Alexander Velikiy
b53b49dcf7
Refactoring of Jump and Drop models ( #865 )
...
* add stair model
* add stair model method
* add types
* fix
* add tests for get stair
* fix
* fix imports
* add todo
* fixes
* get stair indexes to stair model
* fixes
* remove old methods
* use enum
* fix get_model_type
* remove exception
* list(set) -> utils.remove_duplicates
* refactor get_stair
* fixes
* fixes 2
* fixes 3
* todo
4 years ago
Alexandr Velikiy
ae06749b8d
Refactoring of Peak and Trough models #424 ( #680 )
5 years ago
Alexandr Velikiy
6b398d6ee9
Segment class #636 ( #637 )
5 years ago
Alexandr Velikiy
20d1a974bb
Use ModelState classes in models #582 ( #586 )
5 years ago
Alexey Velikiy
30108ae643
jsonclass usage in models + fixes in meta ( #583 )
...
* jsonclass usage in models + fixes in meta
* remove some empty lines
5 years ago
Alexandr Velikiy
7f15bf3996
Add ModelState children classes #576 ( #579 )
5 years ago
Alexandr Velikiy
a9971d64d0
ValueError attempt to get argmin of an empty sequence #518 ( #537 )
5 years ago
Alexandr Velikiy
0f1d7774fe
Find start and end of peaks and troughs #506 ( #507 )
5 years ago
Alexandr Velikiy
e0cc56d425
Not-ending learning #264 ( #484 )
...
- optimize general model
- add logs
5 years ago
Alexandr Velikiy
81c3d79238
Change the pattern filtering logic #366 ( #423 )
5 years ago
Alexandr Velikiy
13305336b7
Change the pattern filtering logic #366 ( #422 )
5 years ago
Alexandr Velikiy
7ab0db6ba9
Update state during learning #406 ( #408 )
5 years ago
Alexandr Velikiy
6d5ec2b6fe
Webhooks don't find any patterns #401 ( #404 )
5 years ago
Alexandr Velikiy
963eaa6276
Remove duplicate code from models #390 ( #391 )
...
just refactoring
5 years ago
Alexandr Velikiy
6e7073b212
Increase the number of parameters obtained during learning #364 ( #383 )
...
Increase the number of parameters obtained during learning #364
5 years ago
Evgeny Smyshlyaev
d399d0b84a
Remove duplicates from models #357 ( #363 )
...
refactoring
5 years ago
Alexandr Velikiy
99c9431f5d
IndexError: list index out of range if segment has NaN #242 ( #349 )
...
add threshold in model
5 years ago
Alexandr Velikiy
5ab3ff64dd
Move data cropping to the models #335 ( #336 )
5 years ago
Alexandr Velikiy
5edc0b1977
Error name parse segment is not defined #315 ( #322 )
...
Fixed: Error name parse segment is not defined #315
5 years ago
Alexandr Velikiy
0689fe6384
WIP:Clean up utils #282 ( #293 )
6 years ago
Evgeny Smyshlyaev
c02be4cbfc
Rename predict to detect #279 ( #284 )
...
* dummy rename
* fixes
* renaming in analytics
6 years ago
Coin de Gamma
b65f1a552c
trim trailing whitespaces
6 years ago
Alexandr Velikiy
d389cf3adb
Move repeating code from models to utils #270 ( #272 )
...
peak / trough / jump / drop / general common code to and utils refactoring
6 years ago
Alexandr Velikiy
7ad0e5360f
Incorrect work of analytics with nan filled dataset #247 ( #248 )
6 years ago
rozetko
9986642659
Fix #231 : .count(np.NaN) -> .isnull().sum()
6 years ago
Alexandr Velikiy
8614499c20
Proccesing for NaN values #231 ( #236 )
6 years ago
Alexey Velikiy
005097dde0
Analytics project structure improvement #215 ( #228 )
...
* bin & analytics folders
* sys path & config relocation
* fix analytics path in node
6 years ago
Alexandr Velikiy
dd139e1feb
Models with filtering#186 ( #218 )
6 years ago
Alexandr Velikiy
4912026113
Fix models for choosing the "wrong" patterns #195 ( #202 )
...
* jump and drop not crash
* fix logiс of try/except block in drops
left one block
* fix logic of try/except in jump
left one block
6 years ago
Alexandr Velikiy
b79abf5299
Anti-segments in general model #142 ( #185 )
6 years ago
Alexandr Velikiy
4824b22df8
Anti-segments in peaks model #142 ( #170 )
6 years ago
Alexandr Velikiy
169c341189
add aggr model to peak models ( #162 )
...
* add aggr model to peak models
change convolve with first pattern.
now it is avarage model instead of only first pattern.
* common model for peaks with comments
6 years ago
Alexandr Velikiy
12c52f5ce9
Consider segment width in models #136 ( #141 )
...
* fit -> do_fit in all models && add self.segment_length
* Move converting indices to timestamps to Model class
* add flexible win size to all models
6 years ago
rozetko
d1ca327b0d
Improve all models
6 years ago
rozetko
48999a934d
Fix timestamps return in all models (convert from ns to ms)
6 years ago
rozetko
9f1b2397d0
Convert timestamps from s to ms
6 years ago
rozetko
2cd685114e
Minor fixes
6 years ago
rozetko
8bd52b64f7
Check for segment length in all models ( #127 )
6 years ago
rozetko
c2c3925979
Make all models work && add reverse peak model ( #124 )
...
- Subtract min value from dataset before passing to model
- Rename StepModel -> DropModel
- Use cache to save state in all models
- Return `Segment { 'from': <timestamp>, 'to': <timestamp>}` instead of `Segment { 'from': <index>, 'to': <index>}` in all models
- Integrate new peaks model (from https://github.com/hastic/hastic-server/pull/123 )
- Integrate new reverse-peaks model (from https://github.com/hastic/hastic-server/pull/123 )
- Refactor: make `predict` method in `Model` not abstract and remove it from all children
- Refactor: add abstract `do_predict` method to models
6 years ago