Bayou is a data-driven program synthesis system for Java that uses learned Bayesian specifications for efficient synthesis.

Click here for the arXiv paper on Bayou.

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

• JDK 1.8
• Python3 (Tested with 3.5.1)
• Tensorflow (Tested with 1.2)
• scikit-learn (Tested with 0.18.1)

git clone https://github.com/capergroup/bayou.git

cd bayou/tool_files/build_scripts
sudo ./install_deps_apt.sh

Or run install_deps_mac.sh for Mac (uses Homebrew).

./build.sh

./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.