ce15b07636
fix(trainer): accept more invalid input interactively
2021-03-02 22:58:22 -05:00
4d35c0bac6
feat(data): add more data
2021-03-02 21:16:34 -05:00
81b54c35aa
feat: add explainer to test results
2021-03-02 13:25:05 -05:00
1ef5c9f1b5
feat: add community ad filtering
...
Also add tooltip on filter hover with description.
2021-03-02 13:19:47 -05:00
090c4eff3c
feat(trainer): make test output more obvious
2021-03-02 12:53:19 -05:00
fd256722a1
feat(data): add more
2021-03-02 12:44:14 -05:00
348c610ca1
fix(trainer): use correct path for csv
2021-03-02 12:43:47 -05:00
2fd2e54401
feat: add automated model creation
2021-03-02 12:38:30 -05:00
6c9dd9164b
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
65558fa199
feat(data): ignore "blu" and add more
2021-02-26 12:07:19 -05:00
33f5421e79
chore: fix modes
2021-02-24 20:23:28 -05:00
83e6b20333
feat(data): add more
2021-02-24 20:01:41 -05:00
c038adc4e9
fix(trainer): replace newlines automatically
2021-02-24 20:01:35 -05:00
819ac1b457
feat(data): add more
2021-02-21 15:50:17 -05:00
2181649b22
feat: add "come" and "join" as stop words
2021-02-21 15:50:05 -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
fcfe1bb727
feat(data): add more data
2021-02-17 18:58:34 -05:00
f874d8ac37
feat(data): add more
2021-02-16 12:15:06 -05:00
03fe8eecc2
feat(data): add more data
2021-02-14 15:40:56 -05:00
c7c89b33bc
feat: give classifier game process info
2021-02-12 20:13:34 -05:00
d921a8cfb0
feat(data): add more data
2021-02-12 11:56:54 -05:00
8eb0507041
feat(data): more data
2021-02-08 22:34:29 -05:00
fb9f5d9b94
feat(data): more data
2021-02-07 12:54:14 -05:00
6985eb2eee
feat(data): add more data
2021-02-03 12:16:03 -05:00
Anna
53e0bc3309
feat(data): more
2021-02-01 00:19:51 -05:00
Anna
fdf0849ea6
feat(data): add more data
2021-01-30 20:51:14 -05:00
Anna
d7d6c53c75
chore: fix permissions
2021-01-30 16:10:59 -05:00
Anna
d1228e6bee
feat(data): add more data
2021-01-30 16:04:37 -05:00
Anna
87c5602319
feat: use separate process for classifying
2021-01-30 16:02:37 -05:00
b2e719faa0
feat(data): add more
2021-01-29 22:44:51 -05:00
41e79cb2c9
feat(data): more
2021-01-29 15:01:44 -05:00
bfd6c1b8e2
feat(data): add more data
2021-01-24 18:30:21 -05:00
b0e3c442d1
feat(data): more
2021-01-23 19:57:03 -05:00
d8ccbc6844
feat(data): more data
2021-01-22 17:42:32 -05:00
245a83afe0
feat(data): more reports
2021-01-22 17:33:17 -05:00
75a75476c7
feat(data): more reports
2021-01-21 18:02:33 -05:00
1a2fa2eab4
feat(data): more reports
2021-01-18 22:19:35 -05:00
9931e334dc
feat(data): add more
2021-01-16 13:20:18 -05:00
1606a13885
chore: update nuget packages
2021-01-13 12:37:40 -05:00
0e30924253
feat(data): add more data
2021-01-12 11:23:38 -05:00
a6b181bdf5
feat(data): add more reports
2021-01-11 10:31:33 -05:00
91fd57db0e
feat(data): add more data
2021-01-06 19:21:03 -05:00
601ccffdc0
feat(data): add even more data
2021-01-05 18:02:03 -05:00
1ae0e0feb1
feat(data): add more data
2021-01-05 11:39:44 -05:00
99a9a63190
feat(data): more data
2021-01-03 19:35:33 -05:00
28a6ed8b59
feat(data): more reports
2021-01-03 16:56:53 -05:00
2d1c67d887
feat(data): more reports
2021-01-02 17:28:30 -05:00
df66d397ed
fix(trainer): use LF newlines for real
2021-01-02 17:28:17 -05:00
081e670da4
fix(trainer): use LF newlines
2021-01-02 16:59:40 -05:00
9f15bb7d0d
feat(trainer): have trainer sort data automatically
2021-01-02 16:59:00 -05:00
63d9ea0608
feat(data): more reports
2021-01-02 16:53:47 -05:00
4f46299c12
feat(data): more reports
2021-01-02 13:52:02 -05:00
0793f009c1
feat(data): add more data
2021-01-02 13:09:00 -05:00
b01973b0c0
chore(data): fix mode
2021-01-02 07:54:49 -05:00
2f7761b9b0
chore(trainer): only save model on full run
2021-01-02 07:31:34 -05:00
a07f21ddd3
feat(data): add more reports
2021-01-02 07:31:09 -05:00
42b8b6569f
feat(data): catch up on reports
2020-12-31 17:10:20 -05:00
eba3830c81
feat(data): add more FC ads
2020-12-29 10:11:56 -05:00
3b126d0424
chore(data): add more data
2020-12-28 22:39:10 -05:00
753e0f710e
refactor(trainer): use correct schema, though it shouldn't matter
2020-12-28 22:04:50 -05:00
1b8f7806f5
refactor: put computation in interface
...
This basically undoes the benefits of the previous commit. May end up being reverted.
2020-12-28 21:48:31 -05:00
effe41a345
refactor(training): compute properties in pipeline
...
Hopefully no longer required the data structure to be updated when new computed properties are added. This should also reduce duplication and make it easier to make bigger changes to the model without needing to update the plugin.
2020-12-28 21:01:35 -05:00
bd05abb5e0
feat(trainer): add trainer to actual repo
2020-12-28 20:14:19 -05:00
