Sebastian Pölsterl

Correct, stock icons are deprecated, but they are usually not displayed (as you can see in the screenshots). The advantage is that their text is automatically translated into the user's...

It is correct that the expected survival time can be estimated with the integral under the survival function. However, this only leads to a reasonable estimate if the last observed...

If you can contribute with a PR, that would be even better.

@PragyanSubedi I did not have time to look into it, I'm afraid.

By definition, it would be the derivative of the cumulative hazard function. In general, directly estimating the hazard function is tricky. I'm curious, what would you like to use the...

@tomikrogerus I'm currently not working on it. PR #196 is inactive too.

The difference is that the `coef_` attribute contains the coefficients for multiple alpha values (each column corresponds to one alpha). `SelectFromModel` excepts a single set of coefficients, thus the exception....

The `score` method just calls `predict` without explicitly specifying an alpha value, in which case the last column of `coef_` is used (corresponding to the smallest alpha in the path)....

Currently, `d_0` is essentially fixed at 1 (see [this part](https://github.com/sebp/scikit-survival/blob/70f019db52c9cb8ebd5d911de64d7cb27a7b39d2/sksurv/tree/_criterion.pyx#L291) of the code). I think it would make sense to make it configurable by adding it as a hyper-parameter to...

That's a very good point. In this case, it seems to be more complicated, because in sklearn's code the criterion does not determine whether a split is valid or not,...