Skip to content

GitLab

  • Menu
Projects Groups Snippets
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
  • s2s-ai-challenge s2s-ai-challenge
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 3
    • Issues 3
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Packages & Registries
    • Packages & Registries
    • Container Registry
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • Aaron Spring
  • s2s-ai-challenges2s-ai-challenge
  • Issues
  • #50

Closed
Open
Created Oct 20, 2021 by Sergi Bech@sergi.bechsala

RPSS should be computed with means of RPS

Hi Aaron.

Checking the verification notebook again we detected that you first compute RPS and then compute the RPPS and finally the mean over forecast_time. Shouldn't we compute first the mean over forecast_time of RPS and then compute RPSS ?

# penalize 
penalize = obs_p.where(fct_p!=1, other=-10).mean('category')
rpss = rpss.where(penalize!=0,other=-10) 
# clip 
rpss = rpss.clip(-10, 1) 
# average over all forecasts 
rpss = rpss.mean('forecast_time')

/cc @aaron.spring @llledo @lluis.palma

Assignee
Assign to
Time tracking

This GitLab is a part of renkulab.io