Alexandr Velikiy
fa9673e347
"Error: Need at least 1 labeled segment" when labeling only negative segment #790 ( #791 )
5 years ago
rozetko
96db3bdef8
Error: too many values to unpack #721 ( #725 )
5 years ago
Evgeny Smyshlyaev
801f5b1c57
Change mutable default values to none #638 ( #682 )
...
* add types, remove mutables from defaults
* fix debug logging
5 years ago
Evgeny Smyshlyaev
e0dde3c8ba
Labeling for anomalies #631 ( #655 )
5 years ago
rozetko
a56ac6ec4e
Endpoint for smoothing data #612 ( #639 )
5 years ago
Evgeny Smyshlyaev
d1cb6f0406
Make class for detection result ( #634 )
5 years ago
Alexandr Velikiy
d58f08c42d
Smoothing for anomaly detector #607 ( #608 )
5 years ago
Alexey Velikiy
194a8b9de6
Analytic types ( #573 )
5 years ago
Evgeny Smyshlyaev
4cef0545e1
Non intersected chunks for consuming data #529 ( #530 )
5 years ago
Evgeny Smyshlyaev
21f39f2a60
Send data to detection in chunks #489 ( #503 )
...
* Add `get_data_chunks` generator to `utils/dataframe.py`
* Add chunks generator usage to `analytic_worker.py`
* Add tests to `tests/test_detector_chunks.py`
* Minor fixes (constants, etc)
5 years ago
Coin de Gamma
821014211f
Change constant executors number to None #490
5 years ago
Alexandr Velikiy
e0cc56d425
Not-ending learning #264 ( #484 )
...
- optimize general model
- add logs
5 years ago
Coin de Gamma
30412d5d38
back WORKERS_EXECUTORS = 20 in analytic_unit_manager.py
5 years ago
Coin de Gamma
8e086f0473
add difinition to prepare_data
5 years ago
Evgeny Smyshlyaev
3c0d87e0cc
Nonetype object has no attribute update #375 ( #374 )
5 years ago
rozetko
8d98007fec
Log all analytics errors #353 ( #356 )
...
* Return error when analytics is not ready
* Log handle_analytic_task exception
* Return error on detection failure
5 years ago
Evgeny Smyshlyaev
6bf1114b7b
Detection return empty result #347 ( #348 )
...
* set constant window size
* improve logging, save detected segments from push\pull process
5 years ago
rozetko
9b6f5482bc
Fix webhooks ( #341 )
5 years ago
Alexandr Velikiy
5ab3ff64dd
Move data cropping to the models #335 ( #336 )
5 years ago
Alexandr Velikiy
1e88ead80a
Convert None to NaN before sending data to model #333 ( #334 )
5 years ago
Alexandr Velikiy
b1428c735f
Error: '<' not supported between instances of 'NoneType' and 'NoneType' #323 ( #332 )
5 years ago
rozetko
d300362b49
Fix threshold detector ( #331 )
5 years ago
rozetko
68f47f78f7
Threshold detector #324 ( #330 )
5 years ago
rozetko
77fbde6fa3
Error: detect missing cache #299 ( #302 )
...
* Pass cache to detect
* rename AnalyticUnitCache to ModelCache
* Send .data from cache
* Drop nans from bucket && set window size from cache && check cache None
* Read proper payload on DETECT message
6 years ago
Evgeny Smyshlyaev
ec3a3a093a
Analytic unit worker bucket #273 ( #297 )
6 years ago
Evgeny Smyshlyaev
d4f6783652
Pull / push data from Grafana to analytics #267 ( #290 )
...
* add data puller
* Do not send response on PUSH event
* Stub analytics PUSH message handling
6 years ago
Evgeny Smyshlyaev
c02be4cbfc
Rename predict to detect #279 ( #284 )
...
* dummy rename
* fixes
* renaming in analytics
6 years ago
Alexey Velikiy
4f4b25d9a3
Analytic unit predict event #277 ( #280 )
6 years ago
Alexey Velikiy
ce8523fafa
Cancel learning on analytic unit deletion #266 ( #269 )
...
* basic cancelation in analytics
* cancelation task on node
* basic cancelation in analytics
6 years ago
Alexey Velikiy
7ec2616cb4
Workers for analyticunits #203 ( #265 )
...
* rm async from analytic_unit_worker + some refactorings in maager
* AnalyticUnitManager
* workers for analytic units
6 years ago
Alexandr Velikiy
7ad0e5360f
Incorrect work of analytics with nan filled dataset #247 ( #248 )
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
rozetko
9f1b2397d0
Convert timestamps from s to ms
6 years ago
rozetko
942c4ca112
general predictor -> general model ( #130 )
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
Alexey Velikiy
955f2821e3
Analytic unit cache start #117 ( #120 )
6 years ago
rozetko
e884015587
Fix prediction ( #118 )
6 years ago
Coin de Gamma
f4376ccf29
analytics clearup
6 years ago
rozetko
6420f16c3d
Fix learning ( #116 )
6 years ago
Coin de Gamma
1aada3240e
analytics repair
6 years ago
Coin de Gamma
0902209234
One panel - one worker #62
6 years ago