def __init__(self, model_path, corpus_path, emb_path):
raw_corpus = myio.read_corpus(corpus_path)
embedding_layer = myio.create_embedding_layer(
raw_corpus,
n_d = 10,
cut_off = 1,
embs = load_embedding_iterator(emb_path)
)
weights = myio.create_idf_weights(corpus_path, embedding_layer)
say("vocab size={}, corpus size={}\n".format(
embedding_layer.n_V,
len(raw_corpus)
))
model = Model(args=None, embedding_layer=embedding_layer,
weights=weights)
model_data = model.load_model(model_path)
model.set_model(model_data)
model.dropout.set_value(0.0)
say("model initialized\n")
score_func = theano.function(
inputs = [ model.idts, model.idbs ],
outputs = model.scores,
on_unused_input='ignore'
)
self.model = model
self.score_func = score_func
say("scoring function compiled\n")
def main():
print 'Starting at: {}\n'.format(datetime.now())
s_time = time.time()
df = read_df(args.df_path)
df = df.fillna(u'')
label_tags = pickle.load(open(args.tags_file, 'rb'))
print '\nloaded {} tags'.format(len(label_tags))
raw_corpus = myio.read_corpus(args.corpus_w_tags, with_tags=True)
embedding_layer = create_embedding_layer(
n_d=200,
embs=load_embedding_iterator(args.embeddings),
only_words=False if args.use_embeddings else True,
# only_words will take the words from embedding file and make random initial embeddings
trainable=args.trainable
)
ids_corpus = myio.map_corpus(raw_corpus, embedding_layer, label_tags, max_len=args.max_seq_len)
print("vocab size={}, corpus size={}\n".format(embedding_layer.n_V, len(raw_corpus)))
padding_id = embedding_layer.vocab_map["<padding>"]
if args.reweight:
weights = myio.create_idf_weights(args.corpus_w_tags, embedding_layer, with_tags=True)
if args.layer.lower() == "lstm":
from models import LstmMultiTagsClassifier as Model
elif args.layer.lower() in ["bilstm", "bigru"]:
from models import BiRNNMultiTagsClassifier as Model
elif args.layer.lower() == "cnn":
from models import CnnMultiTagsClassifier as Model
elif args.layer.lower() == "gru":
from models import GruMultiTagsClassifier as Model
else:
raise Exception("no correct layer given")
if args.cross_val:
train, dev, test = myio.create_cross_val_batches(df, ids_corpus, args.batch_size, padding_id)
else:
dev = list(myio.create_batches(
df, ids_corpus, 'dev', args.batch_size, padding_id, N_neg=args.n_neg, samples_file=args.samples_file))
test = list(myio.create_batches(
df, ids_corpus, 'test', args.batch_size, padding_id, N_neg=args.n_neg, samples_file=args.samples_file))
# baselines_eval(train, dev, test)
model = Model(args, embedding_layer, len(label_tags), weights=weights if args.reweight else None)
model.ready()
print 'total (non) trainable params: ', model.num_parameters()
if args.load_pre_trained_part:
# need to remove the old assigns to embeddings
model.init_assign_ops = model.load_pre_trained_part(args.load_pre_trained_part)
print '\nmodel init_assign_ops: {}\n'.format(model.init_assign_ops)
model.train_model(df, ids_corpus, dev=dev, test=test)
print '\nEnded at: {}'.format(datetime.now())
def main(args):
raw_corpus = myio.read_corpus(args.corpus)
embedding_layer = myio.create_embedding_layer(
raw_corpus,
n_d=args.hidden_dim,
embs=load_embedding_iterator(args.embeddings)
if args.embeddings else None)
ids_corpus = myio.map_corpus(raw_corpus,
embedding_layer,
max_len=args.max_seq_len)
say("vocab size={}, corpus size={}\n".format(embedding_layer.n_V,
len(raw_corpus)))
padding_id = embedding_layer.vocab_map["<padding>"]
if args.reweight:
weights = myio.create_idf_weights(args.corpus, embedding_layer)
if args.dev:
dev_raw = myio.read_annotations(args.dev, K_neg=-1, prune_pos_cnt=-1)
dev = myio.create_eval_batches(ids_corpus,
dev_raw,
padding_id,
pad_left=not args.average,
merge=args.merge)
if args.test:
test_raw = myio.read_annotations(args.test, K_neg=-1, prune_pos_cnt=-1)
test = myio.create_eval_batches(ids_corpus,
test_raw,
padding_id,
pad_left=not args.average,
merge=args.merge)
if args.train:
start_time = time.time()
train = myio.read_annotations(args.train)
train_batches = myio.create_batches(ids_corpus,
train,
args.batch_size,
padding_id,
pad_left=not args.average,
merge=args.merge)
say("{} to create batches\n".format(time.time() - start_time))
say("{} batches, {} tokens in total, {} triples in total\n".format(
len(train_batches), sum(len(x[0].ravel()) for x in train_batches),
sum(len(x[1].ravel()) for x in train_batches)))
train_batches = None
model = Model(args,
embedding_layer,
weights=weights if args.reweight else None)
model.ready()
# set parameters using pre-trained network
if args.load_pretrain:
model.encoder.load_pretrained_parameters(args)
model.train(ids_corpus, train, (dev, dev_raw) if args.dev else None,
(test, test_raw) if args.test else None)
def main(args):
raw_corpus = myio.read_corpus(args.corpus)
embedding_layer = myio.create_embedding_layer(
raw_corpus,
n_d = args.hidden_dim,
cut_off = args.cut_off,
embs = load_embedding_iterator(args.embeddings) if args.embeddings else None
)
ids_corpus = myio.map_corpus(raw_corpus, embedding_layer)
say("vocab size={}, corpus size={}\n".format(
embedding_layer.n_V,
len(raw_corpus)
))
padding_id = embedding_layer.vocab_map["<padding>"]
bos_id = embedding_layer.vocab_map["<s>"]
eos_id = embedding_layer.vocab_map["</s>"]
if args.reweight:
weights = myio.create_idf_weights(args.corpus, embedding_layer)
if args.dev:
dev = myio.read_annotations(args.dev, K_neg=20, prune_pos_cnt=-1)
dev = myio.create_eval_batches(ids_corpus, dev, padding_id)
if args.test:
test = myio.read_annotations(args.test, K_neg=20, prune_pos_cnt=-1)
test = myio.create_eval_batches(ids_corpus, test, padding_id)
if args.heldout:
with open(args.heldout) as fin:
heldout_ids = fin.read().split()
heldout_corpus = dict((id, ids_corpus[id]) for id in heldout_ids if id in ids_corpus)
train_corpus = dict((id, ids_corpus[id]) for id in ids_corpus
if id not in heldout_corpus)
heldout = myio.create_batches(heldout_corpus, [ ], args.batch_size,
padding_id, bos_id, eos_id, auto_encode=True)
heldout = [ myio.create_one_batch(b1, t2, padding_id) for t1, b1, t2 in heldout ]
say("heldout examples={}\n".format(len(heldout_corpus)))
if args.train:
model = Model(args, embedding_layer,
weights=weights if args.reweight else None)
start_time = time.time()
train = myio.read_annotations(args.train)
if not args.use_anno: train = [ ]
train_batches = myio.create_batches(ids_corpus, train, args.batch_size,
model.padding_id, model.bos_id, model.eos_id, auto_encode=True)
say("{} to create batches\n".format(time.time()-start_time))
model.ready()
model.train(
ids_corpus if not args.heldout else train_corpus,
train,
dev if args.dev else None,
test if args.test else None,
heldout if args.heldout else None
)
def main(args):
raw_corpus = myio.read_corpus(args.corpus)
embedding_layer = myio.create_embedding_layer(
raw_corpus,
n_d = args.hidden_dim,
embs = load_embedding_iterator(args.embeddings) if args.embeddings else None
)
ids_corpus = myio.map_corpus(raw_corpus, embedding_layer, max_len=args.max_seq_len)
say("vocab size={}, corpus size={}\n".format(
embedding_layer.n_V,
len(raw_corpus)
))
padding_id = embedding_layer.vocab_map["<padding>"]
if args.reweight:
weights = myio.create_idf_weights(args.corpus, embedding_layer)
if args.dev:
dev_raw = myio.read_annotations(args.dev, K_neg=-1, prune_pos_cnt=-1)
dev = myio.create_eval_batches(ids_corpus, dev_raw, padding_id,
pad_left=not args.average, merge=args.merge)
if args.test:
test_raw = myio.read_annotations(args.test, K_neg=-1, prune_pos_cnt=-1)
test = myio.create_eval_batches(ids_corpus, test_raw, padding_id,
pad_left=not args.average, merge=args.merge)
if args.train:
start_time = time.time()
train = myio.read_annotations(args.train)
train_batches = myio.create_batches(ids_corpus, train, args.batch_size,
padding_id, pad_left = not args.average, merge=args.merge)
say("{} to create batches\n".format(time.time()-start_time))
say("{} batches, {} tokens in total, {} triples in total\n".format(
len(train_batches),
sum(len(x[0].ravel()) for x in train_batches),
sum(len(x[1].ravel()) for x in train_batches)
))
train_batches = None
model = Model(args, embedding_layer,
weights=weights if args.reweight else None)
model.ready()
# set parameters using pre-trained network
if args.load_pretrain:
model.encoder.load_pretrained_parameters(args)
model.train(
ids_corpus,
train,
(dev, dev_raw) if args.dev else None,
(test, test_raw) if args.test else None
)
def api(label_tags, test_y, y_scores, all_ids):
eval_samples = []
for sample in range(test_y.shape[0]):
if (test_y[sample, :] == np.ones(test_y.shape[1])).any():
eval_samples.append(sample)
test_y, y_scores = test_y[eval_samples, :], y_scores[eval_samples, :]
ev = Evaluation(y_scores, None, test_y)
all_rankedat10_tags = []
query_ids = []
for sample_id, sample_output in zip(eval_samples, y_scores):
q_id = all_ids[sample_id]
query_ids.append(q_id)
cols = np.argsort(sample_output)[-10:]
rankedat10_tags = []
for col in cols[::-1]:
label_name = label_tags[col]
rankedat10_tags.append(label_name)
all_rankedat10_tags.append(rankedat10_tags)
all_Pat5, all_Pat10, all_Rat5, all_Rat10 = \
ev.Precision(5, True), ev.Precision(10, True), ev.Recall(5, True), ev.Recall(10, True)
upper_bounds_pat5 = ev.upper_bound(5, True)
upper_bounds_pat10 = ev.upper_bound(10, True)
all_MAP = ev.MeanAveragePrecision(True)
assert len(all_Pat5) == len(all_rankedat10_tags)
R = (query_ids, all_rankedat10_tags, list(all_Pat5), list(all_Pat10),
list(all_Rat5), list(all_Rat10), upper_bounds_pat5,
upper_bounds_pat10, all_MAP)
raw_corpus = myio.read_corpus(args.corpus_w_tags, with_tags=True)
with open(args.results_file, 'w') as f:
for i in range(len(R[0])):
query_id, rankedat10_tags, Pat5, Pat10, Rat5, Rat10, UB5, UB10, MAP = \
R[0][i], R[1][i], R[2][i], R[3][i], R[4][i], R[5][i], R[6][i], R[7][i], R[8][i]
real_tags = raw_corpus[str(query_id)][2]
real_tags = list(set(real_tags) & set(label_tags))
real_tags = " ".join([str(x) for x in real_tags])
rankedat10_tags = " ".join([str(x) for x in rankedat10_tags])
f.write("{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n".format(
query_id, real_tags, rankedat10_tags, Pat5, Pat10, Rat5, Rat10,
UB5, UB10, MAP))
def __init__(self,
model_path,
corpus_path,
emb_path,
session,
layer='lstm'):
raw_corpus = myio.read_corpus(corpus_path)
embedding_layer = create_embedding_layer(n_d=10,
embs=load_embedding_iterator(
args.embeddings),
only_words=False)
# weights = myio.create_idf_weights(corpus_path, embedding_layer) # todo
say("vocab size={}, corpus size={}\n".format(embedding_layer.n_V,
len(raw_corpus)))
if layer.lower() == "lstm":
from models import LstmQR as Model
elif layer.lower() in ["bilstm", "bigru"]:
from models import BiRNNQR as Model
elif layer.lower() == "cnn":
from models import CnnQR as Model
elif layer.lower() == "gru":
from models import GruQR as Model
model = Model(args={"layer": args.layer},
embedding_layer=embedding_layer,
weights=None)
model.load_n_set_model(model_path, session)
say("model initialized\n")
self.model = model
def score_func(titles, bodies, cur_sess):
feed_dict = {
self.model.titles_words_ids_placeholder:
titles.T, # IT IS TRANSPOSE ;)
self.model.bodies_words_ids_placeholder:
bodies.T, # IT IS TRANSPOSE ;)
self.model.dropout_prob: 0.,
}
_scores = cur_sess.run(self.model.scores, feed_dict)
return _scores
self.score_func = score_func
say("scoring function compiled\n")
default="") # embeddings file
argparser.add_argument("--test_file", type=str, default="")
argparser.add_argument("--full_results_file", type=str,
default="") # to write in
argparser.add_argument("--results_file", type=str,
default="") # to write in
argparser.add_argument("--layer", type=str, default="lstm")
args = argparser.parse_args()
print '\n', args, '\n'
with tf.Session() as sess:
myqrapi = QRAPI(args.model, args.corpus, args.embeddings, sess,
args.layer)
raw_corpus = myio.read_corpus(args.corpus)
embedding_layer = myqrapi.model.embedding_layer
ids_corpus = myio.map_corpus(raw_corpus, embedding_layer, max_len=100)
test = myio.read_annotations(args.test_file,
K_neg=-1,
prune_pos_cnt=-1)
test = create_eval_batches(ids_corpus,
test,
myqrapi.model.padding_id,
pad_left=not myqrapi.model.args.average)
testmap, testmrr, testpat1, testpat5, rank_labels, rank_ids, qids, rank_scores = myqrapi.evaluate(
test, sess)
if args.full_results_file:
with open(args.full_results_file, 'w') as f:
