Class: Statsample::Regression::Multiple::GslEngine

Inherits:
BaseEngine show all
Defined in:
lib/statsample/regression/multiple/gslengine.rb

Overview

Class for Multiple Regression Analysis Requires rbgsl and uses a listwise aproach. Slower on prediction of values than Alglib, because predict is ruby based. Better memory management on multiple (+1000) series of regression. If you need pairwise, use RubyEngine Example:

@a = Daru::Vector.new([1,3,2,4,3,5,4,6,5,7])
@b = Daru::Vector.new([3,3,4,4,5,5,6,6,4,4])
@c = Daru::Vector.new([11,22,30,40,50,65,78,79,99,100])
@y = Daru::Vector.new([3,4,5,6,7,8,9,10,20,30])
ds = Daru::DataFrame.new({:a => @a,:b => @b,:c => @c,:y => @y})
lr=Statsample::Regression::Multiple::GslEngine.new(ds,:y)

Instance Attribute Summary

Attributes inherited from BaseEngine

#cases, #digits, #name, #total_cases, #valid_cases

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from BaseEngine

#anova, #assign_names, #coeffs_t, #coeffs_tolerances, #constant_se, #constant_t, #df_e, #df_r, #estimated_variance_covariance_matrix, #f, #mse, #msr, #predicted, #probability, #process, #r2_adjusted, #report_building, #residuals, #se_estimate, #se_r2, #sse, #sse_direct, #ssr, #ssr_direct, #standarized_predicted, #tolerance, univariate?

Methods included from Summarizable

#summary

Constructor Details

#initialize(ds, y_var, opts = Hash.new) ⇒ GslEngine

Returns a new instance of GslEngine.



20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
# File 'lib/statsample/regression/multiple/gslengine.rb', line 20

def initialize(ds,y_var, opts=Hash.new)
  super
  @ds          = ds.reject_values(*Daru::MISSING_VALUES)
  @ds_valid    = @ds
  @valid_cases = @ds_valid.nrows
  @dy          = @ds[@y_var]
  @ds_indep    = ds.dup(ds.vectors.to_a - [y_var])
  # Create a custom matrix
  columns=[]
  @fields=[]
  max_deps = GSL::Matrix.alloc(@ds.nrows, @ds.vectors.size)
  constant_col=@ds.vectors.size-1
  for i in 0...@ds.nrows
    max_deps.set(i,constant_col,1)
  end
  j = 0
  @ds.vectors.each do |f|
    if f != @y_var
      @ds[f].each_index do |i1|
        max_deps.set(i1,j,@ds[f][i1])
      end

      columns.push(@ds[f].to_a)
      @fields.push(f)
      j += 1
    end
  end
  @dep_columns = columns.dup
  @lr_s        = nil
  c, @cov, @chisq, @status = GSL::MultiFit.linear(max_deps, @dy.to_gsl)
  @constant=c[constant_col]
  @coeffs_a=c.to_a.slice(0...constant_col)
  @coeffs=assign_names(@coeffs_a)
  c=nil
end

Class Method Details

._load(data) ⇒ Object



59
60
61
62
# File 'lib/statsample/regression/multiple/gslengine.rb', line 59

def self._load(data)
  h=Marshal.load(data)
  self.new(h['ds'], h['y_var'])
end

Instance Method Details

#_dump(i) ⇒ Object



56
57
58
# File 'lib/statsample/regression/multiple/gslengine.rb', line 56

def _dump(i)
  Marshal.dump({'ds'=>@ds,'y_var'=>@y_var})
end

#build_standarizedObject



100
101
102
103
# File 'lib/statsample/regression/multiple/gslengine.rb', line 100

def build_standarized
  @ds_s=@ds.standardize
  @lr_s=GslEngine.new(@ds_s,@y_var)
end

#coeffsObject



64
65
66
# File 'lib/statsample/regression/multiple/gslengine.rb', line 64

def coeffs
  @coeffs
end

#coeffs_seObject

Standard error for coeffs



115
116
117
118
119
120
121
122
123
124
# File 'lib/statsample/regression/multiple/gslengine.rb', line 115

def coeffs_se
  out  = {}
  evcm = estimated_variance_covariance_matrix
  @ds_valid.vectors.to_a.each_with_index do |f,i|
    mi = i+1
    next if f == @y_var
    out[f] = evcm[mi,mi]
  end
  out
end

#constantObject



87
88
89
# File 'lib/statsample/regression/multiple/gslengine.rb', line 87

def constant
  @constant
end

#lr_sObject



94
95
96
97
98
99
# File 'lib/statsample/regression/multiple/gslengine.rb', line 94

def lr_s
  if @lr_s.nil?
    build_standarized
  end
  @lr_s
end

#matrix_resolutionObject

Coefficients using a constant Based on www.xycoon.com/ols1.htm



69
70
71
72
73
74
75
76
77
# File 'lib/statsample/regression/multiple/gslengine.rb', line 69

def matrix_resolution
  columns=@dep_columns.dup.map {|xi| xi.map{|i| i.to_f}}
  columns.unshift([1.0]*@ds.cases)
  y=Matrix.columns([@dy.data.map  {|i| i.to_f}])
  x=Matrix.columns(columns)
  xt=x.t
  matrix=((xt*x)).inverse*xt
  matrix*y
end

#process_s(v) ⇒ Object



104
105
106
# File 'lib/statsample/regression/multiple/gslengine.rb', line 104

def process_s(v)
  lr_s.process(v)
end

#rObject



81
82
83
# File 'lib/statsample/regression/multiple/gslengine.rb', line 81

def r
  Bivariate::pearson(@dy, predicted)
end

#r2Object



78
79
80
# File 'lib/statsample/regression/multiple/gslengine.rb', line 78

def r2
  r**2
end

#sstObject



84
85
86
# File 'lib/statsample/regression/multiple/gslengine.rb', line 84

def sst
  @dy.ss
end

#standarized_coeffsObject



90
91
92
93
# File 'lib/statsample/regression/multiple/gslengine.rb', line 90

def standarized_coeffs
  l=lr_s
  l.coeffs
end

#standarized_residualsObject

???? Not equal to SPSS output



108
109
110
111
112
# File 'lib/statsample/regression/multiple/gslengine.rb', line 108

def standarized_residuals
  res=residuals
  red_sd=residuals.sds
  Daru::Vector.new(res.collect {|v| v.quo(red_sd) })
end