8614499c20
Proccesing for NaN values #231 ( #236 )
6 years ago
780aefa6fe
Tests for #231 ( #230 )
6 years ago
rozetko
79b302ab7e
Fix launch.json analytics path #215
6 years ago
0d921aafb2
Incorrect work of models with single patterns #234 ( #235 )
...
add first value of patterns list = val[0] instead 0
6 years ago
005097dde0
Analytics project structure improvement #215 ( #228 )
...
* bin & analytics folders
* sys path & config relocation
* fix analytics path in node
6 years ago
9f96b99a37
fix conflict
6 years ago
dd139e1feb
Models with filtering#186 ( #218 )
6 years ago
43b027e470
Unit testing for analytics project #216 ( #223 )
6 years ago
2782955572
Analytics works with one labeled segment#191/212 ( #217 )
...
* Analytics works with one labeled segment
if/else instead of exception
6 years ago
c1ae1a9b19
Server logs improvements #48 ( #205 )
...
improve logs
6 years ago
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
b79abf5299
Anti-segments in general model #142 ( #185 )
6 years ago
de3b64ce95
Decouple processes to different docker containers#187(WIP) ( #188 )
...
analytics and server moved to separate containers, added docker-compose file
6 years ago
3e51fd027a
fix according review
6 years ago
8fa210d23f
remove debug logging
6 years ago
3042ddc81b
fix compose
6 years ago
f72cc35589
fix ZMQ connection string
6 years ago
94aa2349b8
add new dockerfiles
6 years ago
ab099cfd63
Drop model minor fix
6 years ago
rozetko
d6d0b9f36a
Support datasource kit interface #176 ( #177 )
...
* Fix indentation in drop model
* Update datasource-kit version
* GrafanaMetric -> Metric
6 years ago
d885b7ec22
Anti-segments in general model #142 ( #174 )
6 years ago
93e74a45df
Anti-segments in drops model #142 ( #173 )
6 years ago
4824b22df8
Anti-segments in peaks model #142 ( #170 )
6 years ago
dc92d4e201
Anti-segments in troughs model #142 ( #171 )
6 years ago
793c8186f1
Anti-segments in jumps model #142 ( #172 )
6 years ago
142c6baa0a
common model to drop_model ( #166 )
6 years ago
40fd1e296b
Common model in jumps ( #165 )
...
- add common model
- add convolve window
- add WINDOW_SIZE
6 years ago
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
cc2f793ffb
add common model in troughs ( #164 )
...
common model with last comments
6 years ago
f158c5050b
aggr model ( #161 )
...
* aggr model
new defs for aggregate model
* Update utils
raise exception
6 years ago
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
edcf487479
Update custom_model.py
6 years ago
rozetko
d1ca327b0d
Improve all models
6 years ago
65585939ae
minor drop and jump models improvements ( #131 )
6 years ago
rozetko
126eec22a5
Add empty config field check
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
d0a0400fb6
Reverse peak -> trough
6 years ago
rozetko
942c4ca112
general predictor -> general model ( #130 )
6 years ago
rozetko
5f36e5fdf6
Convert cache fields in reverse peak model to float ( #128 )
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
rozetko
592588e12b
Hotfix: return cache from pattern_detector.train
6 years ago
rozetko
9b3a68d4cd
Make drops work ( #121 )
6 years ago
955f2821e3
Analytic unit cache start #117 ( #120 )
6 years ago
6f9f53cb1b
WIP: Jump and drop v1 ( #119 )
...
* new jump model with height
* antipeak
* universal n/w jumps
* jump and drop models
* rm unneeded lines and trailing spaces
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
Alexandr Velikiy
rozetko
Coin de Gamma