require 'daru'
require 'rbplotly'
require 'daru/plotly'
require 'statsample'

wine = Daru::DataFrame.from_csv('./winequality-both.csv')
wine.head 10 # 最初の10行を表示

wine['type'].uniq.to_a

reds = wine.where(wine['type'].eq('red'))
reds.head 10

whites = wine.where(wine['type'].eq 'white')
whites.head 10

include Daru::Plotly::Methods # plot, generate_data

red_qualities = generate_data(reds['quality'], type: :histogram, opts: { name: 'red', marker: { color: '#80273F' } })
white_qualities = generate_data(whites['quality'], type: :histogram, opts: { name: 'white', marker: { color: 'white' }})
Plotly::Plot.new(
  data: red_qualities + white_qualities,
  layout: { paper_bgcolor: 'silver', plot_bgcolor: 'silver', font: { color: 'white' } }
).show

reds['quality'].mean # 平均値

whites['quality'].mean

Statsample::Analysis.store(Statsample::Test::T) do
  t = Statsample::Test.t_two_samples_independent(reds['quality'], whites['quality'])
  summary t
end
Statsample::Analysis.run_batch

wine.corr

plot(wine.corr, type: :heatmap).show