Skip to content

Commit 5a78bef

Browse files
albertvillanovapre-commit-ci[bot]
albertvillanova
and
pre-commit-ci[bot]
authored
Fix self-assign GH Action for multiple assignees (#368)
* Fix self-assign GH Action for multiple assignees * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Remove unnecessary method Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
1 parent f879518 commit 5a78bef

2 files changed

Lines changed: 87 additions & 20 deletions

File tree

‎.github/workflows/self-assign.yaml‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,6 @@ jobs:
88
if: >-
99
(github.event.comment.body == '#take' ||
1010
github.event.comment.body == '#self-assign')
11-
&& !github.event.issue.assignee
1211
steps:
1312
- run: |
1413
echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"

‎ac_dc/visualization/visualization.py‎

Lines changed: 87 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -368,7 +368,9 @@ def get_cond(key, cutoff, max_cutoff):
368368
f"Filtering on documents, for {self.num_docs} {self.lang} documents"
369369
)
370370

371-
Visualization.display_dataset(self.docs, np.invert(all_conds), "Discarded documents", "docs")
371+
Visualization.display_dataset(
372+
self.docs, np.invert(all_conds), "Discarded documents", "docs"
373+
)
372374

373375
# st.subheader("Display discarded documents by filter")
374376
display_discarded_documents_by_filter = st.checkbox(
@@ -380,37 +382,74 @@ def get_cond(key, cutoff, max_cutoff):
380382

381383
if "number_words" in columns:
382384
cond_filter = np.invert(np.all(conds["number_words"], axis=0))
383-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the number of words", "docs")
385+
Visualization.display_dataset(
386+
self.docs,
387+
cond_filter,
388+
"Discarded documents for the filter on the number of words",
389+
"docs",
390+
)
384391

385392
if "repetitions_ratio" in columns:
386393
cond_filter = np.invert(np.all(conds["repetitions_ratio"], axis=0))
387-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the repetitions ratio", "docs")
394+
Visualization.display_dataset(
395+
self.docs,
396+
cond_filter,
397+
"Discarded documents for the filter on the repetitions ratio",
398+
"docs",
399+
)
388400

389401
if "special_characters_ratio" in columns:
390402
cond_filter = np.invert(
391403
np.all(conds["special_characters_ratio"], axis=0)
392404
)
393-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the special characters ratio", "docs")
405+
Visualization.display_dataset(
406+
self.docs,
407+
cond_filter,
408+
"Discarded documents for the filter on the special characters ratio",
409+
"docs",
410+
)
394411

395412
if "stopwords_ratio" in columns:
396413
cond_filter = np.invert(np.all(conds["stopwords_ratio"], axis=0))
397-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the stop words ratio", "docs")
414+
Visualization.display_dataset(
415+
self.docs,
416+
cond_filter,
417+
"Discarded documents for the filter on the stop words ratio",
418+
"docs",
419+
)
398420

399421
if "flagged_words_ratio" in columns:
400422
cond_filter = np.invert(
401423
np.all(conds["flagged_words_ratio"], axis=0)
402424
)
403-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the flagged words ratio", "docs")
425+
Visualization.display_dataset(
426+
self.docs,
427+
cond_filter,
428+
"Discarded documents for the filter on the flagged words ratio",
429+
"docs",
430+
)
404431

405432
if "lang_id_score" in columns:
406433
cond_filter = np.invert(np.all(conds["lang_id_score"], axis=0))
407-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the language identification confidence score", "docs")
434+
Visualization.display_dataset(
435+
self.docs,
436+
cond_filter,
437+
"Discarded documents for the filter on the language identification confidence score",
438+
"docs",
439+
)
408440

409441
if "perplexity_score" in columns:
410442
cond_filter = np.invert(np.all(conds["perplexity_score"], axis=0))
411-
Visualization.display_dataset(self.docs, cond_filter, "Discarded documents for the filter on the perplexity score", "docs")
443+
Visualization.display_dataset(
444+
self.docs,
445+
cond_filter,
446+
"Discarded documents for the filter on the perplexity score",
447+
"docs",
448+
)
412449

413-
Visualization.display_dataset(self.docs, all_conds, "Retained documents", "docs")
450+
Visualization.display_dataset(
451+
self.docs, all_conds, "Retained documents", "docs"
452+
)
414453

415454
st.header("Download data")
416455

@@ -446,22 +485,37 @@ def filtering_of_words(self):
446485
incorrect_substrings = st.checkbox(
447486
"Remove words with incorrect substrings."
448487
)
449-
self.parameters.append(("incorrect_substrings", incorrect_substrings))
488+
self.parameters.append(
489+
("incorrect_substrings", incorrect_substrings)
490+
)
450491

451492
checkbox = st.checkbox(
452-
"Diplay distribution", value=True, key="display_distribution_incorrect_substrings"
493+
"Diplay distribution",
494+
value=True,
495+
key="display_distribution_incorrect_substrings",
453496
)
454497
if checkbox:
455498
incor_sub = np.array(self.words["incorrect_substrings"]) * 1
456499
with_incor_sub = np.sum(incor_sub)
457500
without_incor_sub = len(incor_sub) - with_incor_sub
458-
st.markdown(f"Number of words with incorrect substrings: {with_incor_sub}")
459-
st.markdown(f"Number of words without incorrect substrings: {without_incor_sub}")
501+
st.markdown(
502+
f"Number of words with incorrect substrings: {with_incor_sub}"
503+
)
504+
st.markdown(
505+
f"Number of words without incorrect substrings: {without_incor_sub}"
506+
)
460507

461508
if incorrect_substrings:
462-
cond_incorrect_substrings = np.invert(self.words["incorrect_substrings"])
509+
cond_incorrect_substrings = np.invert(
510+
self.words["incorrect_substrings"]
511+
)
463512
else:
464-
cond_incorrect_substrings = np.array([True for i in range(len(self.words["incorrect_substrings"]))])
513+
cond_incorrect_substrings = np.array(
514+
[
515+
True
516+
for i in range(len(self.words["incorrect_substrings"]))
517+
]
518+
)
465519
Visualization.print_discarded_by_cond(cond_incorrect_substrings)
466520
conds_words["incorrect_substrings"] = cond_incorrect_substrings
467521

@@ -479,7 +533,9 @@ def filtering_of_words(self):
479533
f"we consider in this section words for only {self.num_docs_for_words} documents."
480534
)
481535

482-
Visualization.display_dataset(self.words, np.invert(all_conds_words), "Discarded words", "words")
536+
Visualization.display_dataset(
537+
self.words, np.invert(all_conds_words), "Discarded words", "words"
538+
)
483539

484540
# st.subheader("Display discarded words by filter")
485541
display_discarded_words_by_filter = st.checkbox(
@@ -490,13 +546,25 @@ def filtering_of_words(self):
490546

491547
if "len_word" in columns:
492548
cond_filter = np.invert(conds_words["len_word"])
493-
Visualization.display_dataset(self.words, cond_filter, "Discarded words for the filter on length", "words")
549+
Visualization.display_dataset(
550+
self.words,
551+
cond_filter,
552+
"Discarded words for the filter on length",
553+
"words",
554+
)
494555

495556
if "incorrect_substrings" in columns:
496557
cond_filter = np.invert(conds_words["incorrect_substrings"])
497-
Visualization.display_dataset(self.words, cond_filter, "Discarded words for the filter on incorrect substrings", "words")
558+
Visualization.display_dataset(
559+
self.words,
560+
cond_filter,
561+
"Discarded words for the filter on incorrect substrings",
562+
"words",
563+
)
498564

499-
Visualization.display_dataset(self.words, all_conds_words, "Retained words", "words")
565+
Visualization.display_dataset(
566+
self.words, all_conds_words, "Retained words", "words"
567+
)
500568

501569
def download_parameters(self):
502570
st.sidebar.subheader("Download parameters")

0 commit comments

Comments
 (0)