to_histogram 1.0.8 → 1.0.9
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/averages.rb +15 -0
- data/lib/bucketizer.rb +19 -12
- data/lib/stdout_print.rb +18 -28
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: d76599692e37ff86d3d2ebaa05aa54da8b9da7ab
|
4
|
+
data.tar.gz: 3149b591c776df617496904bb2066a8f8fd64d41
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: dd0e9518fe1e6841687b91093acf793edbe89ec56b85b7778f3272a1b48146375893a4a3b08ff073b0efd9ed5d35d3356ad063d1aa5d1d702a408783f720bbf8
|
7
|
+
data.tar.gz: 609d746f2f3fe63a9a12b2db5480aaddaf17d9e66cbdd71f15b7829777c7f7d28766593e6024e8be57320cc13f4486b3a2daec52167ac2e5553a0de3154e5444
|
data/lib/averages.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
module Averages
|
2
|
+
def mean(array)
|
3
|
+
array.reduce(:+) / array.length
|
4
|
+
end
|
5
|
+
|
6
|
+
def median(array)
|
7
|
+
array[array.length / 2]
|
8
|
+
end
|
9
|
+
|
10
|
+
def mode(array)
|
11
|
+
frequency = array.inject(Hash.new(0)) { |h,v| h[v] += 1; h }
|
12
|
+
|
13
|
+
array.max_by { |v| frequency[v] }
|
14
|
+
end
|
15
|
+
end
|
data/lib/bucketizer.rb
CHANGED
@@ -6,20 +6,17 @@ module ToHistogram
|
|
6
6
|
@arr = array.sort
|
7
7
|
@num_buckets = num_buckets
|
8
8
|
@percentile =percentile
|
9
|
-
|
9
|
+
|
10
|
+
remove_elements_outside_of_percentile
|
11
|
+
@bucket_increments = get_bucket_increment
|
10
12
|
end
|
11
13
|
attr_reader :bucket_increments, :arr
|
12
14
|
|
13
15
|
def create_buckets
|
14
16
|
l_index = 0
|
15
|
-
next_bucket = @bucket_increments
|
17
|
+
next_bucket = get_initial_next_bucket(@bucket_increments)
|
16
18
|
buckets = []
|
17
19
|
|
18
|
-
# Remove any elements outside of the percentile
|
19
|
-
if(@percentile != 100)
|
20
|
-
@arr = @arr[0..(@arr.length * (@percentile / 100.0) - 1).to_i]
|
21
|
-
end
|
22
|
-
|
23
20
|
# Deal with the special case where we have elements that == 0 and an increment sizes of 1 (count 0 as a value and don't lump it in with 1)
|
24
21
|
if(@arr.count(0) > 0 && next_bucket == 1)
|
25
22
|
bucket_0 = []
|
@@ -56,15 +53,25 @@ module ToHistogram
|
|
56
53
|
end
|
57
54
|
|
58
55
|
private
|
59
|
-
def
|
60
|
-
|
56
|
+
def get_initial_next_bucket(increments)
|
57
|
+
if(@arr[0] != nil && @arr[0] < 0)
|
58
|
+
return (@arr[0] + increments)
|
59
|
+
else
|
60
|
+
return increments
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
def remove_elements_outside_of_percentile
|
65
|
+
if(@percentile != 100)
|
66
|
+
@arr = @arr[0..(@arr.length * (@percentile / 100.0) - 1).to_i]
|
67
|
+
end
|
68
|
+
end
|
61
69
|
|
70
|
+
def get_bucket_increment
|
62
71
|
if(@arr.length == 0)
|
63
72
|
return 0
|
64
|
-
elsif(@arr.length <= @num_buckets)
|
65
|
-
increment = ((@arr[-1] - @arr[0]) / @num_buckets)
|
66
73
|
else
|
67
|
-
increment = ((@arr[
|
74
|
+
increment = ((@arr[-1] - @arr[0]) / @num_buckets.to_f).ceil
|
68
75
|
end
|
69
76
|
|
70
77
|
return increment
|
data/lib/stdout_print.rb
CHANGED
@@ -1,9 +1,14 @@
|
|
1
|
+
require_relative './averages'
|
2
|
+
|
1
3
|
module ToHistogram
|
2
4
|
|
3
5
|
class StdoutPrint
|
4
|
-
|
6
|
+
include Averages
|
7
|
+
|
8
|
+
def initialize(histogram, original_array, stdout=$stdout)
|
5
9
|
@histogram = histogram
|
6
10
|
@original_array = original_array.sort
|
11
|
+
@stdout = stdout
|
7
12
|
end
|
8
13
|
|
9
14
|
def invoke
|
@@ -14,25 +19,25 @@ module ToHistogram
|
|
14
19
|
|
15
20
|
private
|
16
21
|
def print_header
|
17
|
-
puts "\n**************************************************************"
|
18
|
-
puts "Results for #to_histogram(num_buckets: #{@histogram.num_buckets}, percentile: #{@histogram.percentile}, print_info: true)"
|
22
|
+
@stdout.puts "\n**************************************************************"
|
23
|
+
@stdout.puts "Results for #to_histogram(num_buckets: #{@histogram.num_buckets}, percentile: #{@histogram.percentile}, print_info: true)"
|
19
24
|
|
20
|
-
puts "\n"
|
25
|
+
@stdout.puts "\n"
|
21
26
|
|
22
27
|
percentile_info = (@histogram.percentile == 100) ? '' : "(Numbers limited to the #{@histogram.percentile}th percentile)"
|
23
|
-
puts "Data set used in this calculation #{percentile_info}"
|
24
|
-
puts "Data set Size: #{@histogram.arr.length} items"
|
25
|
-
puts "Min Value: #{@histogram.arr[0]}, Max Value: #{@histogram.arr[-1]}"
|
26
|
-
puts "Mean: #{mean(@histogram.arr)}, Median: #{median(@histogram.arr)}, Mode: #{mode(@histogram.arr)}"
|
27
|
-
puts "\n"
|
28
|
+
@stdout.puts "Data set used in this calculation #{percentile_info}"
|
29
|
+
@stdout.puts "Data set Size: #{@histogram.arr.length} items"
|
30
|
+
@stdout.puts "Min Value: #{@histogram.arr[0]}, Max Value: #{@histogram.arr[-1]}"
|
31
|
+
@stdout.puts "Mean: #{mean(@histogram.arr)}, Median: #{median(@histogram.arr)}, Mode: #{mode(@histogram.arr)}"
|
32
|
+
@stdout.puts "\n"
|
28
33
|
|
29
|
-
puts "Histogram bucket sizes: #{@histogram.increments}"
|
30
|
-
puts "**************************************************************\n\n"
|
34
|
+
@stdout.puts "Histogram bucket sizes: #{@histogram.increments}"
|
35
|
+
@stdout.puts "**************************************************************\n\n"
|
31
36
|
end
|
32
37
|
|
33
38
|
def print_body
|
34
39
|
total_data_value_length = (@histogram.map { |b| b.length }).reduce(:+)
|
35
|
-
printf("%-20s %-20s %-30s %-20s \n\n", "Range", "Frequency", " Percentage", "Histogram (each * =~ 1%)")
|
40
|
+
@stdout.printf("%-20s %-20s %-30s %-20s \n\n", "Range", "Frequency", " Percentage", "Histogram (each * =~ 1%)")
|
36
41
|
|
37
42
|
@histogram.each_with_index do |b, i|
|
38
43
|
next_bucket = (@histogram[i + 1]) ? @histogram[i + 1][0] : b[-1]
|
@@ -48,24 +53,9 @@ module ToHistogram
|
|
48
53
|
end
|
49
54
|
end
|
50
55
|
|
51
|
-
printf("%-20s | %-20s | %-30s | %-20s \n", range, frequency, ('%.4f' % percentage), stars)
|
52
|
-
last_value = b[-1]
|
56
|
+
@stdout.printf("%-20s | %-20s | %-30s | %-20s \n", range, frequency, ('%.4f' % percentage), stars)
|
53
57
|
end
|
54
58
|
end
|
55
59
|
|
56
|
-
def mean(array)
|
57
|
-
array.reduce(:+) / array.length
|
58
|
-
end
|
59
|
-
|
60
|
-
def median(array)
|
61
|
-
array[array.length / 2]
|
62
|
-
end
|
63
|
-
|
64
|
-
def mode(array)
|
65
|
-
frequency = array.inject(Hash.new(0)) { |h,v| h[v] += 1; h }
|
66
|
-
|
67
|
-
array.max_by { |v| frequency[v] }
|
68
|
-
end
|
69
|
-
|
70
60
|
end
|
71
61
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: to_histogram
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.9
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Brett Sykes
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-11-
|
11
|
+
date: 2015-11-08 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: 'Adds #to_histogram to Array. Returns a histogram distribution object
|
14
14
|
from an Array and optionally prints detailed info to stdout.'
|
@@ -17,6 +17,7 @@ executables: []
|
|
17
17
|
extensions: []
|
18
18
|
extra_rdoc_files: []
|
19
19
|
files:
|
20
|
+
- lib/averages.rb
|
20
21
|
- lib/bucketizer.rb
|
21
22
|
- lib/histogram.rb
|
22
23
|
- lib/stdout_print.rb
|