Actuarial reserving in Python
MPL-2.0 License
Bot releases are hidden (Show)
Minor bug fixes: #524 ParallelogramOlf and #525 Unplanned Trend deprecations.
Published by jbogaardt 5 months ago
Bump release number
Published by jbogaardt 5 months ago
Fix for compatibility between chainladder==0.8.20
and pandas<2.2.0
Published by jbogaardt 6 months ago
Published by jbogaardt 6 months ago
Full Changelog: https://github.com/casact/chainladder-python/compare/v0.8.18...v0.8.19
Published by jbogaardt about 1 year ago
Minor release with a ew bug fixes.
grain
methodsigma_
weight of Development
estimator. Previous algorithm did not honor link ratio exlcusions.Published by jbogaardt over 1 year ago
Bump of 0.8.16
Published by jbogaardt over 1 year ago
Full Changelog: https://github.com/casact/chainladder-python/compare/v0.8.15...v0.8.16
Published by jbogaardt over 1 year ago
Full Changelog: https://github.com/casact/chainladder-python/compare/v0.8.14...v0.8.15
Published by jbogaardt almost 2 years ago
A big thank you to our new contributors this release
Full Changelog: https://github.com/casact/chainladder-python/compare/v0.8.13...v0.8.14
Published by jbogaardt over 2 years ago
The majority of this release was written by @kennethshsu and contains a first-time contribution from @genedan. Thank you!
predict
method that failed to honor development ages appropriatlyheatmap
method.to_frame
methodCaseOutstanding
drop_high
and drop_low
arguments of Development
estimator.Published by jbogaardt over 2 years ago
Introduced ExpectedLoss method
grain
Published by jbogaardt over 2 years ago
Published by jbogaardt over 2 years ago
val_to_dev
bug fixedcl.concat
to_frame
bug fix on empty trianglesto_frame
bug and deprecation notice in origin_as_datetime
argument.pandas>1.4.0
bugExpectedLoss
methodDevelopment
estimatorfillna
method added to Triangle class that supports filling with constants or other Triangles.Published by jbogaardt almost 3 years ago
xlcompose
as a dependencyis_cumulative
property of triangle is not set.drop_high
and drop_low
functionality to include integers and variable length lists. PR courtesy of @kennethshsu.MackChainladder
to zero variance when inbr_
and cdf_
are 0.BarnettZehnwirth.transform
that was previously not applying the log-transform correctlyPublished by jbogaardt almost 3 years ago
Enhancements
projection_period
to all Tail estimators. This allows for analyzing run-off beyond a one year time horizon.TailCurve.fit_period
to allow boolean lists - similar to Development.drop_high
Bug Fixes
grain=='S'
is being interpreted as seconds and not semesters.origin
/development
broadcasting issue that was causing silent bugs in calculations on malformed triangles.Published by jbogaardt about 3 years ago
BootstrapODPSample
column restrictiongrain
slice
Benktander
index broadcastingPublished by jbogaardt about 3 years ago
Minor release to fix some chainladder==0.8.6
regressions.
heatmap
valuation_date
regression when instantiating Triangles as vectorsGridSearch
using n_jobs
argumentPublished by jbogaardt about 3 years ago
np.sum(cl.load_sample('raa'))
val_to_dev
TriangleGroupby.__getitem__
to support column selection on groupby operations to align with pandas, e.g. cl.load_sample('clrd').groupby('LOB')['CumPaidLoss']
Published by jbogaardt over 3 years ago
groupby
hyperparameter to several more estimators including the widely used Development
estimator. This allows fitting development patterns at a higher grain than the Triangle all within the estiamtor or Pipeline.0.8.5
, this code wouldprism = cl.load_sample('prism')
prism / prism.groupby('Line').sum()
model_diagnostics
utility function to be used on fitted estimators.dask
arrays. Current support is basic, but will eventually allow for distributed computations on massive triangles.np.sin(cl.load_sample('raa'))
grain
estimator.