[Spambayes-checkins] spambayes Corpus.py,1.3,1.4
FileCorpus.py,1.5,1.6 Options.py,1.77,1.78 storage.py,1.1,1.2
Tim Stone
timstone4@users.sourceforge.net
Tue Nov 26 00:43:53 2002
- Previous message: [Spambayes-checkins] spambayes sb0.5.exe,1.1.2.1,NONE
- Next message: [Spambayes-checkins] spambayes
Corpus.py,1.3,1.4FileCorpus.py,1.5,1.6 Options.py,1.77,1.78 storage.py,1.1,1.2
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv18305
Modified Files:
Corpus.py FileCorpus.py Options.py storage.py
Log Message:
Added [globals] section to Options, with a verbose boolean
Changed FileCorpus, Corpus, storage to use the verbose global
Changed the test harness in FileCorpus to account for the wanton
destruction of my favorite method: classifier.classify() <wink>
Index: Corpus.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/Corpus.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** Corpus.py 25 Nov 2002 02:29:44 -0000 1.3
--- Corpus.py 26 Nov 2002 00:43:51 -0000 1.4
***************
*** 87,94 ****
import tokenizer
import re
SPAM = True
HAM = False
- Verbose = False
class Corpus:
--- 87,94 ----
import tokenizer
import re
+ from Options import options
SPAM = True
HAM = False
class Corpus:
***************
*** 115,119 ****
'''Add a Message to this corpus'''
! if Verbose:
print 'adding message %s to corpus' % (message.key())
--- 115,119 ----
'''Add a Message to this corpus'''
! if options.verbose:
print 'adding message %s to corpus' % (message.key())
***************
*** 134,138 ****
key = message.key()
! if Verbose:
print 'removing message %s from corpus' % (key)
self.unCacheMessage(key)
--- 134,138 ----
key = message.key()
! if options.verbose:
print 'removing message %s from corpus' % (key)
self.unCacheMessage(key)
***************
*** 152,156 ****
key = message.key()
! if Verbose:
print 'placing %s in corpus cache' % (key)
--- 152,156 ----
key = message.key()
! if options.verbose:
print 'placing %s in corpus cache' % (key)
***************
*** 169,173 ****
# This method should probably not be overridden
! if Verbose:
print 'Flushing %s from corpus cache' % (key)
--- 169,173 ----
# This method should probably not be overridden
! if options.verbose:
print 'Flushing %s from corpus cache' % (key)
***************
*** 249,253 ****
Corpus.cacheMessage(self, msg)
else:
! if Verbose:
print 'Not caching %s because it has expired' % (msg.key())
raise KeyError, msg
--- 249,253 ----
Corpus.cacheMessage(self, msg)
else:
! if options.verbose:
print 'Not caching %s because it has expired' % (msg.key())
raise KeyError, msg
***************
*** 262,266 ****
msg = self[key]
except KeyError, e:
! if Verbose:
print 'message %s has expired' % (key)
self.removeMessage(e[0])
--- 262,266 ----
msg = self[key]
except KeyError, e:
! if options.verbose:
print 'message %s has expired' % (key)
self.removeMessage(e[0])
Index: FileCorpus.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/FileCorpus.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** FileCorpus.py 25 Nov 2002 20:49:12 -0000 1.5
--- FileCorpus.py 26 Nov 2002 00:43:51 -0000 1.6
***************
*** 88,91 ****
--- 88,92 ----
import storage
import sys, os, gzip, fnmatch, getopt, errno, time, stat
+ from Options import options
class FileCorpus(Corpus.Corpus):
***************
*** 133,137 ****
raise ValueError
! if Corpus.Verbose:
print 'adding',message.key(),'to corpus'
--- 134,138 ----
raise ValueError
! if options.verbose:
print 'adding',message.key(),'to corpus'
***************
*** 145,149 ****
'''Remove a Message from this corpus'''
! if Corpus.Verbose:
print 'removing',message.key(),'from corpus'
--- 146,150 ----
'''Remove a Message from this corpus'''
! if options.verbose:
print 'removing',message.key(),'from corpus'
***************
*** 163,167 ****
s = ''
! if Corpus.Verbose and nummsgs > 0:
lst = ', ' + '%s' % (self.keys())
else:
--- 164,168 ----
s = ''
! if options.verbose and nummsgs > 0:
lst = ', ' + '%s' % (self.keys())
else:
***************
*** 205,209 ****
'''Read the Message substance from the file'''
! if Corpus.Verbose:
print 'loading', self.file_name
--- 206,210 ----
'''Read the Message substance from the file'''
! if options.verbose:
print 'loading', self.file_name
***************
*** 221,225 ****
'''Write the Message substance to the file'''
! if Corpus.Verbose:
print 'storing', self.file_name
--- 222,226 ----
'''Write the Message substance to the file'''
! if options.verbose:
print 'storing', self.file_name
***************
*** 232,236 ****
'''Message hara-kiri'''
! if Corpus.Verbose:
print 'physically deleting file',self.pathname()
--- 233,237 ----
'''Message hara-kiri'''
! if options.verbose:
print 'physically deleting file',self.pathname()
***************
*** 251,255 ****
sub = self.getSubstance()
! if Corpus.Verbose:
sub = self.getSubstance()
else:
--- 252,256 ----
sub = self.getSubstance()
! if options.verbose:
sub = self.getSubstance()
else:
***************
*** 294,298 ****
'''Read the Message substance from the file'''
! if Corpus.Verbose:
print 'loading', self.file_name
--- 295,299 ----
'''Read the Message substance from the file'''
! if options.verbose:
print 'loading', self.file_name
***************
*** 312,316 ****
'''Write the Message substance to the file'''
! if Corpus.Verbose:
print 'storing', self.file_name
--- 313,317 ----
'''Write the Message substance to the file'''
! if options.verbose:
print 'storing', self.file_name
***************
*** 445,459 ****
for msg in unsurecorpus:
! type = classbayes.classify(msg)
! print 'Message %s spam probability is %f' % (msg.key(), msg.spamprob)
! if type == 'ham':
print 'Moving %s from unsurecorpus to hamcorpus, \
! based on prob of %f' % (msg.key(), msg.spamprob)
hamcorpus.takeMessage(msg.key(), unsurecorpus)
! elif type == 'spam':
print 'Moving %s from unsurecorpus to spamcorpus, \
! based on prob of %f' % (msg.key(), msg.spamprob)
spamcorpus.takeMessage(msg.key(), unsurecorpus)
--- 446,460 ----
for msg in unsurecorpus:
! prob = classbayes.spamprob(msg.tokenize())
! print 'Message %s spam probability is %f' % (msg.key(), prob)
! if prob < options.ham_cutoff:
print 'Moving %s from unsurecorpus to hamcorpus, \
! based on prob of %f' % (msg.key(), prob)
hamcorpus.takeMessage(msg.key(), unsurecorpus)
! elif prob > options.spam_cutoff:
print 'Moving %s from unsurecorpus to spamcorpus, \
! based on prob of %f' % (msg.key(), prob)
spamcorpus.takeMessage(msg.key(), unsurecorpus)
***************
*** 686,690 ****
sys.exit()
! Corpus.Verbose = False
runTestServer = False
setupTestServer = False
--- 687,691 ----
sys.exit()
! options.verbose = False
runTestServer = False
setupTestServer = False
***************
*** 707,715 ****
cleanupTestServer = True
elif opt == '-v':
! Corpus.Verbose = True
elif opt == '-g':
useGzip = True
elif opt == '-u':
useExistingDB = True
if setupTestServer:
--- 708,718 ----
cleanupTestServer = True
elif opt == '-v':
! options.verbose = True
elif opt == '-g':
useGzip = True
elif opt == '-u':
useExistingDB = True
+ elif opt == '-v':
+ options.verbose = True
if setupTestServer:
Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/Options.py,v
retrieving revision 1.77
retrieving revision 1.78
diff -C2 -d -r1.77 -r1.78
*** Options.py 25 Nov 2002 04:23:31 -0000 1.77
--- Options.py 26 Nov 2002 00:43:51 -0000 1.78
***************
*** 370,373 ****
--- 370,376 ----
html_ui_port: 8880
html_ui_launch_browser: False
+
+ [globals]
+ verbose: False
"""
***************
*** 456,459 ****
--- 459,464 ----
'html_ui': {'html_ui_port': int_cracker,
'html_ui_launch_browser': boolean_cracker,
+ },
+ 'globals': {'verbose': boolean_cracker,
},
}
Index: storage.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/storage.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** storage.py 25 Nov 2002 06:22:26 -0000 1.1
--- storage.py 26 Nov 2002 00:43:51 -0000 1.2
***************
*** 56,60 ****
NO_UPDATEPROBS = False # Probabilities will not be autoupdated with training
UPDATEPROBS = True # Probabilities will be autoupdated with training
- DEBUG = False
class PickledClassifier(classifier.Classifier):
--- 56,59 ----
***************
*** 73,77 ****
# that pickle does its job
! if DEBUG:
print 'Loading state from',self.db_name,'pickle'
--- 72,76 ----
# that pickle does its job
! if options.verbose:
print 'Loading state from',self.db_name,'pickle'
***************
*** 90,99 ****
self.meta.nspam = tempbayes.get_nspam()
! if DEBUG:
print '%s is an existing pickle, with %d ham and %d spam' \
% (self.db_name, self.nham, self.nspam)
else:
# new pickle
! if DEBUG:
print self.db_name,'is a new pickle'
self.wordinfo = {}
--- 89,98 ----
self.meta.nspam = tempbayes.get_nspam()
! if options.verbose:
print '%s is an existing pickle, with %d ham and %d spam' \
% (self.db_name, self.nham, self.nspam)
else:
# new pickle
! if options.verbose:
print self.db_name,'is a new pickle'
self.wordinfo = {}
***************
*** 104,108 ****
'''Store self as a pickle'''
! if DEBUG:
print 'Persisting',self.db_name,'as a pickle'
--- 103,107 ----
'''Store self as a pickle'''
! if options.verbose:
print 'Persisting',self.db_name,'as a pickle'
***************
*** 135,139 ****
'''Load state from WIDict'''
! if DEBUG:
print 'Loading state from',self.db_name,'WIDict'
--- 134,138 ----
'''Load state from WIDict'''
! if options.verbose:
print 'Loading state from',self.db_name,'WIDict'
***************
*** 146,155 ****
self.set_nspam(nspam)
! if DEBUG:
print '%s is an existing DBDict, with %d ham and %d spam' \
% (self.db_name, self.nham, self.nspam)
else:
# new dbdict
! if DEBUG:
print self.db_name,'is a new DBDict'
self.set_nham(0)
--- 145,154 ----
self.set_nspam(nspam)
! if options.verbose:
print '%s is an existing DBDict, with %d ham and %d spam' \
% (self.db_name, self.nham, self.nspam)
else:
# new dbdict
! if options.verbose:
print self.db_name,'is a new DBDict'
self.set_nham(0)
***************
*** 159,163 ****
'''Place state into persistent store'''
! if DEBUG:
print 'Persisting',self.db_name,'state in WIDict'
--- 158,162 ----
'''Place state into persistent store'''
! if options.verbose:
print 'Persisting',self.db_name,'state in WIDict'
***************
*** 185,189 ****
'''Train the database with the message'''
! if DEBUG:
print 'training with',message.key()
--- 184,188 ----
'''Train the database with the message'''
! if options.verbose:
print 'training with',message.key()
***************
*** 199,203 ****
'''Untrain the database with the message'''
! if DEBUG:
print 'untraining with',message.key()
--- 198,202 ----
'''Untrain the database with the message'''
! if options.verbose:
print 'untraining with',message.key()
- Previous message: [Spambayes-checkins] spambayes sb0.5.exe,1.1.2.1,NONE
- Next message: [Spambayes-checkins] spambayes
Corpus.py,1.3,1.4FileCorpus.py,1.5,1.6 Options.py,1.77,1.78 storage.py,1.1,1.2
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
More information about the Spambayes-checkins
mailing list