文章目录
前言
本次作业是用svm对邮件进行分类，筛选出垃圾邮件
邮件为txt文件
- 首先我们要对邮件进行预处理，去除，替换一些符号
- 然后，将处理好的邮件str转化为单词列表
- 根据给定的单词dict，将邮件单词列表转化为0/1表示的列向量
- 根据此向量，训练线性核SVM
- 得到的SVM模型即可用于分类
代码分析
首先，导入类库
import numpy as np
import matplotlib.pyplot as plt
import scipy.io #Used to load the OCTAVE *.mat files
from sklearn import svm #SVM software
import re #regular expression for e-mail processing
from stemming.porter2 import stem#词干提取
import nltk, nltk.stem.porter
%matplotlib inline
查看email文件
print ("emailSample1.txt:")
#这个是window的cmd命令行
!type data\emailSample1.txt
输出：
emailSample1.txt:
> Anyone knows how much it costs to host a web portal ?
>
Well, it depends on how many visitors you’re expecting.
This can be anywhere from less than 10 bucks a month to a couple of $100.
You should checkout http://www.rackspace.com/ or perhaps Amazon EC2
if youre running something big…
To unsubscribe yourself from this mailing list, send an email to:
[email protected]
预处理email文件
def preProcess( email ):
#使邮件小写
email = email.lower()
#正则化处理email，去掉<>，替换为空格
email = re.sub('<[^<>]+>', ' ', email);
#数字替换为'number'
email = re.sub('[0-9]+', 'number', email)
#'http' or 'https://' 替换为'httpaddr'
email = re.sub('(http|https)://[^\s]*', 'httpaddr', email)
#'@'替换为'emailaddr'
email = re.sub('[^\s]+@[^\s]+', 'emailaddr', email);
#''$'替换为'dollar'
email = re.sub('[$]+', 'dollar', email);
return email
将email文件先preProcess，再提取词干，处理成单词列表
def email2TokenList( raw_email ):
stemmer = nltk.stem.porter.PorterStemmer()
#先对raw_email进行预处理
email = preProcess( raw_email )
#将email分割为单词列表
tokens = re.split('[ \@\$\/\#\.\-\:\&\*\+\=\[\]\?\!\(\)\{\}\,\'\"\>\_\<\;\%]', email)
tokenlist = []
for token in tokens:
#删除所有非字母数字字符
token = re.sub('[^a-zA-Z0-9]', '', token);
#词干提取器 played-->play
stemmed = stemmer.stem( token )
#丢掉空的token
if not len(token): continue
#存储唯一的词干
tokenlist.append(stemmed)
return tokenlist
#处理原始的单词映射文件，得到给定单词的字典
def getVocabDict(reverse=False):
vocab_dict = {
}
#打开映射表
with open("data/vocab.txt") as f:
for line in f:
(val, key) = line.split()
if not reverse:
vocab_dict[key] = int(val)
else:
vocab_dict[int(val)] = key
return vocab_dict
#根据给定的单词字典，将单词list转化为索引list
def email2VocabIndices( raw_email, vocab_dict ):
#将email预处理，并加工为单词list
tokenlist = email2TokenList( raw_email )
#得到单词list的索引list
index_list = [ vocab_dict[token] for token in tokenlist if token in vocab_dict ]
return index_list
好了，下面开始提取特征
将email文件化为n的vocab_dict的长度的列向量
def email2FeatureVector( raw_email, vocab_dict ):
n = len(vocab_dict)
result = np.zeros((n,1))
#email单词索引list
vocab_indices = email2VocabIndices( email_contents, vocab_dict )
for idx in vocab_indices:
result[idx] = 1
return result
测试
# " ... run your code on the email sample. You should see that the feature vector
# has length 1899 and 45 non-zero entries."
#得到给定单词列表的字典
vocab_dict = getVocabDict()
#email内容(str)
email_contents = open( 'data/emailSample1.txt', 'r' ).read()
#将email处理为特征向量
test_fv = email2FeatureVector( email_contents, vocab_dict )
print ("Length of feature vector is %d" % len(test_fv))
print ("Number of non-zero entries is: %d" % sum(test_fv==1))
输出：
Length of feature vector is 1899
Number of non-zero entries is: 45
下面开始训练SVM
# 训练集
datafile = 'data/spamTrain.mat'
mat = scipy.io.loadmat( datafile )
X, y = mat['X'], mat['y']
#不需要再X前插入全为1的一列了，SVM软件会自动为我们做的
# 测试集
datafile = 'data/spamTest.mat'
mat = scipy.io.loadmat( datafile )
Xtest, ytest = mat['Xtest'], mat['ytest']
pos = np.array([X[i] for i in range(X.shape[0]) if y[i] == 1])
neg = np.array([X[i] for i in range(X.shape[0]) if y[i] == 0])
print('Total number of training emails = ',X.shape[0])
print('Number of training spam emails = ',pos.shape[0])
print('Number of training nonspam emails = ',neg.shape[0])
输出：
Total number of training emails = 4000
Number of training spam emails = 1277
Number of training nonspam emails = 2723
训练SVM
#创建C=0.1的线性核SVM
linear_svm = svm.SVC(C=0.1, kernel='linear')
#训练svm
linear_svm.fit( X, y.flatten() )
测试准确率
#测试准确率
train_predictions = linear_svm.predict(X).reshape((y.shape[0],1))#list
train_acc = 100. * float(sum(train_predictions == y))/y.shape[0]
print('Training accuracy = %0.2f%%' % train_acc)
test_predictions = linear_svm.predict(Xtest).reshape((ytest.shape[0],1))
test_acc = 100. * float(sum(test_predictions == ytest))/ytest.shape[0]
print('Test set accuracy = %0.2f%%' % test_acc)
输出：
Training accuracy = 99.83%
Test set accuracy = 98.90%
查看垃圾邮件中最常出现的单词
#得到给定单词列表的字典
vocab_dict_flipped = getVocabDict(reverse=True)
#将svm的参数排序（从大到小）
#linear_svm.coef_为svm的参数theta的numpy数组
sorted_indices = np.argsort( linear_svm.coef_, axis=None )[::-1]#[::-1]翻转列表，使得排序从大到小
print("The 15 most important words to classify a spam e-mail are:")
print([ vocab_dict_flipped[x] for x in sorted_indices[:15] ])
print("The 15 least important words to classify a spam e-mail are:")
print([ vocab_dict_flipped[x] for x in sorted_indices[-15:] ])
# 最常见的词
most_common_word = vocab_dict_flipped[sorted_indices[0]]
print('# of spam containing \"%s\" = %d/%d = %0.2f%%'% (most_common_word, sum(pos[:,1190]),pos.shape[0],100.*float(sum(pos[:,1190]))/pos.shape[0]))
print('# of NON spam containing \"%s\" = %d/%d = %0.2f%%'% (most_common_word, sum(neg[:,1190]),neg.shape[0],100.*float(sum(neg[:,1190]))/neg.shape[0]))
输出：
The 15 most important words to classify a spam e-mail are:
[‘otherwis’, ‘clearli’, ‘remot’, ‘gt’, ‘visa’, ‘base’, ‘doesn’, ‘wife’, ‘previous’, ‘player’, ‘mortgag’, ‘natur’, ‘ll’, ‘futur’, ‘hot’]
The 15 least important words to classify a spam e-mail are:
[‘http’, ‘toll’, ‘xp’, ‘ratio’, ‘august’, ‘unsubscrib’, ‘useless’, ‘numberth’, ‘round’, ‘linux’, ‘datapow’, ‘wrong’, ‘urgent’, ‘that’, ‘spam’]
# of spam containing “otherwis” = 804/1277 = 62.96%
# of NON spam containing “otherwis” = 301/2723 = 11.05%
数据集
spamTrain.mat
spamTest,mat
以上两个可以上kaggle查，这里偷个懒
spamSample1.txt
Do You Want To Make $1000 Or More Per Week?
If you are a motivated and qualified individual - I
will personally demonstrate to you a system that will
make you $1,000 per week or more! This is NOT mlm.
Call our 24 hour pre-recorded number to get the
details.
000-456-789
I need people who want to make serious money. Make
the call and get the facts.
Invest 2 minutes in yourself now!
000-456-789
Looking forward to your call and I will introduce you
to people like yourself who
are currently making $10,000 plus per week!
000-456-789
3484lJGv6-241lEaN9080lRmS6-271WxHo7524qiyT5-438rjUv5615hQcf0-662eiDB9057dMtVl72
spamSample2.txt
Best Buy Viagra Generic Online
Viagra 100mg x 60 Pills $125, Free Pills & Reorder Discount, Top Selling 100% Quality & Satisfaction guaranteed!
We accept VISA, Master & E-Check Payments, 90000+ Satisfied Customers!
http://medphysitcstech.ru
vacab.txt
1 aa
2 ab
3 abil
4 abl
5 about
6 abov
7 absolut
8 abus
9 ac
10 accept
11 access
12 accord
13 account
14 achiev
15 acquir
16 across
17 act
18 action
19 activ
20 actual
21 ad
22 adam
23 add
24 addit
25 address
26 administr
27 adult
28 advanc
29 advantag
30 advertis
31 advic
32 advis
33 ae
34 af
35 affect
36 affili
37 afford
38 africa
39 after
40 ag
41 again
42 against
43 agenc
44 agent
45 ago
46 agre
47 agreement
48 aid
49 air
50 al
51 alb
52 align
53 all
54 allow
55 almost
56 alon
57 along
58 alreadi
59 alsa
60 also
61 altern
62 although
63 alwai
64 am
65 amaz
66 america
67 american
68 among
69 amount
70 amp
71 an
72 analysi
73 analyst
74 and
75 ani
76 anim
77 announc
78 annual
79 annuiti
80 anoth
81 answer
82 anti
83 anumb
84 anybodi
85 anymor
86 anyon
87 anyth
88 anywai
89 anywher
90 aol
91 ap
92 apolog
93 app
94 appar
95 appear
96 appl
97 appli
98 applic
99 appreci
100 approach
101 approv
102 apt
103 ar
104 archiv
105 area
106 aren
107 argument
108 arial
109 arm
110 around
111 arrai
112 arriv
113 art
114 articl
115 artist
116 as
117 ascii
118 ask
119 asset
120 assist
121 associ
122 assum
123 assur
124 at
125 atol
126 attach
127 attack
128 attempt
129 attent
130 attornei
131 attract
132 audio
133 aug
134 august
135 author
136 auto
137 autom
138 automat
139 avail
140 averag
141 avoid
142 awai
143 awar
144 award
145 ba
146 babi
147 back
148 background
149 backup
150 bad
151 balanc
152 ban
153 bank
154 bar
155 base
156 basenumb
157 basi
158 basic
159 bb
160 bc
161 bd
162 be
163 beat
164 beberg
165 becaus
166 becom
167 been
168 befor
169 begin
170 behalf
171 behavior
172 behind
173 believ
174 below
175 benefit
176 best
177 beta
178 better
179 between
180 bf
181 big
182 bill
183 billion
184 bin
185 binari
186 bit
187 black
188 blank
189 block
190 blog
191 blood
192 blue
193 bnumber
194 board
195 bodi
196 boi
197 bonu
198 book
199 boot
200 border
201 boss
202 boston
203 botan
204 both
205 bottl
206 bottom
207 boundari
208 box
209 brain
210 brand
211 break
212 brian
213 bring
214 broadcast
215 broker
216 browser
217 bug
218 bui
219 build
220 built
221 bulk
222 burn
223 bush
224 busi
225 but
226 button
227 by
228 byte
229 ca
230 cabl
231 cach
232 calcul
233 california
234 call
235 came
236 camera
237 campaign
238 can
239 canada
240 cannot
241 canon
242 capabl
243 capillari
244 capit
245 car
246 card
247 care
248 career
249 carri
250 cartridg
251 case
252 cash
253 cat
254 catch
255 categori
256 caus
257 cb
258 cc
259 cd
260 ce
261 cell
262 cent
263 center
264 central
265 centuri
266 ceo
267 certain
268 certainli
269 cf
270 challeng
271 chanc
272 chang
273 channel
274 char
275 charact
276 charg
277 charset
278 chat
279 cheap
280 check
281 cheer
282 chief
283 children
284 china
285 chip
286 choic
287 choos
288 chri
289 citi
290 citizen
291 civil
292 claim
293 class
294 classifi
295 clean
296 clear
297 clearli
298 click
299 client
300 close
301 clue
302 cnet
303 cnumber
304 co
305 code
306 collect
307 colleg
308 color
309 com
310 combin
311 come
312 comfort
313 command
314 comment
315 commentari
316 commerci
317 commiss
318 commit
319 common
320 commun
321 compani
322 compar
323 comparison
324 compat
325 compet
326 competit
327 compil
328 complet
329 comprehens
330 comput
331 concentr
332 concept
333 concern
334 condit
335 conf
336 confer
337 confid
338 confidenti
339 config
340 configur
341 confirm
342 conflict
343 confus
344 congress
345 connect
346 consid
347 consolid
348 constitut
349 construct
350 consult
351 consum
352 contact
353 contain
354 content
355 continu
356 contract
357 contribut
358 control
359 conveni
360 convers
361 convert
362 cool
363 cooper
364 copi
365 copyright
366 core
367 corpor
368 correct
369 correspond
370 cost
371 could
372 couldn
373 count
374 countri
375 coupl
376 cours
377 court
378 cover
379 coverag
380 crash
381 creat
382 creativ
383 credit
384 critic
385 cross
386 cultur
387 current
388 custom
389 cut
390 cv
391 da
392 dagga
393 dai
394 daili
395 dan
396 danger
397 dark
398 data
399 databas
400 datapow
401 date
402 dave
403 david
404 dc
405 de
406 dead
407 deal
408 dear
409 death
410 debt
411 decad
412 decid
413 decis
414 declar
415 declin
416 decor
417 default
418 defend
419 defens
420 defin
421 definit
422 degre
423 delai
424 delet
425 deliv
426 deliveri
427 dell
428 demand
429 democrat
430 depart
431 depend
432 deposit
433 describ
434 descript
435 deserv
436 design
437 desir
438 desktop
439 despit
440 detail
441 detect
442 determin
443 dev
444 devel
445 develop
446 devic
447 di
448 dial
449 did
450 didn
451 diet
452 differ
453 difficult
454 digit
455 direct
456 directli
457 director
458 directori
459 disabl
460 discount
461 discov
462 discoveri
463 discuss
464 disk
465 displai
466 disposit
467 distanc
468 distribut
469 dn
470 dnumber
471 do
472 doc
473 document
474 doe
475 doer
476 doesn
477 dollar
478 dollarac
479 dollarnumb
480 domain
481 don
482 done
483 dont
484 doubl
485 doubt
486 down
487 download
488 dr
489 draw
490 dream
491 drive
492 driver
493 drop
494 drug
495 due
496 dure
497 dvd
498 dw
499 dynam
500 ea
501 each
502 earli
503 earlier
504 earn
505 earth
506 easi
507 easier
508 easili
509 eat
510 eb
511 ebai
512 ec
513 echo
514 econom
515 economi
516 ed
517 edg
518 edit
519 editor
520 educ
521 eff
522 effect
523 effici
524 effort
525 either
526 el
527 electron
528 elimin
529 els
530 email
531 emailaddr
532 emerg
533 empir
534 employ
535 employe
536 en
537 enabl
538 encod
539 encourag
540 end
541 enemi
542 enenkio
543 energi
544 engin
545 english
546 enhanc
547 enjoi
548 enough
549 ensur
550 enter
551 enterpris
552 entertain
553 entir
554 entri
555 enumb
556 environ
557 equal
558 equip
559 equival
560 error
561 especi
562 essenti
563 establish
564 estat
565 estim
566 et
567 etc
568 euro
569 europ
570 european
571 even
572 event
573 eventu
574 ever
575 everi
576 everyon
577 everyth
578 evid
579 evil
580 exactli
581 exampl
582 excel
583 except
584 exchang
585 excit
586 exclus
587 execut
588 exercis
589 exist
590 exmh
591 expand
592 expect
593 expens
594 experi
595 expert
596 expir
597 explain
598 explor
599 express
600 extend
601 extens
602 extra
603 extract
604 extrem
605 ey
606 fa
607 face
608 fact
609 factor
610 fail
611 fair
612 fall
613 fals
614 famili
615 faq
616 far
617 fast
618 faster
619 fastest
620 fat
621 father
622 favorit
623 fax
624 fb
625 fd
626 featur
627 feder
628 fee
629 feed
630 feedback
631 feel
632 femal
633 few
634 ffffff
635 ffnumber
636 field
637 fight
638 figur
639 file
640 fill
641 film
642 filter
643 final
644 financ
645 financi
646 find
647 fine
648 finish
649 fire
650 firewal
651 firm
652 first
653 fit
654 five
655 fix
656 flag
657 flash
658 flow
659 fnumber
660 focu
661 folder
662 folk
663 follow
664 font
665 food
666 for
667 forc
668 foreign
669 forev
670 forget
671 fork
672 form
673 format
674 former
675 fortun
676 forward
677 found
678 foundat
679 four
680 franc
681 free
682 freedom
683 french
684 freshrpm
685 fri
686 fridai
687 friend
688 from
689 front
690 ftoc
691 ftp
692 full
693 fulli
694 fun
695 function
696 fund
697 further
698 futur
699 ga
700 gain
701 game
702 gari
703 garrigu
704 gave
705 gcc
706 geek
707 gener
708 get
709 gif
710 gift
711 girl
712 give
713 given
714 global
715 gnome
716 gnu
717 gnupg
718 go
719 goal
720 god
721 goe
722 gold
723 gone
724 good
725 googl
726 got
727 govern
728 gpl
729 grand
730 grant
731 graphic
732 great
733 greater
734 ground
735 group
736 grow
737 growth
738 gt
739 guarante
740 guess
741 gui
742 guid
743 ha
744 hack
745 had
746 half
747 ham
748 hand
749 handl
750 happen
751 happi
752 hard
753 hardwar
754 hat
755 hate
756 have
757 haven
758 he
759 head
760 header
761 headlin
762 health
763 hear
764 heard
765 heart
766 heaven
767 hei
768 height
769 held
770 hello
771 help
772 helvetica
773 her
774 herba
775 here
776 hermio
777 hettinga
778 hi
779 high
780 higher
781 highli
782 highlight
783 him
784 histori
785 hit
786 hold
787 home
788 honor
789 hope
790 host
791 hot
792 hour
793 hous
794 how
795 howev
796 hp
797 html
798 http
799 httpaddr
800 huge
801 human
802 hundr
803 ibm
804 id
805 idea
806 ident
807 identifi
808 idnumb
809 ie
810 if
811 ignor
812 ii
813 iii
814 iiiiiiihnumberjnumberhnumberjnumberhnumb
815 illeg
816 im
817 imag
818 imagin
819 immedi
820 impact
821 implement
822 import
823 impress
824 improv
825 in
826 inc
827 includ
828 incom
829 increas
830 incred
831 inde
832 independ
833 index
834 india
835 indian
836 indic
837 individu
838 industri
839 info
840 inform
841 initi
842 inlin
843 innov
844 input
845 insert
846 insid
847 instal
848 instanc
849 instant
850 instead
851 institut
852 instruct
853 insur
854 int
855 integr
856 intel
857 intellig
858 intend
859 interact
860 interest
861 interfac
862 intern
863 internet
864 interview
865 into
866 intro
867 introduc
868 inumb
869 invest
870 investig
871 investor
872 invok
873 involv
874 ip
875 ireland
876 irish
877 is
878 island
879 isn
880 iso
881 isp
882 issu
883 it
884 item
885 itself
886 jabber
887 jame
888 java
889 jim
890 jnumberiiiiiiihepihepihf
891 job
892 joe
893 john
894 join
895 journal
896 judg
897 judgment
898 jul
899 juli
900 jump
901 june
902 just
903 justin
904 keep
905 kei
906 kept
907 kernel
908 kevin
909 keyboard
910 kid
911 kill
912 kind
913 king
914 kingdom
915 knew
916 know
917 knowledg
918 known
919 la
920 lack
921 land
922 languag
923 laptop
924 larg
925 larger
926 largest
927 laser
928 last
929 late
930 later
931 latest
932 launch
933 law
934 lawrenc
935 le
936 lead
937 leader
938 learn
939 least
940 leav
941 left
942 legal
943 lender
944 length
945 less
946 lesson
947 let
948 letter
949 level
950 lib
951 librari
952 licens
953 life
954 lifetim
955 light
956 like
957 limit
958 line
959 link
960 linux
961 list
962 listen
963 littl
964 live
965 ll
966 lo
967 load
968 loan
969 local
970 locat
971 lock
972 lockergnom
973 log
974 long
975 longer
976 look
977 lose
978 loss
979 lost
980 lot
981 love
982 low
983 lower
984 lowest
985 lt
986 ma
987 mac
988 machin
989 made
990 magazin
991 mai
992 mail
993 mailer
994 main
995 maintain
996 major
997 make
998 maker
999 male
1000 man
1001 manag
1002 mani
1003 manual
1004 manufactur
1005 map
1006 march
1007 margin
1008 mark
1009 market
1010 marshal
1011 mass
1012 master
1013 match
1014 materi
1015 matter
1016 matthia
1017 mayb
1018 me
1019 mean
1020 measur
1021 mechan
1022 media
1023 medic
1024 meet
1025 member
1026 membership
1027 memori
1028 men
1029 mention
1030 menu
1031 merchant
1032 messag
1033 method
1034 mh
1035 michael
1036 microsoft
1037 middl
1038 might
1039 mike
1040 mile
1041 militari
1042 million
1043 mime
1044 mind
1045 mine
1046 mini
1047 minimum
1048 minut
1049 miss
1050 mistak
1051 mobil
1052 mode
1053 model
1054 modem
1055 modifi
1056 modul
1057 moment
1058 mon
1059 mondai
1060 monei
1061 monitor
1062 month
1063 monthli
1064 more
1065 morn
1066 mortgag
1067 most
1068 mostli
1069 mother
1070 motiv
1071 move
1072 movi
1073 mpnumber
1074 mr
1075 ms
1076 msg
1077 much
1078 multi
1079 multipart
1080 multipl
1081 murphi
1082 music
1083 must
1084 my
1085 myself
1086 name
1087 nation
1088 natur
1089 nbsp
1090 near
1091 nearli
1092 necessari
1093 need
1094 neg
1095 net
1096 netscap
1097 network
1098 never
1099 new
1100 newslett
1101 next
1102 nextpart
1103 nice
1104 nigeria
1105 night
1106 no
1107 nobodi
1108 non
1109 none
1110 nor
1111 normal
1112 north
1113 not
1114 note
1115 noth
1116 notic
1117 now
1118 nt
1119 null
1120 number
1121 numbera
1122 numberam
1123 numberanumb
1124 numberb
1125 numberbit
1126 numberc
1127 numbercb
1128 numbercbr
1129 numbercfont
1130 numbercli
1131 numbercnumb
1132 numbercp
1133 numberctd
1134 numberd
1135 numberdari
1136 numberdnumb
1137 numberenumb
1138 numberf
1139 numberfb
1140 numberff
1141 numberffont
1142 numberfp
1143 numberftd
1144 numberk
1145 numberm
1146 numbermb
1147 numberp
1148 numberpd
1149 numberpm
1150 numberpx
1151 numberst
1152 numberth
1153 numbertnumb
1154 numberx
1155 object
1156 oblig
1157 obtain
1158 obvious
1159 occur
1160 oct
1161 octob
1162 of
1163 off
1164 offer
1165 offic
1166 offici
1167 often
1168 oh
1169 ok
1170 old
1171 on
1172 onc
1173 onli
1174 onlin
1175 open
1176 oper
1177 opinion
1178 opportun
1179 opt
1180 optim
1181 option
1182 or
1183 order
1184 org
1185 organ
1186 origin
1187 os
1188 osdn
1189 other
1190 otherwis
1191 our
1192 out
1193 outlook
1194 output
1195 outsid
1196 over
1197 own
1198 owner
1199 oz
1200 pacif
1201 pack
1202 packag
1203 page
1204 pai
1205 paid
1206 pain
1207 palm
1208 panel
1209 paper
1210 paragraph
1211 parent
1212 part
1213 parti
1214 particip
1215 particular
1216 particularli
1217 partit
1218 partner
1219 pass
1220 password
1221 past
1222 patch
1223 patent
1224 path
1225 pattern
1226 paul
1227 payment
1228 pc
1229 peac
1230 peopl
1231 per
1232 percent
1233 percentag
1234 perfect
1235 perfectli
1236 perform
1237 perhap
1238 period
1239 perl
1240 perman
1241 permiss
1242 person
1243 pgp
1244 phone
1245 photo
1246 php
1247 phrase
1248 physic
1249 pick
1250 pictur
1251 piec
1252 piiiiiiii
1253 pipe
1254 pjnumber
1255 place
1256 plai
1257 plain
1258 plan
1259 planet
1260 plant
1261 planta
1262 platform
1263 player
1264 pleas
1265 plu
1266 plug
1267 pm
1268 pocket
1269 point
1270 polic
1271 polici
1272 polit
1273 poor
1274 pop
1275 popul
1276 popular
1277 port
1278 posit
1279 possibl
1280 post
1281 potenti
1282 pound
1283 powel
1284 power
1285 powershot
1286 practic
1287 pre
1288 predict
1289 prefer
1290 premium
1291 prepar
1292 present
1293 presid
1294 press
1295 pretti
1296 prevent
1297 previou
1298 previous
1299 price
1300 principl
1301 print
1302 printabl
1303 printer
1304 privaci
1305 privat
1306 prize
1307 pro
1308 probabl
1309 problem
1310 procedur
1311 process
1312 processor
1313 procmail
1314 produc
1315 product
1316 profession
1317 profil
1318 profit
1319 program
1320 programm
1321 progress
1322 project
1323 promis
1324 promot
1325 prompt
1326 properti
1327 propos
1328 proprietari
1329 prospect
1330 protect
1331 protocol
1332 prove
1333 proven
1334 provid
1335 proxi
1336 pub
1337 public
1338 publish
1339 pudg
1340 pull
1341 purchas
1342 purpos
1343 put
1344 python
1345 qnumber
1346 qualifi
1347 qualiti
1348 quarter
1349 question
1350 quick
1351 quickli
1352 quit
1353 quot
1354 radio
1355 ragga
1356 rais
1357 random
1358 rang
1359 rate
1360 rather
1361 ratio
1362 razor
1363 razornumb
1364 re
1365 reach
1366 read
1367 reader
1368 readi
1369 real
1370 realiz
1371 realli
1372 reason
1373 receiv
1374 recent
1375 recipi
1376 recommend
1377 record
1378 red
1379 redhat
1380 reduc
1381 refer
1382 refin
1383 reg
1384 regard
1385 region
1386 regist
1387 regul
1388 regular
1389 rel
1390 relat
1391 relationship
1392 releas
1393 relev
1394 reliabl
1395 remain
1396 rememb
1397 remot
1398 remov
1399 replac
1400 repli
1401 report
1402 repositori
1403 repres
1404 republ
1405 request
1406 requir
1407 research
1408 reserv
1409 resid
1410 resourc
1411 respect
1412 respond
1413 respons
1414 rest
1415 result
1416 retail
1417 return
1418 reveal
1419 revenu
1420 revers
1421 review
1422 revok
1423 rh
1424 rich
1425 right
1426 risk
1427 road
1428 robert
1429 rock
1430 role
1431 roll
1432 rom
1433 roman
1434 room
1435 root
1436 round
1437 rpm
1438 rss
1439 rule
1440 run
1441 sa
1442 safe
1443 sai
1444 said
1445 sale
1446 same
1447 sampl
1448 san
1449 saou
1450 sat
1451 satellit
1452 save
1453 saw
1454 scan
1455 schedul
1456 school
1457 scienc
1458 score
1459 screen
1460 script
1461 se
1462 search
1463 season
1464 second
1465 secret
1466 section
1467 secur
1468 see
1469 seed
1470 seek
1471 seem
1472 seen
1473 select
1474 self
1475 sell
1476 seminar
1477 send
1478 sender
1479 sendmail
1480 senior
1481 sens
1482 sensit
1483 sent
1484 sep
1485 separ
1486 septemb
1487 sequenc
1488 seri
1489 serif
1490 seriou
1491 serv
1492 server
1493 servic
1494 set
1495 setup
1496 seven
1497 seventh
1498 sever
1499 sex
1500 sexual
1501 sf
1502 shape
1503 share
1504 she
1505 shell
1506 ship
1507 shop
1508 short
1509 shot
1510 should
1511 show
1512 side
1513 sign
1514 signatur
1515 signific
1516 similar
1517 simpl
1518 simpli
1519 sinc
1520 sincer
1521 singl
1522 sit
1523 site
1524 situat
1525 six
1526 size
1527 skeptic
1528 skill
1529 skin
1530 skip
1531 sleep
1532 slow
1533 small
1534 smart
1535 smoke
1536 smtp
1537 snumber
1538 so
1539 social
1540 societi
1541 softwar
1542 sold
1543 solut
1544 solv
1545 some
1546 someon
1547 someth
1548 sometim
1549 son
1550 song
1551 soni
1552 soon
1553 sorri
1554 sort
1555 sound
1556 sourc
1557 south
1558 space
1559 spain
1560 spam
1561 spamassassin
1562 spamd
1563 spammer
1564 speak
1565 spec
1566 special
1567 specif
1568 specifi
1569 speech
1570 speed
1571 spend
1572 sponsor
1573 sport
1574 spot
1575 src
1576 ssh
1577 st
1578 stabl
1579 staff
1580 stai
1581 stand
1582 standard
1583 star
1584 start
1585 state
1586 statement
1587 statu
1588 step
1589 steve
1590 still
1591 stock
1592 stop
1593 storag
1594 store
1595 stori
1596 strategi
1597 stream
1598 street
1599 string
1600 strip
1601 strong
1602 structur
1603 studi
1604 stuff
1605 stupid
1606 style
1607 subject
1608 submit
1609 subscrib
1610 subscript
1611 substanti
1612 success
1613 such
1614 suffer
1615 suggest
1616 suit
1617 sum
1618 summari
1619 summer
1620 sun
1621 super
1622 suppli
1623 support
1624 suppos
1625 sure
1626 surpris
1627 suse
1628 suspect
1629 sweet
1630 switch
1631 system
1632 tab
1633 tabl
1634 tablet
1635 tag
1636 take
1637 taken
1638 talk
1639 tape
1640 target
1641 task
1642 tax
1643 teach
1644 team
1645 tech
1646 technic
1647 techniqu
1648 technolog
1649 tel
1650 telecom
1651 telephon
1652 tell
1653 temperatur
1654 templ
1655 ten
1656 term
1657 termin
1658 terror
1659 terrorist
1660 test
1661 texa
1662 text
1663 than
1664 thank
1665 that
1666 the
1667 thei
1668 their
1669 them
1670 themselv
1671 then
1672 theori
1673 there
1674 therefor
1675 these
1676 thi
1677 thing
1678 think
1679 thinkgeek
1680 third
1681 those
1682 though
1683 thought
1684 thousand
1685 thread
1686 threat
1687 three
1688 through
1689 thu
1690 thursdai
1691 ti
1692 ticket
1693 tim
1694 time
1695 tip
1696 tire
1697 titl
1698 tm
1699 to
1700 todai
1701 togeth
1702 token
1703 told
1704 toll
1705 tom
1706 toner
1707 toni
1708 too
1709 took
1710 tool
1711 top
1712 topic
1713 total
1714 touch
1715 toward
1716 track
1717 trade
1718 tradit
1719 traffic
1720 train
1721 transact
1722 transfer
1723 travel
1724 treat
1725 tree
1726 tri
1727 trial
1728 trick
1729 trip
1730 troubl
1731 true
1732 truli
1733 trust
1734 truth
1735 try
1736 tue
1737 tuesdai
1738 turn
1739 tv
1740 two
1741 type
1742 uk
1743 ultim
1744 un
1745 under
1746 understand
1747 unfortun
1748 uniqu
1749 unison
1750 unit
1751 univers
1752 unix
1753 unless
1754 unlik
1755 unlimit
1756 unseen
1757 unsolicit
1758 unsubscrib
1759 until
1760 up
1761 updat
1762 upgrad
1763 upon
1764 urgent
1765 url
1766 us
1767 usa
1768 usag
1769 usb
1770 usd
1771 usdollarnumb
1772 useless
1773 user
1774 usr
1775 usual
1776 util
1777 vacat
1778 valid
1779 valu
1780 valuabl
1781 var
1782 variabl
1783 varieti
1784 variou
1785 ve
1786 vendor
1787 ventur
1788 veri
1789 verifi
1790 version
1791 via
1792 video
1793 view
1794 virtual
1795 visa
1796 visit
1797 visual
1798 vnumber
1799 voic
1800 vote
1801 vs
1802 vulner
1803 wa
1804 wai
1805 wait
1806 wake
1807 walk
1808 wall
1809 want
1810 war
1811 warm
1812 warn
1813 warranti
1814 washington
1815 wasn
1816 wast
1817 watch
1818 water
1819 we
1820 wealth
1821 weapon
1822 web
1823 weblog
1824 websit
1825 wed
1826 wednesdai
1827 week
1828 weekli
1829 weight
1830 welcom
1831 well
1832 went
1833 were
1834 west
1835 what
1836 whatev
1837 when
1838 where
1839 whether
1840 which
1841 while
1842 white
1843 whitelist
1844 who
1845 whole
1846 whose
1847 why
1848 wi
1849 wide
1850 width
1851 wife
1852 will
1853 william
1854 win
1855 window
1856 wing
1857 winner
1858 wireless
1859 wish
1860 with
1861 within
1862 without
1863 wnumberp
1864 woman
1865 women
1866 won
1867 wonder
1868 word
1869 work
1870 worker
1871 world
1872 worldwid
1873 worri
1874 worst
1875 worth
1876 would
1877 wouldn
1878 write
1879 written
1880 wrong
1881 wrote
1882 www
1883 ximian
1884 xml
1885 xp
1886 yahoo
1887 ye
1888 yeah
1889 year
1890 yesterdai
1891 yet
1892 york
1893 you
1894 young
1895 your
1896 yourself
1897 zdnet
1898 zero
1899 zip
emailSample1.txt
> Anyone knows how much it costs to host a web portal ?
>
Well, it depends on how many visitors you're expecting.
This can be anywhere from less than 10 bucks a month to a couple of $100.
You should checkout http://www.rackspace.com/ or perhaps Amazon EC2
if youre running something big..
To unsubscribe yourself from this mailing list, send an email to:
[email protected]
emailSample2.txt
Folks,
my first time posting - have a bit of Unix experience, but am new to Linux.
Just got a new PC at home - Dell box with Windows XP. Added a second hard disk
for Linux. Partitioned the disk and have installed Suse 7.2 from CD, which went
fine except it didn't pick up my monitor.
I have a Dell branded E151FPp 15" LCD flat panel monitor and a nVidia GeForce4
Ti4200 video card, both of which are probably too new to feature in Suse's default
set. I downloaded a driver from the nVidia website and installed it using RPM.
Then I ran Sax2 (as was recommended in some postings I found on the net), but
it still doesn't feature my video card in the available list. What next?
Another problem. I have a Dell branded keyboard and if I hit Caps-Lock twice,
the whole machine crashes (in Linux, not Windows) - even the on/off switch is
inactive, leaving me to reach for the power cable instead.
If anyone can help me in any way with these probs., I'd be really grateful -
I've searched the 'net but have run out of ideas.
Or should I be going for a different version of Linux such as RedHat? Opinions
welcome.
Thanks a lot,
Peter
--
Irish Linux Users' Group: [email protected]
http://www.linux.ie/mailman/listinfo/ilug for (un)subscription information.
List maintainer: [email protected]