Sha256: c1f77ca01485c9ac76989231347a7219147957e12edc2d595821febf18c4fa04
Contents?: true
Size: 1.25 KB
Versions: 7
Compression:
Stored size: 1.25 KB
Contents
# frozen_string_literal: true
require 'rumale/base/evaluator'
module Rumale
module EvaluationMeasure
# Purity is a class that calculates the purity of cluatering results.
#
# @example
# require 'rumale/evaluation_measure/purity'
#
# evaluator = Rumale::EvaluationMeasure::Purity.new
# puts evaluator.score(ground_truth, predicted)
#
# *Reference*
# - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
class Purity
include ::Rumale::Base::Evaluator
# Calculate purity
#
# @param y_true [Numo::Int32] (shape: [n_samples]) Ground truth labels.
# @param y_pred [Numo::Int32] (shape: [n_samples]) Predicted cluster labels.
# @return [Float] Purity
def score(y_true, y_pred)
# initiazlie some variables.
purity = 0
n_samples = y_pred.size
class_ids = y_true.to_a.uniq
cluster_ids = y_pred.to_a.uniq
# calculate purity.
cluster_ids.each do |k|
pr_sample_ids = y_pred.eq(k).where.to_a
purity += class_ids.map { |j| (pr_sample_ids & y_true.eq(j).where.to_a).size }.max
end
purity.fdiv(n_samples)
end
end
end
end
Version data entries
7 entries across 7 versions & 1 rubygems