/scitree

Collection of Decision Tree Algorithms

Primary LanguageC++Apache License 2.0Apache-2.0

Scitree

Scitree is a collection of decision forest model algorithms.
Basically this is a wrapper around the Yggdrasil Decision Forests C ++ libraries.

Examples

dataset_train = # Dataset
dataset_predict = # Dataset

ref =
  Scitree.Config.init()
  |> Scitree.Config.label("class")
  |> Scitree.Config.learner(:random_forest)
  |> Scitree.Config.task(:classification)
  |> Scitree.train(dataset_train)
  |> Scitree.predict(dataset_predict)

more examples

Dependencies

  • Python3 (Tested with version 3.8.10)
  • NumPy installed for compiling Tensorflow
  • Bazel v3.7.2 for compiling Yggdrasil and all its dependencies
  • GCC >= 9.3.0
  • build-essential (base-devel)

Getting started

In order to use Scitree, you will need Elixir installed. Then create an Elixir project via the mix build tool:

$ mix new my_app

Then you can add Scitree as dependency in your mix.exs. At the moment you will have to use a Git dependency while we work on our first release:

def deps do
  [
    {:scitree, "~> 0.1.0", github: "jeantux/scitree", branch: "main"}
  ]
end

Alternatively, inside a script or Livebook:

Mix.install([{:scitree, "~> 0.1.0", github: "jeantux/scitree", branch: "main"}])