def evaluate(args, model, vocab, global_step, eval_analogy=False):
"""Evaluation helper"""
if 'eval_tokens' not in globals():
global eval_tokens
eval_tokens_set = evaluation.get_tokens_in_evaluation_datasets(args)
if not args.no_eval_analogy:
eval_tokens_set.update(vocab.idx_to_token)
# GloVe does not support computing vectors for OOV words
eval_tokens_set = filter(lambda t: t in vocab, eval_tokens_set)
eval_tokens = list(eval_tokens_set)
# Compute their word vectors
context = get_context(args)
mx.nd.waitall()
token_embedding = nlp.embedding.TokenEmbedding(unknown_token=None,
allow_extend=True)
token_embedding[eval_tokens] = model[eval_tokens]
results = evaluation.evaluate_similarity(
args, token_embedding, context[0], logfile=os.path.join(
args.logdir, 'similarity.tsv'), global_step=global_step)
if eval_analogy:
assert not args.no_eval_analogy
results += evaluation.evaluate_analogy(
args, token_embedding, context[0], logfile=os.path.join(
args.logdir, 'analogy.tsv'))
return results
def evaluate(args, embedding, vocab, global_step, eval_analogy=False):
"""Evaluation helper"""
if 'eval_tokens' not in globals():
global eval_tokens
eval_tokens_set = evaluation.get_tokens_in_evaluation_datasets(args)
if not args.no_eval_analogy:
eval_tokens_set.update(vocab.idx_to_token)
if not args.ngram_buckets:
# Word2Vec does not support computing vectors for OOV words
eval_tokens_set = filter(lambda t: t in vocab, eval_tokens_set)
eval_tokens = list(eval_tokens_set)
if not os.path.isdir(args.logdir):
os.makedirs(args.logdir)
# Compute their word vectors
context = get_context(args)
mx.nd.waitall()
token_embedding = nlp.embedding.TokenEmbedding(unknown_token=None,
allow_extend=True)
token_embedding[eval_tokens] = embedding[eval_tokens]
results = evaluation.evaluate_similarity(args,
token_embedding,
context[0],
logfile=os.path.join(
args.logdir,
'similarity.tsv'),
global_step=global_step)
if eval_analogy:
assert not args.no_eval_analogy
results += evaluation.evaluate_analogy(args,
token_embedding,
context[0],
logfile=os.path.join(
args.logdir, 'analogy.tsv'))
return results
def evaluate(args, embedding, vocab, global_step, eval_analogy=False):
"""Evaluation helper"""
if 'eval_tokens' not in globals():
global eval_tokens
eval_tokens_set = evaluation.get_tokens_in_evaluation_datasets(args)
if not args.no_eval_analogy:
eval_tokens_set.update(vocab.idx_to_token)
# Word2Vec does not support computing vectors for OOV words
eval_tokens = list(filter(lambda t: t in vocab, eval_tokens_set))
os.makedirs(args.logdir, exist_ok=True)
# Compute their word vectors
context = get_context(args)
idx_to_token = eval_tokens
mx.nd.waitall()
token_embedding = embedding.to_token_embedding(idx_to_token,
ctx=context[0])
results = evaluation.evaluate_similarity(args,
token_embedding,
context[0],
logfile=os.path.join(
args.logdir,
'similarity.tsv'),
global_step=global_step)
if eval_analogy:
assert not args.no_eval_analogy
results += evaluation.evaluate_analogy(args,
token_embedding,
context[0],
logfile=os.path.join(
args.logdir, 'analogy.tsv'),
global_step=global_step)
return results
enforce_max_size(token_embedding_, args_.max_vocab_size)
known_tokens = set(token_embedding_.idx_to_token)
# Auto-extend token_embedding with unknown extra eval tokens
if token_embedding_.unknown_lookup is not None:
eval_tokens = evaluation.get_tokens_in_evaluation_datasets(args_)
# pylint: disable=pointless-statement
token_embedding_[[
t for t in eval_tokens - known_tokens
if t in token_embedding_.unknown_lookup
]]
if len(token_embedding_.idx_to_token) > args_.max_vocab_size:
logging.warning(
'Computing embeddings for OOV words that occur '
'in the evaluation dataset lead to having '
'more words than --max-vocab-size. '
'Have %s words (--max-vocab-size %s)',
len(token_embedding_.idx_to_token), args_.max_vocab_size)
similarity_results = evaluation.evaluate_similarity(
args_,
token_embedding_,
ctx,
logfile=os.path.join(args_.logdir, 'similarity{}.tsv'.format(name)))
analogy_results = evaluation.evaluate_analogy(
args_,
token_embedding_,
ctx,
logfile=os.path.join(args_.logdir, 'analogy{}.tsv'.format(name)))
else:
token_embedding_ = load_embedding_from_path(args_)
name = ''
enforce_max_size(token_embedding_, args_.analogy_max_vocab_size)
known_tokens = set(token_embedding_.idx_to_token)
if args_.similarity_datasets:
with utils.print_time('find relevant tokens for similarity'):
tokens = evaluation.get_similarity_task_tokens(args_)
vocab = nlp.Vocab(nlp.data.count_tokens(tokens))
with utils.print_time('set {} embeddings'.format(len(tokens))):
vocab.set_embedding(token_embedding_)
evaluation.evaluate_similarity(
args_, vocab.embedding, ctx, logfile=os.path.join(
args_.logdir, 'similarity{}.tsv'.format(name)))
if args_.analogy_datasets:
with utils.print_time('extend open vocabulary with '
'OOV tokens for analogy'):
tokens = evaluation.get_analogy_task_tokens(args_)
if token_embedding_.unknown_token is not None:
tokens.update(token_embedding_.idx_to_token[1:])
else:
tokens.update(token_embedding_.idx_to_token)
vocab = nlp.Vocab(nlp.data.count_tokens(tokens))
with utils.print_time('set {} embeddings'.format(len(tokens))):
vocab.set_embedding(token_embedding_)
evaluation.evaluate_analogy(
args_, vocab.embedding, ctx, logfile=os.path.join(
args_.logdir, 'analogy{}.tsv'.format(name)))
else:
token_embedding_ = load_embedding_from_path(args_)
name = ''
enforce_max_size(token_embedding_, args_.max_vocab_size)
known_tokens = set(token_embedding_.idx_to_token)
# Auto-extend token_embedding with unknown extra eval tokens
if token_embedding_.unknown_lookup is not None:
eval_tokens = evaluation.get_tokens_in_evaluation_datasets(args_)
# pylint: disable=pointless-statement
token_embedding_[[
t for t in eval_tokens - known_tokens
if t in token_embedding_.unknown_lookup
]]
if args_.max_vocab_size is not None and len(
token_embedding_.idx_to_token) > args_.max_vocab_size:
logging.warning('Computing embeddings for OOV words that occur '
'in the evaluation dataset lead to having '
'more words than --max-vocab-size. '
'Have %s words (--max-vocab-size %s)',
len(token_embedding_.idx_to_token),
args_.max_vocab_size)
similarity_results = evaluation.evaluate_similarity(
args_, token_embedding_, ctx, logfile=os.path.join(
args_.logdir, 'similarity{}.tsv'.format(name)))
analogy_results = evaluation.evaluate_analogy(
args_, token_embedding_, ctx, logfile=os.path.join(
args_.logdir, 'analogy{}.tsv'.format(name)))