Skip to content
Branch: master
Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
Cox residuals.ipynb
Custom Regression Models.ipynb
Customer Churn.ipynb
Mixture of Exponentials and Binning.ipynb
Modelling time-lagged conversion rates.ipynb
Piecewise Exponential Models and Creating Custom Models.ipynb
Proportional hazard assumption.ipynb
SaaS churn and piecewise regression models.ipynb
US Presidential Cabinet survival.ipynb


In this folder are some examples of lifelines usage, some with and some without comments and context. You can see some common patterns using lifelines and survival analysis.

  • Cox residuals: A notebook displaying how to create residuals for the Cox model.
  • Custom Regression Models: A notebook with examples on how to create a custom parametric regression model.
  • Customer Churn: A notebook analyzing customer subscription churn from a TelCom.
  • Mixture of Exponentials and Binning: A notebook on dealing with binning (like from an instrument or rounding) and a mixture of distributions.
  • Modelling time-lagged conversion rates: A notebook on custom univariate models that have a fraction of subjects that never experience the event of interest. Also known as cure models.
  • Piecewise Exponential Models and Creating Custom Models: A notebook demonstrating how to create custom univariate models. Lots of examples.
  • Proportional hazard assumption: A notebook for diagnosing and fixing violations of the proportional hazard assumption.
  • SaaS churn and piecewise regression models: A notebook that demonstrates how to use the PiecewiseExponentialRegressionFitter for understanding SaaS customer churn.
  • US Presidential Cabinet survival: Analyzing tenure in presidential cabinets over the different generations.
  • aalen_and_cook_simulation: A demonstration of how the Cox model fails when missing independent risk factors.
  • cure_model: A custom regression model of a cure model.
  • haft_model: An implementation of a heterogeneous-AFT model. Subjects' variance can vary with their factors.
  • left_censoring_experiments: Comparing some parametric univariate models on left-censoring data.

Other examples

You can’t perform that action at this time.