Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- (spamfilter)
- tasdik at Acer in ~/Dropbox/projects/spamfilter on master [!]
- $ make run
- python test.py
- Enter Corpus Directory['eg: corpus2'] : corpus2
- Enter Spam Sub Directory[eg : 'spam']: spam
- Enter Clean Emails Sub Directory[eg :'ham']: ham
- Enter Limit of files per class(spam/ham)[eg: 1000]: 1500
- Training 1500 emails in spam class
- Skipping file 2912.2005-06-30.SA_and_HP.spam.txt because of bad coding
- Skipping file 3620.2005-07-06.SA_and_HP.spam.txt because of bad coding
- Skipping file 1669.2005-06-22.SA_and_HP.spam.txt because of bad coding
- Skipping file 3635.2005-07-06.SA_and_HP.spam.txt because of bad coding
- Skipping file 0075.2002-04-24.SA_and_HP.spam.txt because of bad coding
- Skipping file 1981.2005-06-24.SA_and_HP.spam.txt because of bad coding
- Skipping file 1934.2005-06-24.SA_and_HP.spam.txt because of bad coding
- Skipping file 3556.2005-07-05.SA_and_HP.spam.txt because of bad coding
- Skipping file 2406.2005-06-27.SA_and_HP.spam.txt because of bad coding
- Skipping file 1280.2002-09-22.SA_and_HP.spam.txt because of bad coding
- Skipping file 3977.2005-07-14.SA_and_HP.spam.txt because of bad coding
- Skipping file 2432.2005-06-27.SA_and_HP.spam.txt because of bad coding
- Skipping file 5070.2005-07-21.SA_and_HP.spam.txt because of bad coding
- Skipping file 3554.2005-07-05.SA_and_HP.spam.txt because of bad coding
- Skipping file 3050.2005-07-01.SA_and_HP.spam.txt because of bad coding
- Skipping file 2132.2005-06-25.SA_and_HP.spam.txt because of bad coding
- Skipping file 0085.2002-05-05.SA_and_HP.spam.txt because of bad coding
- Skipping file 3739.2005-07-06.SA_and_HP.spam.txt because of bad coding
- Skipping file 2789.2005-06-29.SA_and_HP.spam.txt because of bad coding
- Skipping file 4575.2005-07-19.SA_and_HP.spam.txt because of bad coding
- Skipping file 1161.2002-09-08.SA_and_HP.spam.txt because of bad coding
- Skipping file 2928.2005-06-30.SA_and_HP.spam.txt because of bad coding
- Skipping file 1988.2005-06-24.SA_and_HP.spam.txt because of bad coding
- Skipping file 3205.2005-07-02.SA_and_HP.spam.txt because of bad coding
- Skipping file 1563.2005-06-21.SA_and_HP.spam.txt because of bad coding
- Skipping file 0018.2001-07-13.SA_and_HP.spam.txt because of bad coding
- Skipping file 4968.2005-07-20.SA_and_HP.spam.txt because of bad coding
- Skipping file 2798.2005-06-29.SA_and_HP.spam.txt because of bad coding
- Skipping file 1053.2002-08-25.SA_and_HP.spam.txt because of bad coding
- Skipping file 0982.2002-08-08.SA_and_HP.spam.txt because of bad coding
- Skipping file 2661.2005-06-29.SA_and_HP.spam.txt because of bad coding
- Skipping file 1244.2002-09-19.SA_and_HP.spam.txt because of bad coding
- No of Features : 14492,
- Number of spam email : 1468,
- Number of ham email : 0,
- Total number of emails: 1468
- Training 1500 emails in ham class
- No of Features : 18792,
- Number of spam email : 1468,
- Number of ham email : 1500,
- Total number of emails: 2968
- Training took 5.0 minutes : 15.292683 seconds
- ########################################
- Testing the classifier on Test Dataset
- Enter corpus directory: [eg: corpus3] corpus3
- Enter spam directory: spam
- Enter number of files to be scanned [defaults to 1000 files]: 1000
- Testing spam files
- Skipping file: '3898.2005-03-13.BG.spam.txt'' due to bad encoding!
- Classified 5130.2005-06-05.BG.spam.txt incorrectly
- Skipping file: '1472.2004-11-07.BG.spam.txt'' due to bad encoding!
- Skipping file: '5834.2005-07-19.BG.spam.txt'' due to bad encoding!
- Classified 5065.2005-05-31.BG.spam.txt incorrectly
- Skipping file: '4809.2005-05-14.BG.spam.txt'' due to bad encoding!
- Skipping file: '0452.2004-09-03.BG.spam.txt'' due to bad encoding!
- Classified 2480.2005-01-03.BG.spam.txt incorrectly
- Classified 2425.2004-12-30.BG.spam.txt incorrectly
- Skipping file: '0314.2004-08-23.BG.spam.txt'' due to bad encoding!
- Skipping file: '2572.2005-01-07.BG.spam.txt'' due to bad encoding!
- Skipping file: '2947.2005-01-23.BG.spam.txt'' due to bad encoding!
- Classified 0969.2004-10-08.BG.spam.txt incorrectly
- Skipping file: '3956.2005-03-17.BG.spam.txt'' due to bad encoding!
- Skipping file: '2697.2005-01-13.BG.spam.txt'' due to bad encoding!
- Classified 0841.2004-09-29.BG.spam.txt incorrectly
- Skipping file: '1796.2004-11-24.BG.spam.txt'' due to bad encoding!
- Classified 4608.2005-04-30.BG.spam.txt incorrectly
- Skipping file: '2271.2004-12-22.BG.spam.txt'' due to bad encoding!
- Skipping file: '0036.2004-08-03.BG.spam.txt'' due to bad encoding!
- Classified 0299.2004-08-21.BG.spam.txt incorrectly
- Classified 0442.2004-09-02.BG.spam.txt incorrectly
- Skipping file: '1292.2004-10-28.BG.spam.txt'' due to bad encoding!
- Skipping file: '0104.2004-08-08.BG.spam.txt'' due to bad encoding!
- Skipping file: '3356.2005-02-10.BG.spam.txt'' due to bad encoding!
- Skipping file: '2817.2005-01-19.BG.spam.txt'' due to bad encoding!
- Skipping file: '0018.2004-08-02.BG.spam.txt'' due to bad encoding!
- Skipping file: '3358.2005-02-10.BG.spam.txt'' due to bad encoding!
- Skipping file: '2173.2004-12-18.BG.spam.txt'' due to bad encoding!
- Skipping file: '0911.2004-10-04.BG.spam.txt'' due to bad encoding!
- Classified 4787.2005-05-12.BG.spam.txt incorrectly
- Skipping file: '3897.2005-03-13.BG.spam.txt'' due to bad encoding!
- Classified 2995.2005-01-24.BG.spam.txt incorrectly
- Classified 5869.2005-07-20.BG.spam.txt incorrectly
- Skipping file: '2087.2004-12-13.BG.spam.txt'' due to bad encoding!
- Skipping file: '2268.2004-12-22.BG.spam.txt'' due to bad encoding!
- Classified 0915.2004-10-05.BG.spam.txt incorrectly
- Skipping file: '1925.2004-12-02.BG.spam.txt'' due to bad encoding!
- Skipping file: '0680.2004-09-19.BG.spam.txt'' due to bad encoding!
- Classified 1942.2004-12-03.BG.spam.txt incorrectly
- Classified 4857.2005-05-16.BG.spam.txt incorrectly
- Skipping file: '1336.2004-10-30.BG.spam.txt'' due to bad encoding!
- Classified 0827.2004-09-29.BG.spam.txt incorrectly
- Skipping file: '5740.2005-07-14.BG.spam.txt'' due to bad encoding!
- Skipping file: '0425.2004-09-01.BG.spam.txt'' due to bad encoding!
- Skipping file: '2381.2004-12-28.BG.spam.txt'' due to bad encoding!
- Skipping file: '1268.2004-10-27.BG.spam.txt'' due to bad encoding!
- Skipping file: '4023.2005-03-20.BG.spam.txt'' due to bad encoding!
- Skipping file: '0089.2004-08-07.BG.spam.txt'' due to bad encoding!
- Skipping file: '1201.2004-10-24.BG.spam.txt'' due to bad encoding!
- Skipping file: '5743.2005-07-15.BG.spam.txt'' due to bad encoding!
- Skipping file: '0793.2004-09-27.BG.spam.txt'' due to bad encoding!
- Classified 3801.2005-03-07.BG.spam.txt incorrectly
- Classified 0842.2004-09-29.BG.spam.txt incorrectly
- Files classified correctly : 946 out of 964
- Precision : 0.98132780083
- ########################################
Add Comment
Please, Sign In to add comment