NLTK - Working with Brown Corpus

#1

To load category in brown Corpora we have two option use category name or fileids. But when I tried than both given different result. “category name” is giving 2997 length of list and “fileids” giving 95 len. Why? if both are similer ???

#2

hi @Vinay-Mittal-2143588655728125
these thing are not similar fileids tell about the text files in corpora
and words is count of all the words in the corpora
thats why it giving differenet numbers because they are not same

#3

Capture
Capture1706×679 31.6 KB

Hello @Rahul_garg, Sorry but I did not understand. Please check it this image. cat have 2997 list and id have only 95.

#4

hi @Vinay-Mittal-2143588655728125
fileids() tell abouts the documents number
and categories tell about the classification of data classes.
so fileids(["cb02]) is a single document file

#5

https://www.nltk.org/book/ch02.html
for reference

#6

Ohkk ohkk I got it
Thanks Rahul