[ML] Speed up trend model component prediction #73
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
5 tasks
tveasey
changed the title
droberts195
approved these changes
Apr 25, 2018
|
Agreed, I'll hold off merging for the time being. |
droberts195
added a commit
that referenced
this pull request
Apr 27, 2018
Should have been part of #73
|
When this is backported to 6.x please also backport 001291a |
tveasey
added a commit
that referenced
this pull request
May 4, 2018
#73) We have multiple trend models and use a weighted combination of these to make a prediction at some future time. Depending on the time the prediction is required and the current decay rate, a number of these will have very low weight. We can exclude these altogether from the prediction and save the time to compute corresponding prediction with minimal impact on the result.
droberts195
added a commit
that referenced
this pull request
May 4, 2018
Should have been part of #73
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Whilst profiling end-of-bucket processing to evaluate #54 another hotspot was uncovered.
We have multiple trend models and use a weighted combination of these to make a prediction at some future time. Depending on the time the prediction is required and the current decay rate, a number of these will have very low weight. We can exclude these altogether from the prediction and save the time to compute corresponding prediction with minimal impact on the result.
This saves another 7% on the end-of-bucket processing for the test scenario described in #53. It has a small impact on predictions for count and metric model and so a small impact on results.