Created
June 28, 2012 16:30
-
-
Save ploubser/3012324 to your computer and use it in GitHub Desktop.
Simple client side function for determining outliers in a set
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
module MCollective | |
class Aggregate | |
class Outliers<Base | |
def startup_hook | |
result[:value] = {:high => [], :low =>[]} | |
result[:type] = :collection | |
@aggregate_format = "%s : %s" unless @aggregate_format | |
@data_set = [] | |
@quartiles = {:high => nil, | |
:low=> nil} | |
end | |
def process_result(value, reply) | |
@data_set << value | |
end | |
def summarize | |
@data_set.sort! | |
set_quartiles | |
find_outliers | |
end | |
def set_quartiles | |
n = @data_set.size | |
l = Float((1.0/4.0)*(n + 1)) | |
u = Float((3.0/4.0)*(n + 1)) | |
l = l.truncate + 1 unless Integer(l) == l | |
u = u.truncate | |
iqr = @data_set[u] = @data_set[l] | |
@quartiles[:low] = @data_set[l] - (1.5 * iqr) | |
@quartiles[:high] = @data_set[u] + (1.5 * iqr) | |
end | |
def find_outliers | |
@data_set.each do |data_item| | |
result[:value][:high] << data_item if data_item > @quartiles[:high] | |
result[:value][:low] << data_item if data_item < @quartiles[:low] | |
end | |
end | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment