GGoMa/multi_label

한 줄 소개

Updated on 22.11.03
multi_label.py
'''
---GGoMa/multi_label Auto Generate Code---
Author		: GGoMa
Project Name: multi_label
Project Link: https://blockai.kr/GGoMa/multi_label (BlockAI)
Create Date	: 2022-11-03

---Requirements---
# 사용자의 환경(OS, CUDA 등)에 따라 라이브러리 버전을 맞춰주세요
pip install torch==1.12 torchvision==0.13.0 torchtext==0.13.0 torchaudio==0.12.0
pip install pytorch-lightning
pip install tqdm
pip install pandas
pip install scikit-learn

---Folder Structure---
--📂 data
   |--📂 input
      |--📄 train.*
      |--📄 val.*
      |--📄 test.*
--📄 multi_label.py
--📄 multi_label.ipynb
--📄 requirements.txt
'''

import os
import argparse
import copy
from glob import glob

from tqdm import tqdm
import numpy as np
import pandas as pd
from sklearn import preprocessing

import torch
import pytorch_lightning as pl

path_sep = os.sep


# https://pytorch.org/tutorials/beginner/basics/data_tutorial.html#creating-a-custom-dataset-for-your-files
class Dataset(torch.utils.data.Dataset):
    def __init__(self, inputs, targets=[]):
        self.inputs = inputs
        self.targets = targets

    # 학습 및 추론 과정에서 데이터를 1개씩 꺼내오는 곳
    def __getitem__(self, idx):
        # 정답이 있다면 if문을, 없다면 else문을 수행합니다
        if len(self.targets) == 0:
            return torch.tensor(self.inputs[idx])
        else:
            return torch.tensor(self.inputs[idx]), torch.tensor(self.targets[idx])

    # 입력하는 개수만큼 데이터를 사용합니다
    # 'return 100'이면 1에폭에 100개의 데이터만 사용합니다
    def __len__(self):
        return len(self.inputs)


# https://pytorch-lightning.readthedocs.io/en/stable/extensions/datamodules.html
class Dataloader(pl.LightningDataModule):
# 데이터의 종류에 따라 코드 수정이 필요할 수 있습니다
    def __init__(self, data_folder, batch_size, shuffle):
        super().__init__()
        self.data_folder = data_folder
        self.batch_size = batch_size
        self.shuffle = shuffle

        self.train_dataset = None
        self.val_dataset = None
        self.test_dataset = None
        self.predict_dataset = None
        self.set_preprocessing()

    def set_preprocessing(self):
        data = pd.read_csv(glob(os.path.join(self.data_folder, 'input', 'train.*'))[0], sep=',', index_col=None, encoding='utf-8')
        columns = data.columns
        self.target_columns = [columns[None]]


    def preprocessing(self, data):
        columns = data.columns.tolist()
        # 타겟 데이터가 없으면 빈 배열을 리턴합니다.
        try:
            targets = data[self.target_columns].values.tolist()
            inputs = data.drop(self.target_columns, axis=1).values.tolist()
        except:
            targets = []
            inputs = data.values.tolist()

        return inputs, targets

    def setup(self, stage='fit'):
        if stage == 'fit':
            train_data = pd.read_csv(glob(os.path.join(self.data_folder, 'input', 'train.*'))[0], sep=',', index_col=None, encoding='utf-8')

            # 학습데이터 준비
            train_inputs, train_targets = self.preprocessing(train_data)

            # 검증데이터 준비
            val_data = pd.read_csv(glob(os.path.join(self.data_folder, 'input', 'val.*'))[0], sep=',', index_col=None, encoding='utf-8')
            val_inputs, val_targets = self.preprocessing(val_data)

            # train 데이터만 shuffle을 적용해줍니다, 필요하다면 val, test 데이터에도 shuffle을 적용할 수 있습니다
            self.train_dataset = Dataset(train_inputs, train_targets)
            self.val_dataset = Dataset(val_inputs, val_targets)
        else:
            # 평가데이터 준비
            test_data = pd.read_csv(glob(os.path.join(self.data_folder, 'input', 'test.*'))[0], sep=',', index_col=None, encoding='utf-8')
            test_inputs, test_targets = self.preprocessing(test_data)
            self.test_dataset = Dataset(test_inputs, test_targets)
            self.predict_dataset = Dataset(test_inputs, [])

    def train_dataloader(self):
        return torch.utils.data.DataLoader(self.train_dataset, batch_size=self.batch_size, shuffle=args.shuffle)

    def val_dataloader(self):
        return torch.utils.data.DataLoader(self.val_dataset, batch_size=self.batch_size)

    def test_dataloader(self):
        return torch.utils.data.DataLoader(self.test_dataset, batch_size=self.batch_size)

    def predict_dataloader(self):
        return torch.utils.data.DataLoader(self.predict_dataset, batch_size=self.batch_size)


# https://pytorch-lightning.readthedocs.io/en/stable/common/lightning_module.html
class Model(pl.LightningModule):
    def __init__(self):
        super().__init__()
        self.save_hyperparameters()

        self.linear_1 = torch.nn.Linear(in_features=170, out_features=1024)
        self.batchnorm1d_1 = torch.nn.BatchNorm1d(num_features=1024)
        self.linear_2 = torch.nn.Linear(in_features=1024, out_features=23)

        self.relu_1 = torch.nn.ReLU()
        self.dropout_1 = torch.nn.Dropout(p=0.3)
        self.bcewithlogitsloss_1 = torch.nn.BCEWithLogitsLoss()

    def forward(self, x):
        x = self.linear_1(x)
        x = self.batchnorm1d_1(x)
        x = self.relu_1(x)
        x = self.dropout_1(x)
        x = self.linear_2(x)

        return x

    def training_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = self.bcewithlogitsloss_1(logits, y.float())
        self.log("train_loss", loss)

        return loss

    def validation_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = self.bcewithlogitsloss_1(logits, y.float())
        self.log("val_loss", loss)

        return loss

    def test_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = self.bcewithlogitsloss_1(logits, y.float())
        self.log("test_loss", loss)

        return loss

    def predict_step(self, batch, batch_idx):
        x = batch
        logits = self(x)

        return logits

    def configure_optimizers(self):
        # 이곳에서 lr 값을 변경할 수 있습니다
        optimizer = torch.optim.AdamW(self.parameters(), lr=0.0005)
        return optimizer


if __name__ == '__main__':
    # https://docs.python.org/ko/3/library/argparse.html
    # 하이퍼 파라미터 등 각종 설정값을 입력받습니다
    # 터미널 실행 예시 : python3 run.py --batch_size=64 ...
    # 실행 시 '--batch_size=64' 같은 인자를 입력하지 않으면 default 값이 기본으로 실행됩니다
    parser = argparse.ArgumentParser()
    parser.add_argument('--data_folder', default='./data')
    parser.add_argument('--batch_size', default=5000)
    parser.add_argument('--max_epoch', default=1000)
    parser.add_argument('--shuffle', default=False)
    args = parser.parse_args()

    dataloader = Dataloader(args.data_folder, args.batch_size, args.shuffle)
    model = Model()

    # 'patience=10'이면 10에폭동안 monitor값이 좋아지지 않으면 학습을 자동 중단합니다
    early_stop_callback = pl.callbacks.EarlyStopping(monitor='val_loss', patience=10)
    # https://pytorch-lightning.readthedocs.io/en/stable/common/trainer.html
    # 학습 및 추론을 위한 Trainer 설정
    # gpu가 없으면 'gpus=0'을, gpu가 여러개면 'gpus=4'처럼 사용하실 gpu의 개수를 입력해주세요
    trainer = pl.Trainer(gpus=1, max_epochs=args.max_epoch, callbacks=[early_stop_callback])
    trainer.fit(model=model, datamodule=dataloader)
    # 테스트 데이터에 타겟값이 있을때만 trainer.test를 실행할 수 있습니다
    trainer.test(model=model, datamodule=dataloader)
    predictions = trainer.predict(model=model, datamodule=dataloader)
Readme.md
문의하기