SQLNet - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #machine-learning #deep-learning #docker #nodejs #java #windows #awesome #cli #kubernetes #awesome-list #pytorch #mcp

SQLNet

(★ 433)

Neural Network for generating structured queries from natural language.

파일 탐색기

최종 버전 다운로드 (.zip)

- .keep
- - __init__.py
  - dbengine.py
- - __init__.py
  - seq2sql.py
  - sqlnet.py
- __init__.py
- utils.py
.gitignore
data.tar.bz2
download_glove.sh
extract_vocab.py
LICENSE
README.md
requirements.txt
test.py
train.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/xiaojunxu/SQLNet

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd SQLNet

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# SQLNet

This repo provides an implementation of SQLNet and Seq2SQL neural networks for predicting SQL queries on [WikiSQL dataset](https://github.com/salesforce/WikiSQL). The paper is available at [here](https://arxiv.org/abs/1711.04436).

## Citation

> Xiaojun Xu, Chang Liu, Dawn Song. 2017. SQLNet: Generating Structured Queries from Natural Language Without Reinforcement Learning.

## Bibtex

```
@article{xu2017sqlnet,
  title={SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning},
  author={Xu, Xiaojun and Liu, Chang and Song, Dawn},
  journal={arXiv preprint arXiv:1711.04436},
  year={2017}
}
```

## Installation
The data is in `data.tar.bz2`. Unzip the code by running
```bash
tar -xjvf data.tar.bz2
```

The code is written using PyTorch in Python 2.7. Check [here](http://pytorch.org/) to install PyTorch. You can install other dependency by running 
```bash
pip install -r requirements.txt
```

## Downloading the glove embedding.
Download the pretrained glove embedding from [here](https://github.com/stanfordnlp/GloVe) using
```bash
bash download_glove.sh
```

## Extract the glove embedding for training.
Run the following command to process the pretrained glove embedding for training the word embedding:
```bash
python extract_vocab.py
```

## Train
The training script is `train.py`. To see the detailed parameters for running:
```bash
python train.py -h
```

Some typical usage are listed as below:

Train a SQLNet model with column attention:
```bash
python train.py --ca
```

Train a SQLNet model with column attention and trainable embedding (requires pretraining without training embedding, i.e., executing the command above):
```bash
python train.py --ca --train_emb
```

Pretrain a [Seq2SQL model](https://arxiv.org/abs/1709.00103) on the re-splitted dataset
```bash
python train.py --baseline --dataset 1
```

Train a Seq2SQL model with Reinforcement Learning after pretraining
```bash
python train.py --baseline --dataset 1 --rl
```

## Test
The script for evaluation on the dev split and test split. The parameters for evaluation is roughly the same as the one used for training. For example, the commands for evaluating the models from above commands are:

Test a trained SQLNet model with column attention
```bash
python test.py --ca
```

Test a trained SQLNet model with column attention and trainable embedding:
```bash
python test.py --ca --train_emb
```

Test a trained [Seq2SQL model](https://arxiv.org/abs/1709.00103) withour RL on the re-splitted dataset
```bash
python test.py --baseline --dataset 1
```

Test a trained Seq2SQL model with Reinforcement learning
```bash
python test.py --baseline --dataset 1 --rl
```