Commit Graph

283 Commits

Author SHA1 Message Date
Anna 70b2863442
chore: bump version to 1.7.0 2021-03-04 16:53:42 -05:00
Anna 6db8a80894
feat: stop trying to separate static sub messages 2021-03-04 16:48:11 -05:00
Anna d782d48226
chore: add community ads to description 2021-03-03 23:42:06 -05:00
Anna 2325e78e0d
chore: update csv library 2021-03-03 23:35:57 -05:00
Anna 5e9274223d
refactor: break ui code into parts 2021-03-03 23:34:52 -05:00
Anna 00817f97dd
fix(trainer): remove auto-translate textvalue artifacts 2021-03-03 20:36:53 -05:00
Anna 6b9b17971b
fix: process pf strings as sestrings 2021-03-03 20:29:24 -05:00
Anna 30d44bd01b
refactor: use property instead of field 2021-03-03 20:15:11 -05:00
Anna 77fe37ff42
feat(data): add more data 2021-03-03 19:55:54 -05:00
Anna 3a93d4260e
fix(build): provide correct arguments 2021-03-03 19:52:38 -05:00
Anna 6320819d5b
fix(build): only update model when it actually changes 2021-03-03 19:47:22 -05:00
Anna e4286bd5d1
feat(data): add more data 2021-03-03 18:05:57 -05:00
Anna 6aae1a0f36
feat: add some debug data collection buttons 2021-03-03 18:05:43 -05:00
Anna bf34559e63
fix(trainer): clean up some warnings 2021-03-02 23:01:16 -05:00
Anna 56b652fad3
fix(trainer): accept more invalid input interactively 2021-03-02 22:58:22 -05:00
Anna 4f693b7cf7
feat(data): add more data 2021-03-02 21:16:34 -05:00
Anna 0578984857
feat(build): update model on every push 2021-03-02 21:16:13 -05:00
Anna a336ac3342
feat: add explainer to test results 2021-03-02 13:25:05 -05:00
Anna 175aa55ba9
feat: add community ad filtering
Also add tooltip on filter hover with description.
2021-03-02 13:19:47 -05:00
Anna ced993bd0b
fix: actually make multiboxing work 2021-03-02 13:08:42 -05:00
Anna 41dcbdaf8d
refactor: always use TextUnformatted 2021-03-02 12:54:07 -05:00
Anna 0d0b5aeb24
fix: make multi-boxing work 2021-03-02 12:53:56 -05:00
Anna 79f4c702b2
feat(trainer): make test output more obvious 2021-03-02 12:53:19 -05:00
Anna 7c7bc22859
feat(data): add more 2021-03-02 12:44:14 -05:00
Anna 359b7cef3c
fix(trainer): use correct path for csv 2021-03-02 12:43:47 -05:00
Anna 0b1594e961
fix(build): specify latest fedora 2021-03-02 12:39:41 -05:00
Anna e2a8e0154a
feat: add automated model creation 2021-03-02 12:38:30 -05:00
Anna 1836b6dad7
feat(trainer): run on net5 and accept csv path
Hopefully will use this to automate model deployment.
2021-03-02 04:52:36 -05:00
Anna 7ef4a487e2
feat(data): ignore "blu" and add more 2021-02-26 12:07:19 -05:00
Anna 39146ad61d
chore(defs): cut out the global section 2021-02-25 19:26:54 -05:00
Anna c973542dc5
chore: bump version to 1.6.0 2021-02-25 18:57:03 -05:00
Anna 7afd3268eb
refactor: reduce indent level 2021-02-24 21:02:41 -05:00
Anna 6a7c9ffd4b
feat: add update button escape hatch 2021-02-24 21:01:15 -05:00
Anna be62b6ee9b
chore: increase priority and remove experimental line 2021-02-24 20:59:16 -05:00
Anna 548345aaf4
feat: add model status information 2021-02-24 20:58:47 -05:00
Anna 08efe6991c
chore: remove old test suite
As definitions are no longer being updated, the test suite for them
can be removed. The ML trainer already has statistics on how accurate
it is for both training mode and model creation mode, as well as an
interactive mode to test new messages.
2021-02-24 20:26:16 -05:00
Anna 35faec5fe6
chore: fix modes 2021-02-24 20:23:28 -05:00
Anna cec8adf393
feat: begin removing support for defs
Remove the global section, which filtered Free Company ads and RP
ads. Prevent reporting of messages that were filtered by
definitions. Make the ML mode default and mark definitions mode as
obsolete.
2021-02-24 20:23:28 -05:00
Anna e5d755e42c
feat(data): add more 2021-02-24 20:01:41 -05:00
Anna 3eb7007186
fix(trainer): replace newlines automatically 2021-02-24 20:01:35 -05:00
Anna 870856c8ca
refactor: handle events in their own classes
Also deprecate /prmt and replace with /nosol.
2021-02-24 20:01:12 -05:00
Anna 3be14696c6
feat(data): add more 2021-02-21 15:50:17 -05:00
Anna da6accf432
feat: add "come" and "join" as stop words 2021-02-21 15:50:05 -05:00
Anna 5d08f57134
fix(defs): add restocker rmt 2021-02-21 12:36:05 -05:00
Anna 84644d2806
feat(data): add more data
Also pull out stop words into field.
2021-02-20 19:25:15 -05:00
Anna b36377c16e
feat: add normalisation to pipeline
Add a step to normalise messages to the ML pipeline. This ensures
computed properties run on the raw data (which is actually partially
normalised by the compute context). This prevents properties which
rely on symbols (e.g. "B>") from being unable to work properly when
normalisation happens before they have access to the input.
2021-02-17 21:45:09 -05:00
Anna c65fb94ad6
feat: better handle puncutation
Certain symbols are turned into one space so the model sees multiple
words instead of one. Previously "[RP]Hi" would turn into "RPHi" and
be its own token. Now it turns into "RP" and "Hi", counting as two
tokens. This change increased the model's accuracy.

Also make "18", "http", "https", and LGBT-related words into stop
words (meaning they're ignored). Each of these stop words made the
model more accurate and reduced unwanted bias.

Messages destined for ML are now normalised by the plugin in the same
way the model's input is for training. This should make the results
come closer to expected.
2021-02-17 20:01:34 -05:00
Anna 9ea3cd03f3
chore: set plugin to a higher priority 2021-02-17 18:58:58 -05:00
Anna 7f27a17f4f
feat(data): add more data 2021-02-17 18:58:34 -05:00
Anna 8c7b127f55
feat: ignore private pfs unless told otherwise 2021-02-16 19:41:59 -05:00