File age measurements show the distribution of file ages (days since the first commit) and the recency of file updates (days since the latest commit).
File | # lines | # units | last modified (days ago) | created (days ago) | # changes |
---|---|---|---|---|---|
jsonql.py in cc_net |
948 | 97 | 456 | 819 | 15 |
mine.py in cc_net |
464 | 20 | 456 | 819 | 13 |
dedup.py in cc_net |
360 | 24 | 456 | 819 | 7 |
minify.py in cc_net |
230 | 22 | 456 | 819 | 12 |
process_wet_file.py in cc_net |
197 | 18 | 450 | 819 | 11 |
flat_hash_set.py in cc_net |
160 | 28 | 456 | 819 | 4 |
setup.py in root |
43 | - | 450 | 819 | 12 |
__main__.py in cc_net |
6 | 1 | 456 | 819 | 4 |
__init__.py in cc_net |
1 | - | 456 | 819 | 2 |
expand_corpus.py in cc_net/tools |
230 | 15 | 456 | 680 | 6 |
regroup.py in cc_net |
81 | 5 | 456 | 680 | 3 |
get_wiki_cirrus.py in cc_net |
74 | 6 | 456 | 680 | 3 |
pyproject.toml in root |
20 | - | 456 | 680 | 5 |
perplexity.py in cc_net |
284 | 26 | 456 | 672 | 3 |
execution.py in cc_net |
172 | 9 | 456 | 672 | 8 |
split_by_lang.py in cc_net |
117 | 10 | 456 | 672 | 3 |
make_dmoz_corpus.py in cc_net/tools |
55 | 4 | 456 | 672 | 3 |
tokenizer.py in cc_net |
55 | 6 | 456 | 672 | 2 |
text_normalizer.py in cc_net |
150 | 8 | 456 | 629 | 2 |
dl_cc_100.py in cc_net/tools |
133 | 6 | 456 | 456 | 1 |
File | # lines | # units | last modified (days ago) | created (days ago) | # changes |
---|---|---|---|---|---|
__init__.py in cc_net |
1 | - | 456 | 819 | 2 |
__main__.py in cc_net |
6 | 1 | 456 | 819 | 4 |
pyproject.toml in root |
20 | - | 456 | 680 | 5 |
tokenizer.py in cc_net |
55 | 6 | 456 | 672 | 2 |
make_dmoz_corpus.py in cc_net/tools |
55 | 4 | 456 | 672 | 3 |
get_wiki_cirrus.py in cc_net |
74 | 6 | 456 | 680 | 3 |
regroup.py in cc_net |
81 | 5 | 456 | 680 | 3 |
split_by_lang.py in cc_net |
117 | 10 | 456 | 672 | 3 |
dl_cc_100.py in cc_net/tools |
133 | 6 | 456 | 456 | 1 |
text_normalizer.py in cc_net |
150 | 8 | 456 | 629 | 2 |
flat_hash_set.py in cc_net |
160 | 28 | 456 | 819 | 4 |
execution.py in cc_net |
172 | 9 | 456 | 672 | 8 |
minify.py in cc_net |
230 | 22 | 456 | 819 | 12 |
expand_corpus.py in cc_net/tools |
230 | 15 | 456 | 680 | 6 |
perplexity.py in cc_net |
284 | 26 | 456 | 672 | 3 |
dedup.py in cc_net |
360 | 24 | 456 | 819 | 7 |
mine.py in cc_net |
464 | 20 | 456 | 819 | 13 |
jsonql.py in cc_net |
948 | 97 | 456 | 819 | 15 |
setup.py in root |
43 | - | 450 | 819 | 12 |
process_wet_file.py in cc_net |
197 | 18 | 450 | 819 | 11 |
File | # lines | # units | last modified (days ago) | created (days ago) | # changes |
---|---|---|---|---|---|
__init__.py in cc_net/tools |
1 | - | |||
dl_cc_100.py in cc_net/tools |
133 | 6 | 456 | 456 | 1 |
text_normalizer.py in cc_net |
150 | 8 | 456 | 629 | 2 |
perplexity.py in cc_net |
284 | 26 | 456 | 672 | 3 |
execution.py in cc_net |
172 | 9 | 456 | 672 | 8 |
split_by_lang.py in cc_net |
117 | 10 | 456 | 672 | 3 |
make_dmoz_corpus.py in cc_net/tools |
55 | 4 | 456 | 672 | 3 |
tokenizer.py in cc_net |
55 | 6 | 456 | 672 | 2 |
expand_corpus.py in cc_net/tools |
230 | 15 | 456 | 680 | 6 |
regroup.py in cc_net |
81 | 5 | 456 | 680 | 3 |
get_wiki_cirrus.py in cc_net |
74 | 6 | 456 | 680 | 3 |
pyproject.toml in root |
20 | - | 456 | 680 | 5 |
jsonql.py in cc_net |
948 | 97 | 456 | 819 | 15 |
mine.py in cc_net |
464 | 20 | 456 | 819 | 13 |
dedup.py in cc_net |
360 | 24 | 456 | 819 | 7 |
minify.py in cc_net |
230 | 22 | 456 | 819 | 12 |
process_wet_file.py in cc_net |
197 | 18 | 450 | 819 | 11 |
flat_hash_set.py in cc_net |
160 | 28 | 456 | 819 | 4 |
setup.py in root |
43 | - | 450 | 819 | 12 |
__main__.py in cc_net |
6 | 1 | 456 | 819 | 4 |
File | # lines | # units | last modified (days ago) | created (days ago) | # changes |
---|---|---|---|---|---|
__init__.py in cc_net/tools |
1 | - | |||
process_wet_file.py in cc_net |
197 | 18 | 450 | 819 | 11 |
setup.py in root |
43 | - | 450 | 819 | 12 |
jsonql.py in cc_net |
948 | 97 | 456 | 819 | 15 |
mine.py in cc_net |
464 | 20 | 456 | 819 | 13 |
dedup.py in cc_net |
360 | 24 | 456 | 819 | 7 |
perplexity.py in cc_net |
284 | 26 | 456 | 672 | 3 |
expand_corpus.py in cc_net/tools |
230 | 15 | 456 | 680 | 6 |
minify.py in cc_net |
230 | 22 | 456 | 819 | 12 |
execution.py in cc_net |
172 | 9 | 456 | 672 | 8 |
flat_hash_set.py in cc_net |
160 | 28 | 456 | 819 | 4 |
text_normalizer.py in cc_net |
150 | 8 | 456 | 629 | 2 |
dl_cc_100.py in cc_net/tools |
133 | 6 | 456 | 456 | 1 |
split_by_lang.py in cc_net |
117 | 10 | 456 | 672 | 3 |
regroup.py in cc_net |
81 | 5 | 456 | 680 | 3 |
get_wiki_cirrus.py in cc_net |
74 | 6 | 456 | 680 | 3 |
make_dmoz_corpus.py in cc_net/tools |
55 | 4 | 456 | 672 | 3 |
tokenizer.py in cc_net |
55 | 6 | 456 | 672 | 2 |
pyproject.toml in root |
20 | - | 456 | 680 | 5 |
__main__.py in cc_net |
6 | 1 | 456 | 819 | 4 |