Ayush Shridhar 88b754261e Add an option to use nltk's tokenizer instead of plain split() (#718)		2019-07-29 14:13:13 +02:00
..
__init__.py	Import retriever services and add Docker image definition (#251)	2019-04-09 16:30:09 +02:00
bug_retriever.py	Make DB version handling saner to use	2019-07-26 23:37:46 +02:00
check.py	Use zstandard instead of xz (#524)	2019-06-24 13:16:44 +02:00
comment_level_labeler.py	Move comment_level_labeler script in the scripts directory	2019-06-08 20:36:13 +02:00
commit_classifier.py	Make DB version handling saner to use	2019-07-26 23:37:46 +02:00
commit_retriever.py	Make DB version handling saner to use	2019-07-26 23:37:46 +02:00
evaluate_similarity.py	Add an option to use nltk's tokenizer instead of plain split() (#718)	2019-07-29 14:13:13 +02:00
generate_duplicate_sheet.py	In the retrieval task, download only new or changed bugs	2019-06-09 00:32:23 +02:00
get_type_labels.py	Use 'everchanged' operator instead of 'changedafter' operator with 1970 (#598)	2019-06-18 22:01:15 -07:00
get_untriaged.py	In the retrieval task, download only new or changed bugs	2019-06-09 00:32:23 +02:00
microannotate_generator.py	Transform 20000 commits at a time, as 40000 are too many	2019-07-24 12:28:43 +02:00
regressor_finder.py	Find regressors in a timespan of 6 months for now	2019-07-29 12:30:28 +02:00
retrieve_training_metrics.py	Move log messages to stderr (#635)	2019-06-27 10:58:07 +02:00
trainer.py	Use db.download in trainer.py instead of manually reimplementing download and decompression (#739)	2019-07-22 11:42:55 +02:00