Test Scripts Script

The test scripts script runs all of the other scripts, including the feature derivative scripts, to check for bugs. This is not a full coverage test, and should not be taken as such. Instead, it is intended to catch simple bugs introduced in the fns module. It can also be used to check that the python enviroment has all of the required packages to run the feature interpretability module.

This does not save any individual script output. It does print the time it took to run to the command line.

Code Documentation

Runs all scripts to test for errors. Does not save script output.

Input Line for Tensorflow Models on Coupon Data: python test_scripts.py -P tensorflow -E coupon

Input Line for PYT Nested Cylinder Models: python test_scripts.py -P pytorch -E nestedcylinder

Arguments

Runs all feature interpretability scripts to test for errors.

usage: python test_scripts.py [-h] [--PACKAGE] [--EXPERIMENT]

Named Arguments

--PACKAGE, -P

Possible choices: tensorflow, pytorch

Which python package was used to create the model

Default: “tensorflow”

--EXPERIMENT, -E

Possible choices: coupon, nestedcylinder

Which experiment the model was trained on

Default: “coupon”