Zerihun

I am facing a similar issue when trying to install jupyterlab/toc

I get similar RuntimeWarnings when I use BetaGeomFitter.fit(), and when I check the result, it is a poor fit. The `bgf.summary` gives the coef statistics as NaN as show below....

Yes, I have tried different values for penalizer_coef from 0.0 to 0.1, and I get the same runtime warnings. ```python from lifetimes import BetaGeoFitter bgf = BetaGeoFitter(penalizer_coef=0.01) bgf.fit(df_rfm['frequency'], df_rfm['recency'], df_rfm['T'])...

> > Yes, I have tried different values for penalizer_coef from 0.0 to 0.1, and I get the same runtime warnings. > > You might need to go higher. I...

I think the problem here is the issue of very very small number division. I can see why the model would work when I increase the time from daily to...

> Hi @zerualem , did you find a solution? Or was resampling by week the best solution? For now, re-sampling is the only option for me. Read here also [...

> @zerualem: the code link provided to google colab does not work when clicked as it an href pointing elsewhere. @extrospective Here is the code ```python from lifetimes.plotting import *...

@bobbywlindsey thanks for the suggestion. After upgrading to SageMaker 2.97 and now instead of throwing an error, I get a warning. ```Python WARNING:root:instance_type should not be a pipeline variable ()....

I faced similar issue on the attached dataset depending on the train-test split random-state number. It works only when I use random_state=42 on my system. I tried it on [Google...