Meaningful error message if sample splitting was not yet set

Calling
```
dml_plr_obj = DoubleMLPLR$new(make_plr_CCDDHNR2018(),
lrn("regr.ranger"), lrn("regr.ranger"),
draw_sample_splitting = FALSE)
dml_plr_obj$fit()
```
produces error message
```
Error in .__ResamplingCustom__instantiate(self = self, private = private, :
Assertion on 'train_sets' failed: Must be of type 'list', not 'NULL'.
```

More meaningful would be something in the lines of https://github.com/DoubleML/doubleml-for-py/blob/a574e0afcab0e7cce475925f1344399e75dd4a11/doubleml/double_ml.py#L238-L239.

Start by reproducing the example through DoubleMLPLR$new(..., draw_sample_splitting = FALSE) and $fit(). Trace where the missing sample splitting reaches the resampling validation, using the linked Python implementation as the intended behavior. Done means the example reports a meaningful sample-splitting error instead of the raw train_sets NULL assertion.

Written by the indexing model from the issue text.