machineJS

machineJS copied to clipboard

ClimbsRocks

then, ideally, we can run a regression against them to see which ones matter for your dataset and which ones do not. in a perfect world, we'd then use that...

ClimbsRocks

see if i can move more and more material into an advancedAPI.md file, and keep the opening documentation super straightforward. take inspiration from Brain.js here- make the API as easy...

ClimbsRocks

1. installation 2. example csv header table 3. list of available header options do all of this before explaining the benefits, etc. showing them what it can do is way...

ClimbsRocks

ClimbsRocks

naive bayes, in particular. this is mostly for the nlp problem type.

ClimbsRocks

set default to only use linear models for nlp

1

non-linear models like a random forest are actually less accurate oftentimes, because they tend to overfit the data, and are obviously much slower.

ClimbsRocks

Write a series of blog posts covering different customizations you can make to machineJS. among them: - [ ] changing the number of rounds we use for RandomizedSearchCV to find...

ClimbsRocks

Cannot find pySetup/utils.py

20

Whenever I try and run anything (machineJs or tests), I get the following: sospan-2:machineJS justin$ npm run test:regression > [email protected] test:regression /Users/justin/DeepLearning/machineJS/machineJS > mocha test/regression/test.js regression problems module.js:339 throw err;...

eanie

Persist everything to disk so a trained instance can be loaded

1

The goal is to train machineJS, serialize it and all of it's components to JSON/.pkl, then be able to load in all the trained components again on a different machine.

ClimbsRocks