diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2020-11-25 13:00:54 +0100 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2020-11-25 13:00:54 +0100 |
| commit | 4a9633f0f989f4103a5c35721c5984e21a5d2192 (patch) | |
| tree | 3f6c819fc951ca16844df06ba61cfab209e74466 /fuzzycat/cluster.py | |
| parent | 368d2f75b5ef80bba822f38632787c2918317200 (diff) | |
| download | fuzzycat-4a9633f0f989f4103a5c35721c5984e21a5d2192.tar.gz fuzzycat-4a9633f0f989f4103a5c35721c5984e21a5d2192.zip | |
move enums into common
Diffstat (limited to 'fuzzycat/cluster.py')
| -rw-r--r-- | fuzzycat/cluster.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/fuzzycat/cluster.py b/fuzzycat/cluster.py index bff80f9..7843577 100644 --- a/fuzzycat/cluster.py +++ b/fuzzycat/cluster.py @@ -299,6 +299,9 @@ def release_key_title_ngram(doc: KeyDoc, n=3) -> Tuple[str, str]: class Cluster: """ Setup and run clustering over a potentially large (100m) number of records. + + Two main options are iterable (TODO: work on parsed docs), and the key + function to apply to value to group by. """ def __init__(self, iterable: collections.abc.Iterable, |