rcurtin_irc changed the topic of #mlpack to: mlpack: a scalable machine learning library (https://www.mlpack.org/) -- channel logs: https://libera.irclog.whitequark.org/mlpack -- NOTE: messages sent here might not be seen by bridged users on matrix, gitter, or slack
Dhruv has joined #mlpack
Dhruv is now known as lumi_232
<lumi_232> Hello I am Dhruv Nagill a 3rd year undergraduate from NIT Trichy. I have 2 years of experience in the reinforcement learning domain. I saw last years project "Addition of PPO, Twin Delayed DDPG, Hindsight Experience Replay to RL Codebase". I noticed that PPO is still listed as one of the algorithms to be implemented. I want to implement PPO and
<lumi_232> the other algorithms listed in the Ideas for Google Summer of Code 2024. May I please know what are the steps I can take to maximise my chances of getting selected for this project? PPO is a fundamental algorithm and is very often used as reference, mlpack not having a PPO implementation is a major setback. I wish to implement it and integrate it
<lumi_232> before GSoC itself.
lumi_232 has quit [Quit: Client closed]
Dhruv has joined #mlpack
Dhruv is now known as lumi_232
lumi_232 has quit [Quit: Client closed]
Dhruv has joined #mlpack
Dhruv is now known as lumi_232
lumi_232 has quit [Client Quit]
lumi_232 has joined #mlpack
lumi_232 has quit [Client Quit]
Guest35 has joined #mlpack
<Guest35> hey
<Guest35> i am getting low cross validation test accuracy in random forest, can someone point out what is wrong with my code
<Guest35> #include "mlpack.hpp"
<Guest35> #include <iostream>
<Guest35> using namespace std;
<Guest35> int main(){
<Guest35>     arma::mat dataset;
<Guest35>     bool loaded = mlpack::data::Load("heartrm.csv", dataset);
<Guest35>     if(!loaded){
<Guest35>         std::cout<<"dataset not loaded\n";
<Guest35>         return -1;
<Guest35>     }
<Guest35>     arma::Row<size_t>labels;
<Guest35>     labels = arma::conv_to<arma::Row<size_t>>::from(dataset.row(dataset.n_rows-1));
<Guest35>     dataset.shed_row(dataset.n_rows-1);
<Guest35>     arma::mat Xtrain, Xtest;
<Guest35>     arma::Row<size_t> Ytrain, Ytest;
<Guest35>     mlpack::data::Split(dataset, labels, Xtrain, Xtest, Ytrain, Ytest, 0.25);
<Guest35>     mlpack::tree::RandomForest<> rf;
<Guest35>     rf = mlpack::tree::RandomForest<>(Xtrain, Ytrain, 5/*classes*/, 10/*numTrees*/, 3);
<Guest35> ok got it
Guest35 has quit [Quit: Client closed]