Issue creating custom configuration for multi output regression

[robertritz]

Could you provide a bit more help with the custom configuration dictionary? I'm attempting to set up a simple custom configuration using the SelectFromModel example you gave. Here is my current config:

tpot_config = {
    'sklearn.multioutput.MultiOutputRegressor': {
        'estimator': {
            'sklearn.ensemble.ExtraTreesRegressor': {
                'n_estimators': [100],
                'max_features': np.arange(0.05, 1.01, 0.05)
            }
        }
    }
}

And here is my code to run TPOT:

pipeline_optimizer = TPOTRegressor(generations=5, population_size=20, max_time_mins=480, n_jobs=-1, verbosity=2, random_state=12345, config_dict=tpot_config)
pipeline_optimizer.fit(X_train, y_train)
print(pipeline_optimizer.score(X_test, y_test))
pipeline_optimizer.export('tpot_exported_pipeline.py')

I receive an error:
ValueError: Error: Input data is not in a valid format. Please confirm that the input data is scikit-learn compatible. For example, the features must be a 2-D array and target labels must be a 1-D array.

Is it necessary to specify the parameters to search for each algorithm? Before reading the documentation and your example I naively just passed through a list of algorithms like so:

tpot_config = {
    'sklearn.multioutput.MultiOutputRegressor': {
        'estimator': ['ExtraTreesRegressor']
      }
}

There are sklearn algorithms that are inherently multioutput, but with MultiOutputRegressor I get many more options. Thanks!

[robertritz]

Wow I completely misinterpreted the error message. The issue is not regarding my config at all, but the input data. I'm passing through a dataframe instead of an array. This is what happens when you don't get enough sleep.

[aayux]

@robertritz how does passing an array resolve this error?

The error is raised in _check_dataset() when it catches an AssertionError or ValueError from sklearn's check_X_y() function (see linked).

For 2-dimensional y, the function would require an additional argument multi_output=True to work as expected. Or am I missing something here?

Here's a partial trace:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.5/dist-packages/tpot/base.py in _check_dataset(self, features, target, sample_weight)
   1069             if target is not None:
-> 1070                 X, y = check_X_y(features, target, accept_sparse=True, dtype=np.float64)
   1071                 return X, y

/usr/local/lib/python3.5/dist-packages/sklearn/utils/validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    751     else:
--> 752         y = column_or_1d(y, warn=True)
    753         _assert_all_finite(y)

/usr/local/lib/python3.5/dist-packages/sklearn/utils/validation.py in column_or_1d(y, warn)
    787 
--> 788     raise ValueError("bad input shape {0}".format(shape))
    789