histogram 0.2.1.3 → 0.2.1.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +18 -8
- data/Rakefile +0 -1
- data/histogram.gemspec +6 -2
- data/lib/histogram.rb +11 -5
- data/lib/histogram/version.rb +1 -1
- data/spec/histogram_spec.rb +24 -15
- metadata +41 -41
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: deecc5f583bc853f2e7dccdb1e4cb8311acb45c0
|
4
|
+
data.tar.gz: 879bdf4508f55f29a1c560328d11b48ef2acc48d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c29c405ec579ac016526801f7845767aae155ee186f63dd8610d3d1596e1542126c2749623d84ae64c11e68a95b9b6d446d4b5a34bbecdfe11a20cd7d2d8fdaf
|
7
|
+
data.tar.gz: 81fc3b7306f61085b57cf103d6815f894841af07549421647ff343179b521f794e6ac4237cf49d6158587ab79c3aebf0b47e908ceeb26c8daaa3995feb333abe
|
data/README.md
CHANGED
@@ -4,7 +4,10 @@
|
|
4
4
|
|
5
5
|
Generates histograms similar to R's hist and numpy's histogram functions.
|
6
6
|
Inspired somewhat by [Richard Cottons's matlab implementation](http://www.mathworks.com/matlabcentral/fileexchange/21033-calculate-number-of-bins-for-histogram)
|
7
|
-
and the wikipedia [histogram
|
7
|
+
and the wikipedia [histogram
|
8
|
+
article](http://en.wikipedia.org/wiki/Histogram).
|
9
|
+
|
10
|
+
Tested on latest MRI 1.9.x, 2.x, and jruby (no NArray support for jruby). Known to work on MRI 1.8.7.
|
8
11
|
|
9
12
|
### Typical usage:
|
10
13
|
|
@@ -12,13 +15,13 @@ and the wikipedia [histogram article](http://en.wikipedia.org/wiki/Histogram).
|
|
12
15
|
|
13
16
|
data = [0,1,2,2,2,2,2,3,3,3,3,3,3,3,3,3,5,5,9,9,10]
|
14
17
|
# by default, uses Scott's method to calculate optimal number of bins
|
15
|
-
# and the bin values are midpoints between the bin edges
|
16
|
-
(bins, freqs) = data.histogram
|
17
|
-
# equivalent to: data.histogram(:scott, :bin_boundary => :avg)
|
18
|
+
# and the bin values are midpoints between the bin edges
|
19
|
+
(bins, freqs) = data.histogram
|
20
|
+
# equivalent to: data.histogram(:scott, :bin_boundary => :avg)
|
18
21
|
|
19
22
|
### Multiple types of binning behavior:
|
20
23
|
|
21
|
-
# :scott, :fd, :sturges, or :middle
|
24
|
+
# :scott, :fd, :sturges, or :middle
|
22
25
|
data.histogram(:fd) # use Freedman-Diaconis method to calc num bins
|
23
26
|
data.histogram(:middle) # (median value between the three methods)
|
24
27
|
(bins, freqs) = data.histogram(20) # use 20 bins
|
@@ -33,7 +36,7 @@ and the wikipedia [histogram article](http://en.wikipedia.org/wiki/Histogram).
|
|
33
36
|
(bins, freqs) = data.histogram(:bin_width => 0.5)
|
34
37
|
|
35
38
|
### Multiple Datasets:
|
36
|
-
|
39
|
+
|
37
40
|
Sometimes, we want to create histograms where the bins are calculated based on
|
38
41
|
all the data sets. That way, the resulting frequencies will all line up:
|
39
42
|
|
@@ -41,12 +44,12 @@ all the data sets. That way, the resulting frequencies will all line up:
|
|
41
44
|
(bins, *freqs) = set1.histogram(30, :other_sets => [[3,3,4,4,5], [-1,0,0,3,3,6]])
|
42
45
|
|
43
46
|
### Histograms with weights/fractions:
|
44
|
-
|
47
|
+
|
45
48
|
# histogramming with weights
|
46
49
|
data.histogram(20, :weights => [3,3,8,8,9,9,3,3,3,3])
|
47
50
|
|
48
51
|
### Works with NArray objects
|
49
|
-
|
52
|
+
|
50
53
|
require 'histogram/narray' # enables NArray#histogram
|
51
54
|
# if the calling object is an NArray, the output is two NArrays:
|
52
55
|
(bins, freqs) = NArray.float(20).random!(3).histogram(20)
|
@@ -56,6 +59,13 @@ all the data sets. That way, the resulting frequencies will all line up:
|
|
56
59
|
|
57
60
|
gem install histogram
|
58
61
|
|
62
|
+
## Acknowledgements
|
63
|
+
|
64
|
+
Big thanks to those who have made contributions!
|
65
|
+
|
66
|
+
* deal with zero std ([Greg Dean](https://github.com/gsdean))
|
67
|
+
* support for 1.8.7 and jruby ([Kiera Radman](https://github.com/kierarad))
|
68
|
+
|
59
69
|
## See Also
|
60
70
|
|
61
71
|
[aggregate](http://github.com/josephruscio/aggregate), [rserve-client](http://rubygems.org/gems/rserve-client), [rsruby](http://github.com/alexgutteridge/rsruby)
|
data/Rakefile
CHANGED
data/histogram.gemspec
CHANGED
@@ -19,12 +19,16 @@ Gem::Specification.new do |spec|
|
|
19
19
|
spec.require_paths = ["lib"]
|
20
20
|
|
21
21
|
|
22
|
-
[ "bundler ~> 1.3",
|
22
|
+
[ "bundler ~> 1.3",
|
23
23
|
"rake ~> 10.1.0",
|
24
24
|
"simplecov ~> 0.7.1",
|
25
25
|
"rspec ~> 2.13.0",
|
26
|
-
"
|
26
|
+
"rdoc"
|
27
27
|
].each do |argline|
|
28
28
|
spec.add_development_dependency *argline.split(' ', 2).compact
|
29
29
|
end
|
30
|
+
|
31
|
+
unless RUBY_PLATFORM =~ /java/
|
32
|
+
spec.add_development_dependency "narray"
|
33
|
+
end
|
30
34
|
end
|
data/lib/histogram.rb
CHANGED
@@ -1,5 +1,11 @@
|
|
1
1
|
|
2
|
-
class NArray
|
2
|
+
class NArray
|
3
|
+
end
|
4
|
+
|
5
|
+
unless Math.respond_to?(:log2)
|
6
|
+
def Math.log2(num)
|
7
|
+
Math.log(num, 2)
|
8
|
+
end
|
3
9
|
end
|
4
10
|
|
5
11
|
module Histogram
|
@@ -44,8 +50,8 @@ module Histogram
|
|
44
50
|
# :sorted => false
|
45
51
|
#
|
46
52
|
def iqrange(obj, opts={})
|
47
|
-
opt = {method
|
48
|
-
srted = opt[:sorted] ? obj : obj.sort
|
53
|
+
opt = {:method => DEFAULT_QUARTILE_METHOD, :sorted => false}.merge( opts )
|
54
|
+
srted = opt[:sorted] ? obj : obj.sort
|
49
55
|
sz = srted.size
|
50
56
|
answer =
|
51
57
|
case opt[:method]
|
@@ -89,9 +95,9 @@ module Histogram
|
|
89
95
|
(mean, stddev) = Histogram.sample_stats(self)
|
90
96
|
range / ( 3.5*stddev*(self.size**(-1.0/3)) )
|
91
97
|
when :sturges
|
92
|
-
1 + Math::
|
98
|
+
1 + Math::log2(self.size)
|
93
99
|
when :fd
|
94
|
-
2 * Histogram.iqrange(self, method
|
100
|
+
2 * Histogram.iqrange(self, :method => quartile_method) * (self.size**(-1.0/3))
|
95
101
|
end
|
96
102
|
nbins = 1 if nbins <= 0
|
97
103
|
nbins = 1 if nbins.nan?
|
data/lib/histogram/version.rb
CHANGED
data/spec/histogram_spec.rb
CHANGED
@@ -2,6 +2,16 @@ require 'spec_helper'
|
|
2
2
|
|
3
3
|
require 'histogram'
|
4
4
|
|
5
|
+
class Float
|
6
|
+
def round(n=nil)
|
7
|
+
if n
|
8
|
+
((n**10) * self).to_i/(10**n)
|
9
|
+
else
|
10
|
+
super()
|
11
|
+
end
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
5
15
|
RSpec::Matchers.define :be_within_rounding_error_of do |expected|
|
6
16
|
match do |actual|
|
7
17
|
(act, exp) = [actual, expected].map {|ar| ar.collect {|v| v.to_f.round(8) } }
|
@@ -91,14 +101,14 @@ shared_examples 'something that can histogram' do
|
|
91
101
|
end
|
92
102
|
|
93
103
|
describe Histogram do
|
94
|
-
tmp = {
|
95
|
-
obj0
|
96
|
-
obj1
|
97
|
-
obj2
|
98
|
-
obj3
|
99
|
-
obj4
|
100
|
-
obj5
|
101
|
-
obj6
|
104
|
+
tmp = {
|
105
|
+
:obj0 => (0..10).to_a,
|
106
|
+
:obj1 => [0, 1, 1.5, 2.0, 5.0, 6.0, 7, 8, 9, 9],
|
107
|
+
:obj2 => [-1, 0, 1, 1.5, 2.0, 5.0, 6.0, 7, 8, 9, 9, 10],
|
108
|
+
:obj3 => [1, 1, 2, 2, 3, 3, 4, 4, 4],
|
109
|
+
:obj4 => [2, 2, 2, 2, 2, 4],
|
110
|
+
:obj5 => [1,2,3,3,3,4,5,6,7,8],
|
111
|
+
:obj6 => [0,0,0,0,0]
|
102
112
|
}
|
103
113
|
data = tmp.each {|k,v| [k, v.map(&:to_f).extend(Histogram)] }
|
104
114
|
|
@@ -112,12 +122,12 @@ describe Histogram do
|
|
112
122
|
it_behaves_like 'something that can histogram'
|
113
123
|
end
|
114
124
|
|
115
|
-
have_narray =
|
125
|
+
have_narray =
|
116
126
|
begin
|
117
127
|
require 'narray'
|
118
128
|
NArray.respond_to?(:to_na)
|
119
129
|
true
|
120
|
-
rescue
|
130
|
+
rescue LoadError
|
121
131
|
false
|
122
132
|
end
|
123
133
|
|
@@ -152,16 +162,15 @@ describe Histogram do
|
|
152
162
|
end
|
153
163
|
|
154
164
|
it 'calculates the interquartile range via moore_mccabe' do
|
155
|
-
Histogram.iqrange(even, method
|
156
|
-
Histogram.iqrange(odd, method
|
165
|
+
Histogram.iqrange(even, :method => :moore_mccabe).should == 4.0
|
166
|
+
Histogram.iqrange(odd, :method => :moore_mccabe).should == 4.0
|
157
167
|
end
|
158
168
|
|
159
169
|
it 'calculates the interquartile range via tukey' do
|
160
|
-
Histogram.iqrange(even, method
|
161
|
-
Histogram.iqrange(odd, method
|
170
|
+
Histogram.iqrange(even, :method => :tukey).should == 4.0
|
171
|
+
Histogram.iqrange(odd, :method => :tukey).should == 3.0
|
162
172
|
end
|
163
173
|
|
164
174
|
|
165
175
|
end
|
166
176
|
end
|
167
|
-
|
metadata
CHANGED
@@ -1,85 +1,85 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: histogram
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.1.
|
4
|
+
version: 0.2.1.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- John T. Prince
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-10-
|
11
|
+
date: 2014-10-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
15
|
-
|
15
|
+
version_requirements: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - ~>
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '1.3'
|
20
|
-
|
21
|
-
prerelease: false
|
22
|
-
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirement: !ruby/object:Gem::Requirement
|
23
21
|
requirements:
|
24
|
-
- -
|
22
|
+
- - ~>
|
25
23
|
- !ruby/object:Gem::Version
|
26
24
|
version: '1.3'
|
25
|
+
prerelease: false
|
26
|
+
type: :development
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
|
-
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - ~>
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: 10.1.0
|
34
|
-
|
35
|
-
prerelease: false
|
36
|
-
version_requirements: !ruby/object:Gem::Requirement
|
34
|
+
requirement: !ruby/object:Gem::Requirement
|
37
35
|
requirements:
|
38
|
-
- -
|
36
|
+
- - ~>
|
39
37
|
- !ruby/object:Gem::Version
|
40
38
|
version: 10.1.0
|
39
|
+
prerelease: false
|
40
|
+
type: :development
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: simplecov
|
43
|
-
|
43
|
+
version_requirements: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- -
|
45
|
+
- - ~>
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: 0.7.1
|
48
|
-
|
49
|
-
prerelease: false
|
50
|
-
version_requirements: !ruby/object:Gem::Requirement
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
51
49
|
requirements:
|
52
|
-
- -
|
50
|
+
- - ~>
|
53
51
|
- !ruby/object:Gem::Version
|
54
52
|
version: 0.7.1
|
53
|
+
prerelease: false
|
54
|
+
type: :development
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: rspec
|
57
|
-
|
57
|
+
version_requirements: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- -
|
59
|
+
- - ~>
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: 2.13.0
|
62
|
-
|
63
|
-
prerelease: false
|
64
|
-
version_requirements: !ruby/object:Gem::Requirement
|
62
|
+
requirement: !ruby/object:Gem::Requirement
|
65
63
|
requirements:
|
66
|
-
- -
|
64
|
+
- - ~>
|
67
65
|
- !ruby/object:Gem::Version
|
68
66
|
version: 2.13.0
|
67
|
+
prerelease: false
|
68
|
+
type: :development
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
71
|
-
|
70
|
+
name: rdoc
|
71
|
+
version_requirements: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- -
|
73
|
+
- - '>='
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: '0'
|
76
|
-
|
77
|
-
prerelease: false
|
78
|
-
version_requirements: !ruby/object:Gem::Requirement
|
76
|
+
requirement: !ruby/object:Gem::Requirement
|
79
77
|
requirements:
|
80
|
-
- -
|
78
|
+
- - '>='
|
81
79
|
- !ruby/object:Gem::Version
|
82
80
|
version: '0'
|
81
|
+
prerelease: false
|
82
|
+
type: :development
|
83
83
|
description: gives objects the ability to 'histogram' in several useful ways
|
84
84
|
email:
|
85
85
|
- jtprince@gmail.com
|
@@ -88,7 +88,7 @@ executables:
|
|
88
88
|
extensions: []
|
89
89
|
extra_rdoc_files: []
|
90
90
|
files:
|
91
|
-
-
|
91
|
+
- .gitignore
|
92
92
|
- Gemfile
|
93
93
|
- LICENSE
|
94
94
|
- README.md
|
@@ -106,24 +106,24 @@ homepage: https://github.com/jtprince/histogram
|
|
106
106
|
licenses:
|
107
107
|
- MIT
|
108
108
|
metadata: {}
|
109
|
-
post_install_message:
|
109
|
+
post_install_message:
|
110
110
|
rdoc_options: []
|
111
111
|
require_paths:
|
112
112
|
- lib
|
113
113
|
required_ruby_version: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
|
-
- -
|
115
|
+
- - '>='
|
116
116
|
- !ruby/object:Gem::Version
|
117
117
|
version: '0'
|
118
118
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
119
119
|
requirements:
|
120
|
-
- -
|
120
|
+
- - '>='
|
121
121
|
- !ruby/object:Gem::Version
|
122
122
|
version: '0'
|
123
123
|
requirements: []
|
124
|
-
rubyforge_project:
|
125
|
-
rubygems_version: 2.
|
126
|
-
signing_key:
|
124
|
+
rubyforge_project:
|
125
|
+
rubygems_version: 2.1.9
|
126
|
+
signing_key:
|
127
127
|
specification_version: 4
|
128
128
|
summary: histograms data in different ways
|
129
129
|
test_files:
|