logfiction 0.1.0
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 +7 -0
- data/.gitignore +11 -0
- data/.rspec +3 -0
- data/.travis.yml +7 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +35 -0
- data/LICENSE.txt +21 -0
- data/README.md +74 -0
- data/README_ja.md +3 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/exe/logfiction +8 -0
- data/lib/logfiction/version.rb +3 -0
- data/lib/logfiction.rb +419 -0
- data/logfiction.gemspec +40 -0
- metadata +105 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 162ac121bd2301e280c2356317b0b402a01d6614f30790c0474149e6a08474ca
|
4
|
+
data.tar.gz: 4789b4a0b9a13d1a761fdfeb20e25d9d8af321224e1ab693c82f381ad1cb42ae
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 280807f16e592033080bc0de0192ae01b3962fb4590fe38b4c6354c25904f17d95ff8f9c21e935742a22000e2fca7461ed7f525bc940f8479f2699ffa1ea92a9
|
7
|
+
data.tar.gz: 344c49ac6037f3d804d8ea885a317a279101f84e81ab571360ca02dc4d43b3bbf8792ef15569fd1abe37cf1dd347295bccfa0e9408176d7c50a33592392e1a44
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at tomohiro.furusawa.629@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
logfiction (0.1.0)
|
5
|
+
|
6
|
+
GEM
|
7
|
+
remote: https://rubygems.org/
|
8
|
+
specs:
|
9
|
+
diff-lcs (1.3)
|
10
|
+
rake (10.5.0)
|
11
|
+
rspec (3.8.0)
|
12
|
+
rspec-core (~> 3.8.0)
|
13
|
+
rspec-expectations (~> 3.8.0)
|
14
|
+
rspec-mocks (~> 3.8.0)
|
15
|
+
rspec-core (3.8.0)
|
16
|
+
rspec-support (~> 3.8.0)
|
17
|
+
rspec-expectations (3.8.3)
|
18
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
19
|
+
rspec-support (~> 3.8.0)
|
20
|
+
rspec-mocks (3.8.0)
|
21
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
22
|
+
rspec-support (~> 3.8.0)
|
23
|
+
rspec-support (3.8.0)
|
24
|
+
|
25
|
+
PLATFORMS
|
26
|
+
ruby
|
27
|
+
|
28
|
+
DEPENDENCIES
|
29
|
+
bundler (~> 2.0)
|
30
|
+
logfiction!
|
31
|
+
rake (~> 10.0)
|
32
|
+
rspec (~> 3.0)
|
33
|
+
|
34
|
+
BUNDLED WITH
|
35
|
+
2.0.1
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2019 rilmayer
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Logfiction
|
2
|
+
|
3
|
+
This gem is log data generator for learning log analysis, simulation, etc...
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'logfiction'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install logfiction
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
```ruby
|
23
|
+
require 'logfiction'
|
24
|
+
|
25
|
+
la = Logfiction::AccessLog.new()
|
26
|
+
|
27
|
+
# generate 10000 row fiction log!
|
28
|
+
logs = la.generate_accesslog(n=10000)
|
29
|
+
|
30
|
+
#=> [{:timestamp=>2018-06-29 09:04:08 +0900,
|
31
|
+
# :user_id=>54,
|
32
|
+
# :state_id=>2,
|
33
|
+
# :items=>[23],
|
34
|
+
# :state_name=>"detail_page_view"},
|
35
|
+
# {:timestamp=>2018-06-29 09:04:09 +0900,
|
36
|
+
# :user_id=>23,
|
37
|
+
# :state_id=>0,
|
38
|
+
# :items=>[],
|
39
|
+
# :state_name=>"top_page_view"},
|
40
|
+
# {:timestamp=>2018-06-29 09:04:10 +0900,
|
41
|
+
# :user_id=>36,
|
42
|
+
# :state_id=>1,
|
43
|
+
# :items=>[30, 31, 32, 33, 34, 35, 36, 37, 38, 39],
|
44
|
+
# :state_name=>"list_page_view"},
|
45
|
+
# ...
|
46
|
+
|
47
|
+
# CSV Output
|
48
|
+
la.export_logfile(filetype='CSV',filepath='/path/to/file')
|
49
|
+
|
50
|
+
# => timestamp,user_id,state_id,items,state_name
|
51
|
+
# 2018-06-29 11:18:58 +0900,47,2,65,detail_page_view
|
52
|
+
# 2018-06-29 11:18:59 +0900,66,0,"",top_page_view
|
53
|
+
# 2018-06-29 11:19:02 +0900,64,1,50:51:52:53:54:55:56:57:58:59,list_page_view
|
54
|
+
# 2018-06-29 11:19:11 +0900,12,3,89,item_purchase
|
55
|
+
# 2018-06-29 11:19:12 +0900,12,0,"",top_page_view
|
56
|
+
```
|
57
|
+
|
58
|
+
## Development
|
59
|
+
|
60
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
61
|
+
|
62
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
63
|
+
|
64
|
+
## Contributing
|
65
|
+
|
66
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/logfiction. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
67
|
+
|
68
|
+
## License
|
69
|
+
|
70
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
71
|
+
|
72
|
+
## Code of Conduct
|
73
|
+
|
74
|
+
Everyone interacting in the Logfiction project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/logfiction/blob/master/CODE_OF_CONDUCT.md).
|
data/README_ja.md
ADDED
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "logfiction"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/exe/logfiction
ADDED
data/lib/logfiction.rb
ADDED
@@ -0,0 +1,419 @@
|
|
1
|
+
require "logfiction/version"
|
2
|
+
require 'time'
|
3
|
+
require 'csv'
|
4
|
+
|
5
|
+
module Logfiction
|
6
|
+
class FileTypeError < StandardError; end
|
7
|
+
|
8
|
+
SESSION_OUT_MIN_TIME = 30 * 60 # sec (30 min)
|
9
|
+
USER_ACTION_INTERVAL = [1, 120] # lowwer to upper(sec)
|
10
|
+
|
11
|
+
attr_accessor :users, :items, :states, :transions, :assumptions, :access_log
|
12
|
+
|
13
|
+
class AccessLog
|
14
|
+
def initialize(assumptions={})
|
15
|
+
@users = []
|
16
|
+
@items = []
|
17
|
+
@states = []
|
18
|
+
@start_state = []
|
19
|
+
@transitions = []
|
20
|
+
@auto_transiton = {}
|
21
|
+
@assumptions = {}
|
22
|
+
@access_log = {}
|
23
|
+
# access_log: user_id & seuquence of states
|
24
|
+
# ex.) {user_id1(int):
|
25
|
+
# [{timestamp: timestamp(str),
|
26
|
+
# state_id: state_id(int),
|
27
|
+
# item [item(int), ...]}, ...], ...}
|
28
|
+
|
29
|
+
# set assumption
|
30
|
+
set_assumptions(assumptions)
|
31
|
+
end
|
32
|
+
|
33
|
+
# Set assumptions
|
34
|
+
# assumptions: object(hash)
|
35
|
+
# time_access_from(str): from what time generate logs
|
36
|
+
# user_n_sessions(int): how many sessions in day
|
37
|
+
# user_max_states(int): how many states in session
|
38
|
+
# n_users(int): how many users
|
39
|
+
# n_items(int): how many items
|
40
|
+
def set_assumptions(assumptions={})
|
41
|
+
@assumptions = {
|
42
|
+
time_access_from: Time.parse("2018-06-29 09:00:00"),
|
43
|
+
user_max_sessions: 5,
|
44
|
+
user_max_actions: 100,
|
45
|
+
n_users: 100,
|
46
|
+
n_items: 100
|
47
|
+
}
|
48
|
+
if assumptions != {}
|
49
|
+
# [TODO] validate assumptions
|
50
|
+
assumptions.each do |key, value|
|
51
|
+
@assumptions[key] = value
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
# User generater
|
57
|
+
# Input: n_users(int), users(hash)
|
58
|
+
# Ouptput: array of user_info
|
59
|
+
# user_info(hash): {user_id: user_id(int), options}
|
60
|
+
def generate_users(n_users=100, users=[])
|
61
|
+
if users.size == 0
|
62
|
+
user_ids = (0..n_users - 1).to_a
|
63
|
+
@users = user_ids.map{|user_id| { user_id: user_id } }
|
64
|
+
else
|
65
|
+
# [TODO] validate input data
|
66
|
+
@users = users
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
# Item generater
|
71
|
+
# Input: n_items(int), items(hash)
|
72
|
+
# Ouptput: object of array
|
73
|
+
# item(object): { item_id: item_id, options}
|
74
|
+
def generate_items(n_items=100, items=[])
|
75
|
+
if items.size == 0
|
76
|
+
item_ids = (0..n_items - 1).to_a
|
77
|
+
@items = item_ids.map{|item_id| { item_id: item_id } }
|
78
|
+
else
|
79
|
+
# [TODO] validate input data
|
80
|
+
@items = items
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
# States generater
|
85
|
+
# Input: state_transtion(object)
|
86
|
+
# Output: nill
|
87
|
+
def generate_state_transiton(state_transtion={})
|
88
|
+
if state_transtion == {}
|
89
|
+
# default setting is like EC
|
90
|
+
states = [
|
91
|
+
{state_id: 0, state_name: 'top_page_view', item_type: :no_item, request: '/'},
|
92
|
+
{state_id: 1, state_name: 'list_page_view', item_type: :many, request: '/list'},
|
93
|
+
{state_id: 2, state_name: 'detail_page_view', item_type: :one, request: '/item'},
|
94
|
+
{state_id: 3, state_name: 'item_purchase', item_type: :one, request: '/purchace'}
|
95
|
+
]
|
96
|
+
|
97
|
+
start_state = [0]
|
98
|
+
|
99
|
+
taranstion = [
|
100
|
+
# probability is 0.6 if user transit from top(id:0) to list(id:1) page.
|
101
|
+
# transition restrict by item is none.
|
102
|
+
{from: 0, to: 1, probability: 0.6, dependent_item: false},
|
103
|
+
|
104
|
+
# probability is 0.4 if user transit from list(id:1) to detail(id:2) page
|
105
|
+
# "to state" item should be choosed "from state" items.
|
106
|
+
{from: 1, to: 2, probability: 0.4, dependent_item: true},
|
107
|
+
|
108
|
+
# probability is 0.2 if user transit from detatil(id:2) to purchase(id:3) page
|
109
|
+
# "to state" item should be choosed "from state" items.
|
110
|
+
# after transition to state '3', automatically transition to state "0"
|
111
|
+
{from: 2, to: 3, probability: 0.2, dependent_item: true, auto_transiton: 0}
|
112
|
+
]
|
113
|
+
@start_state, @transitions = start_state, taranstion
|
114
|
+
else
|
115
|
+
@start_state = state_transtion[:start_state]
|
116
|
+
@transitions = state_transtion[:states]
|
117
|
+
end
|
118
|
+
# convert states
|
119
|
+
states_hash = {}
|
120
|
+
states.each do |state|
|
121
|
+
states_hash[state[:state_id]] = state
|
122
|
+
end
|
123
|
+
@states = states_hash
|
124
|
+
|
125
|
+
# generate auto transiton
|
126
|
+
@transitions.each do |transition|
|
127
|
+
if transition[:auto_transiton]
|
128
|
+
@auto_transiton[transition[:to]] = transition[:auto_transiton]
|
129
|
+
end
|
130
|
+
end
|
131
|
+
end
|
132
|
+
|
133
|
+
# generate state with items
|
134
|
+
# Input: items
|
135
|
+
# Output: items
|
136
|
+
def get_next_items(from_state_id, to_state_id, current_items)
|
137
|
+
unless from_state_id
|
138
|
+
to_item_type = @states[to_state_id]
|
139
|
+
|
140
|
+
unless to_item_type
|
141
|
+
return []
|
142
|
+
end
|
143
|
+
|
144
|
+
to_item_type = [:item_type]
|
145
|
+
if to_item_type == 'many'
|
146
|
+
item_list = @items.each_slice(10).to_a
|
147
|
+
pick_index = rand(item_list.size)
|
148
|
+
return item_list[pick_index]
|
149
|
+
elsif to_item_type == 'one'
|
150
|
+
pick_index = rand(@items.size)
|
151
|
+
return [@items[pick_index]]
|
152
|
+
else
|
153
|
+
return []
|
154
|
+
end
|
155
|
+
else
|
156
|
+
from_item_type = @states[from_state_id][:item_type]
|
157
|
+
|
158
|
+
to_state = @states[to_state_id]
|
159
|
+
unless to_state
|
160
|
+
return []
|
161
|
+
end
|
162
|
+
to_item_type = to_state[:item_type]
|
163
|
+
|
164
|
+
dependent_item = false
|
165
|
+
@transitions.each do |transiton|
|
166
|
+
# normal transition
|
167
|
+
dependent_item = true if transiton[:from] == from_state_id && transiton[:to] == to_state_id
|
168
|
+
|
169
|
+
# back transition
|
170
|
+
dependent_item = true if transiton[:from] == to_state_id && transiton[:to] == from_state_id
|
171
|
+
end
|
172
|
+
|
173
|
+
unless dependent_item
|
174
|
+
return []
|
175
|
+
end
|
176
|
+
|
177
|
+
# no_item -> many
|
178
|
+
if from_item_type == :no_item && to_item_type == :many
|
179
|
+
item_list = @items.each_slice(10).to_a
|
180
|
+
pick_index = rand(item_list.size)
|
181
|
+
return item_list[pick_index]
|
182
|
+
|
183
|
+
# many -> one
|
184
|
+
elsif from_item_type == :many && to_item_type == :one
|
185
|
+
pick_index = rand(current_items.size)
|
186
|
+
return [current_items[pick_index]]
|
187
|
+
|
188
|
+
# one -> many
|
189
|
+
elsif from_item_type == :one && to_item_type == :many
|
190
|
+
next_items = []
|
191
|
+
item_list = @items.each_slice(10).to_a
|
192
|
+
item_list.each_with_index do |items, i|
|
193
|
+
if items.include?(current_items[0])
|
194
|
+
next_items = items
|
195
|
+
end
|
196
|
+
end
|
197
|
+
return next_items
|
198
|
+
|
199
|
+
# one -> one
|
200
|
+
elsif from_item_type == :one && to_item_type == :one
|
201
|
+
return current_items
|
202
|
+
|
203
|
+
else
|
204
|
+
return []
|
205
|
+
end
|
206
|
+
end
|
207
|
+
end
|
208
|
+
|
209
|
+
# randam choice from states, which has a different probability
|
210
|
+
# [TODO] more logically correct sampling
|
211
|
+
# Input: states_with_probability(Array of state_with_probability(Hash))
|
212
|
+
# state_id(int): probability(int)
|
213
|
+
# Output: state_id(int)
|
214
|
+
def choice_next_state(states_with_probability)
|
215
|
+
# transrate probability to number of trials
|
216
|
+
n_trials = 100
|
217
|
+
total = states_with_probability.values.inject(:+) * n_trials
|
218
|
+
pick = rand(total)
|
219
|
+
currentStack = 0
|
220
|
+
states_with_probability.each do |state_id, probability|
|
221
|
+
if (pick <= currentStack + probability * n_trials)
|
222
|
+
return state_id
|
223
|
+
else
|
224
|
+
currentStack += probability * n_trials
|
225
|
+
end
|
226
|
+
end
|
227
|
+
return states_with_probability.keys.sample
|
228
|
+
end
|
229
|
+
|
230
|
+
# random walk update user state
|
231
|
+
# Input:
|
232
|
+
# current_states(Hash):
|
233
|
+
# before_state(Hash):
|
234
|
+
# state_id(int): state_id
|
235
|
+
# item(Array): item list
|
236
|
+
# states_sequence(Array): states sequence list
|
237
|
+
def update_user_state(user_id)
|
238
|
+
next_state_interval = USER_ACTION_INTERVAL[0] + rand * USER_ACTION_INTERVAL[1]
|
239
|
+
states_sequence = @access_log[user_id] || []
|
240
|
+
|
241
|
+
# first action
|
242
|
+
if states_sequence == []
|
243
|
+
@access_log[user_id] = []
|
244
|
+
next_state_id = @start_state.sample
|
245
|
+
next_timestamp = @assumptions[:time_access_from] + next_state_interval
|
246
|
+
next_items = []
|
247
|
+
else
|
248
|
+
from_state = states_sequence.last
|
249
|
+
|
250
|
+
# check auto transiton
|
251
|
+
auto_transiton_state = @auto_transiton[from_state[:state_id]]
|
252
|
+
unless auto_transiton_state == nil
|
253
|
+
next_state_id = auto_transiton_state
|
254
|
+
next_timestamp = from_state[:timestamp] + 1
|
255
|
+
else
|
256
|
+
|
257
|
+
# new session
|
258
|
+
unless states_sequence.last[:state_id]
|
259
|
+
next_state_id = @start_state.sample
|
260
|
+
next_timestamp = from_state[:timestamp] + (next_state_interval + SESSION_OUT_MIN_TIME)
|
261
|
+
else
|
262
|
+
|
263
|
+
# pickup possible transition states
|
264
|
+
possible_transition_states = []
|
265
|
+
|
266
|
+
# add state from transition_states
|
267
|
+
total_probability = 0
|
268
|
+
@transitions.each do |transition|
|
269
|
+
if transition[:from] == from_state[:state_id]
|
270
|
+
possible_transition_states << {state_id: transition[:to], probability: transition[:probability]}
|
271
|
+
total_probability += transition[:probability]
|
272
|
+
end
|
273
|
+
end
|
274
|
+
|
275
|
+
# add state back and exit
|
276
|
+
# exclude auto transion
|
277
|
+
back_state_id = states_sequence.last(2)[0][:state_id]
|
278
|
+
if states_sequence.size == 1 || @auto_transiton.keys.include?(back_state_id)
|
279
|
+
# exit only
|
280
|
+
possible_transition_states << {state_id: false, probability: 1 - total_probability}
|
281
|
+
else
|
282
|
+
exit_probability = (1 - total_probability) * 0.3
|
283
|
+
back_probability = (1 - total_probability) * 0.7
|
284
|
+
|
285
|
+
# exit and back
|
286
|
+
possible_transition_states << {state_id: false, probability: exit_probability}
|
287
|
+
possible_transition_states << {state_id: back_state_id, probability: back_probability}
|
288
|
+
|
289
|
+
end
|
290
|
+
|
291
|
+
# choice next state
|
292
|
+
state_probability_hash = possible_transition_states.map {|sp| {sp[:state_id] => sp[:probability]} }.reduce(&:merge)
|
293
|
+
next_state_id = choice_next_state(state_probability_hash)
|
294
|
+
next_timestamp = from_state[:timestamp] + next_state_interval
|
295
|
+
end
|
296
|
+
end
|
297
|
+
|
298
|
+
from_state_id = from_state[:state_id]
|
299
|
+
from_statre_items = from_state[:items]
|
300
|
+
next_items = self.get_next_items(from_state_id, next_state_id, from_statre_items)
|
301
|
+
end
|
302
|
+
|
303
|
+
log = {
|
304
|
+
timestamp: next_timestamp,
|
305
|
+
state_id: next_state_id,
|
306
|
+
items: next_items
|
307
|
+
}
|
308
|
+
|
309
|
+
@access_log[user_id] << log
|
310
|
+
|
311
|
+
# return n_actions and n_sessions
|
312
|
+
n_actions = @access_log[user_id].size
|
313
|
+
n_sessions = 0
|
314
|
+
@access_log[user_id].each do |state|
|
315
|
+
n_sessions += 1 unless state[:state_id]
|
316
|
+
end
|
317
|
+
|
318
|
+
return n_actions, n_sessions
|
319
|
+
end
|
320
|
+
|
321
|
+
# Output:
|
322
|
+
# n_actions(int): total number of user's actions
|
323
|
+
# n_sessions: total number of user's sessions
|
324
|
+
def generate_accesslog(n=10000, output_form)
|
325
|
+
|
326
|
+
# set default value unless another manual settting done
|
327
|
+
if @transitions.size == 0
|
328
|
+
self.generate_state_transiton()
|
329
|
+
end
|
330
|
+
|
331
|
+
if @users.size == 0
|
332
|
+
self.generate_users(n_users=100, users=[])
|
333
|
+
end
|
334
|
+
|
335
|
+
if @items.size == 0
|
336
|
+
self.generate_items(n_items=100, items=[])
|
337
|
+
end
|
338
|
+
|
339
|
+
n_row = 1
|
340
|
+
while n_row < n
|
341
|
+
@users.each do |user|
|
342
|
+
user_id = user[:user_id]
|
343
|
+
n_actions = 0
|
344
|
+
n_sessions = 0
|
345
|
+
user_max_sessions = @assumptions[:user_max_sessions]
|
346
|
+
user_max_actions = @assumptions[:user_max_actions]
|
347
|
+
while n_actions < user_max_actions && n_sessions < user_max_sessions
|
348
|
+
n_actions, n_sessions = self.update_user_state(user_id)
|
349
|
+
n_row += 1
|
350
|
+
end
|
351
|
+
end
|
352
|
+
end
|
353
|
+
self.output_accesslog(n=10000, output_form={})
|
354
|
+
end
|
355
|
+
|
356
|
+
def output_accesslog(n=10000, output_form={})
|
357
|
+
# default settings
|
358
|
+
output_form = {
|
359
|
+
basic_log: [:timestamp, :user_id, :state_id, :items],
|
360
|
+
state: [:state_name],
|
361
|
+
user: []
|
362
|
+
}
|
363
|
+
if output_form != {}
|
364
|
+
output_form.each do |key, value|
|
365
|
+
output_form[key] = value
|
366
|
+
end
|
367
|
+
end
|
368
|
+
|
369
|
+
output_accesslogs = []
|
370
|
+
@access_log.each do |user_id, logs|
|
371
|
+
logs.each do |log|
|
372
|
+
if log[:state_id]
|
373
|
+
output_accesslog = {}
|
374
|
+
|
375
|
+
# basic_log
|
376
|
+
output_form[:basic_log].each do |log_item|
|
377
|
+
if log_item == :items
|
378
|
+
output_accesslog[log_item] = log[log_item].map{|e| e[:item_id] }.join(":")
|
379
|
+
elsif log_item == :user_id
|
380
|
+
output_accesslog[log_item] = user_id
|
381
|
+
else
|
382
|
+
output_accesslog[log_item] = log[log_item]
|
383
|
+
end
|
384
|
+
end
|
385
|
+
|
386
|
+
# states
|
387
|
+
output_form[:state].each do |log_item|
|
388
|
+
output_accesslog[log_item] = @states[log[:state_id]][log_item]
|
389
|
+
end
|
390
|
+
|
391
|
+
# users
|
392
|
+
output_form[:user].each do |log_item|
|
393
|
+
output_accesslog[log_item] = @users[log[:state_id]][log_item]
|
394
|
+
end
|
395
|
+
|
396
|
+
output_accesslogs << output_accesslog
|
397
|
+
end
|
398
|
+
end
|
399
|
+
end
|
400
|
+
output_accesslogs.sort{|a, b| a[:timestamp] <=> b[:timestamp]}
|
401
|
+
end
|
402
|
+
|
403
|
+
def export_logfile(n_max=10000, filetype='CSV', filepath='./fiction_log.csv')
|
404
|
+
logs = self.generate_accesslog(n_max=10000)
|
405
|
+
headers = logs.first.keys
|
406
|
+
if filetype == 'CSV'
|
407
|
+
CSV.open(filepath, "wb") do |output|
|
408
|
+
output.puts headers
|
409
|
+
logs.each do |log|
|
410
|
+
output.puts headers.map{|key| log[key]}
|
411
|
+
end
|
412
|
+
end
|
413
|
+
else
|
414
|
+
#[TODO] support output type (json, tsv, ...)
|
415
|
+
raise FileTypeError, "Your input file type is not support..."
|
416
|
+
end
|
417
|
+
end
|
418
|
+
end
|
419
|
+
end
|
data/logfiction.gemspec
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "logfiction/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "logfiction"
|
8
|
+
spec.version = Logfiction::VERSION
|
9
|
+
spec.authors = ["rilmayer"]
|
10
|
+
spec.email = ["tomohiro.furusawa.629@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{log data generator for learning log analysis, simulation, etc...}
|
13
|
+
spec.description = %q{log data generator for learning log analysis, simulation, etc...}
|
14
|
+
spec.homepage = "https://github.com/rilmayer/logfiction"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
if spec.respond_to?(:metadata)
|
20
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
21
|
+
spec.metadata["source_code_uri"] = "https://github.com/rilmayer/logfiction"
|
22
|
+
spec.metadata["changelog_uri"] = "https://github.com/rilmayer/logfiction"
|
23
|
+
else
|
24
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
25
|
+
"public gem pushes."
|
26
|
+
end
|
27
|
+
|
28
|
+
# Specify which files should be added to the gem when it is released.
|
29
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
30
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
31
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
32
|
+
end
|
33
|
+
spec.bindir = "exe"
|
34
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
35
|
+
spec.require_paths = ["lib"]
|
36
|
+
|
37
|
+
spec.add_development_dependency "bundler", "~> 2.0"
|
38
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
39
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
40
|
+
end
|
metadata
ADDED
@@ -0,0 +1,105 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: logfiction
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- rilmayer
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-04-21 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '2.0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '2.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
description: log data generator for learning log analysis, simulation, etc...
|
56
|
+
email:
|
57
|
+
- tomohiro.furusawa.629@gmail.com
|
58
|
+
executables:
|
59
|
+
- logfiction
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- ".rspec"
|
65
|
+
- ".travis.yml"
|
66
|
+
- CODE_OF_CONDUCT.md
|
67
|
+
- Gemfile
|
68
|
+
- Gemfile.lock
|
69
|
+
- LICENSE.txt
|
70
|
+
- README.md
|
71
|
+
- README_ja.md
|
72
|
+
- Rakefile
|
73
|
+
- bin/console
|
74
|
+
- bin/setup
|
75
|
+
- exe/logfiction
|
76
|
+
- lib/logfiction.rb
|
77
|
+
- lib/logfiction/version.rb
|
78
|
+
- logfiction.gemspec
|
79
|
+
homepage: https://github.com/rilmayer/logfiction
|
80
|
+
licenses:
|
81
|
+
- MIT
|
82
|
+
metadata:
|
83
|
+
homepage_uri: https://github.com/rilmayer/logfiction
|
84
|
+
source_code_uri: https://github.com/rilmayer/logfiction
|
85
|
+
changelog_uri: https://github.com/rilmayer/logfiction
|
86
|
+
post_install_message:
|
87
|
+
rdoc_options: []
|
88
|
+
require_paths:
|
89
|
+
- lib
|
90
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
91
|
+
requirements:
|
92
|
+
- - ">="
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: '0'
|
95
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- - ">="
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '0'
|
100
|
+
requirements: []
|
101
|
+
rubygems_version: 3.0.3
|
102
|
+
signing_key:
|
103
|
+
specification_version: 4
|
104
|
+
summary: log data generator for learning log analysis, simulation, etc...
|
105
|
+
test_files: []
|