This adds a Javascript port of Datawig. Datawig-JS is based on Tensorflow-JS and enables client-side missing value imputation for Excel files. The port includes an implementation of white-box interpretabilty (based on a method described in https://pubmed.ncbi.nlm.nih.gov/24239590/). Also, the prototype supports active learning workflows by iteratively tuning the underlying model with the provided data.
The code is a very early prototype.
Since this PR is adding a lot of .js and .css files, I recommend having a look at the diff of this commit.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
Description of changes:
This adds a Javascript port of Datawig. Datawig-JS is based on Tensorflow-JS and enables client-side missing value imputation for Excel files. The port includes an implementation of white-box interpretabilty (based on a method described in https://pubmed.ncbi.nlm.nih.gov/24239590/). Also, the prototype supports active learning workflows by iteratively tuning the underlying model with the provided data.
The code is a very early prototype.
Since this PR is adding a lot of .js and .css files, I recommend having a look at the diff of this commit.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.