EntityLSTM(dataset,parameters)
transition_params_trained = model.restore_from_pretrained_model(
parameters,
dataset,
sess,
token_to_vector=token_to_vector,
pretrained_dataset=pretrained_dataset)
del token_to_vector
predictions = training_predict_LSTM.prediction_step(
sess, dataset, "deploy", model, 0,
parameters['conll_like_result_folder'],
transition_params_trained)
sess.close()
tf.reset_default_graph()
shutil.rmtree(parameters['conll_like_result_folder'])
return predictions, model
# If nothing to predict, skip actual prediction
if len(tokenized_sents) == 0:
sys.stdout.write('\tnothing to predict %s\n' % p_or_n)
return []
sys.stdout.write('\tvectorizing words %s\n' % p_or_n)
if use_lstm:
print('todo: incorporate lstm')
# vectorize tokenized sentences
#X = []
#for sent in tokenized_sents:
# id_seq = []
# for w in sent:
# if w in vocab:
# id_seq.append(vocab[w])
# else:
# id_seq.append(vocab['oov'])
# X.append(id_seq)
else:
from cliner.feature_extraction.features import extract_features
# vectorize validation X
text_features = extract_features(tokenized_sents)
flat_X_feats = vocab.transform(flatten(text_features))
X = reconstruct_list(flat_X_feats, save_list_structure(text_features))
sys.stdout.write('\tpredicting labels %s\n' % p_or_n)
# Predict labels
if use_lstm:
print("TEST_PREDICT")
exit()
else:
from cliner.machine_learning import crf
predictions = crf.predict(clf, X)
# Format labels from output
return predictions
