Popularity
5.7
Growing
Activity
0.0
Declining
68
4
3

Description

Turn data into functions! A simple and functional machine learning library written in elixir.

Monthly Downloads: 2
Programming language: Elixir
License: MIT License
Tags: Statistics     Machine Learning     Elixir    

Emel alternatives and similar packages

Based on the "Statistics" category

Do you think we are missing an alternative of Emel or a related project?

Add another 'Statistics' Package

README

# emel

Turn data into functions! A simple and functional machine learning library written in elixir.

emel neural network

## Installation

The package can be installed by adding emel to your list of dependencies in mix.exs:

  def deps do
  [
    {:emel, "~> 0.3.0"}
  ]
  end

The docs can be found at https://hexdocs.pm/emel/0.3.0.

## Usage

  # set up the aliases for the module
  alias Emel.Ml.KNearestNeighbors, as: KNN

  dataset = [
    %{"x1" => 0.0, "x2" => 0.0, "x3" => 0.0, "y" => 0.0},
    %{"x1" => 0.5, "x2" => 0.5, "x3" => 0.5, "y" => 1.5},
    %{"x1" => 1.0, "x2" => 1.0, "x3" => 1.0, "y" => 3.0},
    %{"x1" => 1.5, "x2" => 1.5, "x3" => 1.5, "y" => 4.5},
    %{"x1" => 2.0, "x2" => 2.0, "x3" => 2.0, "y" => 6.0},
    %{"x1" => 2.5, "x2" => 2.5, "x3" => 2.5, "y" => 7.5},
    %{"x1" => 3.0, "x2" => 3.3, "x3" => 3.0, "y" => 9.0}
  ]

  # turn the dataset into a function
  f = KNN.predictor(dataset, ["x1", "x2", "x3"], "y", 2)

  # make predictions
  f.(%{"x1" => 1.725, "x2" => 1.725, "x3" => 1.725})
  # 5.25

### Implemented Algorithms

  alias Emel.Ml.DecisionTree, as: DecisionTree
  alias Emel.Help.Model, as: Mdl
  alias Emel.Math.Statistics, as: Stat

  dataset = [
    %{risk: "high", collateral: "none", income: "low", debt: "high", credit_history: "bad"},
    %{risk: "high", collateral: "none", income: "moderate", debt: "high", credit_history: "unknown"},
    %{risk: "moderate", collateral: "none", income: "moderate", debt: "low", credit_history: "unknown"},
    %{risk: "high", collateral: "none", income: "low", debt: "low", credit_history: "unknown"},
    %{risk: "low", collateral: "none", income: "high", debt: "low", credit_history: "unknown"},
    %{risk: "low", collateral: "adequate", income: "high", debt: "low", credit_history: "unknown"},
    %{risk: "high", collateral: "none", income: "low", debt: "low", credit_history: "bad"},
    %{risk: "moderate", collateral: "adequate", income: "high", debt: "low", credit_history: "bad"},
    %{risk: "low", collateral: "none", income: "high", debt: "low", credit_history: "good"},
    %{risk: "low", collateral: "adequate", income: "high", debt: "high", credit_history: "good"},
    %{risk: "high", collateral: "none", income: "low", debt: "high", credit_history: "good"},
    %{risk: "moderate", collateral: "none", income: "moderate", debt: "high", credit_history: "good"},
    %{risk: "low", collateral: "none", income: "high", debt: "high", credit_history: "good"},
    %{risk: "high", collateral: "none", income: "moderate", debt: "high", credit_history: "bad"}
  ]

  {training_set, test_set} = Mdl.training_and_test_sets(dataset, 0.75)

  f = DecisionTree.classifier(training_set, [:collateral, :income, :debt, :credit_history], :risk)

  predictions = Enum.map(test_set, fn row -> f.(row) end)
  actual_values = Enum.map(test_set, fn %{risk: v} -> v end)
  Stat.similarity(predictions, actual_values)
  # 0.75

### Mathematics