Skip to content
GitLab
Projects Groups Topics Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
  • Sign in
  • plf plf
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributor statistics
    • Graph
    • Compare revisions
    • Locked files
  • Issues 20.5k
    • Issues 20.5k
    • List
    • Boards
    • Service Desk
    • Milestones
    • Iterations
    • Requirements
  • Merge requests 1
    • Merge requests 1
  • Deployments
    • Deployments
    • Releases
  • Packages and registries
    • Packages and registries
    • Package Registry
    • Container Registry
    • Terraform modules
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Commits
  • Issue Boards
Collapse sidebar
  • ACS
  • Public
  • Power System Automation and Monitoring
  • ProLoaFProLoaF
  • plfplf
  • Issues
  • #26
Closed
Open
Issue created May 28, 2021 by Gonca Guerses-Tran@gonca.guerses.tranOwner

fc_baselines.py - eval_baselines requires different arguments for different baseline methods -> can't test several baselines at once (code fails)

'Under the "Evaluate All" section, with NUM_PRED = 7 for example,

  • For 'sarimax': the second argument of eval_baseline must be set to "y_val[:NUM_PRED,:,target_column]", or the function fails because of mismatched sizes
  • However, for 'simple-naive', 'seasonal-naive', or 'naive-stl' : the second argument of eval_baseline must be set to "y_val[:,:,target_column]", (without NUM_PRED) or the function fails because of mismatched sizes
  • Basically, as far as I can tell, it is impossible to use 1 setting and run all the different baseline types in one go.
Assignee
Assign to
Time tracking