convoys
convoys copied to clipboard
Implementation of statistical models to analyze time lagged conversions
Steps to reproduce: - clone the repo - `python -m venv venv` and `source venv/bin/activate` - `pip install convoys==0.2.1` - `python examples/dob_violations.py` Stacktrace: File "examples/dob_violations.py", line 50, in run() File...
The commentary of the chart with both Weibull and Kaplan-Meier curves mistakenly reverses the solid/dashed pattern.
I am running into an numpy type error (see below) whenever I set value for the parameters `mcmc==True` or `ci==0.95` in any convoys model. This is consistent across data sources...
This is to be merged in maybe 3-6 months, to give people a chance to change how they use convoys.
Calling fit on `GeneralizedGamma` within a Jupyter Labs notebook results in a lot of whitespace in the output. I think this is because `sys.stdout.flush()` does not play well Labs. 
http://data.princeton.edu/pop509/ParametricSurvival.pdf I don't see an obvious pdf in that documentation though. Perhaps I need to re-read it though.
`numpy.int` was deprecated in `1.2.0` [[ref](https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations)] This type is being used in the [Gamma model ](https://github.com/better/convoys/blob/99e832d2170ba9670e5e16bb3f632ac9055291f3/convoys/multi.py#L25) Happy to raise a PR to change to `numpy.int_`
Add `colormap` argument to `plot_cohorts` so that line plots for each group can have an ordinal colour. For example: 