Jason Shin

`fit` function is working fine now, hopefully. There's still a problem with `predict`

Prediction is still always returning 1s. To debug the issue: 1. Grab the classifier attributes, alpha, polarity, threshold, feature_index, and alpha 2. get the Python implementation 3. Try running Python's...

Python experiment ``` import numpy as np clfs = [ { "p": -1, "threshold": 0.6455696225166321, "feature_index": 0, "alpha": 11.512925148010254 }, { "p": -1, "threshold": 0.6455696225166321, "feature_index": 1, "alpha": 11.512925148010254 },...

I'm still trying to figure out why `w.where(tf.notEqual(tensorY, predLabeledPreds), tf.zeros([nSamples]))` at some point returns all `NaN`s Debug steps - Before the code returns `NaN` s, see what you are getting...

thanks, let me check out the PR soon

Hey @h4ck4life thanks for your first contribution to machinelearn.js! Not sure if you are already aware, we have a unit test for ensuring exports are correctly done under https://github.com/machinelearnjs/machinelearnjs/blob/develop/test/integration/require.test.ts ....

There is a test failure due to the doc processor cannot handle certain type. Could you please take a look at it? Let me know if it's too hard.

Also, could you make sure these things? 1. Export `StratifiedShuffleSplit` in `index.ts` (check model_selection/index.ts) so the users can actually use it 2. add an integration test 3. Please add unit...

Sounds good, it will be a major addition to machinelearn.js. Would you mind giving me a brief idea on how you want to introduce GA in machinelearn.js? Will there be...

I like the idea of initially introducing the smaller components of GA like evolution, fitness, mutation and selection as separate APIs. I think a massive addition like GA should belong...