| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2019-03-07 | 733 Bytes | |
| v0.11.0 source code.tar.gz | 2019-03-07 | 605.9 kB | |
| v0.11.0 source code.zip | 2019-03-07 | 622.9 kB | |
| Totals: 3 Items | 1.2 MB | 0 | |
0.11.0
- Move most models (all but Pareto) to autograd for automatic differentiation of their likelihood. This results in faster (at least 3x) and more successful convergence, plus allows for some really exciting extensions (coming soon).
GammaGammaFitter,BetaGeoFitter,ModifiedBetaGeoFitterandBetaGeoBetaBinomFitterhave three new attributes:confidence_interval_,variance_matrix_andstandard_errors_params_on fitted models is not longer an OrderedDict, but a Pandas SeriesGammaGammaFittercan accept aweightsargument now.customer_lifelime_valueinGammaGammanow accepts a frequency argument.- fixed a bug that was causing
ParetoNBDFitterto generate data incorrectly.