10.5281/zenodo.4816284
https://zenodo.org/records/4816284
oai:zenodo.org:4816284
Cameron Davidson-Pilon
Cameron Davidson-Pilon
Jonas Kalderstam
Jonas Kalderstam
Noah Jacobson
Noah Jacobson
Sean Reed
Sean Reed
Ben Kuhn
Ben Kuhn
@wavemm
Paul Zivich
Paul Zivich
University of North Carolina
Mike Williamson
Mike Williamson
Kapacity
AbdealiJK
AbdealiJK
Corridor Platforms
Deepyaman Datta
Deepyaman Datta
Junior Principal MLE @quantumblack
Andrew Fiore-Gartland
Andrew Fiore-Gartland
Fred Hutchinson Cancer Research Center
Alex Parij
Alex Parij
Autodesk
Daniel WIlson
Daniel WIlson
@seerai
Gabriel
Gabriel
Luis Moneda
Luis Moneda
@nubank
Arturo Moncada-Torres
Arturo Moncada-Torres
@IKNL
Kyle Stark
Kyle Stark
@GoodRx
Harsh Gadgil
Harsh Gadgil
Jona
Jona
Berlin Institute for Medical Systems Biology
JoseLlanes
JoseLlanes
Karthikeyan Singaravelan
Karthikeyan Singaravelan
Visa Inc.
Lilian Besson
Lilian Besson
École Normale Supérieure de Rennes (ENS Rennes)
Miguel Sancho Peña
Miguel Sancho Peña
@IBM
Steven Anton
Steven Anton
ID Analytics
Andreas Klintberg
Andreas Klintberg
GrowthJeff
GrowthJeff
Javad Noorbakhsh
Javad Noorbakhsh
@broadinstitute
Matthew Begun
Matthew Begun
Ravin Kumar
Ravin Kumar
Sean Hussey
Sean Hussey
Agero
Skipper Seabold
Skipper Seabold
HCA Healthcare
CamDavidsonPilon/lifelines: 0.26.0
Zenodo
2021
2021-05-27
https://github.com/CamDavidsonPilon/lifelines/tree/0.26.0
10.5281/zenodo.805993
0.26.0
Other (Open)
0.26.0 - 2021-05-26
New features
.BIC_ is now present on fitted models.
CoxPHFitter with spline baseline can accept pre-computed knot locations.
Left censoring fitting in KaplanMeierFitter is now "expected". That is, predict always predicts the survival function (as does every other model), confidence_interval_ is always the CI for the survival function (as does every other model), and so on. In summary: the API for estimates doesn't change depending on what your censoring your dataset is.
Bug fixes
Fixed an annoying bug where at_risk-table label's were not aligning properly when data spanned large ranges. See merging PR for details.
Fixed a bug in find_best_parametric_model where the wrong BIC value was being computed.
Fixed regression bug when using an array as a penalizer in Cox models.