Last active
August 29, 2015 14:13
-
-
Save bhb/c8edde45a0be12617956 to your computer and use it in GitHub Desktop.
Compute stats for array of numbers
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
def percentile(arr, pcent) | |
sorted = arr.sort | |
# http://en.wikipedia.org/wiki/Percentile#Linear_interpolation_between_closest_ranks | |
percent_ranks = (1..arr.length).map { |i| (100.0 / sorted.length) * ( i - 0.5) } | |
if pcent < percent_ranks.first | |
sorted[0] | |
elsif pcent > percent_ranks.last | |
sorted.last | |
else | |
idx = percent_ranks.find_index { |rank| rank == pcent } | |
return sorted[idx] if idx != nil | |
idx = rank_at = nil | |
percent_ranks.each_with_index do |rank, i| | |
if rank < pcent && pcent < percent_ranks[i+1] | |
idx = i | |
rank_at = rank | |
end | |
end | |
sorted[idx] + (arr.length * (pcent-rank_at).to_f/100 * (sorted[idx+1] - sorted[idx])) | |
end | |
end | |
def stats(arr) | |
arr = arr.clone.extend(Stats) | |
lowest = arr.min | |
highest = arr.max | |
total = arr.inject(:+) | |
len = arr.length | |
average = total.to_f / len # to_f so we don't get an integer result | |
sorted = arr.sort | |
variance = (arr.inject(0) {|accum, i| accum + (i-average)**2 }.to_f/(len)) | |
std_dev = Math.sqrt(variance) | |
median = len % 2 == 1 ? sorted[len/2] : (sorted[len/2 - 1] + sorted[len/2]).to_f / 2 | |
{ | |
:min => lowest, | |
:max => highest, | |
:avg => average, | |
:std_dev => std_dev, | |
:med => median, | |
:pct_50 => percentile(arr, 50), | |
:pct_90 => percentile(arr, 90) | |
}.tap do |stats| | |
if (stats[:med]-stats[:pct_50]).abs > 0.000001 | |
raise "med was #{stats[:med].inspect} but 50% percenile was #{stats[:pct_50].inspect} for #{arr.inspect}}" | |
end | |
end | |
end | |
module Stats | |
def sum | |
self.inject(0){|accum, i| accum + i } | |
end | |
def mean | |
self.sum/self.length.to_f | |
end | |
def sample_variance | |
m = self.mean | |
sum = self.inject(0){|accum, i| accum +(i-m)**2 } | |
sum/(self.length - 1).to_f | |
end | |
def standard_deviation | |
return Math.sqrt(self.sample_variance) | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment