492445a469
Split off useful math functions to math.py
2013-08-02 17:27:39 -04:00
33c3586bea
trainola: suppress peaks if larger ones are nearby
...
Might fix the problem Mark noticed where turn-off transients
are erroneously matching the drop that follows startup transients.
2013-07-31 19:12:16 -04:00
62e11a11c0
Fix issue with column ordering in the exemplars
...
If the max scale in the exemplar was a column we weren't using, it
would bail out when looking for that correlation later. Change things
around so exemplars in RAM only keep around the columns we care about.
2013-07-18 22:51:27 -04:00
2bdcee2c36
More helpful error if exemplar stream doesn't exist
2013-07-15 15:19:52 -04:00
6dce8c5296
More output
2013-07-11 18:56:53 -04:00
25c35a56f6
Trainola inserts into the destination stream now
2013-07-10 12:59:39 -04:00
d610deaef0
More trainola work
2013-07-10 11:38:32 -04:00
5a2a32bec5
WIP on trainola improvements
2013-07-09 17:56:26 -04:00
706c3933f9
Add trainola from nilmrun
2013-07-09 17:55:57 -04:00