Skip to content

NicoleKenn/causalDeepVASE

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

64 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

Special Package Requirements

🌠 rpy2
🌠 keras (🔔 please use the version of 2.3.1, which can be installed using "pip install Keras==2.3.1".)
🌠 Deeplift (🔔 please use the version of 0.5.1-theano, which should be downloaded online.)
🌠 Tensorflow (🔔 please use the version of 2.2.0, which can be installed using "pip install tensorflow==2.2.0".)
🌠 jpype
🌠 R environment
🌠 Java environment

Installation

Please download the source code to your local workplace.

Source Code

📁The sub folder /MGM contains the Python version of MGM implementation.
📁 The sub folder /DL contains the Python implemenation of DeepPINK procedure (knockoff data generation, DNN, and FDR).
📁 The sub folder /causal contains the Python implementation of DG procedure.

Example

The source code /Example.ipynb demonstrates how to use causalDeepVASE.

Acknowledgement and References

🏆 Some components of this project come from the follwing projects:

⭐ The MGM Java implemention is from causalMGM and Tetrad.
⭐ The DeepPINK implementation is from DeepPINK.
⭐ The FDR filter function is from DeepKnockoffs.
⭐ The Python implementation of DG algorithm is based on its Java version from Tetrad.
⭐ The implementation of the PC algorithm used in this project is from pcalg.

Contact

📧 Please let us know if you have any questions, bug reports, or feedback via the following email:

📧 hyp15@pitt.edu

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 48.2%
  • Python 29.1%
  • R 19.9%
  • C 2.8%