Powered by AppSignal & Oban Pro
Would you like to see your link here? Contact us
Notesclub

EXGBoost Titanic

livebooks/exgboost/titanic.livemd

EXGBoost Titanic

Mix.install([
  {:exgboost, "~> 0.5"},
  {:explorer, "~> 0.8"},
  {:nx, "~> 0.6"},
  {:kino, "~> 0.12"},
  {:kino_vega_lite, "~> 0.1"}
])

Alias

alias Explorer.DataFrame
alias Explorer.Series
require Explorer.DataFrame

Load data

train_data_input = Kino.Input.file("train data")
test_data_input = Kino.Input.file("test data")
train_data =
  train_data_input
  |> Kino.Input.read()
  |> Map.get(:file_ref)
  |> Kino.Input.file_path()
  |> DataFrame.from_csv!()

Kino.DataTable.new(train_data)
test_data =
  test_data_input
  |> Kino.Input.read()
  |> Map.get(:file_ref)
  |> Kino.Input.file_path()
  |> DataFrame.from_csv!()

Kino.DataTable.new(test_data)

Preprocess

defmodule Preprocess do
  defp load_csv(kino_input) do
    kino_input
    |> Kino.Input.read()
    |> Map.get(:file_ref)
    |> Kino.Input.file_path()
    |> DataFrame.from_csv!()
  end

  defp fill_empty(data, fill_map) do
    fill_map
    |> Enum.reduce(data, fn {column_name, fill_value}, acc ->
      DataFrame.put(
        acc,
        column_name,
        Series.fill_missing(data[column_name], fill_value)
      )
    end)
  end

  defp replace_dummy(data, columns_names) do
    data
    |> DataFrame.dummies(columns_names)
    |> DataFrame.concat_columns(DataFrame.discard(data, columns_names))
  end

  defp to_tensor(data) do
    data
    |> DataFrame.to_columns()
    |> Map.values()
    |> Nx.tensor()
    |> Nx.transpose()
  end

  def process(kino_input, id_key, label_key) do
    data_org = load_csv(kino_input)

    id_list = Series.to_list(data_org[id_key])

    has_label_key =
      data_org
      |> DataFrame.names()
      |> Enum.member?(label_key)

    labels =
      if has_label_key do
        Series.to_tensor(data_org[label_key])
      else
        nil
      end

    inputs =
      if has_label_key do
        DataFrame.discard(data_org, [label_key])
      else
        data_org
      end
      |> DataFrame.discard([id_key, "Cabin", "Name", "Ticket"])
      |> fill_empty(%{"Age" => 0.0, "Embarked" => "S", "Fare" => 0.0})
      |> replace_dummy(["Sex", "Embarked"])
      |> to_tensor()

    {id_list, labels, inputs}
  end
end
{
  train_id_list,
  train_labels,
  train_inputs
} = Preprocess.process(train_data_input, "PassengerId", "Survived")
{
  test_id_list,
  nil,
  test_inputs
} = Preprocess.process(test_data_input, "PassengerId", "Survived")

Training

loss_plot =
  VegaLite.new(width: 700)
  |> VegaLite.mark(:line)
  |> VegaLite.encode_field(:x, "step", type: :quantitative)
  |> VegaLite.encode_field(:y, "mlogloss", type: :quantitative)
  |> Kino.VegaLite.new()
step_callback =
  EXGBoost.Training.Callback.new(
    :after_iteration,
    fn state ->
      if rem(state.iteration, 1000) == 0 do
        Kino.VegaLite.push(
          loss_plot,
          %{"step" => state.iteration, "mlogloss" => state.metrics["training"]["mlogloss"]}
        )
      end

      state
    end,
    :loss_plot
  )
booster =
  EXGBoost.train(train_inputs, train_labels,
    num_class: 2,
    objective: :multi_softprob,
    num_boost_rounds: 200_000,
    learning_rates: fn _ -> 0.1 end,
    max_depth: 6,
    early_stopping_rounds: 10,
    evals: [{train_inputs, train_labels, "training"}],
    callbacks: [step_callback]
  )

Kino.nothing()

Prediction

preds = EXGBoost.predict(booster, test_inputs) |> Nx.argmax(axis: -1)
results =
  preds
  |> Nx.to_flat_list()
  |> Enum.map(&round(&1))
  |> then(
    &%{
      "PassengerId" => test_id_list,
      "Survived" => &1
    }
  )
  |> DataFrame.new()

Kino.DataTable.new(results)
results
|> DataFrame.dump_csv!()
|> then(&Kino.Download.new(fn -> &1 end, filename: "result.csv"))