machineJS

machineJS copied to clipboard

1. voluntary data gathering to run ML on our own library once trained, ask users if they'd be ok sharing some summary info about their data and the parameters of...

ClimbsRocks

ClimbsRocks

to keep it consistent, i'll have to copy over the data formatting from the benchmark xgboost file.

ClimbsRocks

improve accuracy

1

there's a bug somewhere that's killing the accuracy. scores on homesite and telstra are lagging dramatically behind what others are getting with xgboost alone. my initial reaction was that we...

ClimbsRocks

the first one will exit out of machineJS and send control over to the first round of ensembler if we are in validationRound in machineJS and hear another sigint, then...

ClimbsRocks

it might be only during the predicting phase, as we had other classifiers training at the same time, which should not be happening if we're still in the searchCV phase

ClimbsRocks

right now we are assuming there is only one output column

ClimbsRocks

i think right now that we're searching for too many parameters at once, leading to possibly adverse interactions between them. let's see if we can focus in on only searching...

ClimbsRocks

do not overwhelm the user with unnecessary information have lots of examples have a totally separate Advanced section, where we cover all the deep custom ways you can tweak the...

ClimbsRocks

create a json that is a summary of everything. ok, it will probably have to be a folder, and in that folder we'll have a .pkl of each of the...

ClimbsRocks