bio-biostars-analytics 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.document +5 -0
- data/.travis.yml +13 -0
- data/Gemfile +20 -0
- data/LICENSE.txt +20 -0
- data/README.md +96 -0
- data/README.rdoc +48 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/bin/biostar_api_stats +260 -0
- data/bin/biostar_crawled_stats +251 -0
- data/bin/biostars-analytics +6 -0
- data/data/20140328_api.tsv +1619 -0
- data/data/20140328_crawled.tsv +109599 -0
- data/lib/bio-biostars-analytics.rb +12 -0
- data/lib/bio-biostars-analytics/biostars-analytics.rb +365 -0
- data/test/helper.rb +18 -0
- data/test/test_bio-biostars-analytics.rb +12 -0
- metadata +193 -0
@@ -0,0 +1,12 @@
|
|
1
|
+
# Please require your code below, respecting the naming conventions in the
|
2
|
+
# bioruby directory tree.
|
3
|
+
#
|
4
|
+
# For example, say you have a plugin named bio-plugin, the only uncommented
|
5
|
+
# line in this file would be
|
6
|
+
#
|
7
|
+
# require 'bio/bio-plugin/plugin'
|
8
|
+
#
|
9
|
+
# In this file only require other files. Avoid other source code.
|
10
|
+
|
11
|
+
require 'bio-biostars-analytics/biostars-analytics.rb'
|
12
|
+
|
@@ -0,0 +1,365 @@
|
|
1
|
+
|
2
|
+
require 'rubygems'
|
3
|
+
require 'hpricot'
|
4
|
+
require 'open-uri'
|
5
|
+
require 'chronic'
|
6
|
+
require 'date'
|
7
|
+
require 'json'
|
8
|
+
|
9
|
+
module BioBiostarsAnalytics
|
10
|
+
|
11
|
+
# Categories in Biostar:
|
12
|
+
# Type ID Type
|
13
|
+
# 1 Question
|
14
|
+
# 2 Answer
|
15
|
+
# 3 Comment
|
16
|
+
# 4 Tutorial
|
17
|
+
# 5 Blog
|
18
|
+
# 6 Forum
|
19
|
+
# 7 News
|
20
|
+
# 8
|
21
|
+
# 9 Tool
|
22
|
+
# 10 FixMe
|
23
|
+
# 11 Video
|
24
|
+
# 12 Job
|
25
|
+
# 13 Research Paper
|
26
|
+
# 14 Tip
|
27
|
+
# 15 Poll
|
28
|
+
# 16 Ad
|
29
|
+
@@CATEGORIES = 16
|
30
|
+
|
31
|
+
# Extract the date (day, month, year) from a Biostar forum post formatted date string.
|
32
|
+
def self.extract_date(datestring)
|
33
|
+
# Major headache: weird years like "3.4 years ago"
|
34
|
+
if datestring.match(/\d+\.\d+ years ago/) then
|
35
|
+
return Chronic.parse("#{(datestring.sub(/\d+\./, '').sub(/\s.*$/, '').to_i * 5.2).to_i} weeks ago",
|
36
|
+
:now => Chronic.parse(datestring.sub(/\.\d+/, '')))
|
37
|
+
else
|
38
|
+
return Chronic.parse(datestring)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
# Extracts data from the rendered forum post as well as the Biostar's "post" API.
|
43
|
+
#
|
44
|
+
# Algorithm:
|
45
|
+
# 1. mine data from the rendered forum post
|
46
|
+
# 2. retrieve limited information from Biostar's API
|
47
|
+
# 3. check that gathered data matches up
|
48
|
+
# 4. log it
|
49
|
+
def self.minecontent(log, id)
|
50
|
+
# This hash aggregates information about a particular Biostar question and its answers/comments:
|
51
|
+
post = { 'id' => id }
|
52
|
+
|
53
|
+
#
|
54
|
+
# First: mine data from the rendered forum post
|
55
|
+
#
|
56
|
+
|
57
|
+
url = "http://www.biostars.org/p/#{id}/"
|
58
|
+
page = nil
|
59
|
+
|
60
|
+
begin
|
61
|
+
page = open(url)
|
62
|
+
rescue
|
63
|
+
return
|
64
|
+
end
|
65
|
+
|
66
|
+
if page.base_uri.to_s != url then
|
67
|
+
# Answer URL.
|
68
|
+
return
|
69
|
+
end
|
70
|
+
|
71
|
+
# Question URL that contains the question, its answers and edits.
|
72
|
+
doc = Hpricot(page.read)
|
73
|
+
|
74
|
+
# Bail out if this page does not explicitly mentions a question.
|
75
|
+
return unless doc.search('doc.title') or doc.search('doc.title')[0].inner_html.match(/^Question:/)
|
76
|
+
|
77
|
+
users = []
|
78
|
+
|
79
|
+
# Extract user interactions: questions asked, answered and edits being made
|
80
|
+
times = doc.search('span.relativetime|div.lastedit').map { |element|
|
81
|
+
element.inner_html.sub(/^[^0-9]+/, '').sub(/by\s+$/, '').split("\n").first.strip
|
82
|
+
}
|
83
|
+
links = (doc/'a').delete_if { |link|
|
84
|
+
if link.get_attribute('href') then
|
85
|
+
not link.get_attribute('href').match(/^\/u\/\d+\//) # Has to be a relative link, or we catch Dropbox link-outs too...
|
86
|
+
else
|
87
|
+
true
|
88
|
+
end
|
89
|
+
}.map { |userlink| "#{userlink.get_attribute('href').gsub(/[\/u]+/, '')}\t#{userlink.inner_html}" }
|
90
|
+
votes = doc.search('div.vote-count').map { |vote|
|
91
|
+
if vote.inner_html.match(/^\d+$/) then
|
92
|
+
vote.inner_html.to_i
|
93
|
+
else
|
94
|
+
nil
|
95
|
+
end
|
96
|
+
}
|
97
|
+
tags = doc.search('a.tag').map { |link|
|
98
|
+
link.inner_html
|
99
|
+
}
|
100
|
+
# Sanity check: times and users need to match up (i.e., both arrays need to be of the same length)
|
101
|
+
unless times.length == links.length then
|
102
|
+
$stderr.puts "Post ##{id}: recorded times and author links do not match up (#{times.length} vs. #{links.length})."
|
103
|
+
return
|
104
|
+
end
|
105
|
+
# Sanity check: there cannot be more votes than times/links
|
106
|
+
if votes.length > times.length then
|
107
|
+
$stderr.puts "Post ##{id}: there are more votes than recorded user actions? (#{votes.length} vs. #{links.length})"
|
108
|
+
return
|
109
|
+
end
|
110
|
+
# Question/answer specific stats regarding votes:
|
111
|
+
question_vote = votes[0]
|
112
|
+
answer_number = votes[1..-1].compact.length
|
113
|
+
answer_min_vote = votes[1..-1].compact.sort[0]
|
114
|
+
answer_max_vote = votes[1..-1].compact.sort[-1]
|
115
|
+
answer_avg_vote = nil
|
116
|
+
answer_avg_vote = (answer_min_vote + answer_max_vote).to_f / 2.0 if answer_min_vote and answer_max_vote
|
117
|
+
# Helper variables to deal with the "votes" array, which is shorter than the times/links arrays.
|
118
|
+
# These variables determine when the index counter for the "votes" array is incremented and when
|
119
|
+
# said index is valid.
|
120
|
+
vote_used = false
|
121
|
+
vote_index = 0
|
122
|
+
# Go through each time occurrence/author link pair (and also consider votes):
|
123
|
+
post['records'] = times.length
|
124
|
+
times.each_index { |index|
|
125
|
+
# Sanity check: first time is not an update...
|
126
|
+
if index == 0 and times[index].match(/updated/) then
|
127
|
+
$stderr.puts "Post ##{id}: First recorded time is also an update?"
|
128
|
+
return
|
129
|
+
end
|
130
|
+
# Sanity check: first time is also not a comment...
|
131
|
+
if index == 0 and votes[index] == nil then
|
132
|
+
$stderr.puts "Post ##{id}: First recorded time is a comment?"
|
133
|
+
return
|
134
|
+
end
|
135
|
+
action = 'answered'
|
136
|
+
action = 'asked' if index == 0
|
137
|
+
if votes[vote_index] == nil and not vote_used then
|
138
|
+
action = 'commented'
|
139
|
+
vote_used = true
|
140
|
+
end
|
141
|
+
if times[index].match(/updated/) then
|
142
|
+
action = 'edited'
|
143
|
+
else
|
144
|
+
vote_index += 1
|
145
|
+
vote_used = false
|
146
|
+
end
|
147
|
+
times[index] = times[index].sub(/^[^0-9]+/, '')
|
148
|
+
datetime = extract_date(times[index])
|
149
|
+
post["#{index}"] = {
|
150
|
+
'datestring' => times[index],
|
151
|
+
'year' => datetime.year,
|
152
|
+
'month' => datetime.month,
|
153
|
+
'day' => datetime.day,
|
154
|
+
'action' => action,
|
155
|
+
'uid' => links[index],
|
156
|
+
'question_vote' => question_vote,
|
157
|
+
'answer_number' => answer_number,
|
158
|
+
'answer_min_vote' => answer_min_vote,
|
159
|
+
'answer_max_vote' => answer_max_vote,
|
160
|
+
'answer_avg_vote' => answer_avg_vote,
|
161
|
+
'tags' => tags
|
162
|
+
}
|
163
|
+
}
|
164
|
+
|
165
|
+
page.close
|
166
|
+
|
167
|
+
#
|
168
|
+
# Second: retrieve limited information from Biostar's API
|
169
|
+
#
|
170
|
+
|
171
|
+
url = "http://www.biostars.org/api/post/#{id}/"
|
172
|
+
|
173
|
+
begin
|
174
|
+
doc = JSON.parse(open(url).read)
|
175
|
+
rescue
|
176
|
+
return
|
177
|
+
end
|
178
|
+
|
179
|
+
# Extract the limited information the API offers:
|
180
|
+
post['api_creation_date'] = Chronic.parse(doc['creation_date'])
|
181
|
+
post['api_answer_number'] = doc['answer_count']
|
182
|
+
post['api_question_vote'] = doc['score']
|
183
|
+
post['api_type'] = doc['type']
|
184
|
+
post['api_type_id'] = doc['type_id']
|
185
|
+
|
186
|
+
#
|
187
|
+
# Third: check that gathered data matches up (API and data mined results are matching)
|
188
|
+
#
|
189
|
+
|
190
|
+
# Warning: number of answers matches
|
191
|
+
#
|
192
|
+
# Cannot be used as sanity check, because the Biostar implementation actually returns
|
193
|
+
# a wrong number of answers. For example, http://www.biostars.org/p/7542/ (20 March 2014)
|
194
|
+
# says "4 answers" even though there are clearly just three answers being displayed.
|
195
|
+
# The same applies to underreporting of answers, such as in http://www.biostars.org/p/10927/
|
196
|
+
# (20 March 2014), where 12 answers are shown on the web-page, but the summary on top
|
197
|
+
# reports only 11 answers.
|
198
|
+
unless post['api_answer_number'] == post['0']['answer_number'] then
|
199
|
+
$stderr.puts "Post ##{id}: number of answers differ (#{post['api_answer_number']} vs. #{post['0']['answer_number']}). Resetting number returned by API; using actual count of answers visible to the user."
|
200
|
+
post['api_answer_number'] = post['0']['answer_number']
|
201
|
+
end
|
202
|
+
|
203
|
+
# Sanity check: voting score for the question matches
|
204
|
+
unless post['api_question_vote'] == post['0']['question_vote'] then
|
205
|
+
$stderr.puts "Post ##{id}: mismatch between API's reported question vote and data mined voting score (#{post['api_question_vote']} vs. #{post['0']['question_vote']})."
|
206
|
+
return
|
207
|
+
end
|
208
|
+
|
209
|
+
#
|
210
|
+
# Fourth: log it
|
211
|
+
#
|
212
|
+
|
213
|
+
(0..post['records']-1).each { |index|
|
214
|
+
record = post["#{index}"]
|
215
|
+
log.puts "#{post['id']}\t#{record['datestring']}\t#{record['year']}\t#{record['month']}\t#{record['day']}\t#{record['action']}\t#{record['uid']}\t#{record['question_vote']}\t#{record['answer_number']}\t#{record['answer_min_vote']}\t#{record['answer_max_vote']}\t#{record['answer_avg_vote']}\t#{record['tags'].join(',')}\t#{post['api_type']}\t#{post['api_type_id']}"
|
216
|
+
}
|
217
|
+
end
|
218
|
+
|
219
|
+
# Extracts data from Biostar's "stats" API.
|
220
|
+
def self.minehistory(log, age)
|
221
|
+
url = "http://www.biostars.org/api/stats/#{age}/"
|
222
|
+
|
223
|
+
begin
|
224
|
+
stats = JSON.parse(open(url).read)
|
225
|
+
rescue
|
226
|
+
return
|
227
|
+
end
|
228
|
+
|
229
|
+
# Extract the limited information the API offers:
|
230
|
+
parseddate = Chronic.parse(stats['date'])
|
231
|
+
stats['year'] = parseddate.year
|
232
|
+
stats['month'] = parseddate.month
|
233
|
+
stats['day'] = parseddate.day
|
234
|
+
|
235
|
+
(1..@@CATEGORIES).each { |category|
|
236
|
+
stats["new_posts_in_category_#{category}"] = 0
|
237
|
+
}
|
238
|
+
|
239
|
+
# Types of votes in Biostar:
|
240
|
+
# Accept
|
241
|
+
# Bookmark
|
242
|
+
# Downvote
|
243
|
+
# Upvote
|
244
|
+
stats['new_votes_of_type_Accept'] = 0
|
245
|
+
stats['new_votes_of_type_Bookmark'] = 0
|
246
|
+
stats['new_votes_of_type_Downvote'] = 0
|
247
|
+
stats['new_votes_of_type_Upvote'] = 0
|
248
|
+
|
249
|
+
stats['posters'] = []
|
250
|
+
stats['poster_ages'] = []
|
251
|
+
stats['root_post_ages'] = []
|
252
|
+
stats['vote_post_ages'] = []
|
253
|
+
stats['biostarbabies'] = []
|
254
|
+
|
255
|
+
if stats.has_key?('x_new_users') then
|
256
|
+
stats['x_new_users'].each { |post|
|
257
|
+
@user_age[post['id']] = age
|
258
|
+
stats['biostarbabies'] = stats['biostarbabies'] + [ post['id'] ]
|
259
|
+
}
|
260
|
+
stats['new_users'] = stats['x_new_users'].length
|
261
|
+
else
|
262
|
+
stats['new_users'] = 0
|
263
|
+
end
|
264
|
+
|
265
|
+
if stats.has_key?('x_new_posts') then
|
266
|
+
stats['x_new_posts'].each { |post|
|
267
|
+
@post_age[post['id']] = age
|
268
|
+
stats['posters'] = stats['posters'] + [ post['author_id'] ]
|
269
|
+
stats['poster_ages'] = stats['poster_ages'] + [ @user_age[post['author_id']] ]
|
270
|
+
stats['root_post_ages'] = stats['root_post_ages'] + [ @post_age[post['root_id']] ] if post['root_id'] != post['id']
|
271
|
+
stats["new_posts_in_category_#{post['type_id']}"] = stats["new_posts_in_category_#{post['type_id']}"] + 1
|
272
|
+
}
|
273
|
+
stats['new_posts'] = stats['x_new_posts'].length
|
274
|
+
else
|
275
|
+
stats['new_posts'] = 0
|
276
|
+
end
|
277
|
+
|
278
|
+
# Poster age might not be applicable when having gone too far back in time...
|
279
|
+
stats['poster_ages'].reject! { |i| i == nil }
|
280
|
+
|
281
|
+
if stats.has_key?('x_new_votes') then
|
282
|
+
stats['x_new_votes'].each { |vote|
|
283
|
+
stats['vote_post_ages'] = stats['vote_post_ages'] + [ @post_age[vote['post_id']] ] if vote['type'] == 'Upvote' or vote['type'] == 'Downvote'
|
284
|
+
stats["new_votes_of_type_#{vote['type']}"] = stats["new_votes_of_type_#{vote['type']}"] + 1
|
285
|
+
}
|
286
|
+
stats['new_votes'] = stats['x_new_votes'].length
|
287
|
+
else
|
288
|
+
stats['new_votes'] = 0
|
289
|
+
end
|
290
|
+
|
291
|
+
line = "#{age}\t#{stats['date']}\t#{stats['year']}\t#{stats['month']}\t#{stats['day']}\t"
|
292
|
+
(1..@@CATEGORIES).each { |category|
|
293
|
+
line << "#{stats["new_posts_in_category_#{category}"]}\t"
|
294
|
+
}
|
295
|
+
line << "#{stats['new_votes_of_type_Accept']}\t"
|
296
|
+
line << "#{stats['new_votes_of_type_Bookmark']}\t"
|
297
|
+
line << "#{stats['new_votes_of_type_Downvote']}\t"
|
298
|
+
line << "#{stats['new_votes_of_type_Upvote']}\t"
|
299
|
+
line << "#{stats['new_posts']}\t#{stats['new_votes']}\t#{stats['new_users']}\t"
|
300
|
+
line << "#{stats['posters'].join(',')}\t#{stats['poster_ages'].join(',')}\t#{stats['root_post_ages'].join(',')}\t#{stats['vote_post_ages'].join(',')}\t#{stats['biostarbabies'].join(',')}\t"
|
301
|
+
|
302
|
+
log.puts line
|
303
|
+
end
|
304
|
+
|
305
|
+
def self.cli
|
306
|
+
if not ARGV.length.between?(2, 3) or
|
307
|
+
not ARGV[0].match(/\d+/) or
|
308
|
+
not ARGV[1].match(/\d+/) or
|
309
|
+
(ARGV.length == 3 and not ARGV[2].match(/\d+/))then
|
310
|
+
puts 'Usage: biostars-analytics max_post_number months_look_back [min_post_number]'
|
311
|
+
puts ''
|
312
|
+
puts 'Required parameters:'
|
313
|
+
puts ' max_post_number : highest number (ID) of the post that should'
|
314
|
+
puts ' be mined for data; the crawler will go over'
|
315
|
+
puts ' posts min_post_number to max_post_number'
|
316
|
+
puts ' months_look_back : how many months back should queries to the'
|
317
|
+
puts ' Biostar API go (1 month = 30 days); default'
|
318
|
+
puts ' value is 1'
|
319
|
+
puts ''
|
320
|
+
puts 'Optional parameters:'
|
321
|
+
puts ' min_post_number : lowest number (ID) of the post that should'
|
322
|
+
puts ' be mined for data'
|
323
|
+
puts ''
|
324
|
+
puts 'Output (date matches the script\'s invokation):'
|
325
|
+
puts ' <date>_crawled.tsv : data mined from crawling over posts'
|
326
|
+
puts ' <date>_api.tsv : data extracted from the Biostar API'
|
327
|
+
puts ''
|
328
|
+
puts 'Example 1: mining Biostars in March 2014:'
|
329
|
+
puts ' biostars-analytics 96000 54'
|
330
|
+
puts ''
|
331
|
+
puts 'Example 2: mining last month data with post numbers determined manually:'
|
332
|
+
puts ' biostars-analytics 234 1 123'
|
333
|
+
exit 1
|
334
|
+
end
|
335
|
+
|
336
|
+
max_post_number = ARGV[0].to_i
|
337
|
+
months_look_back = ARGV[1].to_i
|
338
|
+
min_post_number = 1
|
339
|
+
min_post_number = ARGV[2].to_i if ARGV.length == 3
|
340
|
+
|
341
|
+
# Make sure not to buffer stdout, so that it is possible to
|
342
|
+
# snoop around whilst the script is running.
|
343
|
+
STDOUT.sync = true
|
344
|
+
|
345
|
+
today = Time.now.strftime('%Y%m%d')
|
346
|
+
crawler_log = File.open("#{today}_crawled.tsv", 'w')
|
347
|
+
api_log = File.open("#{today}_api.tsv", 'w')
|
348
|
+
|
349
|
+
(min_post_number..max_post_number).each { |i|
|
350
|
+
minecontent(crawler_log, i)
|
351
|
+
}
|
352
|
+
|
353
|
+
@post_age = {}
|
354
|
+
@user_age = {}
|
355
|
+
|
356
|
+
(1..months_look_back*30).to_a.reverse.each { |i|
|
357
|
+
minehistory(api_log, i)
|
358
|
+
}
|
359
|
+
|
360
|
+
crawler_log.close
|
361
|
+
api_log.close
|
362
|
+
end
|
363
|
+
|
364
|
+
end
|
365
|
+
|
data/test/helper.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
require 'test/unit'
|
11
|
+
require 'shoulda'
|
12
|
+
|
13
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
14
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
15
|
+
require 'bio-biostars-analytics'
|
16
|
+
|
17
|
+
class Test::Unit::TestCase
|
18
|
+
end
|
@@ -0,0 +1,12 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestBioBiostarsAnalytics < Test::Unit::TestCase
|
4
|
+
should 'convert a relative time to an absolute time' do
|
5
|
+
assert_contains([
|
6
|
+
"#{BioBiostarsAnalytics::extract_date('3.5 years ago')}",
|
7
|
+
"#{BioBiostarsAnalytics::extract_date('5 days ago')}",
|
8
|
+
"#{BioBiostarsAnalytics::extract_date('8 months ago')}"
|
9
|
+
], /^\d{4}-\d+-\d+ \d+:\d+:\d+.*/)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
metadata
ADDED
@@ -0,0 +1,193 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bio-biostars-analytics
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Joachim Baran
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: shoulda
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rdoc
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.12'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.12'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: jeweler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 2.0.1
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 2.0.1
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: bundler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.0.21
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.0.21
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: bio
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 1.4.2
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 1.4.2
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rdoc
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ~>
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.12'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ~>
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.12'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: hpricot
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ~>
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 0.8.6
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ~>
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 0.8.6
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: chronic
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ~>
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 0.10.2
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ~>
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 0.10.2
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: json
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ~>
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: 1.8.0
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ~>
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: 1.8.0
|
139
|
+
description: Ruby script for data-mining biostars.org using web-crawling techniques
|
140
|
+
as well as utilizing the Biostars RESTful API. Statistical analysis requires R (http://www.r-project.org).
|
141
|
+
email: joachim.baran@gmail.com
|
142
|
+
executables:
|
143
|
+
- biostars-analytics
|
144
|
+
- biostar_api_stats
|
145
|
+
- biostar_crawled_stats
|
146
|
+
extensions: []
|
147
|
+
extra_rdoc_files:
|
148
|
+
- LICENSE.txt
|
149
|
+
- README.md
|
150
|
+
- README.rdoc
|
151
|
+
files:
|
152
|
+
- .document
|
153
|
+
- .travis.yml
|
154
|
+
- Gemfile
|
155
|
+
- LICENSE.txt
|
156
|
+
- README.md
|
157
|
+
- README.rdoc
|
158
|
+
- Rakefile
|
159
|
+
- VERSION
|
160
|
+
- bin/biostar_api_stats
|
161
|
+
- bin/biostar_crawled_stats
|
162
|
+
- bin/biostars-analytics
|
163
|
+
- data/20140328_api.tsv
|
164
|
+
- data/20140328_crawled.tsv
|
165
|
+
- lib/bio-biostars-analytics.rb
|
166
|
+
- lib/bio-biostars-analytics/biostars-analytics.rb
|
167
|
+
- test/helper.rb
|
168
|
+
- test/test_bio-biostars-analytics.rb
|
169
|
+
homepage: http://github.com/joejimbo/bioruby-biostars-analytics
|
170
|
+
licenses:
|
171
|
+
- MIT
|
172
|
+
metadata: {}
|
173
|
+
post_install_message:
|
174
|
+
rdoc_options: []
|
175
|
+
require_paths:
|
176
|
+
- lib
|
177
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
178
|
+
requirements:
|
179
|
+
- - '>='
|
180
|
+
- !ruby/object:Gem::Version
|
181
|
+
version: '0'
|
182
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
183
|
+
requirements:
|
184
|
+
- - '>='
|
185
|
+
- !ruby/object:Gem::Version
|
186
|
+
version: '0'
|
187
|
+
requirements: []
|
188
|
+
rubyforge_project:
|
189
|
+
rubygems_version: 2.0.5
|
190
|
+
signing_key:
|
191
|
+
specification_version: 4
|
192
|
+
summary: Biostars data-mining and statistical analysis.
|
193
|
+
test_files: []
|