Newer
Older
schema: '2.0'
stages:
download_dataset@enron_spam:
cmd: PYTHONPATH=. python experiments/scripts/download_dataset.py --dataset_name
enron_spam --output_dir data/datasets/enron_spam
deps:
- path: experiments/scripts/download_dataset.py
size: 53096069
nfiles: 3
get_model@enron_spam:
cmd: PYTHONPATH=. python experiments/scripts/get_model.py --dataset_name enron_spam
--output_dir data/models/enron_spam
deps:
- path: data/preprocessed/enron_spam
md5: b75efba1a62182dc8ac32acd1faf92ed.dir
size: 61709260
- path: experiments/scripts/get_model.py
md5: 5050f51b4019bba97af47971f6c7cab4
size: 747
outs:
- path: data/models/enron_spam/
md5: 3e16b22f59532c66beeadea958e0579a.dir
size: 18505614
nfiles: 6
classify@enron_spam:
cmd: PYTHONPATH=. python experiments/scripts/classify.py --dataset_name enron_spam
--output_dir data/classification/enron_spam
deps:
- path: data/models/enron_spam/
md5: 3e16b22f59532c66beeadea958e0579a.dir
size: 18505614
nfiles: 6
- path: data/preprocessed/enron_spam/
md5: b75efba1a62182dc8ac32acd1faf92ed.dir
size: 61709260
nfiles: 3
explain@enron_spam:
cmd: PYTHONPATH=. python experiments/scripts/explain.py --dataset_name enron_spam
--output_dir data/explanations/enron_spam
deps:
- path: data/models/enron_spam
md5: 3e16b22f59532c66beeadea958e0579a.dir
size: 18505614
nfiles: 6
- path: data/preprocessed/enron_spam
md5: b75efba1a62182dc8ac32acd1faf92ed.dir
size: 61709260
nfiles: 3
download_dataset@poleval:
cmd: PYTHONPATH=. python experiments/scripts/download_dataset.py --dataset_name
poleval --output_dir data/datasets/poleval
deps:
- path: experiments/scripts/download_dataset.py
md5: 9eb915fd5b9216965db519f686408a51
size: 887
outs:
- path: data/datasets/poleval/
md5: 826f974f794e24efcb5aedb054d1fd55.dir
size: 1688836
nfiles: 3
preprocess_dataset@poleval:
cmd: PYTHONPATH=. python experiments/scripts/tag_dataset.py --dataset_name poleval
deps:
- path: data/datasets/poleval/
md5: 826f974f794e24efcb5aedb054d1fd55.dir
size: 1688836
nfiles: 3
- path: experiments/scripts/tag_dataset.py
md5: 854387459b193c5eba6db1273ca5ad23.dir
size: 2277282
nfiles: 3
preprocess_dataset@enron_spam:
cmd: PYTHONPATH=. python experiments/scripts/tag_dataset.py --dataset_name enron_spam
deps:
- path: data/datasets/enron_spam/
md5: 66d44efedf37990b1989c81bbee085e0.dir
size: 53096069
nfiles: 3
- path: experiments/scripts/tag_dataset.py