Class: Rumale::PolynomialModel::FactorizationMachineRegressor

Inherits:
BaseFactorizationMachine show all
Includes:
Base::Regressor
Defined in:
lib/rumale/polynomial_model/factorization_machine_regressor.rb

Overview

FactorizationMachineRegressor is a class that implements Factorization Machine with stochastic gradient descent (SGD) optimization.

Reference

    1. Rendle, “Factorization Machines with libFM,” ACM TIST, vol. 3 (3), pp. 57:1–57:22, 2012.

    1. Rendle, “Factorization Machines,” Proc. ICDM’10, pp. 995–1000, 2010.

Examples:

estimator =
  Rumale::PolynomialModel::FactorizationMachineRegressor.new(
   n_factors: 10, reg_param_linear: 0.1, reg_param_factor: 0.1,
   max_iter: 5000, batch_size: 50, random_seed: 1)
estimator.fit(training_samples, traininig_values)
results = estimator.predict(testing_samples)

Instance Attribute Summary collapse

Attributes included from Base::BaseEstimator

#params

Instance Method Summary collapse

Methods included from Base::Regressor

#score

Constructor Details

#initialize(n_factors: 2, reg_param_linear: 1.0, reg_param_factor: 1.0, max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil) ⇒ FactorizationMachineRegressor

Create a new regressor with Factorization Machine.

Parameters:

  • n_factors (Integer) (defaults to: 2) —

    The maximum number of iterations.

  • reg_param_linear (Float) (defaults to: 1.0) —

    The regularization parameter for linear model.

  • reg_param_factor (Float) (defaults to: 1.0) —

    The regularization parameter for factor matrix.

  • max_iter (Integer) (defaults to: 1000) —

    The maximum number of iterations.

  • batch_size (Integer) (defaults to: 10) —

    The size of the mini batches.

  • optimizer (Optimizer) (defaults to: nil) —

    The optimizer to calculate adaptive learning rate. If nil is given, Nadam is used.

  • random_seed (Integer) (defaults to: nil) —

    The seed value using to initialize the random generator.



51
52
53
54
55
56
57
58
59
60
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 51

def initialize(n_factors: 2, reg_param_linear: 1.0, reg_param_factor: 1.0,
               max_iter: 1000, batch_size: 10, optimizer: nil, random_seed: nil)
  check_params_float(reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor)
  check_params_integer(n_factors: n_factors, max_iter: max_iter, batch_size: batch_size)
  check_params_type_or_nil(Integer, random_seed: random_seed)
  check_params_positive(n_factors: n_factors, reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor,
                        max_iter: max_iter, batch_size: batch_size)
  keywd_args = method(:initialize).parameters.map { |_t, arg| [arg, binding.local_variable_get(arg)] }.to_h.merge(loss: nil)
  super(keywd_args)
end

Instance Attribute Details

#bias_term ⇒ Numo::DFloat (readonly)

Return the bias term for Factoriazation Machine.

Returns:

  • (Numo::DFloat) —

    (shape: [n_outputs])



35
36
37
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 35

def bias_term
  @bias_term
end

#factor_mat ⇒ Numo::DFloat (readonly)

Return the factor matrix for Factorization Machine.

Returns:

  • (Numo::DFloat) —

    (shape: [n_outputs, n_factors, n_features])



27
28
29
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 27

def factor_mat
  @factor_mat
end

#rng ⇒ Random (readonly)

Return the random generator for random sampling.

Returns:

  • (Random) 


39
40
41
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 39

def rng
  @rng
end

#weight_vec ⇒ Numo::DFloat (readonly)

Return the weight vector for Factorization Machine.

Returns:

  • (Numo::DFloat) —

    (shape: [n_outputs, n_features])



31
32
33
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 31

def weight_vec
  @weight_vec
end

Instance Method Details

#fit(x, y) ⇒ FactorizationMachineRegressor

Fit the model with given training data.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The training data to be used for fitting the model.

  • y (Numo::Int32) —

    (shape: [n_samples, n_outputs]) The target values to be used for fitting the model.

Returns:



67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 67

def fit(x, y)
  check_sample_array(x)
  check_tvalue_array(y)
  check_sample_tvalue_size(x, y)

  n_outputs = y.shape[1].nil? ? 1 : y.shape[1]
  _n_samples, n_features = x.shape

  if n_outputs > 1
    @factor_mat = Numo::DFloat.zeros(n_outputs, @params[:n_factors], n_features)
    @weight_vec = Numo::DFloat.zeros(n_outputs, n_features)
    @bias_term = Numo::DFloat.zeros(n_outputs)
    n_outputs.times { |n| @factor_mat[n, true, true], @weight_vec[n, true], @bias_term[n] = partial_fit(x, y[true, n]) }
  else
    @factor_mat, @weight_vec, @bias_term = partial_fit(x, y)
  end

  self
end

#marshal_dump ⇒ Hash

Dump marshal data.

Returns:

  • (Hash) —

    The marshal data about FactorizationMachineRegressor.



104
105
106
107
108
109
110
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 104

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

#marshal_load(obj) ⇒ nil

Load marshal data.

Returns:

  • (nil) 


114
115
116
117
118
119
120
121
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 114

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

#predict(x) ⇒ Numo::DFloat

Predict values for samples.

Parameters:

  • x (Numo::DFloat) —

    (shape: [n_samples, n_features]) The samples to predict the values.

Returns:

  • (Numo::DFloat) —

    (shape: [n_samples, n_outputs]) Predicted values per sample.



91
92
93
94
95
96
97
98
99
100
 
# File 'lib/rumale/polynomial_model/factorization_machine_regressor.rb', line 91

def predict(x)
  check_sample_array(x)
  linear_term = @bias_term + x.dot(@weight_vec.transpose)
  factor_term = if @weight_vec.shape[1].nil?
                  0.5 * (@factor_mat.dot(x.transpose)**2 - (@factor_mat**2).dot(x.transpose**2)).sum(0)
                else
                  0.5 * (@factor_mat.dot(x.transpose)**2 - (@factor_mat**2).dot(x.transpose**2)).sum(1).transpose
                end
  linear_term + factor_term
end