47 lines
1.4 KiB
Python
47 lines
1.4 KiB
Python
from transformers import BertTokenizer, BertForSequenceClassification, TrainingArguments, Trainer
|
|
import random
|
|
import torch
|
|
|
|
with open('train/in.tsv') as f:
|
|
data_train_X = f.readlines()
|
|
|
|
with open('train/expected.tsv') as f:
|
|
data_train_Y = f.readlines()
|
|
|
|
with open('dev-0/in.tsv') as f:
|
|
data_dev_X = f.readlines()
|
|
|
|
with open('test-A/in.tsv') as f:
|
|
data_test_X = f.readlines()
|
|
|
|
class CustomDataset(torch.utils.data.Dataset):
|
|
def __init__(self, encodings, labels=None):
|
|
self.encodings = encodings
|
|
self.labels = labels
|
|
|
|
def __getitem__(self, idx):
|
|
item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
|
|
if self.labels:
|
|
item["labels"] = torch.tensor(self.labels[idx])
|
|
return item
|
|
|
|
def __len__(self):
|
|
return len(self.encodings["input_ids"])
|
|
|
|
data_train = list(zip(data_train_X, data_train_Y))
|
|
data_train = random.sample(data_train, 50000)
|
|
|
|
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
|
|
train_X = tokenizer([text[0] for text in data_train], truncation=True, padding=True)
|
|
train_Y = [int(text[1]) for text in data_train]
|
|
|
|
train_dataset = CustomDataset(train_X, train_Y)
|
|
|
|
model = BertForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=2)
|
|
|
|
training_args = TrainingArguments("model")
|
|
trainer = Trainer(
|
|
model=model, args=training_args, train_dataset=train_dataset)
|
|
trainer.train()
|
|
|