diff --git a/fastNLP/embeddings/bert_embedding.py b/fastNLP/embeddings/bert_embedding.py index 84105444..36670a0b 100644 --- a/fastNLP/embeddings/bert_embedding.py +++ b/fastNLP/embeddings/bert_embedding.py @@ -72,8 +72,8 @@ class BertEmbedding(ContextualEmbedding): if model_dir_or_name.lower() in PRETRAINED_BERT_MODEL_DIR: if 'cn' in model_dir_or_name.lower() and pool_method not in ('first', 'last'): - logger.warn("For Chinese bert, pooled_method should choose from 'first', 'last' in order to achieve" - " faster speed.") + logger.warning("For Chinese bert, pooled_method should choose from 'first', 'last' in order to achieve" + " faster speed.") warnings.warn("For Chinese bert, pooled_method should choose from 'first', 'last' in order to achieve" " faster speed.") diff --git a/fastNLP/io/file_reader.py b/fastNLP/io/file_reader.py index b64b115b..3370e660 100644 --- a/fastNLP/io/file_reader.py +++ b/fastNLP/io/file_reader.py @@ -111,7 +111,7 @@ def _read_conll(path, encoding='utf-8', indexes=None, dropna=True): yield line_idx, res except Exception as e: if dropna: - logger.warn('Invalid instance which ends at line: {} has been dropped.'.format(line_idx)) + logger.warning('Invalid instance which ends at line: {} has been dropped.'.format(line_idx)) continue raise ValueError('Invalid instance which ends at line: {}'.format(line_idx)) elif line.startswith('#'): diff --git a/fastNLP/io/pipe/classification.py b/fastNLP/io/pipe/classification.py index db791ae8..409cfe53 100644 --- a/fastNLP/io/pipe/classification.py +++ b/fastNLP/io/pipe/classification.py @@ -387,7 +387,7 @@ class SST2Pipe(_CLSPipe): f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \ f"data set but not in train data set!." warnings.warn(warn_msg) - logger.warn(warn_msg) + logger.warning(warn_msg) datasets = [] for name, dataset in data_bundle.datasets.items(): if dataset.has_field(Const.TARGET): diff --git a/fastNLP/io/pipe/matching.py b/fastNLP/io/pipe/matching.py index aa6db46f..def750c0 100644 --- a/fastNLP/io/pipe/matching.py +++ b/fastNLP/io/pipe/matching.py @@ -121,7 +121,7 @@ class MatchingBertPipe(Pipe): f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \ f"data set but not in train data set!." warnings.warn(warn_msg) - logger.warn(warn_msg) + logger.warning(warn_msg) has_target_datasets = [dataset for name, dataset in data_bundle.datasets.items() if dataset.has_field(Const.TARGET)] @@ -258,7 +258,7 @@ class MatchingPipe(Pipe): f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \ f"data set but not in train data set!." warnings.warn(warn_msg) - logger.warn(warn_msg) + logger.warning(warn_msg) has_target_datasets = [dataset for name, dataset in data_bundle.datasets.items() if dataset.has_field(Const.TARGET)] diff --git a/fastNLP/io/pipe/utils.py b/fastNLP/io/pipe/utils.py index 4925853f..d05ffe96 100644 --- a/fastNLP/io/pipe/utils.py +++ b/fastNLP/io/pipe/utils.py @@ -130,11 +130,12 @@ def _indexize(data_bundle, input_field_names=Const.INPUT, target_field_names=Con if ('train' not in name) and (ds.has_field(target_field_name))] ) if len(tgt_vocab._no_create_word) > 0: - warn_msg = f"There are {len(tgt_vocab._no_create_word)} target labels" \ + warn_msg = f"There are {len(tgt_vocab._no_create_word)} `{target_field_name}` labels" \ f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \ - f"data set but not in train data set!." + f"data set but not in train data set!.\n" \ + f"These label(s) are {tgt_vocab._no_create_word}" warnings.warn(warn_msg) - logger.warn(warn_msg) + logger.warning(warn_msg) tgt_vocab.index_dataset(*data_bundle.datasets.values(), field_name=target_field_name) data_bundle.set_vocab(tgt_vocab, target_field_name) diff --git a/fastNLP/models/bert.py b/fastNLP/models/bert.py index 2bd15eb0..93a294ab 100644 --- a/fastNLP/models/bert.py +++ b/fastNLP/models/bert.py @@ -65,7 +65,7 @@ class BertForSequenceClassification(BaseModel): self.bert.model.include_cls_sep = True warn_msg = "Bert for sequence classification excepts BertEmbedding `include_cls_sep` True, " \ "but got False. FastNLP has changed it to True." - logger.warn(warn_msg) + logger.warning(warn_msg) warnings.warn(warn_msg) def forward(self, words): @@ -110,7 +110,7 @@ class BertForSentenceMatching(BaseModel): self.bert.model.include_cls_sep = True warn_msg = "Bert for sentence matching excepts BertEmbedding `include_cls_sep` True, " \ "but got False. FastNLP has changed it to True." - logger.warn(warn_msg) + logger.warning(warn_msg) warnings.warn(warn_msg) def forward(self, words): @@ -156,7 +156,7 @@ class BertForMultipleChoice(BaseModel): self.bert.model.include_cls_sep = True warn_msg = "Bert for multiple choice excepts BertEmbedding `include_cls_sep` True, " \ "but got False. FastNLP has changed it to True." - logger.warn(warn_msg) + logger.warning(warn_msg) warnings.warn(warn_msg) def forward(self, words): @@ -206,7 +206,7 @@ class BertForTokenClassification(BaseModel): self.bert.model.include_cls_sep = False warn_msg = "Bert for token classification excepts BertEmbedding `include_cls_sep` False, " \ "but got True. FastNLP has changed it to False." - logger.warn(warn_msg) + logger.warning(warn_msg) warnings.warn(warn_msg) def forward(self, words): @@ -250,7 +250,7 @@ class BertForQuestionAnswering(BaseModel): self.bert.model.include_cls_sep = True warn_msg = "Bert for question answering excepts BertEmbedding `include_cls_sep` True, " \ "but got False. FastNLP has changed it to True." - logger.warn(warn_msg) + logger.warning(warn_msg) warnings.warn(warn_msg) def forward(self, words): diff --git a/fastNLP/modules/encoder/bert.py b/fastNLP/modules/encoder/bert.py index 12379718..16b456fb 100644 --- a/fastNLP/modules/encoder/bert.py +++ b/fastNLP/modules/encoder/bert.py @@ -488,10 +488,10 @@ class BertModel(nn.Module): load(model, prefix='' if hasattr(model, 'bert') else 'bert.') if len(missing_keys) > 0: - logger.warn("Weights of {} not initialized from pretrained model: {}".format( + logger.warning("Weights of {} not initialized from pretrained model: {}".format( model.__class__.__name__, missing_keys)) if len(unexpected_keys) > 0: - logger.warn("Weights from pretrained model not used in {}: {}".format( + logger.warning("Weights from pretrained model not used in {}: {}".format( model.__class__.__name__, unexpected_keys)) logger.info(f"Load pre-trained BERT parameters from file {weights_path}.") @@ -800,7 +800,7 @@ class BertTokenizer(object): for token in tokens: ids.append(self.vocab[token]) if len(ids) > self.max_len: - logger.warn( + logger.warning( "Token indices sequence length is longer than the specified maximum " " sequence length for this BERT model ({} > {}). Running this" " sequence through BERT will result in indexing errors".format(len(ids), self.max_len) @@ -824,8 +824,8 @@ class BertTokenizer(object): with open(vocab_file, "w", encoding="utf-8") as writer: for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]): if index != token_index: - logger.warn("Saving vocabulary to {}: vocabulary indices are not consecutive." - " Please check that the vocabulary is not corrupted!".format(vocab_file)) + logger.warning("Saving vocabulary to {}: vocabulary indices are not consecutive." + " Please check that the vocabulary is not corrupted!".format(vocab_file)) index = token_index writer.write(token + u'\n') index += 1