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
md5: b75efba1a62182dc8ac32acd1faf92ed.dir
size: 61709260
nfiles: 3
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
preprocess_dataset@wiki_pl:
cmd: PYTHONPATH=. python experiments/scripts/tag_dataset.py --dataset_name wiki_pl
deps:
- path: data/datasets/wiki_pl/
md5: abcbccb3e352ed623cace1b95078bd63.dir
size: 29115538
nfiles: 3
- path: experiments/scripts/tag_dataset.py
md5: 8e8039b73b8ea3ce39287ed0a304af9b
size: 3750
outs:
- path: data/preprocessed/wiki_pl/
md5: 3e9b2e1e0542777e0a751d9d7f7f4241.dir
size: 55380570
nfiles: 3
classify@wiki_pl:
cmd: PYTHONPATH=. python experiments/scripts/classify.py --dataset_name wiki_pl
--output_dir data/classification/wiki_pl
deps:
- path: data/models/wiki_pl/
md5: fd453042628fb09c080ef05d34a32cce.dir
size: 501711136
nfiles: 7
- path: data/preprocessed/wiki_pl/
md5: 3e9b2e1e0542777e0a751d9d7f7f4241.dir
size: 55380570
nfiles: 3
- path: experiments/scripts/classify.py
md5: 6fc1a6a0a11ba6cd99a8b6625a96d9f5
size: 1181
outs:
- path: data/classification/wiki_pl
md5: 515330772505f489b55686545bcf23a0.dir
size: 34103198
nfiles: 2
preprocess_dataset@20_news:
cmd: PYTHONPATH=. python experiments/scripts/tag_dataset.py --dataset_name 20_news
deps:
- path: data/datasets/20_news/
md5: 999207f1c2c123c9943397b47f2c3b3a.dir
size: 23460358
nfiles: 3
- path: experiments/scripts/tag_dataset.py
md5: 8e8039b73b8ea3ce39287ed0a304af9b
size: 3750
outs:
- path: data/preprocessed/20_news/
md5: 1ed5ef2dabe4bc05f7377175ed11137b.dir
size: 46845669
nfiles: 3
classify@20_news:
cmd: PYTHONPATH=. python experiments/scripts/classify.py --dataset_name 20_news
--output_dir data/classification/20_news
deps:
- path: data/models/20_news/
md5: 43d68a67ecb8149bd6bf50db9767cb64.dir
size: 439008808
nfiles: 6
- path: data/preprocessed/20_news/
md5: 1ed5ef2dabe4bc05f7377175ed11137b.dir
size: 46845669
nfiles: 3
- path: experiments/scripts/classify.py
md5: 6fc1a6a0a11ba6cd99a8b6625a96d9f5
size: 1181
outs:
- path: data/classification/20_news
md5: 6831f104f7c20541548fe72250c45706.dir
size: 31286120
nfiles: 2
cmd: PYTHONPATH=. python experiments/scripts/attack.py --dataset_name 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
- path: experiments/scripts/attack.py
md5: fc35de09ce5e2aa7043325b2819c0aa0.dir
size: 4869
nfiles: 1
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
explain@wiki_pl:
cmd: PYTHONPATH=. python experiments/scripts/explain.py --dataset_name wiki_pl
--output_dir data/explanations/wiki_pl
deps:
- path: data/models/wiki_pl
md5: fd453042628fb09c080ef05d34a32cce.dir
size: 501711136
nfiles: 7
- path: data/preprocessed/wiki_pl
md5: 3e9b2e1e0542777e0a751d9d7f7f4241.dir
size: 55380570
nfiles: 3
- path: experiments/scripts/explain.py
md5: afc02ef263a59c911098dea969faa932
size: 3234
outs:
- path: data/explanations/wiki_pl/
md5: 5a3b9b069024456412078143e3af15d7.dir
size: 331450794
nfiles: 10065
explain@20_news:
cmd: PYTHONPATH=. python experiments/scripts/explain.py --dataset_name 20_news
--output_dir data/explanations/20_news
deps:
- path: data/models/20_news
md5: 43d68a67ecb8149bd6bf50db9767cb64.dir
size: 439008808
nfiles: 6
- path: data/preprocessed/20_news
md5: 1ed5ef2dabe4bc05f7377175ed11137b.dir
size: 46845669
nfiles: 3
- path: experiments/scripts/explain.py
md5: afc02ef263a59c911098dea969faa932
size: 3234
outs:
- path: data/explanations/20_news/
md5: c8ba90f9757a4e3cc4843d3791ef2446.dir
size: 232912969
nfiles: 14041