https://www.mediawiki.org/wiki/Special:Code/MediaWiki/115128
Revision: 115128
Author: rfaulk
Date: 2012-05-03 14:50:39 +0000 (Thu, 03 May 2012)
Log Message:
-----------
added 28bot to experiments, enabled specification of revision file in postings
command call
Modified Paths:
--------------
trunk/tools/wsor/message_templates/run_postings_and_metrics.py
Modified: trunk/tools/wsor/message_templates/run_postings_and_metrics.py
===================================================================
--- trunk/tools/wsor/message_templates/run_postings_and_metrics.py
2012-05-03 14:48:35 UTC (rev 115127)
+++ trunk/tools/wsor/message_templates/run_postings_and_metrics.py
2012-05-03 14:50:39 UTC (rev 115128)
@@ -22,7 +22,7 @@
Define script usage
"""
class Usage(Exception):
-
+
def __init__(self, msg):
self.msg = msg
@@ -32,53 +32,57 @@
def main(args):
# Set flags for template indices to process
+ """
+
+ """
template_indices = {1 : False, 2 : False, 3 : False,
60 : False, 61 : False, 62 : False, 63 : False, 64 :
False, 65 : False, 66 : False, 67 : False, 68 : False, 69 : False,
70 : False, 71 : False, 72 : False, 73 : False, 74 :
False, 75 : False, 76 : False, 77 : False,
- 84 : False, 85 : False, 86 : False, 99 : False, 100 :
False, 101 : False, 102 : False, 103 : False, 104 : False,
- 105 : False, 106 : False, 107 : False, 108 : False,
109 : False, 110 : False, 111 : False, 112 : False, 113 : False,
- 114 : False, 115 : False, 116 : False, 87 : False, 88
: False,
+ 84 : False, 85 : False, 86 : False, 99 : False, 100 :
False, 101 : False, 102 : False, 103 : False, 104 : False,
+ 105 : False, 106 : False, 107 : False, 108 : False,
109 : False, 110 : False, 111 : False, 112 : False, 113 : False,
+ 114 : False, 115 : False, 116 : False, 87 : False, 88
: False,
89 : False, 90 : False, 91 : False, 92 : False, 93 :
False, 94 : False, 95 : False, 96 : False, 97 : False, 98 : False,
78 : False, 79 : False, 81 : False, 82 : False,
131 : False, 132 : False, 133 : False, 134 : False,
135 : False, 136 : False, 137 : False, 138 : False, 139 : False, 140 : False,
141 : False, 142 : False, # ImageTaggingBot
117 : False, 118 : False, 119 : False, 120 : False,
121 : False, 122 : False, 123 : False, 124 : False, 125 : False, 126 : False,
127 : False, 128 : False, # CorenSearchBot
78 : False, 79 : False, 81 : False, 82 : False, #
TWINKLE
- 4 : True, 5 : True # Welcome templates - chico
- }
-# template_indices = {78 : True}
+ 4 : True, 5 : True, # Welcome templates - chico
+ 143 : False, 144 : False, 145 : False, 146 : False #
28 bot
+ }
+ # template_indices = {78 : True}
# Run postings and metrics
-
-
+
+
generator = 'editcounts'
postings = True
-
+
# postings_cmd = './postings -h db1047 --start=%(start_time)s
--end=%(end_time)s --comment="%(rev_comment)s" --message="{{%(template)s}}"
--outfilename postings_%(file_name)s.tsv'
postings_cmd = './postings -h db42 --start=%(start_time)s
--end=%(end_time)s --message="{{%(template)s}}" --outfilename
postings_%(file_name)s.tsv'
-
+
# metrics_cmd = 'cat ./output/postings_%(file_name)s.tsv | ./metrics -h
db1047 --header --outfilename metrics_%(file_name)s_%(fname_generator)s.tsv
%(generator)s'
metrics_cmd = 'cat ./output/postings_%(file_name)s.tsv | ./metrics -h db42
--header --outfilename metrics_%(file_name)s_%(fname_generator)s.tsv
%(generator)s'
-
- for key in template_indices:
-
+
+ for key in template_indices:
+
if template_indices[key]:
-
+
template_name = 'z' + str(key)
logging.info('Generating postings for %s' % template_name)
-
- name, start_ts, end_ts, comment, user, api_uri =
get_experiment(key)
+ name, start_ts, end_ts, comment, user, api_uri, use_rev_file =
get_experiment(key)
+
if key >= 60 and key <= 116:
filename_part = start_ts[4:8] + '_' + end_ts[4:8] + '_' +
template_name
else:
filename_part = template_name
-
+
# filename_part = 'pt_' + template_name
# filename_part = 'test_' + start_ts[4:8] + '_' + end_ts[4:8] +
'_' + template_name
-
+
if postings:
- cmd = postings_cmd % {'start_time' : start_ts, 'end_time' :
end_ts, 'template' : template_name,
+ cmd = postings_cmd % {'start_time' : start_ts, 'end_time' :
end_ts, 'template' : template_name,
'file_name' : filename_part}
-
+
# Optionally add the user, comment, or api args
if comment != None:
cmd += ' --comment="%s"' % comment
@@ -86,16 +90,18 @@
cmd += ' --user_name="%s"' % user
if api_uri != None:
cmd += ' -a %s' % api_uri
+ if use_rev_file != None:
+ cmd += ' --use_in_file %s' % use_rev_file
else:
cmd = metrics_cmd % {'file_name' : filename_part, 'generator'
: generator, 'fname_generator' : generator}
-
+
logging.info('Issuing command: %s' % cmd)
os.system(cmd)
else:
logging.info('Skipping postings for z%s ' % str(key))
-
+
return 0
@@ -103,11 +109,12 @@
Returns the experiment name and start and end timestamps corresponding to
the key
"""
def get_experiment(index):
-
+
user = None
comment = None
api_uri = None
-
+ use_rev_file = None
+
if index >= 60 and index <= 77:
test_handle = 'Huggle_3'
start_ts = '20111018000000'
@@ -119,7 +126,8 @@
start_ts = '20120201000000'
end_ts = '20120312000000'
api_uri = 'http://pt.wikipedia.org/w/api.php'
-
+ use_rev_file = '/home/rfaulk/pt_welcome_users.tsv'
+
elif index >= 1 and index <= 3:
test_handle = 'Huggle_1_Portuguese'
start_ts = '20111027000000'
@@ -131,13 +139,13 @@
start_ts = '20111108000000'
end_ts = '20111202000000'
comment = '\(\[\[WP:HG\|HG\]\]\)'
-
+
elif index >= 107 and index <= 116:
test_handle = 'Huggle_Short_2'
start_ts = '20111122000000'
end_ts = '20111222000000'
comment = '\(\[\[WP:HG\|HG\]\]\)'
-
+
elif (index >= 78 and index <= 79) or (index >= 81 and index <= 82):
test_handle = 'Twinkle_1'
start_ts = '20111109000000'
@@ -156,21 +164,28 @@
end_ts = '20120226000000'
user = 'CorenSearchBot'
comment = '.*'
-
+
elif index >= 131 and index <= 142:
test_handle = 'ImageTaggingBot'
start_ts = '20111221000000'
end_ts = '20120221000000'
user = 'ImageTaggingBot'
comment = '.*'
-
+
+ elif index >= 143 and index <= 146:
+ test_handle = '28Bot'
+ start_ts = '20120119000000'
+ end_ts = '20120501000000'
+ user = '28bot'
+ comment = '.*'
+
logging.info('Processing %(test_handle)s from %(start_ts)s to %(end_ts)s
on comment "%(comment)s" for user "%(user)s" ...' % {'test_handle' :
test_handle, 'start_ts' : start_ts, 'end_ts' : end_ts, 'comment' : comment,
'user' : user})
-
- return test_handle, start_ts, end_ts, comment, user, api_uri
-
+
+ return test_handle, start_ts, end_ts, comment, user, api_uri, use_rev_file
+
"""
Call main, exit when execution is complete
-"""
+"""
if __name__ == "__main__":
main([])
\ No newline at end of file
_______________________________________________
MediaWiki-CVS mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-cvs
