Class: Rumale::EvaluationMeasure::MeanSquaredLogError

Inherits:

Object

• Object
• Rumale::EvaluationMeasure::MeanSquaredLogError

Includes:

Base::Evaluator

Defined in:

lib/rumale/evaluation_measure/mean_squared_log_error.rb

Overview

MeanSquaredLogError is a class that calculates the mean squared logarithmic error.

Examples:

evaluator = Rumale::EvaluationMeasure::MeanSquaredError.new
puts evaluator.score(ground_truth, predicted)

Instance Method Summary

• #score(y_true, y_pred) ⇒ Float

  Calculate mean squared logarithmic error.

Instance Method Details

#score(y_true, y_pred) ⇒ Float

Calculate mean squared logarithmic error.

Parameters:

• y_true (Numo::DFloat) —

  (shape: [n_samples, n_outputs]) Ground truth target values.

• y_pred (Numo::DFloat) —

  (shape: [n_samples, n_outputs]) Estimated target values.

Returns:

• (Float) —

  Mean squared logarithmic error.

Raises:

• (ArgumentError)

# File 'lib/rumale/evaluation_measure/mean_squared_log_error.rb', line 20

def score(y_true, y_pred)
  check_tvalue_array(y_true)
  check_tvalue_array(y_pred)
  raise ArgumentError, 'Expect to have the same size both y_true and y_pred.' unless y_true.shape == y_pred.shape

  ((Numo::NMath.log(y_true + 1) - Numo::NMath.log(y_pred + 1))**2).mean
end