|
|
54e9f0e8fc
|
Implemented median; disabled median & se (low utility)
|
2022-02-03 15:10:26 +01:00 |
|
|
|
bd17ac4906
|
Better Recommendation Generation
|
2022-02-01 12:22:13 +01:00 |
|
|
|
6e64e76310
|
Better error-message on pagerank ev-iter fail
|
2022-01-31 14:02:00 +01:00 |
|
|
|
33ba27e2d0
|
Implemented Pagerank
|
2022-01-31 13:45:26 +01:00 |
|
|
|
e5d2ca532c
|
Shorter Training
|
2022-01-22 18:12:57 +01:00 |
|
|
|
a6d9a75030
|
Sanitize description of books before rake
|
2021-12-18 18:09:45 +01:00 |
|
|
|
199fab7875
|
New shell-command, nltk for keyword extraction from description
|
2021-12-11 13:58:01 +01:00 |
|
|
|
36baf1aaec
|
Bug: Typo in train
|
2021-12-11 11:54:25 +01:00 |
|
|
|
81fa6ca4d6
|
Faster training (earlier stopping)
|
2021-12-11 11:52:49 +01:00 |
|
|
|
16cc68dfed
|
chmod +x (again)
|
2021-12-05 19:57:05 +01:00 |
|
|
|
da9569fd4c
|
Added 'competence' command (displays recommenders and justifications of
their scores)
|
2021-12-05 19:56:26 +01:00 |
|
|
|
aa95a9b16b
|
chmod +x
|
2021-12-05 19:54:03 +01:00 |
|
|
|
39930d1233
|
kp
|
2021-12-05 19:53:30 +01:00 |
|
|
|
f2fad859dc
|
Added a progress-command (and newly trained weights)
|
2021-11-24 22:35:39 +01:00 |
|
|
|
ef7fceacea
|
Better 'Gradientenabstieg'
|
2021-11-23 20:51:24 +01:00 |
|
|
|
7f51f139f2
|
Actually, we will also train on whitepapers (because otherwise I would
have to fix an ugly bug)
|
2021-10-17 15:52:52 +02:00 |
|
|
|
ce99e5301b
|
Smashed bug with argument-parsing
|
2021-10-17 15:51:26 +02:00 |
|
|
|
8778cfdae6
|
Also dont train on whitepapers
|
2021-10-17 15:50:33 +02:00 |
|
|
|
3588587c92
|
Earlier removal of whitepapers (dont extrapolate from them)
|
2021-10-17 15:48:44 +02:00 |
|
|
|
65e8948202
|
Filter out the whitepapers I have in my libary
|
2021-10-17 15:47:37 +02:00 |
|
|
|
153aa434d5
|
Implemented listScores command
|
2021-10-13 15:10:12 +02:00 |
|
|
|
6689c3bf6b
|
Removed ~ from score and shorter training
|
2021-10-12 20:10:48 +02:00 |
|
|
|
f27d89e43d
|
Added a dark-mode
|
2021-10-05 18:25:27 +02:00 |
|
|
|
7fd1f4fa3f
|
Better shit-detection and mitigation when training
|
2021-10-05 18:08:32 +02:00 |
|
|
|
73364935f0
|
Bug Fix: A function name was overloaded
|
2021-10-04 12:27:12 +02:00 |
|
|
|
ca7b2fd87c
|
Faster termination when training
|
2021-09-30 00:08:53 +02:00 |
|
|
|
8c4e35bf41
|
Bug fix in training
|
2021-09-27 00:22:35 +02:00 |
|
|
|
8964fa2c6a
|
No early stopping if still bad
|
2021-09-26 23:18:21 +02:00 |
|
|
|
1303f302d3
|
Dont train if we are already perfect
|
2021-09-26 23:17:03 +02:00 |
|
|
|
9f9d2390b3
|
Less verbose training
|
2021-09-26 23:15:50 +02:00 |
|
|
|
98aaec1e22
|
Train using gradient
|
2021-09-26 23:13:43 +02:00 |
|
|
|
06a0461e93
|
Better pruning of tags and recommenders
|
2021-09-26 16:51:17 +02:00 |
|
|
|
f3240147d5
|
training now terminates earlier when stagnating (can be disabled via
flag)
|
2021-09-26 15:52:54 +02:00 |
|
|
|
9126bbcc14
|
Stronger linear seperation
|
2021-09-26 14:31:00 +02:00 |
|
|
|
f1c887275c
|
removeUselessSeries and stronger linear seperation
|
2021-09-26 12:46:30 +02:00 |
|
|
|
2bb2e15b73
|
Tweaks to recommendation-display
|
2021-09-25 20:15:14 +02:00 |
|
|
|
92d1b33ee3
|
Made recommendation-graph way better; tweaks to bounds-loss
|
2021-09-25 00:54:09 +02:00 |
|
|
|
6ed1d41e2c
|
Added new tag-based version of recommendation-visualizer and added a
boundary-loss
|
2021-09-24 23:39:55 +02:00 |
|
|
|
212a30298a
|
Stronger regression-loss; more parameter-freedome
|
2021-09-24 19:16:29 +02:00 |
|
|
|
5a4e48d86c
|
Added a regression-loss (push weights towards 1)
|
2021-09-24 19:12:09 +02:00 |
|
|
|
9d6f37af45
|
Mostly refactoring
|
2021-09-24 18:25:37 +02:00 |
|
|
|
d5a6aadbb5
|
We now display se instead of std in the web-view; smol changes to the
penalties while training
|
2021-09-24 17:50:00 +02:00 |
|
|
|
f48fb12f0a
|
No more stability-metric for the nn (but se instead)
|
2021-09-24 17:35:32 +02:00 |
|
|
|
1521f20340
|
Smol tweaks
|
2021-09-24 17:23:34 +02:00 |
|
|
|
9318811d8a
|
Small tweaks to the scroring-algo and less calls to calibre when
training
|
2021-09-24 17:13:36 +02:00 |
|
|
|
fb3a5592df
|
Tweaked training
|
2021-09-24 16:32:43 +02:00 |
|
|
|
cb0ad906eb
|
Implemented Neural Net + training
|
2021-09-24 16:13:55 +02:00 |
|
|
|
0231d97a42
|
Switched to a simpler bayesian model for score generation
|
2021-09-24 14:49:59 +02:00 |
|
|
|
4fa3a57cc7
|
Remove 'useless' read books from recommendation-graph (far away from all
unread books)
|
2021-09-08 22:54:49 +02:00 |
|
|
|
c31a3d78e2
|
Allow keeping useless recommenders (args)
|
2021-09-06 16:21:01 +02:00 |
|
|
|
60067ed263
|
Remove unused recommenders when recommending and allow keeping topLists
via args
|
2021-09-06 16:17:54 +02:00 |
|
|
|
255502cdd2
|
Added support for bigger Top-Lists
|
2021-09-03 21:21:07 +02:00 |
|
|
|
9c4722aa8f
|
Delta
|
2021-07-04 20:44:10 +02:00 |
|
|
|
d537f878b7
|
Better Stuff
|
2021-07-04 20:38:20 +02:00 |
|
|
|
0f1255f614
|
Buffed TopLists a bit
|
2021-07-04 20:25:26 +02:00 |
|
|
|
be0afb59c7
|
Fined tuned wheight of TopLists and Tags
|
2021-07-04 20:08:25 +02:00 |
|
|
|
486a8fb88f
|
Tweaked the scoring (Feedback-Nodes get boosted by 1/4 of the std when
calculating scores for unread books)
|
2021-06-25 13:14:08 +02:00 |
|
|
|
a188e923e2
|
Tweaked the Algo (higher penalty for low number of feedbacks)
|
2021-06-23 18:50:26 +02:00 |
|
|
|
cc6606f468
|
Better Tag-Pruning (keep more good tags)
|
2021-06-23 15:45:32 +02:00 |
|
|
|
a8d9f96e70
|
Mark center of analysis and include topLists in analysis
|
2021-06-22 15:41:24 +02:00 |
|
|
|
07205f37c0
|
Tweaking to the visual apperance
|
2021-06-16 18:01:28 +02:00 |
|
|
|
ff5c1ae139
|
Added remove-egde cli-argument
|
2021-06-16 17:35:40 +02:00 |
|
|
|
532357b186
|
number and depth are no longer required arguments
|
2021-06-16 17:15:53 +02:00 |
|
|
|
03cb19819b
|
Shebang now points to .venv-python
|
2021-06-16 17:12:50 +02:00 |
|
|
|
d20ada2d60
|
Executable Bit for caliGraph.py
|
2021-06-16 17:11:31 +02:00 |
|
|
|
378dbcd5ef
|
Renamed main.py -> caliGraph.py
|
2021-06-16 17:06:57 +02:00 |
|
