Skip to content

Commit 92b2f2f

Browse files
committed
debugging: Are there at all any data points on which our heuristic can beat Idans' in case they disagree?
1 parent f820e62 commit 92b2f2f

20 files changed

+195
-10413
lines changed

bohr.lock

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,7 @@
8484
}
8585
},
8686
"heuristics": {
87-
"heuristics/bugginess.py": "9f9ea19cd5c53bbbd41f94cf7b8f3d14",
87+
"heuristics/bugginess.py": "be425c256797c0b487f0f2caa39248ca",
8888
"heuristics/idans_models.py": "9bc0f7e33ba483a4a297e34aecbfe0c0",
8989
"heuristics/smells.py": "a2254c51be33d4ede33baab98ba18b09",
9090
"heuristics/tools/idansmodel.py": "0fe4b3e05ed4ac48123705a56526dac4"

dvc.lock

Lines changed: 97 additions & 97 deletions
Original file line numberDiff line numberDiff line change
@@ -158,8 +158,8 @@ stages:
158158
md5: 7b32f404edf5982eb4c5f51b956663c4
159159
size: 341651
160160
- path: heuristics/bugginess.py
161-
md5: 9f9ea19cd5c53bbbd41f94cf7b8f3d14
162-
size: 2873
161+
md5: be425c256797c0b487f0f2caa39248ca
162+
size: 448
163163
- path: heuristics/keywords
164164
md5: b4e7587c1b8e4e1461685a305d48bd66.dir
165165
size: 1382
@@ -172,11 +172,11 @@ stages:
172172
bohr_framework_version: 0.4.2
173173
outs:
174174
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_1151-commits.pkl
175-
md5: cde4712cd3c7d97a01d472a96001655f
176-
size: 2792588
175+
md5: 90f0894ad857e8f8011b5f16dab145ae
176+
size: 19189
177177
- path: metrics/bugginess/heuristics.bugginess/heuristic_metrics_1151-commits.json
178-
md5: b96cb136399ae3adae98d63b9f2cfb27
179-
size: 72
178+
md5: 452fdb0e2c252999419be5771a3774cc
179+
size: 58
180180
preprocess_berger:
181181
cmd: cp downloaded-data/berger.csv data && echo "data/berger.csv" >> .gitignore
182182
&& git add .gitignore
@@ -196,8 +196,8 @@ stages:
196196
md5: 71b9738db6cb47e3af599da316e3b570
197197
size: 60847
198198
- path: heuristics/bugginess.py
199-
md5: 9f9ea19cd5c53bbbd41f94cf7b8f3d14
200-
size: 2873
199+
md5: be425c256797c0b487f0f2caa39248ca
200+
size: 448
201201
- path: heuristics/keywords
202202
md5: b4e7587c1b8e4e1461685a305d48bd66.dir
203203
size: 1382
@@ -210,11 +210,11 @@ stages:
210210
bohr_framework_version: 0.4.2
211211
outs:
212212
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_berger.pkl
213-
md5: e0369bc6d68aa85165b5a13925542d15
214-
size: 917772
213+
md5: fca11aa5955796dc3213cb82f79bfe0b
214+
size: 6773
215215
- path: metrics/bugginess/heuristics.bugginess/heuristic_metrics_berger.json
216-
md5: 550545961be81184af6f7287900a4ac2
217-
size: 73
216+
md5: c2fefb5ddd23aee9e2705356b8d131c1
217+
size: 59
218218
preprocess_bugginess-train:
219219
cmd: 7z x downloaded-data/bugginess_train.7z -odata/bugginess_train && echo "data/bugginess_train"
220220
>> .gitignore && git add .gitignore
@@ -236,8 +236,8 @@ stages:
236236
size: 2489726547
237237
nfiles: 3
238238
- path: heuristics/bugginess.py
239-
md5: 9f9ea19cd5c53bbbd41f94cf7b8f3d14
240-
size: 2873
239+
md5: be425c256797c0b487f0f2caa39248ca
240+
size: 448
241241
- path: heuristics/keywords
242242
md5: b4e7587c1b8e4e1461685a305d48bd66.dir
243243
size: 1382
@@ -250,11 +250,11 @@ stages:
250250
bohr_framework_version: 0.4.2
251251
outs:
252252
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_bugginess-train.pkl
253-
md5: 5d1c71dcd36417356cabe2e340ca959d
254-
size: 500879984
253+
md5: c3c190910e5080bf45c49c40a17d07bc
254+
size: 3317794
255255
- path: metrics/bugginess/heuristics.bugginess/heuristic_metrics_bugginess-train.json
256-
md5: 9c903723760f0000193679b361437e41
257-
size: 32
256+
md5: 90747343662116155b09e2920b157b6c
257+
size: 17
258258
bugginess_apply_heuristics__heuristics_bugginess__herzig:
259259
cmd: bohr apply-heuristics bugginess --heuristic-group heuristics.bugginess --dataset
260260
herzig
@@ -263,8 +263,8 @@ stages:
263263
md5: 279936268f488e1e613f81a537f29055
264264
size: 1458311
265265
- path: heuristics/bugginess.py
266-
md5: 9f9ea19cd5c53bbbd41f94cf7b8f3d14
267-
size: 2873
266+
md5: be425c256797c0b487f0f2caa39248ca
267+
size: 448
268268
- path: heuristics/keywords
269269
md5: b4e7587c1b8e4e1461685a305d48bd66.dir
270270
size: 1382
@@ -277,26 +277,26 @@ stages:
277277
bohr_framework_version: 0.4.2
278278
outs:
279279
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_herzig.pkl
280-
md5: 7e673c0cce8687903d67a529058bc0ae
281-
size: 12608796
280+
md5: c0be2ce6de89119120e5fdb5e3da325a
281+
size: 84206
282282
- path: metrics/bugginess/heuristics.bugginess/heuristic_metrics_herzig.json
283-
md5: e622c8996ebf83f338511a8834be4529
284-
size: 73
283+
md5: 6881c30e66d12aec85d162df31e5e04d
284+
size: 58
285285
bugginess_combine_heuristics:
286286
cmd: bohr apply-heuristics bugginess
287287
deps:
288288
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_1151-commits.pkl
289-
md5: cde4712cd3c7d97a01d472a96001655f
290-
size: 2792588
289+
md5: 90f0894ad857e8f8011b5f16dab145ae
290+
size: 19189
291291
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_berger.pkl
292-
md5: e0369bc6d68aa85165b5a13925542d15
293-
size: 917772
292+
md5: fca11aa5955796dc3213cb82f79bfe0b
293+
size: 6773
294294
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_bugginess-train.pkl
295-
md5: 5d1c71dcd36417356cabe2e340ca959d
296-
size: 500879984
295+
md5: c3c190910e5080bf45c49c40a17d07bc
296+
size: 3317794
297297
- path: generated/bugginess/heuristics.bugginess/heuristic_matrix_herzig.pkl
298-
md5: 7e673c0cce8687903d67a529058bc0ae
299-
size: 12608796
298+
md5: c0be2ce6de89119120e5fdb5e3da325a
299+
size: 84206
300300
- path: generated/bugginess/heuristics.idans_models/heuristic_matrix_1151-commits.pkl
301301
md5: 408cd74f3d9abdd6fb8d4a267e9ebb6a
302302
size: 9968
@@ -314,52 +314,52 @@ stages:
314314
bohr_framework_version: 0.4.2
315315
outs:
316316
- path: generated/bugginess/analysis_1151-commits.csv
317-
md5: ada896b3c751cafd3d17009cdb22c735
318-
size: 24023
317+
md5: 7ee692485362475a4d8643cebc3fd7ca
318+
size: 188
319319
- path: generated/bugginess/analysis_berger.csv
320-
md5: 521b206542f64cad5a53928ca9a47940
321-
size: 21390
320+
md5: ff1730095a59d452cd4cd036a7512aa2
321+
size: 188
322322
- path: generated/bugginess/analysis_bugginess-train.csv
323-
md5: c096a26f579273d7dfa245a9c0f6fe70
324-
size: 29166
323+
md5: 35677988058b318d85f21115789295d0
324+
size: 118
325325
- path: generated/bugginess/analysis_herzig.csv
326-
md5: 681e84323ffaa6dc2425600e3f525fa2
327-
size: 25457
326+
md5: 057ffb8087b43c6ef835dc66977d8725
327+
size: 191
328328
- path: generated/bugginess/heuristic_matrix_1151-commits.pkl
329-
md5: caf933c931aa26999d6b892ee97e226a
330-
size: 2801970
329+
md5: e8807acdbe8c2591e493475afca79cae
330+
size: 28542
331331
- path: generated/bugginess/heuristic_matrix_berger.pkl
332-
md5: e4621d6a3f63b15aebad1c2fc22c641a
333-
size: 920946
332+
md5: c8e4b885d513db5897c89259ec572752
333+
size: 9918
334334
- path: generated/bugginess/heuristic_matrix_bugginess-train.pkl
335-
md5: 8e424b0d26a3af93fda99341fe964799
336-
size: 502538673
335+
md5: 294745907cf489e43fea9d5b4ece4a63
336+
size: 4976454
337337
- path: generated/bugginess/heuristic_matrix_herzig.pkl
338-
md5: 2bde91dbc20aca2ae70f88acdaeee838
339-
size: 12650682
338+
md5: 59dca23f438db2d8adbd279115813898
339+
size: 126063
340340
- path: metrics/bugginess/analysis_1151-commits.json
341-
md5: aad59b51d0cab5b84c62da9d3ccd9549
342-
size: 108179
341+
md5: 42cbd02eada4fbeabe3387e9267b8dbc
342+
size: 696
343343
- path: metrics/bugginess/analysis_berger.json
344-
md5: 83f4ffa9d996d2416a0f3f30e1e164aa
345-
size: 105040
344+
md5: 90f8aece1e0ecdf7538bf11775d3e5d3
345+
size: 696
346346
- path: metrics/bugginess/analysis_bugginess-train.json
347-
md5: 17a3470e8a06d8fe6fc93ca8a95d45e1
348-
size: 77088
347+
md5: 682590d1a88367c9ecc4a42d23bbc52f
348+
size: 410
349349
- path: metrics/bugginess/analysis_herzig.json
350-
md5: 9d4f05e95d714c566a7354dbbaf2bd7c
351-
size: 109877
350+
md5: 22dea696b91e19a1567e207708618edc
351+
size: 699
352352
- path: metrics/bugginess/heuristic_metrics_1151-commits.json
353-
md5: c9501dce1b502807e79ec0aad0adce8c
354-
size: 58
353+
md5: cc78f2084295e52c9adc17fc2b4487c6
354+
size: 57
355355
- path: metrics/bugginess/heuristic_metrics_berger.json
356-
md5: e05019fd889583af3b48ad78765ead60
356+
md5: c4d8cb63cccd72944bc70dce56578dbf
357357
size: 58
358358
- path: metrics/bugginess/heuristic_metrics_bugginess-train.json
359359
md5: ee53d260cd541f43e554c20c21acabf7
360360
size: 17
361361
- path: metrics/bugginess/heuristic_metrics_herzig.json
362-
md5: d6f14b937e309f43bb0d7d435b4922ca
362+
md5: 9b7b281f3cf80561509a9d9b31e246e2
363363
size: 58
364364
bugginess_train_label_model:
365365
cmd: bohr train-label-model bugginess bugginess-train
@@ -374,29 +374,29 @@ stages:
374374
md5: 279936268f488e1e613f81a537f29055
375375
size: 1458311
376376
- path: generated/bugginess/heuristic_matrix_1151-commits.pkl
377-
md5: caf933c931aa26999d6b892ee97e226a
378-
size: 2801970
377+
md5: e8807acdbe8c2591e493475afca79cae
378+
size: 28542
379379
- path: generated/bugginess/heuristic_matrix_berger.pkl
380-
md5: e4621d6a3f63b15aebad1c2fc22c641a
381-
size: 920946
380+
md5: c8e4b885d513db5897c89259ec572752
381+
size: 9918
382382
- path: generated/bugginess/heuristic_matrix_bugginess-train.pkl
383-
md5: 8e424b0d26a3af93fda99341fe964799
384-
size: 502538673
383+
md5: 294745907cf489e43fea9d5b4ece4a63
384+
size: 4976454
385385
- path: generated/bugginess/heuristic_matrix_herzig.pkl
386-
md5: 2bde91dbc20aca2ae70f88acdaeee838
387-
size: 12650682
386+
md5: 59dca23f438db2d8adbd279115813898
387+
size: 126063
388388
params:
389389
bohr.json:
390390
bohr_framework_version: 0.4.2
391391
outs:
392392
- path: generated/bugginess/label_model.pkl
393-
md5: 5887422d06b51b9a6e19671efa58514f
394-
size: 1875474
393+
md5: 94fbc13c3bced771519534caa09fe09f
394+
size: 4918
395395
- path: generated/bugginess/label_model_weights.csv
396-
md5: f5f46db38c1260743c569694ff59687d
397-
size: 19690
396+
md5: 3ae8c2dfc199b8120ec173ff859f587e
397+
size: 138
398398
- path: metrics/bugginess/label_model_metrics.json
399-
md5: c6bb24d1e08162da85dbb598f54932fe
399+
md5: 2243c6dcaf7ebcf7c5b4c2d4f6c111a2
400400
size: 430
401401
bugginess_label_dataset_herzig:
402402
cmd: bohr label-dataset bugginess herzig
@@ -405,18 +405,18 @@ stages:
405405
md5: 279936268f488e1e613f81a537f29055
406406
size: 1458311
407407
- path: generated/bugginess/heuristic_matrix_herzig.pkl
408-
md5: 2bde91dbc20aca2ae70f88acdaeee838
409-
size: 12650682
408+
md5: 59dca23f438db2d8adbd279115813898
409+
size: 126063
410410
- path: generated/bugginess/label_model.pkl
411-
md5: 5887422d06b51b9a6e19671efa58514f
412-
size: 1875474
411+
md5: 94fbc13c3bced771519534caa09fe09f
412+
size: 4918
413413
params:
414414
bohr.json:
415415
bohr_framework_version: 0.4.2
416416
outs:
417417
- path: labeled-datasets/herzig.labeled.csv
418-
md5: 36ace7239a0ccfa9c7998253fbca4b68
419-
size: 1536993
418+
md5: ecbc105943cc7efe32679a20c80c4fee
419+
size: 1541807
420420
smells_train_label_model:
421421
cmd: bohr train-label-model smells smells-train
422422
deps:
@@ -488,56 +488,56 @@ stages:
488488
size: 2489726547
489489
nfiles: 3
490490
- path: generated/bugginess/heuristic_matrix_bugginess-train.pkl
491-
md5: 8e424b0d26a3af93fda99341fe964799
492-
size: 502538673
491+
md5: 294745907cf489e43fea9d5b4ece4a63
492+
size: 4976454
493493
- path: generated/bugginess/label_model.pkl
494-
md5: 5887422d06b51b9a6e19671efa58514f
495-
size: 1875474
494+
md5: 94fbc13c3bced771519534caa09fe09f
495+
size: 4918
496496
params:
497497
bohr.json:
498498
bohr_framework_version: 0.4.2
499499
outs:
500500
- path: labeled-datasets/bugginess-train.labeled.csv
501-
md5: 6e760674b91bdd224b1834ee4d0153c0
502-
size: 61591165
501+
md5: 1197fb7089891466331259cf720c53ec
502+
size: 61782839
503503
bugginess_label_dataset_1151-commits:
504504
cmd: bohr label-dataset bugginess 1151-commits
505505
deps:
506506
- path: data/1151-commits.csv
507507
md5: 7b32f404edf5982eb4c5f51b956663c4
508508
size: 341651
509509
- path: generated/bugginess/heuristic_matrix_1151-commits.pkl
510-
md5: caf933c931aa26999d6b892ee97e226a
511-
size: 2801970
510+
md5: e8807acdbe8c2591e493475afca79cae
511+
size: 28542
512512
- path: generated/bugginess/label_model.pkl
513-
md5: 5887422d06b51b9a6e19671efa58514f
514-
size: 1875474
513+
md5: 94fbc13c3bced771519534caa09fe09f
514+
size: 4918
515515
params:
516516
bohr.json:
517517
bohr_framework_version: 0.4.2
518518
outs:
519519
- path: labeled-datasets/1151-commits.labeled.csv
520-
md5: 35f831099bae6a3861fd6144036d074f
521-
size: 359139
520+
md5: fbf361ca8b1d2ae6178262330848a5ea
521+
size: 360139
522522
bugginess_label_dataset_berger:
523523
cmd: bohr label-dataset bugginess berger
524524
deps:
525525
- path: data/berger.csv
526526
md5: 71b9738db6cb47e3af599da316e3b570
527527
size: 60847
528528
- path: generated/bugginess/heuristic_matrix_berger.pkl
529-
md5: e4621d6a3f63b15aebad1c2fc22c641a
530-
size: 920946
529+
md5: c8e4b885d513db5897c89259ec572752
530+
size: 9918
531531
- path: generated/bugginess/label_model.pkl
532-
md5: 5887422d06b51b9a6e19671efa58514f
533-
size: 1875474
532+
md5: 94fbc13c3bced771519534caa09fe09f
533+
size: 4918
534534
params:
535535
bohr.json:
536536
bohr_framework_version: 0.4.2
537537
outs:
538538
- path: labeled-datasets/berger.labeled.csv
539-
md5: 5afa86df35ebc3f2087723f8e509082d
540-
size: 66515
539+
md5: 893dc8d2a2a688a7f839772aae2b412c
540+
size: 66919
541541
bugginess_transformer_train:
542542
cmd: bash classifiers/bugginess-transformer/train.sh labeled-data/bugginess.csv
543543
deps:

0 commit comments

Comments
 (0)