pg_histogram 0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/.ruby-version +1 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +52 -0
- data/Rakefile +9 -0
- data/lib/pg_histogram/histogram.rb +86 -0
- data/lib/pg_histogram/version.rb +3 -0
- data/lib/pg_histogram.rb +5 -0
- data/pg_histogram.gemspec +25 -0
- data/test/database.yml +6 -0
- data/test/histogram_test.rb +75 -0
- data/test/test_helper.rb +27 -0
- metadata +116 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f1fd000101bac4dc9af44882ab5dd641b3062430
|
4
|
+
data.tar.gz: dc532f7711f65c11aa57706edb3ac6a17124f2e1
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: dd6ef99ccd68ce5bf02bcf75c79a76bc95b61b91c0a44417cc4283ccd659b71af989b80f3e225bfd1b720695c79df0cbb8f00b045134a2bf01e91d7348af3c18
|
7
|
+
data.tar.gz: 096ae0c70711f89ca3a3f9d9a5dc0c7f4585a14248504244859a49e24f6e2ff2edb34017d4f21f4e1853e70d644eb793caa346b0a3a03e8f2875d1120e0e9b33
|
data/.gitignore
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.1.3
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 David Roberts
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
# PostgreSQL Histogram (for ActiveRecord)
|
2
|
+
|
3
|
+
This gem allows for you to efficiently create a histogram from large data sets in your Rails applications.
|
4
|
+
|
5
|
+
It uses PostgreSQL's [width_bucket](http://www.postgresql.org/docs/9.3/static/functions-math.html) function to handle the majority of the processing in the database, and only requires 3 database queries.
|
6
|
+
|
7
|
+
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Add this line to your application's Gemfile:
|
12
|
+
|
13
|
+
gem 'pg_histogram'
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install pg_histogram
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
Create a Histogram object using the following three parameters:
|
26
|
+
|
27
|
+
1. ActiveRecord query to use
|
28
|
+
2. Name of column to count frequency of
|
29
|
+
3. Bucket size (OPTIONAL - default is 0.5)
|
30
|
+
|
31
|
+
<!-- -->
|
32
|
+
histogram = PgHistogram::Histogram.new(Widget.all, 'price', 0.5)
|
33
|
+
|
34
|
+
|
35
|
+
Call the results method to retrieve a Hash of bucket minimums and frequency counts
|
36
|
+
|
37
|
+
# create sample data
|
38
|
+
5.times do { Widget.create(price: 1.2) }
|
39
|
+
10.times do { Widget.create(price: 2.9 ) }
|
40
|
+
|
41
|
+
# get the results
|
42
|
+
@histogram_data = histogram.results
|
43
|
+
=> {1.0=>5, 2.5=>10}
|
44
|
+
|
45
|
+
|
46
|
+
The results can be used by your favorite charting libary, such as [Chartkick](https://github.com/ankane/chartkick), to plot the data.
|
47
|
+
|
48
|
+
<%= column_chart @histogram_data %>
|
49
|
+
|
50
|
+
## Dependencies
|
51
|
+
|
52
|
+
This gem has been tested with Ruby 2.1.3 and ActiveRecord 4.1.6. Please open an issue or PR if you experience issues with other versions.
|
data/Rakefile
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
module PgHistogram
|
2
|
+
class Histogram
|
3
|
+
attr_reader :query, :column, :bucket_size
|
4
|
+
|
5
|
+
BUCKET_COL = 'bucket'
|
6
|
+
FREQUENCY_COL = 'frequency'
|
7
|
+
ROUND_METHODS_BY_DIRECTION = {
|
8
|
+
nil => :round,
|
9
|
+
down: :floor,
|
10
|
+
up: :ceil
|
11
|
+
}
|
12
|
+
|
13
|
+
# column_name name must be safe for SQL injection
|
14
|
+
def initialize(query, column_name, bucket_size = 0.5)
|
15
|
+
@query = query
|
16
|
+
@column = column_name.to_s
|
17
|
+
@bucket_size = bucket_size
|
18
|
+
end
|
19
|
+
|
20
|
+
# returns histogram as hash
|
21
|
+
# bucket minimum as a key
|
22
|
+
# frequency as value
|
23
|
+
def results
|
24
|
+
# error handling case
|
25
|
+
if max == min
|
26
|
+
{ min => query.where("#{column} = ?", min).count }
|
27
|
+
else
|
28
|
+
labeled_histogram
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def min
|
33
|
+
@min ||= round_to_increment(query.minimum(column), :down)
|
34
|
+
end
|
35
|
+
|
36
|
+
def max
|
37
|
+
@max ||= round_to_increment(query.maximum(column), :up)
|
38
|
+
end
|
39
|
+
|
40
|
+
private
|
41
|
+
|
42
|
+
def num_buckets
|
43
|
+
@buckets ||= ((max - min) / bucket_size).to_i
|
44
|
+
end
|
45
|
+
|
46
|
+
# returns the bucket label (minimum which can be in bucket) based on bucket #
|
47
|
+
def bucket_num_to_label(bucket_num)
|
48
|
+
min + bucket_size * (bucket_num - 1)
|
49
|
+
end
|
50
|
+
|
51
|
+
# rounds to the nearest bucket_size increment
|
52
|
+
# can optionally pass :up or :down to always round in one direction
|
53
|
+
def round_to_increment(num, direction = nil)
|
54
|
+
return 0 if num.nil?
|
55
|
+
round_method = ROUND_METHODS_BY_DIRECTION[direction]
|
56
|
+
denominator = 1 / bucket_size
|
57
|
+
(num * denominator).send(round_method) / denominator.to_f
|
58
|
+
end
|
59
|
+
|
60
|
+
# executes the query and converts bucket numbers to minimum step in bucket
|
61
|
+
def labeled_histogram
|
62
|
+
query_for_buckets.each_with_object({}) do |row, results|
|
63
|
+
results[bucket_num_to_label(row[BUCKET_COL].to_i)] = row[FREQUENCY_COL].to_i \
|
64
|
+
unless row[BUCKET_COL].nil?
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def query_for_buckets
|
69
|
+
ActiveRecord::Base.connection.execute(
|
70
|
+
<<-SQL
|
71
|
+
SELECT width_bucket(#{column}, #{min}, #{max}, #{num_buckets}) as #{BUCKET_COL},
|
72
|
+
count(*) as #{FREQUENCY_COL}
|
73
|
+
FROM (#{subquery.to_sql}) as subq_results
|
74
|
+
GROUP BY #{BUCKET_COL}
|
75
|
+
ORDER BY #{BUCKET_COL}
|
76
|
+
SQL
|
77
|
+
)
|
78
|
+
end
|
79
|
+
|
80
|
+
# use passed AR query as a subquery to not interfere with group clause
|
81
|
+
def subquery
|
82
|
+
# override default order
|
83
|
+
query.select(column).order('1')
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
data/lib/pg_histogram.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'pg_histogram/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "pg_histogram"
|
8
|
+
spec.version = PgHistogram::VERSION
|
9
|
+
spec.authors = ["David Roberts"]
|
10
|
+
spec.email = ["david.roberts@elocal.com"]
|
11
|
+
spec.description = %q{Creates a Histogram fron an ActiveRecord query}
|
12
|
+
spec.summary = %q{Histograms using PostgreSQL and ActiveRecord}
|
13
|
+
spec.homepage = "https://github.com/eLocal/pg_histogram"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "activerecord", "~> 4.0"
|
22
|
+
spec.add_dependency "pg", "~> 0.1"
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
end
|
data/test/database.yml
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
require_relative 'test_helper'
|
2
|
+
|
3
|
+
class HistogramTest < Minitest::Test
|
4
|
+
|
5
|
+
def setup
|
6
|
+
Widget.delete_all
|
7
|
+
@hist = PgHistogram::Histogram.new(Widget.all, 'price', 0.5)
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_with_1_result
|
11
|
+
Widget.create!(price: 2.00)
|
12
|
+
|
13
|
+
assert_equal 2.0, @hist.min, 'Minimum is the single price'
|
14
|
+
assert_equal 2.0, @hist.max, 'Minimum is the single price'
|
15
|
+
assert_equal 1, @hist.results[2.0], 'Frequency of 2.0 bucket'
|
16
|
+
end
|
17
|
+
|
18
|
+
def test_ignores_nils_with_1_result
|
19
|
+
Widget.create!(price: 3.00)
|
20
|
+
Widget.create!(price: nil)
|
21
|
+
|
22
|
+
results = @hist.results
|
23
|
+
assert_equal 3.0, @hist.min, 'Minimum is the single price'
|
24
|
+
assert_equal 3.0, @hist.max, 'Minimum is the single price'
|
25
|
+
assert_equal 1, results.count, 'Histogram bucket count'
|
26
|
+
assert_equal 1, results[3.0], 'Frequency of 3.0 bucket'
|
27
|
+
end
|
28
|
+
|
29
|
+
def test_ignores_nils_with_multiple_results
|
30
|
+
Widget.create!(price: 3.00)
|
31
|
+
Widget.create!(price: 2.25)
|
32
|
+
Widget.create!(price: nil)
|
33
|
+
|
34
|
+
results = @hist.results
|
35
|
+
assert_equal 2.0, @hist.min, 'Minimum'
|
36
|
+
assert_equal 3.0, @hist.max, 'Maximum'
|
37
|
+
assert_equal 2, results.count, 'Histogram bucket count'
|
38
|
+
assert_equal 1, results[3.0], 'Frequency of 3.0 bucket'
|
39
|
+
assert_equal 1, results[2.0], 'Frequency of 2.0 bucket'
|
40
|
+
end
|
41
|
+
|
42
|
+
def test_with_many_results
|
43
|
+
# use a different bucket size
|
44
|
+
hist = PgHistogram::Histogram.new(Widget.all, 'price', 0.25)
|
45
|
+
|
46
|
+
10.times { Widget.create!(price: 3.0) }
|
47
|
+
8.times { Widget.create!(price: 5.76) }
|
48
|
+
min_price = Widget.create!(price: 0.98).price
|
49
|
+
max_price = Widget.create!(price: 6.0).price
|
50
|
+
results = hist.results
|
51
|
+
|
52
|
+
assert_equal 0.75, hist.min, 'Histogram minimum price'
|
53
|
+
assert_equal 6.0, hist.max, 'Histogram maximum price'
|
54
|
+
assert_equal 21, hist.send(:num_buckets), 'Histogram buckets'
|
55
|
+
assert_equal 4, results.size, 'Histogram buckets with results'
|
56
|
+
assert_equal 1, results[0.75], 'Frequency of 0.75 bucket'
|
57
|
+
assert_equal 10, results[3.0], 'Frequency of 3.0 bucket'
|
58
|
+
assert_equal 8, results[5.75], 'Frequency of 5.75 bucket'
|
59
|
+
assert_equal 1, results[6.0], 'Frequency of 6.0 bucket'
|
60
|
+
end
|
61
|
+
|
62
|
+
def test_rounding_to_bucket_size
|
63
|
+
hist = PgHistogram::Histogram.new(nil, nil, 0.25)
|
64
|
+
|
65
|
+
assert_equal 0.5, hist.send(:round_to_increment, 0.478), '0.478 rounded to 0.25 interval'
|
66
|
+
assert_equal 1.0, hist.send(:round_to_increment, 1.1), '1.1 rounded to 0.25 interval'
|
67
|
+
assert_equal 0.5, hist.send(:round_to_increment, 0.5), '0.5 rounded to 0.25 interval'
|
68
|
+
assert_equal 0.25, hist.send(:round_to_increment, 0.478, :down), '0.478 rounded down to 0.25 interval'
|
69
|
+
assert_equal 1.0, hist.send(:round_to_increment, 1.1, :down), '1.1 rounded down to 0.25 interval'
|
70
|
+
assert_equal 0.5, hist.send(:round_to_increment, 0.5, :down), '0.5 rounded down to 0.25 interval'
|
71
|
+
assert_equal 0.5, hist.send(:round_to_increment, 0.478, :up), '0.478 rounded up to 0.25 interval'
|
72
|
+
assert_equal 1.25, hist.send(:round_to_increment, 1.1, :up), '1.1 rounded up to 0.25 interval'
|
73
|
+
assert_equal 0.5, hist.send(:round_to_increment, 0.5, :up), '0.5 rounded up to 0.25 interval'
|
74
|
+
end
|
75
|
+
end
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'minitest/spec'
|
3
|
+
require 'logger'
|
4
|
+
require 'active_record'
|
5
|
+
require 'yaml'
|
6
|
+
require 'pg_histogram'
|
7
|
+
|
8
|
+
config = YAML.load(File.read('test/database.yml'))
|
9
|
+
ActiveRecord::Base.establish_connection config['test']
|
10
|
+
ActiveRecord::Base.logger = Logger.new 'tmp/test.log'
|
11
|
+
ActiveRecord::Base.logger.level = Logger::DEBUG
|
12
|
+
ActiveRecord::Migration.verbose = false
|
13
|
+
|
14
|
+
|
15
|
+
# Set up the database that we require
|
16
|
+
ActiveRecord::Schema.define do
|
17
|
+
create_table :widgets, force: true do |t|
|
18
|
+
t.float :price
|
19
|
+
t.timestamps
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
|
25
|
+
class Widget < ActiveRecord::Base
|
26
|
+
end
|
27
|
+
|
metadata
ADDED
@@ -0,0 +1,116 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: pg_histogram
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '0.1'
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- David Roberts
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-10-09 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activerecord
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '4.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '4.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: pg
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0.1'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.1'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Creates a Histogram fron an ActiveRecord query
|
70
|
+
email:
|
71
|
+
- david.roberts@elocal.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- ".ruby-version"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- lib/pg_histogram.rb
|
83
|
+
- lib/pg_histogram/histogram.rb
|
84
|
+
- lib/pg_histogram/version.rb
|
85
|
+
- pg_histogram.gemspec
|
86
|
+
- test/database.yml
|
87
|
+
- test/histogram_test.rb
|
88
|
+
- test/test_helper.rb
|
89
|
+
homepage: https://github.com/eLocal/pg_histogram
|
90
|
+
licenses:
|
91
|
+
- MIT
|
92
|
+
metadata: {}
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
version: '0'
|
107
|
+
requirements: []
|
108
|
+
rubyforge_project:
|
109
|
+
rubygems_version: 2.2.2
|
110
|
+
signing_key:
|
111
|
+
specification_version: 4
|
112
|
+
summary: Histograms using PostgreSQL and ActiveRecord
|
113
|
+
test_files:
|
114
|
+
- test/database.yml
|
115
|
+
- test/histogram_test.rb
|
116
|
+
- test/test_helper.rb
|