From d105771a07f886fbcc9f3eefd47d2c8e8a56182e Mon Sep 17 00:00:00 2001 From: "Kyle P. Johnson" Date: Sun, 13 Nov 2016 10:08:16 -0800 Subject: [PATCH] Add setup directions for data dir This script's data needs are not intuitive. I have added a note explaining that (a) it expects pos/neg polarity data, (b) the structure of the data dir (train/test), and (c) a standard resource for such polarity data. --- examples/nn_text_class.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/examples/nn_text_class.py b/examples/nn_text_class.py index e19e93cac..7b4a2fd57 100644 --- a/examples/nn_text_class.py +++ b/examples/nn_text_class.py @@ -1,3 +1,11 @@ +"""This script expects something like a binary sentiment data set, such as + that available here: `http://www.cs.cornell.edu/people/pabo/movie-review-data/` + +It expects a directory structure like: `data_dir/train/{pos|neg}` + and `data_dir/test/{pos|neg}`. Put (say) 90% of the files in the former + and the remainder in the latter. +""" + from __future__ import unicode_literals from __future__ import print_function from __future__ import division