Module: MachineLearningWorkbench::Tools::Normalization

Defined in:
lib/machine_learning_workbench/tools/normalization.rb

Class Method Summary collapse

Class Method Details

.feature_scaling(narr, from: nil, to: [0,1]) ⇒ Object 



5
6
7
8
9
10
11
12
13
 
# File 'lib/machine_learning_workbench/tools/normalization.rb', line 5

def self.feature_scaling narr, from: nil, to: [0,1]
  from ||= narr.minmax
  old_min, old_max = from
  new_min, new_max = to
  ( (narr-old_min)*(new_max-new_min)/(old_max-old_min) ) + new_min
rescue ZeroDivisionError
  # require 'pry'; binding.pry
  raise ArgumentError, "If you get here, chances are there's a bug in `from` or `to`"
end

.z_score(narr, per_column: true) ⇒ Object

Parameters:

  • per_column (bool) (defaults to: true) —

    wheather to compute stats per-column or matrix-wise

Raises:

  • (NotImplementedError) 


16
17
18
19
20
21
22
23
24
25
26
 
# File 'lib/machine_learning_workbench/tools/normalization.rb', line 16

def self.z_score narr, per_column: true
  raise NotImplementedError unless per_column
  raise "this would be a good time to test this implementation"
  means = narr.mean
  stddevs = narr.std
  # address edge case of zero variance
  stddevs.map! { |v| v.zero? ? 1 : v }
  mean_mat = means.repeat narr.rows, 0
  stddev_mat = stddevs.repeat narr.rows, 0
  (narr - mean_mat) / stddev_mat
end