GitHub - OC-NTNU/nature: text mining from nature

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 78 Commits
.idea		.idea
nature		nature
nxml2txt		nxml2txt
.gitignore		.gitignore
README		README
TODO		TODO
checked_terms.csv		checked_terms.csv
make_abstracts.py		make_abstracts.py
make_corpus.py		make_corpus.py
make_full.py		make_full.py
nature-corpus.ini		nature-corpus.ini
nxml2txt_py2		nxml2txt_py2
preproc.tfm		preproc.tfm
set_env.sh		set_env.sh
sources.py		sources.py
sources.txt		sources.txt
trial.ini		trial.ini

Repository files navigation


Requirements:

- python3 (Anaconda dist)
- lxml
- pandas
- requests
- argh

- baleen-python
- baleen-java


For nxml2txt:

- Python2 with lxml


Test:

./make_corpus.py -c nature-corpus.ini -c local.ini -c trial.ini run-all
./make_abs.py -c nature-corpus.ini -c local.ini -c trial.ini run-all
./make_full.py -c nature-corpus.ini -c local.ini -c trial.ini run-all