require 'daru'
require 'distribution'
require 'gnuplotrb'

vector = Daru::Vector.new(
  [20,40,25,50,45,12], index: ['cherry', 'apple', 'barley', 'wheat', 'rice', 'sugar'], 
  name: "Prices of stuff.")

vector['rice']

vector['rice', 'wheat', 'sugar']

vector['barley'..'sugar']

vector['barley'] = 1500
vector

df = Daru::DataFrame.new({
  'col0' => [1,2,3,4,5,6],
  'col2' => ['a','b','c','d','e','f'],
  'col1' => [11,22,33,44,55,66]
  }, 
  index: ['one', 'two', 'three', 'four', 'five', 'six'], 
  order: ['col0', 'col1', 'col2']
)

df['col1']

df['col2', 'col0']

df['col1'..'col2']

df['col1'] = Daru::Vector.new(['this', 'is', 'some','new','data','here'], 
  index: ['one', 'three','two','six','four', 'five'])
df

df.row['four']

df.row['three'..'five']

df.row['five'] = [666,555,333]

vector = Daru::Vector.new([1,3,5,nil,2,53,nil])
vector.mean

df.mean

df.describe

index = Daru::DateTimeIndex.date_range(:start => '2012', :periods => 1000, :freq => '3D')

timeseries = Daru::Vector.new(1000.times.map {rand}, index: index)

timeseries['2012']

timeseries['2012-3']

timeseries['2012-3-10']

index      = Daru::DateTimeIndex.date_range(
  :start => '2012-3-23 11:00', :periods => 20000, :freq => 'S')

seconds_ts = Daru::Vector.new(20000.times.map { rand(50) }, index: index)
seconds_ts['2012-3-23 12:42']

df = Daru::DataFrame.new({
  :temperature => [30.4, 23.5, 44.5, 20.3, 34, 24, 31.45, 28.34, 37, 24],
  :sales       => [350, 150, 500, 200, 480, 250, 330, 400, 420, 560],
  :city        => ['Pune', 'Delhi']*5,
  :staff       => [15,20]*5
})
df

df.plot(type: :scatter, x: :temperature, y: :sales) do |plot, diagram|
  plot.x_label "Temperature"
  plot.y_label "Sales"
  plot.yrange [100, 600]
  plot.xrange [15, 50]
  diagram.tooltip_contents([:city, :staff])
  # Set the color scheme for this diagram.
  diagram.color(Nyaplot::Colors.qual) 
  # Change color of each point WRT to the city that it belongs to.
  diagram.fill_by(:city)
  # Shape each point WRT to the city that it belongs to.
  diagram.shape_by(:city) 
end

rng = Distribution::Normal.rng

index  = Daru::DateTimeIndex.date_range(:start => '2012-4-2', :periods => 1000)
vector = Daru::Vector.new(1000.times.map {rng.call}, index: index)
vector = vector.cumsum
rolling_mean = vector.rolling_mean 60

GnuplotRB::Plot.new(
  [vector      , with: 'lines', title: 'Vector'], 
  [rolling_mean, with: 'lines', title: 'Rolling Mean'],
  xlabel: 'Time', ylabel: 'Value'
)

df = Daru::DataFrame.new({
  a: [1,2,3,4,5,6]*100,
  b: ['a','b','c','d','e','f']*100,
  c: [11,22,33,44,55,66]*100
}, index: (1..600).to_a.shuffle)
df

df.where(df[:a].eq(2).or(df[:c].eq(55)))