Note : Examples are taken from daru : http://nbviewer.jupyter.org/github/SciRuby/sciruby-notebooks/blob/master/Data%20Analysis/Plotting/Visualization.ipynb

In [1]:

require 'daru/view'

Install the spreadsheet gem version ~>1.1.1 for using spreadsheet functions.

Install the mechanize gem version ~>2.7.5 for using mechanize functions.

Out[1]:

true

In [2]:

Daru::View.plotting_library = :nyaplot

Out[2]:

:nyaplot

Categorical Vector Visualization¶

In [3]:

dv = Daru::Vector.new [:a, :a, :a, :b, :b, :c], type: :category

Out[3]:

Daru::Vector(6):category

0	a
1	a
2	a
3	b
4	b
5	c

Bar graph¶

1. Frequency (count)¶

In [4]:

bar_graph1 = Daru::View::Plot.new(dv, type: :bar)

Out[4]:

#<Daru::View::Plot:0x00000003b87dd0 @data=#<Daru::Vector(6):category>
   0   a
   1   a
   2   a
   3   b
   4   b
   5   c, @options={:type=>:bar, :method=>:count}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x00000003b876f0 @properties={:diagrams=>[#<Nyaplot::Diagram:0x00000003b85f08 @properties={:type=>:bar, :options=>{:x=>"data0", :y=>"data1"}, :data=>"d2703cc9-f28f-4c6a-adcf-3be6187d1969"}, @xrange=[:a, :b, :c], @yrange=[0, 3]>], :options=>{}}>>

In [5]:

bar_graph1.chart.class

Out[5]:

Nyaplot::Plot

In [6]:

bar_graph1.show_in_iruby

Out[6]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

In [7]:

dv = Daru::Vector.new ['III']*10 + ['II']*5 + ['I']*5, type: :category, categories: ['I', 'II', 'III']
dv.type

Out[7]:

:category

In [8]:

bar_graph2 = Daru::View::Plot.new(dv, type: :bar)

Out[8]:

#<Daru::View::Plot:0x00000003a3ca20 @data=#<Daru::Vector(20):category>
   0 III
   1 III
   2 III
   3 III
   4 III
   5 III
   6 III
   7 III
   8 III
   9 III
  10  II
  11  II
  12  II
  13  II
  14  II
 ... ..., @options={:type=>:bar, :method=>:count}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x00000003a3c930 @properties={:diagrams=>[#<Nyaplot::Diagram:0x00000003a33600 @properties={:type=>:bar, :options=>{:x=>"data0", :y=>"data1"}, :data=>"5c7ce333-5a85-4667-99dc-70f28f8c1f03"}, @xrange=["I", "II", "III"], @yrange=[0, 10]>], :options=>{}}>>

In [9]:

bar_graph2.class

Out[9]:

Daru::View::Plot

In [10]:

bar_graph2.chart.class

Out[10]:

Nyaplot::Plot

In [11]:

# Nyaplot methods will work.Since #chart is Nyaplot::Plot class object
bar_graph2.chart.x_label 'Cat'
bar_graph2.chart.y_label 'Frequency'

Out[11]:

In [12]:

bar_graph2.chart # or bar_graph2.show_in_iruby

Out[12]:

2. Percentage¶

In [13]:

bar_graph2_per = Daru::View::Plot.new(dv, type: :bar, method: :percentage)

Out[13]:

#<Daru::View::Plot:0x00000003192668 @data=#<Daru::Vector(20):category>
   0 III
   1 III
   2 III
   3 III
   4 III
   5 III
   6 III
   7 III
   8 III
   9 III
  10  II
  11  II
  12  II
  13  II
  14  II
 ... ..., @options={:type=>:bar, :method=>:percentage}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x00000003192500 @properties={:diagrams=>[#<Nyaplot::Diagram:0x00000003190890 @properties={:type=>:bar, :options=>{:x=>"data0", :y=>"data1"}, :data=>"4cfa1107-b2e6-49bb-9c04-375158cfe800"}, @xrange=["I", "II", "III"], @yrange=[0, 50.0]>], :options=>{:yrange=>[0, 100]}}>>

In [14]:

bar_graph2_per.chart.x_label 'Categories'
bar_graph2_per.chart.y_label 'Percentage (%)'
bar_graph2_per.show_in_iruby

Out[14]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

3. Fraction¶

In [15]:

bar_graph2_frac = Daru::View::Plot.new(dv, type: :bar, method: :fraction)

Out[15]:

#<Daru::View::Plot:0x00000002edcbd0 @data=#<Daru::Vector(20):category>
   0 III
   1 III
   2 III
   3 III
   4 III
   5 III
   6 III
   7 III
   8 III
   9 III
  10  II
  11  II
  12  II
  13  II
  14  II
 ... ..., @options={:type=>:bar, :method=>:fraction}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x00000002edcb58 @properties={:diagrams=>[#<Nyaplot::Diagram:0x00000002ed19d8 @properties={:type=>:bar, :options=>{:x=>"data0", :y=>"data1"}, :data=>"9d2ff911-93f1-4a5e-b266-e403eafe49b5"}, @xrange=["I", "II", "III"], @yrange=[0, 0.5]>], :options=>{:yrange=>[0, 1]}}>>

In [16]:

# bar_graph2_frac.chart.x_label 'Categories'
bar_graph2_frac.chart.y_label 'Fraction'
bar_graph2_frac.show_in_iruby

Out[16]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

Categorical data visualization in Dataframe¶

Bar Graph¶

In [17]:

df = Daru::DataFrame.new({
  a: [1, 2, 4, -2, 5, 23, 0],
  b: [3, 1, 3, -6, 2, 1, 0],
  c: ['I', 'II', 'I', 'III', 'I', 'III', 'II']
  })
df.to_category :c
df[:c].type

Out[17]:

:category

In [18]:

bar_graph3 = Daru::View::Plot.new(df, type: :bar, x: :c)

Out[18]:

#<Daru::View::Plot:0x0000000274ff48 @data=#<Daru::DataFrame(7x3)>
       a   b   c
   0   1   3   I
   1   2   1  II
   2   4   3   I
   3  -2  -6 III
   4   5   2   I
   5  23   1 III
   6   0   0  II, @options={:type=>:bar, :x=>:c}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x0000000274e9e0 @properties={:diagrams=>[#<Nyaplot::Diagram:0x0000000266e4d0 @properties={:type=>:bar, :options=>{:value=>:c}, :data=>"71214b09-e3c4-48cf-95d1-5000d0600ded"}, @xrange=["I", "II", "III"], @yrange=[0, 7]>], :options=>{}}>>

In [19]:

bar_graph3.show_in_iruby

Out[19]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

Scatter plot categorized by categorical variable¶¶

Plots can be categorized by¶

Color
Size
Shape

In [20]:

df = Daru::DataFrame.new({
  a: [1, 2, 4, -2, 5, 23, 0],
  b: [3, 1, 3, -6, 2, 1, 0],
  c: ['I', 'II', 'I', 'III', 'I', 'III', 'II']
  })
df.to_category :c
df[:c].type

Out[20]:

:category

In [21]:

scatter_1 = Daru::View::Plot.new(df, type: :scatter, x: :a, y: :b, categorized: {by: :c, method: :color})

Out[21]:

#<Daru::View::Plot:0x00000003c12f70 @data=#<Daru::DataFrame(7x3)>
       a   b   c
   0   1   3   I
   1   2   1  II
   2   4   3   I
   3  -2  -6 III
   4   5   2   I
   5  23   1 III
   6   0   0  II, @options={:type=>:scatter, :x=>:a, :y=>:b, :categorized=>{:by=>:c, :method=>:color}}, @adapter=Daru::View::Adapter::NyaplotAdapter, @chart=#<Nyaplot::Plot:0x00000003c12e58 @properties={:diagrams=>[#<Nyaplot::Diagram:0x00000003c07648 @properties={:type=>:scatter, :options=>{:x=>:a, :y=>:b, :title=>"I", :color=>"rgb(141,211,199)", :tooltip_contents=>["I", "I", "I"]}, :data=>"00976c4d-e2ef-4329-8154-3c8442b6494c"}, @xrange=[1, 5], @yrange=[2, 3]>, #<Nyaplot::Diagram:0x00000003bfd350 @properties={:type=>:scatter, :options=>{:x=>:a, :y=>:b, :title=>"II", :color=>"rgb(255,255,179)", :tooltip_contents=>["II", "II"]}, :data=>"6f96eb03-6646-4b90-9396-375d8821d5cb"}, @xrange=[0, 2], @yrange=[0, 1]>, #<Nyaplot::Diagram:0x00000003befd40 @properties={:type=>:scatter, :options=>{:x=>:a, :y=>:b, :title=>"III", :color=>"rgb(190,186,218)", :tooltip_contents=>["III", "III"]}, :data=>"36e2cd12-ae08-4302-8438-eeb6fd1b29f1"}, @xrange=[-2, 23], @yrange=[-6, 1]>], :options=>{:legend=>true}}>>

In [22]:

scatter_1.show_in_iruby

Out[22]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

In [23]:

scatter_1.chart.xrange [-10, 10]
scatter_1.chart.yrange [-10, 10]

Out[23]:

In [24]:

scatter_2 = Daru::View::Plot.new(df, type: :scatter, x: :a, y: :b, categorized: {by: :c, method: :shape})
scatter_2.show_in_iruby

Out[24]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

In [25]:

scatter_2.chart.xrange [-10, 10]
scatter_2.chart.yrange [-10, 10]

Out[25]:

In [26]:

scatter_3 = Daru::View::Plot.new(df, type: :scatter, x: :a, y: :b, categorized: {by: :c, method: :color, color: [:red, :blue, :green]})
scatter_3.show_in_iruby
scatter_2.chart.xrange [-10, 10]
scatter_2.chart.yrange [-10, 10]

Out[26]:

In [27]:

scatter_4 = Daru::View::Plot.new(df, type: :scatter, x: :a, y: :b, categorized: {by: :c, method: :size, size: [300, 600, 900]})
scatter_4.show_in_iruby
scatter_4.chart.xrange [-10, 10]
scatter_4.chart.yrange [-10, 10]

Out[27]:

Line plot categorized by categorical variable¶

It works similar to Scatter plot above and all options are same except that there's no categorization by size but instead there is categorization by stroke_width in line plots.

In [28]:

df = Daru::DataFrame.new({
  a: [1, 2, 3, 4, 5, 6, 7, 8, 9],
  b: [2, 4, 6, 1, 3, 5, 6, 4, 3],
  c: ['I']*3 + ['II']*3 + ['III']*3
  })
df.to_category :c
df[:c].type

Out[28]:

:category

In [29]:

line_1 = Daru::View::Plot.new(df, type: :line, x: :a, y: :b, categorized: {by: :c, method: :color})
line_1.show_in_iruby

Out[29]:

#<CZTop::Socket::PUB:0x35d48a0 last_endpoint="tcp://127.0.0.1:49287">

In [30]:

line_2 = Daru::View::Plot.new(df, type: :line, x: :a, y: :b, categorized: {by: :c, method: :stroke_width})
line_2.show_in_iruby
line_2.chart.xrange [-10, 10]
line_2.chart.yrange [-10, 10]

Out[30]:

In [ ]: