Class: SVMKit::Preprocessing::MinMaxScaler

Inherits:
Object
  • Object
show all
Includes:
Base::BaseEstimator, Base::Transformer
Defined in:
lib/svmkit/preprocessing/min_max_scaler.rb

Overview

Normalize samples by scaling each feature to a given range.

Examples:

normalizer = SVMKit::Preprocessing::MinMaxScaler.new(feature_range: [0.0, 1.0])
new_training_samples = normalizer.fit_transform(training_samples)
new_testing_samples = normalizer.transform(testing_samples)

Instance Attribute Summary collapse

Attributes included from Base::BaseEstimator

#params

Instance Method Summary collapse

Constructor Details

#new(feature_range: [0.0, 1.0]) ⇒ MinMaxScaler

Creates a new normalizer for scaling each feature to a given range.

Parameters:

  • feature_range (Array) —

    (defaults to: [0.0, 1.0]) The desired range of samples.



35
36
37
38
39
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 35

def initialize(params = {})
  @params = DEFAULT_PARAMS.merge(Hash[params.map { |k, v| [k.to_sym, v] }])
  @min_vec = nil
  @max_vec = nil
end

Instance Attribute Details

#max_vec ⇒ NMatrix (readonly)

Return the vector consists of the maximum value for each feature.

Returns:

  • (NMatrix) —

    (shape: [1, n_features])



28
29
30
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 28

def max_vec
  @max_vec
end

#min_vec ⇒ NMatrix (readonly)

Return the vector consists of the minimum value for each feature.

Returns:

  • (NMatrix) —

    (shape: [1, n_features])



24
25
26
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 24

def min_vec
  @min_vec
end

Instance Method Details

#fit(x) ⇒ MinMaxScaler

Calculate the minimum and maximum value of each feature for scaling.

Parameters:

  • x (NMatrix) —

    (shape: [n_samples, n_features]) The samples to calculate the minimum and maximum values.

Returns:



47
48
49
50
51
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 47

def fit(x, _y = nil)
  @min_vec = x.min(0)
  @max_vec = x.max(0)
  self
end

#fit_transform(x) ⇒ NMatrix

Calculate the minimum and maximum values, and then normalize samples to feature_range.

Parameters:

  • x (NMatrix) —

    (shape: [n_samples, n_features]) The samples to calculate the minimum and maximum values.

Returns:

  • (NMatrix) —

    The scaled samples.



59
60
61
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 59

def fit_transform(x, _y = nil)
  fit(x).transform(x)
end

#marshal_dump ⇒ Hash

Dump marshal data.

Returns:

  • (Hash) —

    The marshal data about MinMaxScaler.



76
77
78
79
80
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 76

def marshal_dump
  { params: @params,
    min_vec: Utils.dump_nmatrix(@min_vec),
    max_vec: Utils.dump_nmatrix(@max_vec) }
end

#marshal_load(obj) ⇒ nil

Load marshal data.

Returns:

  • (nil) 


84
85
86
87
88
89
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 84

def marshal_load(obj)
  @params = obj[:params]
  @min_vec = Utils.restore_nmatrix(obj[:min_vec])
  @max_vec = Utils.restore_nmatrix(obj[:max_vec])
  nil
end

#transform(x) ⇒ NMatrix

Perform scaling the given samples according to feature_range.

Parameters:

  • x (NMatrix) —

    (shape: [n_samples, n_features]) The samples to be scaled.

Returns:

  • (NMatrix) —

    The scaled samples.



67
68
69
70
71
72
 
# File 'lib/svmkit/preprocessing/min_max_scaler.rb', line 67

def transform(x)
  n_samples, = x.shape
  dif_vec = @max_vec - @min_vec
  nx = (x - @min_vec.repeat(n_samples, 0)) / dif_vec.repeat(n_samples, 0)
  nx * (@params[:feature_range][1] - @params[:feature_range][0]) + @params[:feature_range][0]
end