diff options
| -rw-r--r-- | fuzzycat/verify.py | 4 | ||||
| -rw-r--r-- | notes/2020_11_testruns.md | 31 |
2 files changed, 33 insertions, 2 deletions
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index dd57506..e7b397f 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -258,8 +258,8 @@ def compare(a, b): if a_slug_title == b_slug_title: try: - a_subtitles = glom(a, "extra.subtitle") - b_subtitles = glom(b, "extra.subtitle") + a_subtitles = glom(a, "extra.subtitle") or [] + b_subtitles = glom(b, "extra.subtitle") or [] for a_sub in a_subtitles: for b_sub in b_subtitles: if slugify_string(a_sub) != slugify_string(b_sub): diff --git a/notes/2020_11_testruns.md b/notes/2020_11_testruns.md new file mode 100644 index 0000000..31c292c --- /dev/null +++ b/notes/2020_11_testruns.md @@ -0,0 +1,31 @@ +# Test runs + +## Using --min-cluster-size + +Skipping writes of single element clusters cuts clustering from ~42h to ~22h. + +``` +$ time zstdcat -T0 release_export_expanded.json.zst | \ + TMPDIR=/bigger/tmp python -m fuzzycat cluster --min-cluster-size 2 \ + --tmpdir /bigger/tmp -t tsandcrawler | \ + zstd -c9 > cluster_tsandcrawler_min_cluster_size_2.json.zst +... +max cluster size cut off for: 雜報その1 +max cluster size cut off for: 雜録 +2020-11-27 18:31:39.825 DEBUG __main__ - run_cluster: {"key_fail": 0, "key_ok": +154202433, "key_empty": 942, "key_denylist": 0, "num_clusters": 11763096} + +real 1328m46.994s +user 1088m6.837s +sys 98m17.501s +``` + +We find 11763096 clusters, 16GB compressed (zstdcat takes about 5min, +sequential read at 50M/s). + +``` +$ time zstdcat -T0 cluster_tsandcrawler_min_cluster_size_2.json.zst | \ + python -m fuzzycat verify | \ + zstd -T0 -c9 > cluster_tsandcrawler_min_cluster_size_2_verify.tsv.zst +``` + |