Class: SVMKit::LinearModel::LogisticRegression

Inherits:
Object
  • Object
show all
Includes:
Base::BaseEstimator, Base::Classifier
Defined in:
lib/svmkit/linear_model/logistic_regression.rb

Overview

LogisticRegression is a class that implements Logistic Regression with stochastic gradient descent (SGD) optimization. Note that the class performs as a binary classifier.

Reference

    1. Shalev-Shwartz, Y. Singer, N. Srebro, and A. Cotter, “Pegasos: Primal Estimated sub-GrAdient SOlver for SVM,” Mathematical Programming, vol. 127 (1), pp. 3–30, 2011.

Examples:

estimator =
  SVMKit::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 100, batch_size: 20, random_seed: 1)
estimator.fit(training_samples, traininig_labels)
results = estimator.predict(testing_samples)

Instance Attribute Summary collapse

Attributes included from Base::BaseEstimator

#params

Instance Method Summary collapse

Methods included from Base::Classifier

#score

Constructor Details

#initialize(reg_param: 1.0, fit_bias: false, bias_scale: 1.0, max_iter: 100, batch_size: 50, random_seed: nil) ⇒ LogisticRegression

Create a new classifier with Logisitc Regression by the SGD optimization.



46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 46

def initialize(reg_param: 1.0, fit_bias: false, bias_scale: 1.0, max_iter: 100, batch_size: 50, random_seed: nil)
  @params = {}
  @params[:reg_param] = reg_param
  @params[:fit_bias] = fit_bias
  @params[:bias_scale] = bias_scale
  @params[:max_iter] = max_iter
  @params[:batch_size] = batch_size
  @params[:random_seed] = random_seed
  @params[:random_seed] ||= srand
  @weight_vec = nil
  @bias_term = 0.0
  @rng = Random.new(@params[:random_seed])
end

Instance Attribute Details

#bias_term ⇒ Float (readonly)

Return the bias term (a.k.a. intercept) for Logistic Regression.



31
32
33
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 31

def bias_term
  @bias_term
end

#rng ⇒ Random (readonly)

Return the random generator for transformation.



35
36
37
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 35

def rng
  @rng
end

#weight_vec ⇒ Numo::DFloat (readonly)

Return the weight vector for Logistic Regression.



27
28
29
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 27

def weight_vec
  @weight_vec
end

Instance Method Details

#decision_function(x) ⇒ Numo::DFloat

Calculate confidence scores for samples.



116
117
118
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 116

def decision_function(x)
  @weight_vec.dot(x.transpose) + @bias_term
end

#fit(x, y) ⇒ LogisticRegression

Fit the model with given training data.



66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 66

def fit(x, y)
  # Generate binary labels.
  negative_label = y.to_a.uniq.sort.shift
  bin_y = y.to_a.map { |l| l != negative_label ? 1 : 0 }
  # Expand feature vectors for bias term.
  samples = x
  if @params[:fit_bias]
    samples = Numo::NArray.hstack(
      [samples, Numo::DFloat.ones([x.shape[0], 1]) * @params[:bias_scale]]
    )
  end
  # Initialize some variables.
  n_samples, n_features = samples.shape
  rand_ids = [*0...n_samples].shuffle(random: @rng)
  weight_vec = Numo::DFloat.zeros(n_features)
  # Start optimization.
  @params[:max_iter].times do |t|
    # random sampling
    subset_ids = rand_ids.shift(@params[:batch_size])
    rand_ids.concat(subset_ids)
    # update the weight vector.
    eta = 1.0 / (@params[:reg_param] * (t + 1))
    mean_vec = Numo::DFloat.zeros(n_features)
    subset_ids.each do |n|
      z = weight_vec.dot(samples[n, true])
      coef = bin_y[n] / (1.0 + Math.exp(bin_y[n] * z))
      mean_vec += samples[n, true] * coef
    end
    mean_vec *= eta / @params[:batch_size]
    weight_vec = weight_vec * (1.0 - eta * @params[:reg_param]) + mean_vec
    # scale the weight vector.
    norm = Math.sqrt(weight_vec.dot(weight_vec))
    scaler = (1.0 / @params[:reg_param]**0.5) / (norm + 1.0e-12)
    weight_vec *= [1.0, scaler].min
  end
  # Store the learned model.
  if @params[:fit_bias]
    @weight_vec = weight_vec[0...n_features - 1]
    @bias_term = weight_vec[n_features - 1]
  else
    @weight_vec = weight_vec[0...n_features]
    @bias_term = 0.0
  end
  self
end

#marshal_dump ⇒ Hash

Dump marshal data.



142
143
144
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 142

def marshal_dump
  { params: @params, weight_vec: @weight_vec, bias_term: @bias_term, rng: @rng }
end

#marshal_load(obj) ⇒ nil

Load marshal data.



148
149
150
151
152
153
154
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 148

def marshal_load(obj)
  @params = obj[:params]
  @weight_vec = obj[:weight_vec]
  @bias_term = obj[:bias_term]
  @rng = obj[:rng]
  nil
end

#predict(x) ⇒ Numo::Int32

Predict class labels for samples.



124
125
126
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 124

def predict(x)
  Numo::Int32.cast(sigmoid(decision_function(x)).map { |v| v >= 0.5 ? 1 : -1 })
end

#predict_proba(x) ⇒ Numo::DFloat

Predict probability for samples.



132
133
134
135
136
137
138
 
# File 'lib/svmkit/linear_model/logistic_regression.rb', line 132

def predict_proba(x)
  n_samples, = x.shape
  proba = Numo::DFloat.zeros(n_samples, 2)
  proba[true, 1] = sigmoid(decision_function(x))
  proba[true, 0] = 1.0 - proba[true, 1]
  proba
end