I hereby claim:
- I am petekalo on github.
- I am netfl0 (https://keybase.io/netfl0) on keybase.
- I have a public key ASDvy2NRqUBBMsDYH6F2pmCuGAVUdeh6x-9PDFIGoeixJwo
To claim this, I am signing this object:
I hereby claim:
To claim this, I am signing this object:
| """Extract several BOW models from a corpus of text files. | |
| The models are stored in Matrix Market format which can be read | |
| by gensim. The texts are read from .txt files in the directory | |
| specified as TOPDIR. The output is written to the current directory.""" | |
| # NB: All strings are utf8 (not unicode). | |
| import os | |
| import glob | |
| import nltk | |
| import gensim |
| class IterableQuerySet(object): | |
| """Allows iteration over a QuerySet breaking it off into smaller chunks.""" | |
| """Take from http://justcramer.com/2009/02/09/large-sql-result-sets-in-django/""" | |
| def __init__(self, queryset, batch=10000): | |
| self.batch = batch | |
| self.queryset = queryset | |
| def __iter__(self): | |
| at = 0 | |
| ---------------------------------------------- | |
| #TOR CONFIGURATION: | |
| # transparent tor: | |
| #TransPort 9040 | |
| #TransListenAddress 10.0.0.1 | |
| #DNSPort 53 | |
| #DNSListenAddress 10.0.0.1 | |
| ----------------------------------------------- |