Use a setting or an attribute for df_min

[humitos]

The code is using df_min=1 at https://github.com/agjohnson/django-textclassifier/blob/master/textclassifier/classifier.py#L62.

This means that it's counting all the words that appear at least one time in the corpus. Considering that we are working with SPAM, I think it could be useful to be able to set this to 2 or 3 at least, since spam words are very repetitive.

When having a big db, this will help with #8