Error using MultilabelStratifiedKFold

[robertogarces]

Hi Trent! First, thanks for this repository, it have helped me a lot.

I have a question. I use the MultilabelStratifiedKFold for a machine learning model, but since the last week it have been giving me an error. I haven't changed anything on it, so I don't know what can be happening.

The error I'm having is in this line of code:

mskf = MultilabelStratifiedKFold(n_splits=3, shuffle=True, random_state=42)

And the error that it throws is it:

Input In [13], in <cell line: 6>()
      3 oof_preds["fold_idx"] = -1
      4 oof_preds["oof_pred"] = -1
----> 6 mskf = MultilabelStratifiedKFold(n_splits=3, shuffle=True, random_state=42)
      7 mskf_split = mskf.split(dataset, dataset[["rvm_tipo_enc","rvm_marca_enc","rvm_antiguedad","converted"]])
      9 for fold,(train_idx,valid_idx) in enumerate(mskf_split):

File ~\Anaconda3\envs\JARVIS\lib\site-packages\iterstrat\ml_stratifiers.py:157, in MultilabelStratifiedKFold.__init__(self, n_splits, shuffle, random_state)
    156 def __init__(self, n_splits=3, shuffle=False, random_state=None):
--> 157     super(MultilabelStratifiedKFold, self).__init__(n_splits, shuffle, random_state)

TypeError: __init__() takes 2 positional arguments but 4 were given```



What can be happening on here? Thanks a lot!

[trent-b]

Hi @robertogarces, please ensure you are using the latest version (0.1.7). See this Closed issue that began with the 1.0.0 release of scikit-learn: #18. Please let me know if upgrading resolves the issue.

[robertogarces]

Hi @trent-b. I was using the 0.1.6 version, and upgrading it solved the problem. Thank you so much for your quick answer. Greetings!

[trent-b]

Glad upgrading worked!

[spoorgholi74]

Hi, I get the same issue in version 1.2 of scikit-learn and 0.1.7 on this library