yusufuyanik1

Resolved with: https://github.com/pegasystems/pega-datascientist-tools/commit/bdc8422a4cbc12ef2e079935f84ce67d1c64c222

We created a function in Decision Analyzer to calculate area under the curve which represents entropy

[Updated](https://pegasystems.github.io/pega-datascientist-tools/Python/articles/ADMExplained.html) with the points you mentioned. - the adjusted propensity in the table is wrong, is all the same for all bins: You can't see this point from the article...

@StijnKas Yes, we aligned them

(pip show pdstools) is already in the article. Right above the Iine "If your pdstools version is below 3.1". - if we want them to run `pdstools.show_versions()` in the terminal...

I am not sure if this is the same issue but this looks very inconsistent when i access the results ```python df = pl.DataFrame({"index": [1,2,3,4,5]}) df = df.with_columns(progress = pl.col("index")...

I couldn't reproduce the error with a Datamart containing only AGB configurations. However the `plotPredictorPerformance`returns an empty chart because "pyPerformance" is not used in AGB configuration. I will change the...

`json_decode` was the problem, the default `infer_schema_length` is 100 and if there are no treatments (only pyName) in the first 100 rows, then it is not parsing other columns in...

**_"Sort first so any { is present in the first 100?"_** If there is a third property it may still be unseen, for example a dataframe like below the row...

infer_schema_lenght was set to None in this [commit](https://github.com/pegasystems/pega-datascientist-tools/commit/1cde6497be64587fbba5123023501b02896b130b#diff-7cac4e15cab78a4ad078fe4cea8553d5599ed430af3101b3e16497bfc78e9bd0R128) This operation is being applied to modelData, which is a moderately sized(in terms of row count). Also, we are already collecting this...