Storing dataset from Condtional FreqDist

Jason Friedman jsf80238 at gmail.com
Tue Jan 20 03:40:18 CET 2015


> Hello i have trying to store information in arff file but i has been really. Any ideas of how can i do that?
>
>
> with open('fileids3.txt', 'r') as f:
>
>         genres=[word.strip() for word in f.next().split(',')]
>
> with open('adjectifs2.txt', 'r') as g:
>         adj = [word.strip() for word in g.next().split(',')]
>
> freq = nltk.ConditionalFreqDist(
>      (genre, m)
>       for genre in brown.fileids()
>       for m in brown.words(fileids=genre))
>
>
> freq.tabulate(conditions=genres, samples=adj)

What do fileids3.txt and adjectifs2.txt contain (perhaps give us the
first few lines of each)?

What do you want your AARF file to look like (show us what the header
should look like and then the first few lines of data)?



More information about the Python-list mailing list