Aztec Pub Classifier

Classify publications as those which contain a software tool, and those which do not.

Setup

$ sudo pip3 install nltk
$ sudo pip3 install requests

$ python3 getdata.py | python3 preprocess.py | python3 tabletocsv.py

Outputs to frequencydata.csv and creates dictionary.csv

Name		Name	Last commit message	Last commit date
Latest commit History 17 Commits
setup		setup
.gitignore		.gitignore
README.md		README.md
combinedata.py		combinedata.py
data.csv		data.csv
dict.csv		dict.csv
getdata.py		getdata.py
preprocess.py		preprocess.py
tabletocsv.py		tabletocsv.py
testdata.csv		testdata.csv
topwords.py		topwords.py
train_nn.py		train_nn.py