Subsemble NotFittedError about mlens

[flennerhag]

Hi @cpedrinaci,

You've found a bug :)

The problem is that when we check if the model is fitted, we check that parameters haven't changed. We should check the parameters of SimplePartitioner, but because it doesn't have a get_params method, so when we the instance itself, which can lead to trouble.

You can get around this by simply implementing a get_params on the partitioner:

class SimplePartitioner():
    def __init__(self):
        pass

    def our_custom_function(self, X, y=None):
        """Split the data in half based on the sum of features"""
        # Labels should be numerical
        return 1 * (X.sum(axis=1) > X.sum(axis=1).mean())

    def get_params(self, deep=False):
        return {}

Hope this helps! Let me know otherwise.

[cpedrinaci]

That did the trick. Thanks!