Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add window_size and pruning to the timeseries_anomalies.find_anomalies primitive #160

Closed
csala opened this issue Apr 19, 2019 · 0 comments · Fixed by #169
Closed

Add window_size and pruning to the timeseries_anomalies.find_anomalies primitive #160

csala opened this issue Apr 19, 2019 · 0 comments · Fixed by #169
Assignees
@csala
Labels
approved The issue is approved and someone can start working on it new feature A new feature is being requested primitive improvement An improvement over an existing primitive
Milestone
0.1.10

Comments

@csala
Copy link
Contributor

csala commented Apr 19, 2019

The mlprimitives.custom.timeseries_anomalies.find_anomalies primitive is missing two important points form the specification in the original paper that inspired the creation of this primitive:

  • A window_size argument to calculate the thresholds and find the anomalies in batches instead of using the whole sequence at once (called h in the paper)
  • An anomaly pruning step which is performed over the anomalous sequences found withing each of the windows derived from the previous point.

The implementation of this issue will cover #158 and #157
@csala csala added approved The issue is approved and someone can start working on it primitive improvement An improvement over an existing primitive new feature A new feature is being requested labels Apr 19, 2019
This was referenced Apr 19, 2019
Closed
Closed
@csala csala self-assigned this Apr 20, 2019
@csala csala mentioned this issue May 2, 2019
Merged
@csala csala added this to the 0.1.10 milestone May 2, 2019
@csala csala closed this as completed in #169 May 2, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@csala csala

Labels
approved The issue is approved and someone can start working on it new feature A new feature is being requested primitive improvement An improvement over an existing primitive
Projects
None yet
Milestone
0.1.10
Development

Successfully merging a pull request may close this issue.

Issue 160 add window size and pruning to find anomalies MLBazaar/MLPrimitives
1 participant
@csala