Uh oh!
There was an error while loading. Please reload this page.
Chapter 11 - #1074
Conversation
restructuring disposal attributes into mixin class
adding `is_disposal_rate` attribute to triangle
improving docstring and adding codecov coverage
Disposal rate method
Weighted regression
Uh oh!
There was an error while loading. Please reload this page.
Pyright Type CompletenessView the full Project (full
Other symbols referenced but not exported by
Symbols without documentation:
Patch (exported symbols added or changed by this PR): 38.7% fully typed (12 / 31)
Patch symbol details
|
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@## chapter_11_prep #1074 +/- ##
===================================================
+ Coverage 89.38% 89.52% +0.14%
===================================================
Files 89 91 +2 Lines 5179 5299 +120 Branches 663 673 +10 ===================================================
+ Hits 4629 4744 +115 - Misses 386 393 +7 + Partials 164 162 -2
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Summary of Changes
Related GitHub Issue(s)
Additional Context for Reviewers
uv run pytest) and documentation changes (uv run jb build docs --builder=custom --custom-builder=doctest)Note
Medium Risk
New reserving workflow touches triangle cum/incr logic, nan masking, and weighted regression used by development fitting; mistakes could skew forecasts, though coverage includes Friedland fidelity and chainladder parity tests.
Overview
Adds
DisposalRate(Friedland disposal-rate adjustment) as a public adjustment: it requires an a priori ultimate viasample_weight, estimates a disposal pattern fromdisposal_rate_tri, andtransformrebuilds future emergence through derivedldf_/full_triangle_.Triangle gains
DisposalMixin,disposal_rate_tri, andis_disposal_rate, withincr_to_cum/cum_to_incrtreating disposal patterns as additive cumulative ratios instead of link-ratio products.nan_triangleno longer treats all pattern triangles as fully valid masks.Supporting changes:
TriangleWeighthandles full triangles forn_periodsand returns ndarray weights;WeightedRegressionuses weighted means for slope/intercept and exposesrsq_;MethodBase.validate_weightis a static helper; Friedland sample CSVs/docs are refreshed (including removingfriedland_xyz_dispfrom the manifest).Reviewed by Cursor Bugbot for commit c63a887. Bugbot is set up for automated code reviews on this repo. Configure here.