466a16b2b4
feat(data): add more
2021-05-16 13:03:17 -04:00
2b2dd18717
feat(data): add more
2021-05-15 18:15:23 -04:00
10c0a593e3
feat(data): add more
2021-05-12 14:58:43 -04:00
e8ae13a648
feat(data): add more
2021-05-10 12:23:42 -04:00
d8f32ff7b1
feat(data): add more
2021-05-06 10:04:39 -04:00
fcc309b5b3
feat(data): add more
2021-05-04 13:27:48 -04:00
4e2b3c0f0d
feat(data): add more
2021-05-03 16:27:07 -04:00
58bd18cfbe
feat(data): add more
2021-05-01 23:00:04 -04:00
afcd9d244a
feat(data): add more
2021-04-30 15:41:44 -04:00
11176694b8
feat: remove defs, add some loc, add context menu
2021-04-27 20:16:07 -04:00
c23a47ff1c
feat(data): add more
2021-04-25 19:34:15 -04:00
c2f6b71410
feat(data): add more
2021-04-25 11:43:06 -04:00
e550f83d92
feat(data): add more
2021-04-23 13:21:36 -04:00
a47c1c8aa4
feat(data): add more
2021-04-20 15:47:17 -04:00
9a682aa7db
feat(data): add more
2021-04-18 19:26:00 -04:00
33cbdcf327
feat(data): really stress normal
2021-04-17 12:28:45 -04:00
67434ed07d
feat(data): add more
2021-04-17 12:25:46 -04:00
7ee3550400
fix(trainer): ignore gg
2021-04-15 16:13:48 -04:00
7f31f8b825
feat(data): add more
2021-04-15 12:48:56 -04:00
1e70519b29
feat(data): add more
2021-04-14 14:40:16 -04:00
f14a2ede44
feat(data): add more
2021-04-12 14:30:06 -04:00
08d12c5a84
feat(data): add more
2021-04-11 07:46:55 -04:00
da37007270
feat: use imgui tables
2021-04-08 12:09:53 -04:00
8c0142ae62
refactor: update for api level 3
2021-04-05 14:45:04 -04:00
3992b502ad
feat(data): add more
2021-04-02 15:11:56 -04:00
7e6ddceef5
feat: add category for static substitutes
2021-03-31 14:37:08 -04:00
02d5767c43
feat(data): add more data
2021-03-24 18:37:28 -04:00
12e6d55b20
feat(data): add more data
2021-03-22 18:23:22 -04:00
7c9143b211
feat(data): add more
2021-03-19 14:36:10 -04:00
5286cf4b00
feat(data): add more
2021-03-17 12:01:01 -04:00
21c8e86002
feat(data): add more
2021-03-14 20:35:05 -04:00
4685b6167f
feat(data): add more data
2021-03-12 12:34:42 -05:00
6417d1b37b
feat(data): add more data
2021-03-10 19:40:40 -05:00
d215ed6d60
feat(data): add more
2021-03-06 20:40:41 -05:00
ef0624efde
feat(data): add more
2021-03-05 23:01:05 -05:00
20530c6290
feat(trainer): ignore "mounts"
2021-03-05 13:50:16 -05:00
7a8da6df1e
feat(data): add more
2021-03-05 02:24:16 -05:00
f96ef4fc1b
feat(data): add more
2021-03-04 20:06:26 -05:00
0af172e0a6
feat: stop trying to separate static sub messages
2021-03-04 16:48:11 -05:00
4148df1237
feat(data): add more data
2021-03-03 19:55:54 -05:00
891d4f5aae
feat(data): add more data
2021-03-03 18:05:57 -05:00
4d35c0bac6
feat(data): add more data
2021-03-02 21:16:34 -05:00
1ef5c9f1b5
feat: add community ad filtering
...
Also add tooltip on filter hover with description.
2021-03-02 13:19:47 -05:00
fd256722a1
feat(data): add more
2021-03-02 12:44:14 -05:00
65558fa199
feat(data): ignore "blu" and add more
2021-02-26 12:07:19 -05:00
83e6b20333
feat(data): add more
2021-02-24 20:01:41 -05:00
819ac1b457
feat(data): add more
2021-02-21 15:50:17 -05:00
0dc0c2ef00
feat(data): add more data
...
Also pull out stop words into field.
2021-02-20 19:25:15 -05:00
c3df0a1f8e
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
d00b3b0845
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