Projects
- 1. comments classification
this is the first deep learning project use the baby neural network, it is a binary classification. it have some problems, the accurate is low. please fix the problem.
data: http://www.cs.cornell.edu/people/pabo/movie-review-data/rt-polaritydata.tar.gz more data: http://www.cs.cornell.edu/people/pabo/movie-review-data/
”‘sh 安装nltk（自然语言工具库 Natural Language Toolkit） $ pip install nltk
$ python Python 3.5.2 (v3.5.2:4def2a2901a5, Jun 26 2016, 10:47:25) [GCC 4.2.1 (Apple Inc. build 5666) (dot 3)] on darwin Type “help”, “copyright”, “credits” or “license” for more information.
import nltk nltk.download()
下载nltk数据： $ python Python 3.5.2 (v3.5.2:4def2a2901a5, Jun 26 2016, 10:47:25) [GCC 4.2.1 (Apple Inc. build 5666) (dot 3)] on darwin Type “help”, “copyright”, “credits” or “license” for more information. >>> import nltk >>> nltk.download()
ntlk有详细安装文档。
测试nltk安装： >>> from nltk.corpus import brown >>> brown.words() [‘The’, ‘Fulton’, ‘County’, ‘Grand’, ‘Jury’, ‘said’, …]
”’
there are problems with this neural networks, that result not work there are couple of tips for you to figure it out: 1. Is it get enough data? 2. How about the capacity of networks?
