mm.txt

ti－idf算法

offer	0.000000	1.000000	6.000000	
often	0.000000	17.000000	6.000000	
old	0.000000	11.000000	6.000000	
on	0.000000	47.000000	6.000000	
once	0.000000	7.000000	6.000000	
one	0.000000	45.000000	6.000000	
only	0.000000	25.000000	6.000000	
open	0.000000	3.000000	6.000000	
or	0.000000	97.000000	6.000000	
order	0.000000	1.000000	6.000000	
other	0.000000	21.000000	6.000000	
others	0.000000	10.000000	6.000000	
otherwise	0.000000	2.000000	6.000000	
our	0.000000	54.000000	6.000000	
out	0.000000	19.000000	6.000000	
over	0.000000	14.000000	6.000000	
own	0.000000	20.000000	6.000000	
paper	0.000000	1.000000	6.000000	
parents	0.000000	2.000000	6.000000	
part	0.000000	11.000000	6.000000	
party	0.000000	1.000000	6.000000	
passed	0.000000	1.000000	6.000000	
past	0.000000	8.000000	6.000000	
patient	0.000000	2.000000	6.000000	
pay	0.000000	1.000000	6.000000	
people	0.000000	26.000000	6.000000	
person	0.000000	16.000000	6.000000	
personal	0.000000	2.000000	6.000000	
picture	0.000000	1.000000	6.000000	
place	0.000000	5.000000	6.000000	
points	0.000000	1.000000	6.000000	
poor	0.000000	1.000000	6.000000	
possible	0.000000	2.000000	6.000000	
potential	0.000000	2.000000	6.000000	
power	0.000000	9.000000	6.000000	
practice	0.000000	1.000000	6.000000	
present	0.000000	5.000000	6.000000	
price	0.000000	2.000000	6.000000	
problem	0.000000	2.000000	6.000000	
problems	0.000000	2.000000	6.000000	
products	0.000000	2.000000	6.000000	
put	0.000000	6.000000	6.000000	
question	0.000000	1.000000	6.000000	
reach	0.000000	2.000000	6.000000	
read	0.000000	3.000000	6.000000	
real	0.000000	5.000000	6.000000	
really	0.000000	15.000000	6.000000	
reason	0.000000	1.000000	6.000000	
recent	0.000000	1.000000	6.000000	
regret	0.000000	1.000000	6.000000	
required	0.000000	2.000000	6.000000	
respect	0.000000	2.000000	6.000000	
right	0.000000	5.000000	6.000000	
road	0.000000	3.000000	6.000000	
role	0.000000	1.000000	6.000000	
room	0.000000	4.000000	6.000000	
run	0.000000	1.000000	6.000000	
s	0.000000	45.000000	6.000000	
safe	0.000000	1.000000	6.000000	
said	0.000000	8.000000	6.000000	
same	0.000000	11.000000	6.000000	
say	0.000000	8.000000	6.000000	
science	0.000000	2.000000	6.000000	
sea	0.000000	3.000000	6.000000	
second	0.000000	2.000000	6.000000	
see	0.000000	19.000000	6.000000	
seems	0.000000	3.000000	6.000000	
seen	0.000000	1.000000	6.000000	
sent	0.000000	1.000000	6.000000	
serious	0.000000	2.000000	6.000000	
service	0.000000	3.000000	6.000000	
set	0.000000	8.000000	6.000000	
she	0.000000	1.000000	6.000000	
short	0.000000	4.000000	6.000000	
should	0.000000	16.000000	6.000000	
show	0.000000	2.000000	6.000000	
since	0.000000	3.000000	6.000000	
slow	0.000000	1.000000	6.000000	
small	0.000000	4.000000	6.000000	
so	0.000000	42.000000	6.000000	
some	0.000000	15.000000	6.000000	
something	0.000000	9.000000	6.000000	
soon	0.000000	7.000000	6.000000	
stage	0.000000	1.000000	6.000000	
state	0.000000	6.000000	6.000000	
step	0.000000	3.000000	6.000000	
still	0.000000	6.000000	6.000000	
stop	0.000000	9.000000	6.000000	
story	0.000000	1.000000	6.000000	
strong	0.000000	2.000000	6.000000	
student	0.000000	3.000000	6.000000	
study	0.000000	1.000000	6.000000	
success	0.000000	13.000000	6.000000	
such	0.000000	7.000000	6.000000	
suffering	0.000000	1.000000	6.000000	
summer	0.000000	4.000000	6.000000	
sure	0.000000	2.000000	6.000000	
system	0.000000	2.000000	6.000000	
t	0.000000	31.000000	6.000000	
take	0.000000	18.000000	6.000000	
takes	0.000000	5.000000	6.000000	
taking	0.000000	2.000000	6.000000	
team	0.000000	2.000000	6.000000	
tell	0.000000	3.000000	6.000000	
than	0.000000	16.000000	6.000000	
that	0.000000	188.000000	6.000000	
the	0.000000	664.000000	6.000000	
their	0.000000	44.000000	6.000000	
them	0.000000	28.000000	6.000000	
then	0.000000	22.000000	6.000000	
there	0.000000	41.000000	6.000000	
these	0.000000	16.000000	6.000000	
they	0.000000	69.000000	6.000000	
things	0.000000	13.000000	6.000000	
third	0.000000	2.000000	6.000000	
this	0.000000	48.000000	6.000000	
those	0.000000	21.000000	6.000000	
three	0.000000	10.000000	6.000000	
through	0.000000	10.000000	6.000000	
time	0.000000	34.000000	6.000000	
to	0.000000	343.000000	6.000000	
today	0.000000	6.000000	6.000000	
tomorrow	0.000000	3.000000	6.000000	
took	0.000000	1.000000	6.000000	
top	0.000000	1.000000	6.000000	
toward	0.000000	3.000000	6.000000	
towards	0.000000	1.000000	6.000000	
trade	0.000000	1.000000	6.000000	
true	0.000000	11.000000	6.000000	
trying	0.000000	3.000000	6.000000	
two	0.000000	5.000000	6.000000	
unable	0.000000	1.000000	6.000000	
under	0.000000	2.000000	6.000000	
until	0.000000	2.000000	6.000000	
up	0.000000	7.000000	6.000000	
upon	0.000000	14.000000	6.000000	
us	0.000000	43.000000	6.000000	
use	0.000000	10.000000	6.000000	
very	0.000000	13.000000	6.000000	
waiting	0.000000	3.000000	6.000000	
walking	0.000000	1.000000	6.000000	
want	0.000000	6.000000	6.000000	
was	0.000000	30.000000	6.000000	
way	0.000000	7.000000	6.000000	
we	0.000000	143.000000	6.000000	
week	0.000000	1.000000	6.000000	
well	0.000000	15.000000	6.000000	
were	0.000000	10.000000	6.000000	
what	0.000000	77.000000	6.000000	
when	0.000000	54.000000	6.000000	
where	0.000000	7.000000	6.000000	
whether	0.000000	5.000000	6.000000	
which	0.000000	28.000000	6.000000	
while	0.000000	6.000000	6.000000	
who	0.000000	31.000000	6.000000	
whole	0.000000	1.000000	6.000000	
whom	0.000000	1.000000	6.000000	
will	0.000000	42.000000	6.000000	
wise	0.000000	1.000000	6.000000	
with	0.000000	85.000000	6.000000	
within	0.000000	10.000000	6.000000	
without	0.000000	6.000000	6.000000	
wonderful	0.000000	1.000000	6.000000	
word	0.000000	2.000000	6.000000	
work	0.000000	19.000000	6.000000	
world	0.000000	27.000000	6.000000	
would	0.000000	37.000000	6.000000	
year	0.000000	5.000000	6.000000	
years	0.000000	6.000000	6.000000	
yesterday	0.000000	1.000000	6.000000	
you	0.000000	170.000000	6.000000	
young	0.000000	7.000000	6.000000	
your	0.000000	106.000000	6.000000	
第4篇文档
yours	0.001456	11.000000	3.000000	
zhang	0.000839	4.000000	2.000000	
wu	0.000420	2.000000	2.000000	
zhong	0.000420	2.000000	2.000000	
woolen	0.000210	1.000000	2.000000	
woolens	0.000210	1.000000	2.000000	
xiajun	0.000210	1.000000	2.000000	
xuan	0.000210	1.000000	2.000000	
writing	0.000209	6.000000	5.000000	
written	0.000155	2.000000	4.000000	
wonder	0.000035	1.000000	5.000000	
worked	0.000035	1.000000	5.000000	
working	0.000035	1.000000	5.000000	
york	0.000035	1.000000	5.000000	
with	0.000000	40.000000	6.000000	
within	0.000000	1.000000	6.000000	
without	0.000000	4.000000	6.000000	
wonderful	0.000000	1.000000	6.000000	
word	0.000000	2.000000	6.000000	
work	0.000000	7.000000	6.000000	
world	0.000000	2.000000	6.000000	
would	0.000000	20.000000	6.000000	
year	0.000000	5.000000	6.000000	
years	0.000000	11.000000	6.000000	
yesterday	0.000000	2.000000	6.000000	
you	0.000000	47.000000	6.000000	
young	0.000000	2.000000	6.000000	
your	0.000000	34.000000	6.000000	
第5篇文档
vt	0.018626	298.000000	2.000000	
vi	0.007375	118.000000	2.000000	
unit	0.003568	35.000000	1.000000	
v	0.001577	40.000000	3.000000	
weapons	0.000510	5.000000	1.000000	
youth	0.000500	8.000000	2.000000	
wells	0.000408	4.000000	1.000000	
wit	0.000408	4.000000	1.000000	
xenotransplantation	0.000408	4.000000	1.000000	
violence	0.000375	6.000000	2.000000	
vulgar	0.000313	5.000000	2.000000	
wholly	0.000306	3.000000	1.000000	
worthy	0.000306	3.000000	1.000000	
weary	0.000250	4.000000	2.000000	
wisdom	0.000250	4.000000	2.000000	
writer	0.000237	6.000000	3.000000	
war	0.000231	10.000000	4.000000	
yet	0.000231	10.000000	4.000000	
unwilling	0.000204	2.000000	1.000000	
uses	0.000204	2.000000	1.000000	
whimsical	0.000204	2.000000	1.000000	
whizzed	0.000204	2.000000	1.000000	
wrought	0.000204	2.000000	1.000000	
xenotransplants	0.000204	2.000000	1.000000	
yeast	0.000204	2.000000	1.000000	
ways	0.000197	5.000000	3.000000	
victims	0.000188	3.000000	2.000000	
virtually	0.000188	3.000000	2.000000	
visitors	0.000188	3.000000	2.000000	
workmen	0.000188	3.000000	2.000000	
zone	0.000188	3.000000	2.000000	
united	0.000161	7.000000	4.000000	
wait	0.000158	4.000000	3.000000	
whose	0.000158	4.000000	3.000000	
writers	0.000158	4.000000	3.000000	
value	0.000138	6.000000	4.000000	
women	0.000138	6.000000	4.000000	
words	0.000138	6.000000	4.000000	
universal	0.000125	2.000000	2.000000	
universe	0.000125	2.000000	2.000000	
values	0.000125	2.000000	2.000000	
varieties	0.000125	2.000000	2.000000	
velocity	0.000125	2.000000	2.000000	
vernacular	0.000125	2.000000	2.000000	
vice	0.000125	2.000000	2.000000	
wages	0.000125	2.000000	2.000000	
warp	0.000125	2.000000	2.000000	
wash	0.000125	2.000000	2.000000	
washed	0.000125	2.000000	2.000000	
winners	0.000125	2.000000	2.000000	
withdraw	0.000125	2.000000	2.000000	
younger	0.000125	2.000000	2.000000	
used	0.000124	12.000000	5.000000	
vulnerable	0.000118	3.000000	3.000000	
welfare	0.000118	3.000000	3.000000	
widely	0.000118	3.000000	3.000000	
workers	0.000118	3.000000	3.000000	
worries	0.000118	3.000000	3.000000	
western	0.000115	5.000000	4.000000	
unite	0.000102	1.000000	1.000000	
uniting	0.000102	1.000000	1.000000	
universally	0.000102	1.000000	1.000000	
unnatural	0.000102	1.000000	1.000000	
unpopulated	0.000102	1.000000	1.000000	
unseasonable	0.000102	1.000000	1.000000	
unselfishness	0.000102	1.000000	1.000000	
unutterable	0.000102	1.000000	1.000000	
unwieldy	0.000102	1.000000	1.000000	
unworrying	0.000102	1.000000	1.000000	
unworthy	0.000102	1.000000	1.000000	
upgraded	0.000102	1.000000	1.000000	
urge	0.000102	1.000000	1.000000	
usa	0.000102	1.000000	1.000000	
users	0.000102	1.000000	1.000000	
valued	0.000102	1.000000	1.000000	
varions	0.000102	1.000000	1.000000	
vastly	0.000102	1.000000	1.000000	
veerybody	0.000102	1.000000	1.000000	
veterans	0.000102	1.000000	1.000000	
victorians	0.000102	1.000000	1.000000	
victories	0.000102	1.000000	1.000000	
vie	0.000102	1.000000	1.000000	
vies	0.000102	1.000000	1.000000	
vines	0.000102	1.000000	1.000000	
virginal	0.000102	1.000000	1.000000	
virus	0.000102	1.000000	1.000000	
vital	0.000102	1.000000	1.000000	
vitality	0.000102	1.000000	1.000000	
volume	0.000102	1.000000	1.000000	
vs	0.000102	1.000000	1.000000	
waken	0.000102	1.000000	1.000000	
wanderers	0.000102	1.000000	1.000000	
wandering	0.000102	1.000000	1.000000	
warn	0.000102	1.000000	1.000000	
wars	0.000102	1.000000	1.000000	
warships	0.000102	1.000000	1.000000	
wealthier	0.000102	1.000000	1.000000	
weapon	0.000102	1.000000	1.000000	
weaving	0.000102	1.000000	1.000000	
wedges	0.000102	1.000000	1.000000	
weekends	0.000102	1.000000	1.000000	
whimsies	0.000102	1.000000	1.000000	
whimsy	0.000102	1.000000	1.000000	
whiz	0.000102	1.000000	1.000000	
whizzes	0.000102	1.000000	1.000000	
whizzing	0.000102	1.000000	1.000000	
wickedly	0.000102	1.000000	1.000000	
widespread	0.000102	1.000000	1.000000	
wieldy	0.000102	1.000000	1.000000	
wilderness	0.000102	1.000000	1.000000	
windy	0.000102	1.000000	1.000000	
winkling	0.000102	1.000000	1.000000	
wision	0.000102	1.000000	1.000000	
witty	0.000102	1.000000	1.000000	
wonderment	0.000102	1.000000	1.000000	
woolly	0.000102	1.000000	1.000000	
worded	0.000102	1.000000	1.000000	
workings	0.000102	1.000000	1.000000	
workman	0.000102	1.000000	1.000000	
wqy	0.000102	1.000000	1.000000	
wrestling	0.000102	1.000000	1.000000	
writes	0.000102	1.000000	1.000000	
wwe	0.000102	1.000000	1.000000	
xeno	0.000102	1.000000	1.000000	
yardstick	0.000102	1.000000	1.000000	
yardsticks	0.000102	1.000000	1.000000	
yearly	0.000102	1.000000	1.000000	
yorkers	0.000102	1.000000	1.000000	
zainuddin	0.000102	1.000000	1.000000	
zealand	0.000102	1.000000	1.000000	
zeus	0.000102	1.000000	1.000000	
zones	0.000102	1.000000	1.000000	
water	0.000093	9.000000	5.000000	
vast	0.000092	4.000000	4.000000	
violent	0.000092	4.000000	4.000000	
wealth	0.000092	4.000000	4.000000	
why	0.000092	4.000000	4.000000	
using	0.000079	2.000000	3.000000	
verbal	0.000079	2.000000	3.000000	
victim	0.000079	2.000000	3.000000	
vision	0.000079	2.000000	3.000000	
worst	0.000079	2.000000	3.000000	
wrote	0.000079	2.000000	3.000000	
watch	0.000069	3.000000	4.000000	
woman	0.000069	3.000000	4.000000	
won	0.000069	3.000000	4.000000	
worth	0.000069	3.000000	4.000000	
write	0.000069	3.000000	4.000000	
unknown	0.000063	1.000000	2.000000	
unlike	0.000063	1.000000	2.000000	
update	0.000063	1.000000	2.000000	
upgrade	0.000063	1.000000	2.000000	
upsets	0.000063	1.000000	2.000000	
usual	0.000063	1.000000	2.000000	
utter	0.000063	1.000000	2.000000	
vegetable	0.000063	1.