statsample 1.5.0 → 2.0.0

data/examples/dataset.rb

@@ -1,14 +1,34 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
+# == Description
+#
+# This example demonstrates creation of basic Vectors and DataFrames.
 require 'statsample'
 
-Statsample::Analysis.store(Statsample::Dataset) do
-  samples=1000
-  a=Statsample::Vector.new_numeric(samples) {r=rand(5); r==4 ? nil: r}
-  b=Statsample::Vector.new_numeric(samples) {r=rand(5); r==4 ? nil: r}
+Statsample::Analysis.store(Daru::DataFrame) do
+  # We set lazy_update to *true* so that time is not wasted in updating
+  # metdata every time an assignment happens.
+  Daru.lazy_update = true
 
-  ds={'a'=>a,'b'=>b}.to_dataset
+  samples = 1000
+
+  # The 'new_with_size' function lets you specify the size of the 
+  # vector as the argument and the block specifies how each element
+  # of the vector will be created.
+  a = Daru::Vector.new_with_size(samples) {r=rand(5); r==4 ? nil: r}
+  b = Daru::Vector.new_with_size(samples) {r=rand(5); r==4 ? nil: r}
+
+  # Pass the Daru::Vector objects in a Hash to the DataFrame constructor
+  # to make a DataFrame.
+  # 
+  # The *order* option lets you specify the way the vectors in the Hash 
+  # will be ordered. Not specifyin this will order vectors in alphabetical
+  # order by default.
+  ds = Daru::DataFrame.new({:a=>a,:b=>b}, order: [:b, :a])
   summary(ds)
+
+  # Reset lazy_update to *false* to prevent other code from breaking.
+  Daru.lazy_update = false
 end
 
 if __FILE__==$0

data/examples/dominance_analysis.rb

@@ -1,9 +1,10 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
+# == Description
+#
+# Dominance Analysis with statsample
 require 'statsample'
-
-
 Statsample::Analysis.store(Statsample::DominanceAnalysis) do
   sample=300
   a=rnorm(sample)
@@ -11,17 +12,17 @@ Statsample::Analysis.store(Statsample::DominanceAnalysis) do
   c=rnorm(sample)
   d=rnorm(sample)
   
-  ds={'a'=>a,'b'=>b,'cc'=>c,'d'=>d}.to_dataset
+  ds = Daru::DataFrame.new({:a => a,:b => b,:cc => c,:d => d}, clone: false)
   attach(ds)
-  ds['y']=a*5+b*3+cc*2+d+rnorm(300)  
+  ds[:y]=a*5 + b*3 + cc*2 + d + rnorm(300)
   cm=cor(ds)
   summary(cm)
-  lr=lr(ds,'y')
+  lr=lr(ds,:y)
   summary(lr)
-  da=dominance_analysis(ds,'y')
+  da=dominance_analysis(ds,:y)
   summary(da)
   
-  da=dominance_analysis(ds,'y',:name=>"Dominance Analysis using group of predictors", :predictors=>['a', 'b', %w{cc d}])
+  da = dominance_analysis(ds,:y,:name=>"Dominance Analysis using group of predictors", :predictors=>[:a, :b, [:cc, :d]])
   summary(da)
 end
 

data/examples/dominance_analysis_bootstrap.rb

@@ -3,29 +3,34 @@ $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::DominanceAnalysis::Bootstrap) do
-  
+  # Remember to call *update* after an assignment/deletion cycle if lazy_update
+  # is *false*.
+  Daru.lazy_update = true
+
   sample=300
   a=rnorm(sample)
   b=rnorm(sample)
   c=rnorm(sample)
   d=rnorm(sample)  
-  a.name="a"
-  b.name="b"
-  c.name="c"
-  d.name="d"
+  a.rename :a
+  b.rename :b
+  c.rename :c
+  d.rename :d
   
-  ds={'a'=>a,'b'=>b,'cc'=>c,'d'=>d}.to_dataset
+  ds = Daru::DataFrame.new({:a => a,:b => b,:cc => c,:d => d})
   attach(ds)
-  ds['y1']=a*5+b*2+cc*2+d*2+rnorm(sample,0,10)
-  ds['y2']=a*10+rnorm(sample)
+  ds[:y1] = a*5  + b*2 + cc*2 + d*2 + rnorm(sample,0,10)
+  ds[:y2] = a*10 + rnorm(sample)
   
-  dab=dominance_analysis_bootstrap(ds, ['y1','y2'], :debug=>true)
+  dab=dominance_analysis_bootstrap(ds, [:y1,:y2], :debug=>true)
   dab.bootstrap(100,nil)
   summary(dab)
-  ds2=ds['a'..'y1']
-  dab2=dominance_analysis_bootstrap(ds2, 'y1', :debug=>true)
+  ds2=ds[:a..:y1]
+  dab2=dominance_analysis_bootstrap(ds2, :y1, :debug=>true)
   dab2.bootstrap(100,nil)
   summary(dab2)
+
+  Daru.lazy_update = false
 end
 
 if __FILE__==$0

data/examples/histogram.rb

@@ -1,12 +1,26 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+# == Description
+# 
+# This example demonstrates how a histogram can be created 
+# with statsample.
+# 
+# The 'histogram' function creates a histogram by using the 
+# Statsample::Graph::Histogram class. This class accepts data 
+# in a Daru::Vector (as created by `rnorm`).
+# 
+# A line showing normal distribution can be drawn by setting 
+# the `:line_normal_distribution` option to *true*.
+# 
+# See this notebook for an illustration: 
+# http://nbviewer.ipython.org/github/SciRuby/sciruby-notebooks/blob/master/statistics/Creating%20a%20Histogram.ipynb
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Graph::Histogram) do
-  histogram(rnorm(3000,0,20))
+  histogram(rnorm(3000,0,20), :line_normal_distribution => true)
 end
 
-
 if __FILE__==$0
    Statsample::Analysis.run
 end

data/examples/icc.rb

@@ -6,18 +6,17 @@ require 'statsample'
 Statsample::Analysis.store(Statsample::Reliability::ICC) do
 
   size=1000
-  a=Statsample::Vector.new_numeric(size) {rand(10)}
-  b=a.recode{|i|i+rand(4)-2}
-  c=a.recode{|i|i+rand(4)-2}
-  d=a.recode{|i|i+rand(4)-2}
-  @ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
+  a = Daru::Vector.new_with_size(size) {rand(10)}
+  b = a.recode{|i|i+rand(4)-2}
+  c = a.recode{|i|i+rand(4)-2}
+  d = a.recode{|i|i+rand(4)-2}
+  @ds = Daru::DataFrame.new({:a => a,:b => b,:c => c,:d => d})
   @icc=Statsample::Reliability::ICC.new(@ds)
   summary(@icc)
   @icc.type=:icc_3_1
   summary(@icc)
   @icc.type=:icc_a_k
   summary(@icc)
-  
 end
 
 if __FILE__==$0

data/examples/levene.rb

@@ -1,15 +1,29 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
+# == Description
+# 
+# This example demonstrates how a levene test can be performed by
+# using Daru::Vector and the Statsample::Test::Levene class.
+# 
+# Levene's test is an inferential statistic used to assess the
+# equality of variances for a variable calculated for two or more groups.
+# 
+# == References
+# 
+# http://en.wikipedia.org/wiki/Levene%27s_test
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Test::Levene) do
 
-  a=[1,2,3,4,5,6,7,8,100,10].to_numeric
-  b=[30,40,50,60,70,80,90,100,110,120].to_numeric
+  a = Daru::Vector.new([1,2,3,4,5,6,7,8,100,10])
+  b = Daru::Vector.new([30,40,50,60,70,80,90,100,110,120])
+
+  # The 'levene' function is used as a shorthand 
+  # for creating a Statsample::Test::Levene object.
   summary(levene([a,b]))
 end
 
 if __FILE__==$0
-   Statsample::Analysis.run_batch
+  Statsample::Analysis.run_batch
 end

data/examples/multiple_regression.rb

@@ -1,15 +1,18 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
+# == Description
+# 
+# This example shows how multiple regression can be performed using statsample and daru.
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Regression::Multiple) do
 
   samples=2000
-  ds=dataset('a'=>rnorm(samples),'b'=>rnorm(samples),'cc'=>rnorm(samples),'d'=>rnorm(samples))
+  ds=dataset(:a => rnorm(samples),:b => rnorm(samples),:cc => rnorm(samples),:d => rnorm(samples))
   attach(ds)
-  ds['y']=a*5+b*3+cc*2+d+rnorm(samples)
-  summary lr(ds,'y')
+  ds[:y] = a*5+b*3+cc*2+d+rnorm(samples)
+  summary lr(ds,:y)
 end
 
 if __FILE__==$0

data/examples/parallel_analysis.rb

@@ -1,6 +1,11 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
+# == Description
+#
+# This example will explain how a parallel analysis can be performed on a PCA.
+# Parallel Analysis helps in determining how many components are to be retained
+# from the PCA.
 require 'statsample'
 samples=150
 variables=30
@@ -8,18 +13,18 @@ iterations=50
 Statsample::Analysis.store(Statsample::Factor::ParallelAnalysis) do 
   
 rng = Distribution::Normal.rng()
-f1=rnorm(samples)
-f2=rnorm(samples)
-f3=rnorm(samples)
+f1  = rnorm(samples)
+f2  = rnorm(samples)
+f3  = rnorm(samples)
 
 vectors={}
 
 variables.times do |i|
-  vectors["v#{i}"]=samples.times.collect {|nv| f1[nv]*i+(f2[nv]*(15-i))+((f3[nv]*(30-i))*1.5)*rng.call}.to_numeric
-  vectors["v#{i}"].name="Vector #{i}"
+  vectors["v#{i}".to_sym] = Daru::Vector.new(samples.times.collect {|nv| f1[nv]*i+(f2[nv]*(15-i))+((f3[nv]*(30-i))*1.5)*rng.call})
+  vectors["v#{i}".to_sym].rename "Vector #{i}"
 end
 
-  ds=vectors.to_dataset
+  ds = Daru::DataFrame.new(vectors)
 
   pa=Statsample::Factor::ParallelAnalysis.new(ds, :iterations=>iterations, :debug=>true)
   pca=pca(cor(ds))

data/examples/polychoric.rb

@@ -1,26 +1,39 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
-$:.unshift("/home/cdx/usr/lib/statsample-bivariate-extension/lib/")
 
+# == Description
+# Polychoric Correlation using two-step and joint method
+#
+# Polychoric correlation in statsample requires installation of 
+# the [statsample-bivariate-extension](https://rubygems.org/gems/statsample-bivariate-extension) 
+# gem. This gem extends the Statsample::Bivariate class with useful 
+# algorithms for polychoric and tetrachoric correlation.
+# 
+# Statsample will automatically detect presence of polychoric/tetrachoric 
+# algorithms so there is no need to explicitly require the gem.
+# 
+# In this example we'll see how polychoric correlation can be 
+# performed using statsample.
 require 'statsample'
 Statsample::Analysis.store(Statsample::Bivariate::Polychoric) do 
-ct=Matrix[[rand(10)+50, rand(10)+50,  rand(10)+1],
-          [rand(20)+5,  rand(50)+4,   rand(10)+1],
-          [rand(8)+1,   rand(12)+1,   rand(10)+1]]
+  ct=Matrix[[rand(10)+50, rand(10)+50,  rand(10)+1],
+            [rand(20)+5,  rand(50)+4,   rand(10)+1],
+            [rand(8)+1,   rand(12)+1,   rand(10)+1]]
 
-# Estimation of polychoric correlation using two-step (default)
-poly=polychoric(ct, :name=>"Polychoric with two-step", :debug=>false)
-summary poly
+  # Estimation of polychoric correlation using two-step (default)
+  poly=polychoric(ct, :name=>"Polychoric with two-step", :debug=>false)
+  summary poly
 
-# Estimation of polychoric correlation using joint method (slow)
-poly=polychoric(ct, :method=>:joint, :name=>"Polychoric with joint")
-summary poly
+  # Estimation of polychoric correlation using joint method (slow)
+  poly=polychoric(ct, :method=>:joint, :name=>"Polychoric with joint")
+  summary poly
 
-# Uses polychoric series (not recomended)
+  # Uses polychoric series (not recomended)
 
-poly=polychoric(ct, :method=>:polychoric_series, :name=>"Polychoric with polychoric series")
-summary poly
+  poly=polychoric(ct, :method=>:polychoric_series, :name=>"Polychoric with polychoric series")
+  summary poly
 end
+
 if __FILE__==$0
    Statsample::Analysis.run_batch
 end

data/examples/principal_axis.rb

@@ -1,16 +1,20 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
-
+# Principal Axis Analysis¶
+#
+# Here we use the Statsample::Factor::PrincipalAnalysis class 
+# for principal axis analysis for a correlation or covariance matrix.
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Factor::PrincipalAxis) do
 
   matrix=Matrix[
-  [1.0, 0.709501601093587, 0.877596585880047, 0.272219316266807],  [0.709501601093587, 1.0, 0.291633797330304, 0.871141831433844], [0.877596585880047, 0.291633797330304, 1.0, -0.213373722977167], [0.272219316266807, 0.871141831433844, -0.213373722977167, 1.0]]
+  [1.0, 0.709501601093587, 0.877596585880047, 0.272219316266807],  
+  [0.709501601093587, 1.0, 0.291633797330304, 0.871141831433844], 
+  [0.877596585880047, 0.291633797330304, 1.0, -0.213373722977167], 
+  [0.272219316266807, 0.871141831433844, -0.213373722977167, 1.0]]
   
   matrix.extend Statsample::CovariateMatrix
-  
-  #matrix.fields=%w{a b c d}
   fa=principal_axis(matrix,:m=>1,:smc=>false)
   
   summary fa

data/examples/reliability.rb

@@ -1,27 +1,28 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib')
-require 'statsample'
 
-Statsample::Analysis.store(Statsample::Reliability) do
-  
+# == Description
+#
+# Reliability Scale Analysis with statsample
+require 'statsample'
+Statsample::Analysis.store(Statsample::Reliability) do 
   samples=100
   a=rnorm(samples)
   
-  ds=Statsample::Dataset.new
+  ds = Daru::DataFrame.new({})
   
   20.times do |i|
-    ds["v#{i}"]=a+rnorm(samples,0,0.2)
+    ds["v#{i}".to_sym]= a + rnorm(samples,0,0.2)
   end
   
-  ds.update_valid_data
+  ds.update
   
   rel=Statsample::Reliability::ScaleAnalysis.new(ds)
   summary rel
   
-  
   ms=Statsample::Reliability::MultiScaleAnalysis.new(:name=>"Multi Scale analyss") do |m|
-    m.scale "Scale 1", ds.clone(%w{v1 v2 v3 v4 v5 v6 v7 v8 v9 v10})
-    m.scale "Scale 2", ds.clone(%w{v11 v12 v13 v14 v15 v16 v17 v18 v19})
+    m.scale "Scale 1", ds.clone([:v1, :v2, :v3, :v4, :v5, :v6, :v7, :v8, :v9, :v10])
+    m.scale "Scale 2", ds.clone([:v11, :v12, :v13, :v14, :v15, :v16, :v17, :v18, :v19])
   end
   
   summary ms
@@ -30,4 +31,3 @@ end
 if __FILE__==$0
    Statsample::Analysis.run_batch
 end
-

data/examples/scatterplot.rb

@@ -2,6 +2,14 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 $:.unshift('/home/cdx/dev/reportbuilder/lib/')
 
+# == Description
+#
+# Creating a scatterplot with statsample's Statsample::Graph::Scatterplot class.
+# 
+# In this example we'll demonstrate how a normally distributed Daru::Vector can
+# be created using the daru and distribution gems, and how the values generated
+# can be plotted very easily using the 'scatterplot' shorthand and supplying X
+# and Y co-ordinates.
 require 'benchmark'
 require 'statsample'
 n=100

data/examples/t_test.rb

@@ -1,5 +1,12 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib')
+# == Description
+#
+# This example illustrates how a T test can be done and summarized with statsample
+#
+# == References
+#
+# http://en.wikipedia.org/wiki/Student%27s_t-test
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Test::T) do

data/examples/u_test.rb

@@ -1,11 +1,19 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib')
+
+# == Description
+#
+# Example illustrating Mann-Whitney U test with statsample.
+#
+# == References
+# 
+# http://en.wikipedia.org/wiki/Mann%E2%80%93Whitney_U_test
 require 'statsample'
 
 Statsample::Analysis.store(Statsample::Test::UMannWhitney) do
 
-  a=10.times.map {rand(100)}.to_numeric
-  b=20.times.map {(rand(20))**2+50}.to_numeric
+  a = Daru::Vector.new(10.times.map {rand(100)})
+  b = Daru::Vector.new(20.times.map {(rand(20))**2+50})
 
   u=Statsample::Test::UMannWhitney.new(a,b)
   summary u

data/examples/vector.rb

@@ -1,15 +1,18 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
-
+# == Description
+#
+# This example provides a small sneak-peak into creating a Daru::Vector.
+# For details on using Daru::Vector (with example on math, statistics and plotting)
+# see the notebook at this link: 
+# http://nbviewer.ipython.org/github/SciRuby/sciruby-notebooks/blob/master/Data%20Analysis/Usage%20of%20Vector.ipynb
 require 'statsample'
 
-Statsample::Analysis.store(Statsample::Vector) do
-
-  a=Statsample::Vector.new_numeric(1000) {r=rand(5); r==4 ? nil: r;}
+Statsample::Analysis.store(Daru::Vector) do
+  a = Daru::Vector.new_with_size(1000) {r=rand(5); r==4 ? nil: r;}
   summary a
-  b=c(1,2,3,4,6..10)
+  b = Daru::Vector[1,2,3,4,6..10]
   summary b
-  
 end
 
 if __FILE__==$0