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.

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

Analogous Event Loss Set Class #12

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Conversation

dwil
Copy link

@dwil dwil commented Jan 14, 2019

A class designed as a stand in for an Analogous Event analysis.

This class will take a set of loss set sources, event IDs and an occurrence date and build a parametric loss such that the resulting event will only take on the values possible for the supplied event IDs.

Additional Features

  • Load: Allows the user to supply a loading factor for the losses.
  • Occurrence Probability: Allows the user the specify the frequency of the event (i.e. if the event occurs in 30% of trials)

Additional Notes

  • Distributions are reused if possible. This is to avoid duplicate uploads of data.
    • The Severity distribution description includes an MD5 hash of the input data, which is used to identify additional uploads of the same loss data.
    • Frequency and Seasonality distributions will reuse previously created distributions of the same values.
  • state_date is used as the date of occurrence for the event
  • The class inherits all properties of the parametric loss set.
    • As such it is possible to set the event_id and interpolate properties like any other ParametricLossSet
  • An AnalysisProfile is needed for this implementation of the class because it will use filter layers to get the loss values for an specific event ID.
    • This implementation has its limitation but avoids the potential for downloading large data files (i.e. YELTLossSets) and having to parse them client side.

dwil added 4 commits January 14, 2019 11:37
- A class build as a stand in for an analogous event analysis.
- This builds a parametric loss set based on a set of loss sets as sources and event ids.
@dwil dwil requested review from sbmacdonald and briannajp January 14, 2019 17:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant