Bug Report

These tests were run on s390x. s390x is big-endian architecture.

Failure log for helper_test.py

________________________________________________ TestHelperTensorFunctions.test_make_tensor ________________________________________________

self = <helper_test.TestHelperTensorFunctions testMethod=test_make_tensor>

    def test_make_tensor(self):  # type: () -> None
    

For example, if there is a relationship transaction.session_id -> sessions.id and we are calculating a feature transactions: sessions.SUM(transactions.value) any rows for which there is no corresponding session should be given the default value of 0 instead of NaN.

Of course this should not normally occur, but when it does it seems more reasonable to use the default_value.

`DirectF

with the Power Transformer.

I see the code

device = ‘cuda’ if torch.cuda.is_available() else ‘cpu’

repeated often in user code. Maybe we should introduce device='auto' exactly for this case?

Yes

How do i resume training for text classification?

for reproducibility, all classifiers should be seeded by random_state. In our experiments, the random_state is set to the resampleID. This is not correctly set in all the considered classifiers. The current list to check is

all_classifiers = [
"BOSSEnsemble", "TemporalDictionaryEnsemble", "MUSE", "WEASEL",
"ProximityForest", "ElasticEnsemble", "KNeighborsTimeSeriesClassifier",
#"Shap

https://igel.readthedocs.io/en/latest/_sources/readme.rst.txt includes a link to the assets/igel-help.gif, but that path is broken on readthedocs.

readme.rst is included as ../readme.rst in the sphinx build.
The gifs are in asses/igel-help.gif

The sphinx build needs to point to the asset directory, absolutely:

.. image:: /assets/igel-help.gif

I haven't made a patch, because I haven't

I think it could be useful, when one wants to plot only e.g. class 1, to have an option to produce consistent plots for both plot_cumulative_gain and plot_roc

At the moment, instead, only plot_roc supports such option.

Thanks a lot