def load_train_val_examples(args):
lines = []
for guid, text, _, entities in train_data_generator(args.train_file, args.eval_file):
sl = LabeledText(guid, text, entities)
lines.append({'guid': guid, 'text': text, 'entities': entities})
allow_overlap = args.allow_overlap
if args.num_augements > 0:
allow_overlap = False
train_base_examples = load_ner_labeled_examples(
lines,
ner_labels,
seg_len=args.seg_len,
seg_backoff=args.seg_backoff,
num_augements=args.num_augements,
allow_overlap=allow_overlap)
train_examples, val_examples = split_train_eval_examples(
train_base_examples,
train_rate=args.train_rate,
fold=args.fold,
shuffle=True)
logger.info(f"Loaded {len(train_examples)} train examples, "
f"{len(val_examples)} val examples.")
return train_examples, val_examples
def load_train_val_examples(args,
train_data_generator,
glue_labels,
shuffle=True,
train_rate=0.9,
num_augments=0):
all_train_examples = load_glue_examples(train_data_generator,
args.train_file)
if args.train_sample_rate < 1.0:
num_samples = int(len(all_train_examples) * args.train_sample_rate)
all_train_examples = all_train_examples[:num_samples]
# 切分训练集和验证集
# theta 提供split_train_eval_examples辅助函数
from theta.utils import split_train_eval_examples
train_examples, val_examples = split_train_eval_examples(
all_train_examples,
train_rate=args.train_rate,
fold=args.fold,
shuffle=shuffle)
# random.shuffle(all_train_examples)
# num_train_examples = int(len(all_train_examples) * args.train_rate)
# val_examples = all_train_examples[num_train_examples:]
# train_examples = all_train_examples[:num_train_examples]
logger.info(f"Loaded {len(train_examples)} train examples, "
f"{len(val_examples)} val examples.")
return train_examples, val_examples
def load_train_val_examples(args):
all_train_examples = load_glue_examples(train_data_generator,
args.train_file)
# 切分训练集和验证集
# theta 提供split_train_eval_examples辅助函数
from theta.utils import split_train_eval_examples
train_examples, val_examples = split_train_eval_examples(
all_train_examples,
train_rate=args.train_rate,
fold=args.fold,
shuffle=True)
logger.info(f"Loaded {len(train_examples)} train examples, "
f"{len(val_examples)} val examples.")
return train_examples, val_examples
def load_train_val_examples(args, seg_len=0, seg_backoff=0):
train_base_examples = load_examples(args,
train_data_generator,
train_base_file,
seg_len=seg_len,
seg_backoff=seg_backoff)
train_examples, val_examples = split_train_eval_examples(
train_base_examples,
train_rate=args.train_rate,
fold=fold,
shuffle=True,
random_state=args.seed)
logger.info(
f"Loaded {len(train_examples)} train examples, {len(val_examples)} val examples."
)
return train_examples, val_examples
