Stijn Kas

Caching

2

This PR adds caching of tables, currently implemented in the ADMDatamart class. Simply call `save_data(path)` which will save the model data and predictor data as .feather files to the path...

Add admVarImp to Python tools

1

The R functionality supports calculating relative feature importance next to just the univariate performance supplied by the binning. Porting that over to Python should be quite simple, but may be...

I had trouble installing on a new device with a new R instance, I got the following error message: ``` R > library(devtools) Loading required package: usethis > install_github("pegasystems/cdh-datascientist-tools/r", build_vignettes=TRUE)...

Known bug in Python version

With the current version of Python CDH tools, there is a top-n argument which filters out the n top performing predictors. This works fine, but when you add facets to...

Iterable `groupby_rolling` and `groupby_dynamic`

1

### Problem description `groupby` has an `__iter__` method defined, making it quite easy to iteratively work through the groups for debugging. Although for production of course you'd just use `.agg`,...

### Polars version checks - [X] I have checked that this issue has not already been reported. - [X] I have confirmed this bug exists on the [latest version](https://pypi.org/project/polars/) of...

Incorrect column names when applying `json.loads` with different keys

1

### Polars version checks - [X] I have checked that this issue has not already been reported. - [X] I have confirmed this bug exists on the [latest version](https://pypi.org/project/polars/) of...

### pdstools version checks - [X] I have checked that this issue has not already been reported. - [X] I have confirmed this bug exists on the [latest version](https://pypi.org/project/pdstools/) of...

### Is your feature request related to a problem? For the ADMDatamart class, we allow users to apply filters at the plot level, which is a lot more flexible than...