# bayou

**Repository Path**: mirrors/bayou

## Basic Information

- **Project Name**: bayou
- **Description**: Bayou 是 Java API 惯用语的数据驱动程序综合系统，它从 GitHub 上采集数据，通过深度学习算法和训练，将 Java 代码编写部分自动化
- **Primary Language**: Java
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: https://www.oschina.net/p/bayou
- **GVP Project**: No

## Statistics

- **Stars**: 16
- **Forks**: 2
- **Created**: 2020-08-07
- **Last Updated**: 2026-02-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Bayou
Bayou is a data-driven program synthesis system for Java API idioms that uses the novel technique of Neural Sketch Learning.

To learn more, click [here](https://arxiv.org/abs/1703.05698) for the ICLR 2018 paper on Bayou. Click [here](https://github.com/capergroup/bayou/tree/master/doc/external) for the PLDI 2018 tutorial slides on Bayou.

Try Bayou on your browser! Visit www.askbayou.com.

## Requirements
- JDK 1.8
- Python3 (Tested with 3.5.1)
- [Tensorflow](https://www.tensorflow.org) (Tested with 1.4)
- scikit-learn (Tested with 0.19)

## Compiling and Running Bayou from Source on Ubuntu/Mac

#### 1.) Download source from GitHub:
```
git clone https://github.com/capergroup/bayou.git
```

#### 2.) Install Dependencies
```
cd bayou/tool_files/build_scripts
sudo ./install_dependencies.sh
```

#### 3.) Compile Bayou
```
./build.sh
```

#### 4.) Run Bayou
```
cd out/
./start_bayou.sh &
```

Wait until you see:
```
===================================
            Bayou Ready            
===================================
```

then execute:
```
./synthesize.sh
```

You should see as output several programs separated by the characters
```
---------- BEGIN PROGRAM  ----------
```

To run Bayou on some of the provided examples, execute:
```
./synthesize.sh example_inputs/<Program.java>
```
where ```Program.java``` is the name of the example program.