search

flennerhag / mlens

ML-Ensemble – high performance ensemble learning
http://ml-ensemble.com
MIT License
843 stars 108 forks source link

Error when using preprocessing per case in model selection #145

Open bastian-f opened 1 year ago

bastian-f commented 1 year ago

Hello,

I followed this notebook to create an ensemble.

First I tune the base learners with a preprocessing pipeline:

preprocessing = {'sc': [StandardScaler()]}
# Fit the base learners
evl.fit(
    x_train, y_train,
    estimators=base_learners,
    param_dicts=param_dicts,
    preprocessing=preprocessing,
    n_iter=1
)

In the notebook, the model selection is done like this:

in_layer_proba = SuperLearner(model_selection=True).add(base_learners,
                                                        proba=True)
in_layer_class = SuperLearner(model_selection=True).add(base_learners,
                                                        proba=False)

This works fine, but I think the preprocessing part is missing here (the standard scaler), is it not? So I did the following:

in_layer_proba = SuperLearner(model_selection=True).add(
                estimators_per_case, preprocessing_cases, proba=True
)
in_layer_class = SuperLearner(model_selection=True).add(
        estimators_per_case, preprocessing_cases, proba=False
)
preprocess = {'proba': [('layer-1', in_layer_proba)],
                       'class': [('layer-1', in_layer_class)]}
evl.fit(
    x_train, y_train,
    meta_learners,
    param_dicts=param_dicts,
    preprocessing=preprocess,
    n_iter=1
)

And I get the following error. I am not sure if I am doing something wrong or if it is a bug?

bastian-f commented 1 year ago

This is the error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr, x, y)
    232     try:
--> 233         x = tr.transform(x)
    234     except TypeError:

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self, X, y, **kwargs)
    549                 raise TypeError(
--> 550                     "In model selection mode, y is a required argument.")
    551 

TypeError: In model selection mode, y is a required argument.

During handling of the above exception, another exception occurred:

TransportableException                    Traceback (most recent call last)
~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self)
    702                 if getattr(self._backend, 'supports_timeout', False):
--> 703                     self._output.extend(job.get(timeout=self.timeout))
    704                 else:

~/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in get(self, timeout)
    656         else:
--> 657             raise self._value
    658 

~/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    120         try:
--> 121             result = (True, func(*args, **kwds))
    122         except Exception as e:

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self, *args, **kwargs)
    358             text = format_exc(e_type, e_value, e_tb, context=10, tb_offset=1)
--> 359             raise TransportableException(text, e_type)
    360 

TransportableException: TransportableException
___________________________________________________________________________
ValueError                                         Tue Oct 11 15:54:29 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.SubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.SubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.SubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.SubLearner object>
        self.job = 'transform'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in transform(self=<mlens.parallel.learner.SubLearner object>, path=None)
    162             f = "stdout" if self.verbose < 10 - 3 else "stderr"
    163             print_time(t0, msg, file=f)
    164 
    165     def transform(self, path=None):
    166         """Predict with sublearner"""
--> 167         return self.predict(path)
        self.predict = <bound method SubLearner.predict of <mlens.parallel.learner.SubLearner object>>
        path = None
    168 
    169     def _fit(self, transformers):
    170         """Sub-routine to fit sub-learner"""
    171         xtemp, ytemp = slice_array(self.in_array, self.targets, self.in_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in predict(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    152     def predict(self, path=None):
    153         """Predict with sublearner"""
    154         if path is None:
    155             path = self.path
    156         t0 = time()
--> 157         transformers = self._load_preprocess(path)
        transformers = undefined
        self._load_preprocess = <bound method SubLearner._load_preprocess of <mlens.parallel.learner.SubLearner object>>
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
    158 
    159         self._predict(transformers, False)
    160         if self.verbose:
    161             msg = "{:<30} {}".format(self.name_index, "done")

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _load_preprocess(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    180         self.fit_time_ = time() - t0
    181 
    182     def _load_preprocess(self, path):
    183         """Load preprocessing pipeline"""
    184         if self.preprocess is not None:
--> 185             obj = load(path, self.preprocess_index, self.raise_on_exception)
        obj = undefined
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
        self.preprocess_index = 'sc.0.2'
        self.raise_on_exception = True
    186             return obj.estimator
    187         return
    188 
    189     def _predict(self, transformers, score_preds):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in load(path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)], name='sc.0.2', raise_on_exception=True)
     24         obj = _load(f, raise_on_exception)
     25     elif isinstance(path, list):
     26         obj = [tup[1] for tup in path if tup[0] == name]
     27         if not obj:
     28             raise ValueError(
---> 29                 "No preprocessing pipeline in cache. Auxiliary Transformer "
     30                 "have not cached pipelines, or cached to another sub-cache.")
     31         elif not len(obj) == 1:
     32             raise ValueError(
     33                 "Could not load unique preprocessing pipeline. "

ValueError: No preprocessing pipeline in cache. Auxiliary Transformer have not cached pipelines, or cached to another sub-cache.
___________________________________________________________________________

During handling of the above exception, another exception occurred:

JoblibValueError                          Traceback (most recent call last)
~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self, *args, **kwargs)
    349         try:
--> 350             return self.func(*args, **kwargs)
    351         except KeyboardInterrupt:

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self)
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    136 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0)
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    136 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self)
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
    125 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self, path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
    338 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self, transformers, score_preds)
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
    357 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self, transformers, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
    367 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self, X, y)
    133         """
--> 134         return self._run(False, True, X, y)
    135 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self, fit, process, X, y)
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
     70 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr, x, y)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
    236 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self, X, y, **kwargs)
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
    561             if X.shape[0] != y.shape[0]:

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self, X, **kwargs)
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
    238 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self, X, job, **kwargs)
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
    267 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self, caller, job, X, y, path, return_preds, warm_start, split, **kwargs)
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
    674 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self, caller, out, **kwargs)
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
    719 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self, task, parallel, **kwargs)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
    740 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self, args, parallel)
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
    153                  for sublearner in learner(args, 'main'))

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self, iterable)
    792                 self._iterating = False
--> 793             self.retrieve()
    794             # Make sure that we get a last message telling us we are done

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self)
    743 
--> 744                     raise exception
    745 

JoblibValueError: JoblibValueError
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    885         # indeed has already been destroyed, so that exceptions in
    886         # _bootstrap_inner() during normal business hours are properly
    887         # reported.  Also, we only suppress them for daemonic threads;
    888         # if a non-daemonic encounters this, something else is wrong.
    889         try:
--> 890             self._bootstrap_inner()
        self._bootstrap_inner = <bound method Thread._bootstrap_inner of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    891         except:
    892             if self._daemonic and _sys is None:
    893                 return
    894             raise

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap_inner(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    921                 _sys.settrace(_trace_hook)
    922             if _profile_hook:
    923                 _sys.setprofile(_profile_hook)
    924 
    925             try:
--> 926                 self.run()
        self.run = <bound method Thread.run of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    927             except SystemExit:
    928                 pass
    929             except:
    930                 # If sys.stderr is no more (most likely from interpreter

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in run(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    865         from the args and kwargs arguments, respectively.
    866 
    867         """
    868         try:
    869             if self._target:
--> 870                 self._target(*self._args, **self._kwargs)
        self._target = <function worker>
        self._args = (<_queue.SimpleQueue object>, <_queue.SimpleQueue object>, None, (), None, False)
        self._kwargs = {}
    871         finally:
    872             # Avoid a refcycle if the thread is running a function with
    873             # an argument that has a member that points to the thread.
    874             del self._target, self._args, self._kwargs

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in worker(inqueue=<_queue.SimpleQueue object>, outqueue=<_queue.SimpleQueue object>, initializer=None, initargs=(), maxtasks=None, wrap_exception=False)
    116             util.debug('worker got sentinel -- exiting')
    117             break
    118 
    119         job, i, func, args, kwds = task
    120         try:
--> 121             result = (True, func(*args, **kwds))
        result = None
        func = <mlens.externals.joblib._parallel_backends.SafeFunction object>
        args = ()
        kwds = {}
    122         except Exception as e:
    123             if wrap_exception and func is not _helper_reraises_exception:
    124                 e = ExceptionWithTraceback(e, e.__traceback__)
    125             result = (False, e)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self=<mlens.externals.joblib._parallel_backends.SafeFunction object>, *args=(), **kwargs={})
    345     def __init__(self, func):
    346         self.func = func
    347 
    348     def __call__(self, *args, **kwargs):
    349         try:
--> 350             return self.func(*args, **kwargs)
        self.func = <mlens.externals.joblib.parallel.BatchedCalls object>
        args = ()
        kwargs = {}
    351         except KeyboardInterrupt:
    352             # We capture the KeyboardInterrupt and reraise it as
    353             # something different, as multiprocessing does not
    354             # interrupt processing for a KeyboardInterrupt

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.EvalSubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.EvalSubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.EvalSubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.EvalSubLearner object>
        self.job = 'fit'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self=<mlens.parallel.learner.EvalSubLearner object>, path=[('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>)])
    332         if self.scorer is None:
    333             raise ValueError("Cannot generate CV-scores without a scorer")
    334         t0 = time()
    335         transformers = self._load_preprocess(path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
        self._predict = <bound method EvalSubLearner._predict of <mlens.parallel.learner.EvalSubLearner object>>
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
    338 
    339         o = IndexedEstimator(estimator=self.estimator,
    340                              name=self.name_index,
    341                              index=self.index,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), score_preds=None)
    351 
    352     def _predict(self, transformers, score_preds=None):
    353         """Sub-routine to with sublearner"""
    354         # Train set
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
        self.in_index = ((0, 1899),)
    357 
    358         # Validation set
    359         self.test_score_, self.test_pred_time_ = self._score_preds(
    360             transformers, self.out_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), index=((0, 1899),))
    361 
    362     def _score_preds(self, transformers, index):
    363         # Train scores
    364         xtemp, ytemp = slice_array(self.in_array, self.targets, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
        xtemp = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        ytemp = array([2, 2, 1, ..., 2, 0, 3])
        transformers.transform = <bound method Pipeline.transform of Pipeline(nam...se,
       verbose=False))],
     return_y=True)>
    367 
    368         t0 = time()
    369 
    370         if self.error_score is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    129             Preprocessed input data
    130 
    131         y : array-like of shape [n_samples, ], optional
    132             Original or preprocessed targets, depending on the transformers.
    133         """
--> 134         return self._run(False, True, X, y)
        self._run = <bound method Pipeline._run of Pipeline(name='pi...se,
       verbose=False))],
     return_y=True)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
    135 
    136     def fit_transform(self, X, y=None):
    137         """Fit and transform pipeline.
    138 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), fit=False, process=True, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
     64         for tr_name, tr in self._pipeline:
     65             if fit:
     66                 tr.fit(X, y)
     67 
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr = SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False)
     70 
     71         if process:
     72             if self.return_y:
     73                 return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), x=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    230 def transform(tr, x, y):
    231     """Try transforming with X and y. Else, transform with only X."""
    232     try:
    233         x = tr.transform(x)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
        x = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr.transform = <bound method BaseEnsemble.transform of SuperLea...corer=None, shuffle=False,
       verbose=False)>
    236 
    237     return x, y
    238 
    239 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]), **kwargs={})
    555                 return self.predict(X, **kwargs), y
    556 
    557             # Asked to reproduce predictions during fit, here we need to
    558             # account for that in model selection mode,
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        self._backend.transform = <bound method Sequential.transform of Sequential...n=True)])],
   verbose=0)],
      verbose=False)>
        kwargs = {}
    561             if X.shape[0] != y.shape[0]:
    562                 r = y.shape[0] - X.shape[0]
    563                 y = y[r:]
    564             return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), **kwargs={})
    232         if not self.__fitted__:
    233             NotFittedError("Instance not fitted.")
    234 
    235         f, t0 = print_job(self, "Transforming")
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
        out = undefined
        self._predict = <bound method Sequential._predict of Sequential(...n=True)])],
   verbose=0)],
      verbose=False)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        kwargs = {}
    238 
    239         if self.verbose:
    240             print_time(t0, "{:<35}".format("Transform complete"),
    241                        file=f, flush=True)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), job='transform', **kwargs={})
    261             data.
    262         """
    263         r = kwargs.pop('return_preds', True)
    264         with ParallelProcessing(self.backend, self.n_jobs,
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
        out = undefined
        manager.stack = <bound method ParallelProcessing.stack of <mlens.parallel.backend.ParallelProcessing object>>
        self = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        job = 'transform'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        r = True
        kwargs = {}
    267 
    268         if not isinstance(out, list):
    269             out = [out]
    270         out = [p.squeeze() for p in out]

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), job='transform', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=None, path=None, return_preds=True, warm_start=False, split=True, **kwargs={})
    668             Prediction array(s).
    669         """
    670         out = self.initialize(
    671             job=job, X=X, y=y, path=path, warm_start=warm_start,
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
        self.process = <bound method ParallelProcessing.process of <mlens.parallel.backend.ParallelProcessing object>>
        caller = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        out = {}
        kwargs = {}
    674 
    675     def process(self, caller, out, **kwargs):
    676         """Process job.
    677 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), out=None, **kwargs={})
    713                       backend=self.backend) as parallel:
    714 
    715             for task in caller:
    716                 self.job.clear()
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
        self._partial_process = <bound method ParallelProcessing._partial_proces...lens.parallel.backend.ParallelProcessing object>>
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        parallel = Parallel(n_jobs=-1)
        kwargs = {}
    719 
    720                 if task.name in return_names:
    721                     out.append(self.get_preds(dtype=_dtype(task)))
    722 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self=<mlens.parallel.backend.ParallelProcessing object>, task=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), parallel=Parallel(n_jobs=-1), **kwargs={})
    734         task.setup(self.job.predict_in, self.job.targets, self.job.job)
    735 
    736         if not task.__no_output__:
    737             self._gen_prediction_array(task, self.job.job, self.__threading__)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        self.job.args = <bound method Job.args of <mlens.parallel.backend.Job object>>
        kwargs = {}
        parallel = Parallel(n_jobs=-1)
    740 
    741         if not task.__no_output__ and getattr(task, 'n_feature_prop', 0):
    742             self._propagate_features(task)
    743 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}, 'dir': [('sc.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('sc.0.2', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'transform', 'main': {'P': array([[2.60052562e-01, 1.77754706e-03, 5.693393... 1.20693236e-04, 9.98786032e-01]], dtype=float32), 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}}, parallel=Parallel(n_jobs=-1))
    147         if self.verbose >= 2:
    148             safe_print(msg.format('Learners ...'), file=f, end=e2)
    149             t1 = time()
    150 
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
        self.learners = [Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None)]
    153                  for sublearner in learner(args, 'main'))
    154 
    155         if self.verbose >= 2:
    156             print_time(t1, 'done', file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object Layer.__call__.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

---------------------------------------------------------------------------
Sub-process traceback:
---------------------------------------------------------------------------
ValueError                                         Tue Oct 11 15:54:29 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.SubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.SubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.SubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.SubLearner object>
        self.job = 'transform'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in transform(self=<mlens.parallel.learner.SubLearner object>, path=None)
    162             f = "stdout" if self.verbose < 10 - 3 else "stderr"
    163             print_time(t0, msg, file=f)
    164 
    165     def transform(self, path=None):
    166         """Predict with sublearner"""
--> 167         return self.predict(path)
        self.predict = <bound method SubLearner.predict of <mlens.parallel.learner.SubLearner object>>
        path = None
    168 
    169     def _fit(self, transformers):
    170         """Sub-routine to fit sub-learner"""
    171         xtemp, ytemp = slice_array(self.in_array, self.targets, self.in_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in predict(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    152     def predict(self, path=None):
    153         """Predict with sublearner"""
    154         if path is None:
    155             path = self.path
    156         t0 = time()
--> 157         transformers = self._load_preprocess(path)
        transformers = undefined
        self._load_preprocess = <bound method SubLearner._load_preprocess of <mlens.parallel.learner.SubLearner object>>
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
    158 
    159         self._predict(transformers, False)
    160         if self.verbose:
    161             msg = "{:<30} {}".format(self.name_index, "done")

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _load_preprocess(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    180         self.fit_time_ = time() - t0
    181 
    182     def _load_preprocess(self, path):
    183         """Load preprocessing pipeline"""
    184         if self.preprocess is not None:
--> 185             obj = load(path, self.preprocess_index, self.raise_on_exception)
        obj = undefined
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
        self.preprocess_index = 'sc.0.2'
        self.raise_on_exception = True
    186             return obj.estimator
    187         return
    188 
    189     def _predict(self, transformers, score_preds):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in load(path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)], name='sc.0.2', raise_on_exception=True)
     24         obj = _load(f, raise_on_exception)
     25     elif isinstance(path, list):
     26         obj = [tup[1] for tup in path if tup[0] == name]
     27         if not obj:
     28             raise ValueError(
---> 29                 "No preprocessing pipeline in cache. Auxiliary Transformer "
     30                 "have not cached pipelines, or cached to another sub-cache.")
     31         elif not len(obj) == 1:
     32             raise ValueError(
     33                 "Could not load unique preprocessing pipeline. "

ValueError: No preprocessing pipeline in cache. Auxiliary Transformer have not cached pipelines, or cached to another sub-cache.
___________________________________________________________________________

During handling of the above exception, another exception occurred:

TransportableException                    Traceback (most recent call last)
~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self)
    702                 if getattr(self._backend, 'supports_timeout', False):
--> 703                     self._output.extend(job.get(timeout=self.timeout))
    704                 else:

~/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in get(self, timeout)
    656         else:
--> 657             raise self._value
    658 

~/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    120         try:
--> 121             result = (True, func(*args, **kwds))
    122         except Exception as e:

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self, *args, **kwargs)
    358             text = format_exc(e_type, e_value, e_tb, context=10, tb_offset=1)
--> 359             raise TransportableException(text, e_type)
    360 

TransportableException: TransportableException
___________________________________________________________________________
JoblibValueError                                   Tue Oct 11 15:54:32 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.EvalSubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.EvalSubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.EvalSubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.EvalSubLearner object>
        self.job = 'fit'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self=<mlens.parallel.learner.EvalSubLearner object>, path=[('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>)])
    332         if self.scorer is None:
    333             raise ValueError("Cannot generate CV-scores without a scorer")
    334         t0 = time()
    335         transformers = self._load_preprocess(path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
        self._predict = <bound method EvalSubLearner._predict of <mlens.parallel.learner.EvalSubLearner object>>
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
    338 
    339         o = IndexedEstimator(estimator=self.estimator,
    340                              name=self.name_index,
    341                              index=self.index,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), score_preds=None)
    351 
    352     def _predict(self, transformers, score_preds=None):
    353         """Sub-routine to with sublearner"""
    354         # Train set
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
        self.in_index = ((0, 1899),)
    357 
    358         # Validation set
    359         self.test_score_, self.test_pred_time_ = self._score_preds(
    360             transformers, self.out_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), index=((0, 1899),))
    361 
    362     def _score_preds(self, transformers, index):
    363         # Train scores
    364         xtemp, ytemp = slice_array(self.in_array, self.targets, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
        xtemp = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        ytemp = array([2, 2, 1, ..., 2, 0, 3])
        transformers.transform = <bound method Pipeline.transform of Pipeline(nam...se,
       verbose=False))],
     return_y=True)>
    367 
    368         t0 = time()
    369 
    370         if self.error_score is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    129             Preprocessed input data
    130 
    131         y : array-like of shape [n_samples, ], optional
    132             Original or preprocessed targets, depending on the transformers.
    133         """
--> 134         return self._run(False, True, X, y)
        self._run = <bound method Pipeline._run of Pipeline(name='pi...se,
       verbose=False))],
     return_y=True)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
    135 
    136     def fit_transform(self, X, y=None):
    137         """Fit and transform pipeline.
    138 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), fit=False, process=True, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
     64         for tr_name, tr in self._pipeline:
     65             if fit:
     66                 tr.fit(X, y)
     67 
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr = SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False)
     70 
     71         if process:
     72             if self.return_y:
     73                 return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), x=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    230 def transform(tr, x, y):
    231     """Try transforming with X and y. Else, transform with only X."""
    232     try:
    233         x = tr.transform(x)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
        x = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr.transform = <bound method BaseEnsemble.transform of SuperLea...corer=None, shuffle=False,
       verbose=False)>
    236 
    237     return x, y
    238 
    239 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]), **kwargs={})
    555                 return self.predict(X, **kwargs), y
    556 
    557             # Asked to reproduce predictions during fit, here we need to
    558             # account for that in model selection mode,
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        self._backend.transform = <bound method Sequential.transform of Sequential...n=True)])],
   verbose=0)],
      verbose=False)>
        kwargs = {}
    561             if X.shape[0] != y.shape[0]:
    562                 r = y.shape[0] - X.shape[0]
    563                 y = y[r:]
    564             return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), **kwargs={})
    232         if not self.__fitted__:
    233             NotFittedError("Instance not fitted.")
    234 
    235         f, t0 = print_job(self, "Transforming")
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
        out = undefined
        self._predict = <bound method Sequential._predict of Sequential(...n=True)])],
   verbose=0)],
      verbose=False)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        kwargs = {}
    238 
    239         if self.verbose:
    240             print_time(t0, "{:<35}".format("Transform complete"),
    241                        file=f, flush=True)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), job='transform', **kwargs={})
    261             data.
    262         """
    263         r = kwargs.pop('return_preds', True)
    264         with ParallelProcessing(self.backend, self.n_jobs,
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
        out = undefined
        manager.stack = <bound method ParallelProcessing.stack of <mlens.parallel.backend.ParallelProcessing object>>
        self = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        job = 'transform'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        r = True
        kwargs = {}
    267 
    268         if not isinstance(out, list):
    269             out = [out]
    270         out = [p.squeeze() for p in out]

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), job='transform', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=None, path=None, return_preds=True, warm_start=False, split=True, **kwargs={})
    668             Prediction array(s).
    669         """
    670         out = self.initialize(
    671             job=job, X=X, y=y, path=path, warm_start=warm_start,
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
        self.process = <bound method ParallelProcessing.process of <mlens.parallel.backend.ParallelProcessing object>>
        caller = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        out = {}
        kwargs = {}
    674 
    675     def process(self, caller, out, **kwargs):
    676         """Process job.
    677 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), out=None, **kwargs={})
    713                       backend=self.backend) as parallel:
    714 
    715             for task in caller:
    716                 self.job.clear()
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
        self._partial_process = <bound method ParallelProcessing._partial_proces...lens.parallel.backend.ParallelProcessing object>>
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        parallel = Parallel(n_jobs=-1)
        kwargs = {}
    719 
    720                 if task.name in return_names:
    721                     out.append(self.get_preds(dtype=_dtype(task)))
    722 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self=<mlens.parallel.backend.ParallelProcessing object>, task=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), parallel=Parallel(n_jobs=-1), **kwargs={})
    734         task.setup(self.job.predict_in, self.job.targets, self.job.job)
    735 
    736         if not task.__no_output__:
    737             self._gen_prediction_array(task, self.job.job, self.__threading__)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        self.job.args = undefined
        kwargs = {}
        parallel = Parallel(n_jobs=-1)
    740 
    741         if not task.__no_output__ and getattr(task, 'n_feature_prop', 0):
    742             self._propagate_features(task)
    743 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}, 'dir': [('sc.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('sc.0.2', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'transform', 'main': {'P': array([[2.60052562e-01, 1.77754706e-03, 5.693393... 1.20693236e-04, 9.98786032e-01]], dtype=float32), 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}}, parallel=Parallel(n_jobs=-1))
    147         if self.verbose >= 2:
    148             safe_print(msg.format('Learners ...'), file=f, end=e2)
    149             t1 = time()
    150 
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
        self.learners = [Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None)]
    153                  for sublearner in learner(args, 'main'))
    154 
    155         if self.verbose >= 2:
    156             print_time(t1, 'done', file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object Layer.__call__.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self=Parallel(n_jobs=-1))
    739 %s""" % (this_report, exception.message)
    740                     # Convert this to a JoblibException
    741                     exception_type = _mk_exception(exception.etype)[0]
    742                     exception = exception_type(report)
    743 
--> 744                     raise exception
        exception = undefined
    745 
    746     def __call__(self, iterable):
    747         if self._jobs:
    748             raise ValueError('This Parallel instance is already running')

JoblibValueError: JoblibValueError
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    885         # indeed has already been destroyed, so that exceptions in
    886         # _bootstrap_inner() during normal business hours are properly
    887         # reported.  Also, we only suppress them for daemonic threads;
    888         # if a non-daemonic encounters this, something else is wrong.
    889         try:
--> 890             self._bootstrap_inner()
        self._bootstrap_inner = <bound method Thread._bootstrap_inner of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    891         except:
    892             if self._daemonic and _sys is None:
    893                 return
    894             raise

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap_inner(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    921                 _sys.settrace(_trace_hook)
    922             if _profile_hook:
    923                 _sys.setprofile(_profile_hook)
    924 
    925             try:
--> 926                 self.run()
        self.run = <bound method Thread.run of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    927             except SystemExit:
    928                 pass
    929             except:
    930                 # If sys.stderr is no more (most likely from interpreter

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in run(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    865         from the args and kwargs arguments, respectively.
    866 
    867         """
    868         try:
    869             if self._target:
--> 870                 self._target(*self._args, **self._kwargs)
        self._target = <function worker>
        self._args = (<_queue.SimpleQueue object>, <_queue.SimpleQueue object>, None, (), None, False)
        self._kwargs = {}
    871         finally:
    872             # Avoid a refcycle if the thread is running a function with
    873             # an argument that has a member that points to the thread.
    874             del self._target, self._args, self._kwargs

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in worker(inqueue=<_queue.SimpleQueue object>, outqueue=<_queue.SimpleQueue object>, initializer=None, initargs=(), maxtasks=None, wrap_exception=False)
    116             util.debug('worker got sentinel -- exiting')
    117             break
    118 
    119         job, i, func, args, kwds = task
    120         try:
--> 121             result = (True, func(*args, **kwds))
        result = None
        func = <mlens.externals.joblib._parallel_backends.SafeFunction object>
        args = ()
        kwds = {}
    122         except Exception as e:
    123             if wrap_exception and func is not _helper_reraises_exception:
    124                 e = ExceptionWithTraceback(e, e.__traceback__)
    125             result = (False, e)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self=<mlens.externals.joblib._parallel_backends.SafeFunction object>, *args=(), **kwargs={})
    345     def __init__(self, func):
    346         self.func = func
    347 
    348     def __call__(self, *args, **kwargs):
    349         try:
--> 350             return self.func(*args, **kwargs)
        self.func = <mlens.externals.joblib.parallel.BatchedCalls object>
        args = ()
        kwargs = {}
    351         except KeyboardInterrupt:
    352             # We capture the KeyboardInterrupt and reraise it as
    353             # something different, as multiprocessing does not
    354             # interrupt processing for a KeyboardInterrupt

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.EvalSubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.EvalSubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.EvalSubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.EvalSubLearner object>
        self.job = 'fit'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self=<mlens.parallel.learner.EvalSubLearner object>, path=[('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>)])
    332         if self.scorer is None:
    333             raise ValueError("Cannot generate CV-scores without a scorer")
    334         t0 = time()
    335         transformers = self._load_preprocess(path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
        self._predict = <bound method EvalSubLearner._predict of <mlens.parallel.learner.EvalSubLearner object>>
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
    338 
    339         o = IndexedEstimator(estimator=self.estimator,
    340                              name=self.name_index,
    341                              index=self.index,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), score_preds=None)
    351 
    352     def _predict(self, transformers, score_preds=None):
    353         """Sub-routine to with sublearner"""
    354         # Train set
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
        self.in_index = ((0, 1899),)
    357 
    358         # Validation set
    359         self.test_score_, self.test_pred_time_ = self._score_preds(
    360             transformers, self.out_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), index=((0, 1899),))
    361 
    362     def _score_preds(self, transformers, index):
    363         # Train scores
    364         xtemp, ytemp = slice_array(self.in_array, self.targets, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
        xtemp = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        ytemp = array([2, 2, 1, ..., 2, 0, 3])
        transformers.transform = <bound method Pipeline.transform of Pipeline(nam...se,
       verbose=False))],
     return_y=True)>
    367 
    368         t0 = time()
    369 
    370         if self.error_score is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    129             Preprocessed input data
    130 
    131         y : array-like of shape [n_samples, ], optional
    132             Original or preprocessed targets, depending on the transformers.
    133         """
--> 134         return self._run(False, True, X, y)
        self._run = <bound method Pipeline._run of Pipeline(name='pi...se,
       verbose=False))],
     return_y=True)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
    135 
    136     def fit_transform(self, X, y=None):
    137         """Fit and transform pipeline.
    138 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), fit=False, process=True, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
     64         for tr_name, tr in self._pipeline:
     65             if fit:
     66                 tr.fit(X, y)
     67 
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr = SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False)
     70 
     71         if process:
     72             if self.return_y:
     73                 return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), x=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    230 def transform(tr, x, y):
    231     """Try transforming with X and y. Else, transform with only X."""
    232     try:
    233         x = tr.transform(x)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
        x = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr.transform = <bound method BaseEnsemble.transform of SuperLea...corer=None, shuffle=False,
       verbose=False)>
    236 
    237     return x, y
    238 
    239 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]), **kwargs={})
    555                 return self.predict(X, **kwargs), y
    556 
    557             # Asked to reproduce predictions during fit, here we need to
    558             # account for that in model selection mode,
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        self._backend.transform = <bound method Sequential.transform of Sequential...n=True)])],
   verbose=0)],
      verbose=False)>
        kwargs = {}
    561             if X.shape[0] != y.shape[0]:
    562                 r = y.shape[0] - X.shape[0]
    563                 y = y[r:]
    564             return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), **kwargs={})
    232         if not self.__fitted__:
    233             NotFittedError("Instance not fitted.")
    234 
    235         f, t0 = print_job(self, "Transforming")
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
        out = undefined
        self._predict = <bound method Sequential._predict of Sequential(...n=True)])],
   verbose=0)],
      verbose=False)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        kwargs = {}
    238 
    239         if self.verbose:
    240             print_time(t0, "{:<35}".format("Transform complete"),
    241                        file=f, flush=True)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), job='transform', **kwargs={})
    261             data.
    262         """
    263         r = kwargs.pop('return_preds', True)
    264         with ParallelProcessing(self.backend, self.n_jobs,
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
        out = undefined
        manager.stack = <bound method ParallelProcessing.stack of <mlens.parallel.backend.ParallelProcessing object>>
        self = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        job = 'transform'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        r = True
        kwargs = {}
    267 
    268         if not isinstance(out, list):
    269             out = [out]
    270         out = [p.squeeze() for p in out]

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), job='transform', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=None, path=None, return_preds=True, warm_start=False, split=True, **kwargs={})
    668             Prediction array(s).
    669         """
    670         out = self.initialize(
    671             job=job, X=X, y=y, path=path, warm_start=warm_start,
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
        self.process = <bound method ParallelProcessing.process of <mlens.parallel.backend.ParallelProcessing object>>
        caller = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        out = {}
        kwargs = {}
    674 
    675     def process(self, caller, out, **kwargs):
    676         """Process job.
    677 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), out=None, **kwargs={})
    713                       backend=self.backend) as parallel:
    714 
    715             for task in caller:
    716                 self.job.clear()
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
        self._partial_process = <bound method ParallelProcessing._partial_proces...lens.parallel.backend.ParallelProcessing object>>
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        parallel = Parallel(n_jobs=-1)
        kwargs = {}
    719 
    720                 if task.name in return_names:
    721                     out.append(self.get_preds(dtype=_dtype(task)))
    722 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self=<mlens.parallel.backend.ParallelProcessing object>, task=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), parallel=Parallel(n_jobs=-1), **kwargs={})
    734         task.setup(self.job.predict_in, self.job.targets, self.job.job)
    735 
    736         if not task.__no_output__:
    737             self._gen_prediction_array(task, self.job.job, self.__threading__)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        self.job.args = <bound method Job.args of <mlens.parallel.backend.Job object>>
        kwargs = {}
        parallel = Parallel(n_jobs=-1)
    740 
    741         if not task.__no_output__ and getattr(task, 'n_feature_prop', 0):
    742             self._propagate_features(task)
    743 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}, 'dir': [('sc.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('sc.0.2', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'transform', 'main': {'P': array([[2.60052562e-01, 1.77754706e-03, 5.693393... 1.20693236e-04, 9.98786032e-01]], dtype=float32), 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}}, parallel=Parallel(n_jobs=-1))
    147         if self.verbose >= 2:
    148             safe_print(msg.format('Learners ...'), file=f, end=e2)
    149             t1 = time()
    150 
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
        self.learners = [Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None)]
    153                  for sublearner in learner(args, 'main'))
    154 
    155         if self.verbose >= 2:
    156             print_time(t1, 'done', file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object Layer.__call__.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

---------------------------------------------------------------------------
Sub-process traceback:
---------------------------------------------------------------------------
ValueError                                         Tue Oct 11 15:54:29 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.SubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.SubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.SubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.SubLearner object>
        self.job = 'transform'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in transform(self=<mlens.parallel.learner.SubLearner object>, path=None)
    162             f = "stdout" if self.verbose < 10 - 3 else "stderr"
    163             print_time(t0, msg, file=f)
    164 
    165     def transform(self, path=None):
    166         """Predict with sublearner"""
--> 167         return self.predict(path)
        self.predict = <bound method SubLearner.predict of <mlens.parallel.learner.SubLearner object>>
        path = None
    168 
    169     def _fit(self, transformers):
    170         """Sub-routine to fit sub-learner"""
    171         xtemp, ytemp = slice_array(self.in_array, self.targets, self.in_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in predict(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    152     def predict(self, path=None):
    153         """Predict with sublearner"""
    154         if path is None:
    155             path = self.path
    156         t0 = time()
--> 157         transformers = self._load_preprocess(path)
        transformers = undefined
        self._load_preprocess = <bound method SubLearner._load_preprocess of <mlens.parallel.learner.SubLearner object>>
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
    158 
    159         self._predict(transformers, False)
    160         if self.verbose:
    161             msg = "{:<30} {}".format(self.name_index, "done")

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _load_preprocess(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    180         self.fit_time_ = time() - t0
    181 
    182     def _load_preprocess(self, path):
    183         """Load preprocessing pipeline"""
    184         if self.preprocess is not None:
--> 185             obj = load(path, self.preprocess_index, self.raise_on_exception)
        obj = undefined
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
        self.preprocess_index = 'sc.0.2'
        self.raise_on_exception = True
    186             return obj.estimator
    187         return
    188 
    189     def _predict(self, transformers, score_preds):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in load(path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)], name='sc.0.2', raise_on_exception=True)
     24         obj = _load(f, raise_on_exception)
     25     elif isinstance(path, list):
     26         obj = [tup[1] for tup in path if tup[0] == name]
     27         if not obj:
     28             raise ValueError(
---> 29                 "No preprocessing pipeline in cache. Auxiliary Transformer "
     30                 "have not cached pipelines, or cached to another sub-cache.")
     31         elif not len(obj) == 1:
     32             raise ValueError(
     33                 "Could not load unique preprocessing pipeline. "

ValueError: No preprocessing pipeline in cache. Auxiliary Transformer have not cached pipelines, or cached to another sub-cache.
___________________________________________________________________________
___________________________________________________________________________

During handling of the above exception, another exception occurred:

JoblibException                           Traceback (most recent call last)
/tmp/ipykernel_88346/411782330.py in <module>
----> 1 ens = mlens_opt.fit(x_train, y_train, x_test, y_test)

~/git/python/libs/training/ensemble/mlens_classifier.py in fit(self, x_train, y_train, x_test, y_test)
    177             preprocessing=preprocess,
    178             # TODO use parameter
--> 179             n_iter=2  # bump this up to do a larger grid search
    180         )
    181         print(pd.DataFrame(evl.results))

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in fit(self, X, y, estimators, param_dicts, n_iter, preprocessing)
    490         job = set_job(estimators, preprocessing)
    491         self._initialize(job, estimators, preprocessing, param_dicts, n_iter)
--> 492         self._fit(X, y, job)
    493         self._get_results()
    494         return self

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in _fit(self, X, y, job)
    178     def _fit(self, X, y, job):
    179         with ParallelEvaluation(self.backend, self.n_jobs) as manager:
--> 180             manager.process(self, job, X, y)
    181 
    182     def collect(self, path, case):

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self, caller, case, X, y, path, **kwargs)
    854 
    855             caller.indexer.fit(self.job.predict_in, self.job.targets, self.job.job)
--> 856             caller(parallel, self.job.args(**kwargs), case)

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in __call__(self, parallel, args, case)
    152                 t1 = time()
    153 
--> 154             self._run('estimators', parallel, args)
    155             self.collect(args['dir'], 'estimators')
    156 

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in _run(self, case, parallel, args)
    174 
    175         parallel(delayed(subtask, not _threading)()
--> 176                  for task in generator for subtask in task(args, inp))
    177 
    178     def _fit(self, X, y, job):

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self, iterable)
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time

~/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self)
    742                     exception = exception_type(report)
    743 
--> 744                     raise exception
    745 
    746     def __call__(self, iterable):

JoblibException: JoblibException
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/runpy.py in _run_module_as_main(mod_name='ipykernel_launcher', alter_argv=1)
    188         sys.exit(msg)
    189     main_globals = sys.modules["__main__"].__dict__
    190     if alter_argv:
    191         sys.argv[0] = mod_spec.origin
    192     return _run_code(code, main_globals, None,
--> 193                      "__main__", mod_spec)
        mod_spec = ModuleSpec(name='ipykernel_launcher', loader=<_f...b/python3.7/site-packages/ipykernel_launcher.py')
    194 
    195 def run_module(mod_name, init_globals=None,
    196                run_name=None, alter_sys=False):
    197     """Execute a module's code without importing it

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/runpy.py in _run_code(code=<code object <module> at 0x7fe079c4b0c0, file "/...3.7/site-packages/ipykernel_launcher.py", line 5>, run_globals={'__annotations__': {}, '__builtins__': <module 'builtins' (built-in)>, '__cached__': '/home/bastian/.conda/envs/machine_learning/lib/p...ges/__pycache__/ipykernel_launcher.cpython-37.pyc', '__doc__': 'Entry point for launching an IPython kernel.\n\nTh...orts until\nafter removing the cwd from sys.path.\n', '__file__': '/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel_launcher.py', '__loader__': <_frozen_importlib_external.SourceFileLoader object>, '__name__': '__main__', '__package__': '', '__spec__': ModuleSpec(name='ipykernel_launcher', loader=<_f...b/python3.7/site-packages/ipykernel_launcher.py'), 'app': <module 'ipykernel.kernelapp' from '/home/bastia.../python3.7/site-packages/ipykernel/kernelapp.py'>, ...}, init_globals=None, mod_name='__main__', mod_spec=ModuleSpec(name='ipykernel_launcher', loader=<_f...b/python3.7/site-packages/ipykernel_launcher.py'), pkg_name='', script_name=None)
     80                        __cached__ = cached,
     81                        __doc__ = None,
     82                        __loader__ = loader,
     83                        __package__ = pkg_name,
     84                        __spec__ = mod_spec)
---> 85     exec(code, run_globals)
        code = <code object <module> at 0x7fe079c4b0c0, file "/...3.7/site-packages/ipykernel_launcher.py", line 5>
        run_globals = {'__annotations__': {}, '__builtins__': <module 'builtins' (built-in)>, '__cached__': '/home/bastian/.conda/envs/machine_learning/lib/p...ges/__pycache__/ipykernel_launcher.cpython-37.pyc', '__doc__': 'Entry point for launching an IPython kernel.\n\nTh...orts until\nafter removing the cwd from sys.path.\n', '__file__': '/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel_launcher.py', '__loader__': <_frozen_importlib_external.SourceFileLoader object>, '__name__': '__main__', '__package__': '', '__spec__': ModuleSpec(name='ipykernel_launcher', loader=<_f...b/python3.7/site-packages/ipykernel_launcher.py'), 'app': <module 'ipykernel.kernelapp' from '/home/bastia.../python3.7/site-packages/ipykernel/kernelapp.py'>, ...}
     86     return run_globals
     87 
     88 def _run_module_code(code, init_globals=None,
     89                     mod_name=None, mod_spec=None,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel_launcher.py in <module>()
     12     if sys.path[0] == "":
     13         del sys.path[0]
     14 
     15     from ipykernel import kernelapp as app
     16 
---> 17     app.launch_new_instance()

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/traitlets/config/application.py in launch_instance(cls=<class 'ipykernel.kernelapp.IPKernelApp'>, argv=None, **kwargs={})
    841 
    842         If a global instance already exists, this reinitializes and starts it
    843         """
    844         app = cls.instance(**kwargs)
    845         app.initialize(argv)
--> 846         app.start()
        app.start = <bound method IPKernelApp.start of <ipykernel.kernelapp.IPKernelApp object>>
    847 
    848 #-----------------------------------------------------------------------------
    849 # utility functions, for convenience
    850 #-----------------------------------------------------------------------------

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/kernelapp.py in start(self=<ipykernel.kernelapp.IPKernelApp object>)
    707                 tr.run()
    708             except KeyboardInterrupt:
    709                 pass
    710         else:
    711             try:
--> 712                 self.io_loop.start()
        self.io_loop.start = <bound method BaseAsyncIOLoop.start of <tornado.platform.asyncio.AsyncIOMainLoop object>>
    713             except KeyboardInterrupt:
    714                 pass
    715 
    716 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/tornado/platform/asyncio.py in start(self=<tornado.platform.asyncio.AsyncIOMainLoop object>)
    194         except (RuntimeError, AssertionError):
    195             old_loop = None  # type: ignore
    196         try:
    197             self._setup_logging()
    198             asyncio.set_event_loop(self.asyncio_loop)
--> 199             self.asyncio_loop.run_forever()
        self.asyncio_loop.run_forever = <bound method BaseEventLoop.run_forever of <_Uni...EventLoop running=True closed=False debug=False>>
    200         finally:
    201             asyncio.set_event_loop(old_loop)
    202 
    203     def stop(self) -> None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/asyncio/base_events.py in run_forever(self=<_UnixSelectorEventLoop running=True closed=False debug=False>)
    536         sys.set_asyncgen_hooks(firstiter=self._asyncgen_firstiter_hook,
    537                                finalizer=self._asyncgen_finalizer_hook)
    538         try:
    539             events._set_running_loop(self)
    540             while True:
--> 541                 self._run_once()
        self._run_once = <bound method BaseEventLoop._run_once of <_UnixS...EventLoop running=True closed=False debug=False>>
    542                 if self._stopping:
    543                     break
    544         finally:
    545             self._stopping = False

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/asyncio/base_events.py in _run_once(self=<_UnixSelectorEventLoop running=True closed=False debug=False>)
   1781                         logger.warning('Executing %s took %.3f seconds',
   1782                                        _format_handle(handle), dt)
   1783                 finally:
   1784                     self._current_handle = None
   1785             else:
-> 1786                 handle._run()
        handle._run = <bound method Handle._run of <Handle <TaskWakeup...0x7fe02b1b9f10>(<Future finis...890>, ...],))>)>>
   1787         handle = None  # Needed to break cycles when an exception occurs.
   1788 
   1789     def _set_coroutine_origin_tracking(self, enabled):
   1790         if bool(enabled) == bool(self._coroutine_origin_tracking_enabled):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/asyncio/events.py in _run(self=<Handle <TaskWakeupMethWrapper object at 0x7fe02b1b9f10>(<Future finis...890>, ...],))>)>)
     83     def cancelled(self):
     84         return self._cancelled
     85 
     86     def _run(self):
     87         try:
---> 88             self._context.run(self._callback, *self._args)
        self._context.run = <built-in method run of Context object>
        self._callback = <TaskWakeupMethWrapper object>
        self._args = (<Future finished result=(24, <bound method...7fe...1817d0>, <zmq.sugar.fr...x7fe077181890>, ...],))>,)
     89         except Exception as exc:
     90             cb = format_helpers._format_callback_source(
     91                 self._callback, self._args)
     92             msg = f'Exception in callback {cb}'

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/kernelbase.py in dispatch_queue(self=<ipykernel.ipkernel.IPythonKernel object>)
    499         even when the handler is async
    500         """
    501 
    502         while True:
    503             try:
--> 504                 await self.process_one()
        self.process_one = <bound method Kernel.process_one of <ipykernel.ipkernel.IPythonKernel object>>
    505             except Exception:
    506                 self.log.exception("Error in message handler")
    507 
    508     _message_counter = Any(

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/kernelbase.py in process_one(self=<ipykernel.ipkernel.IPythonKernel object>, wait=True)
    488         else:
    489             try:
    490                 t, dispatch, args = self.msg_queue.get_nowait()
    491             except (asyncio.QueueEmpty, QueueEmpty):
    492                 return None
--> 493         await dispatch(*args)
        dispatch = <bound method Kernel.dispatch_shell of <ipykernel.ipkernel.IPythonKernel object>>
        args = ([<zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>, <zmq.sugar.frame.Frame object>],)
    494 
    495     async def dispatch_queue(self):
    496         """Coroutine to preserve order of message handling
    497 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/kernelbase.py in dispatch_shell(self=<ipykernel.ipkernel.IPythonKernel object>, msg={'buffers': [], 'content': {'allow_stdin': True, 'code': 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', 'silent': False, 'stop_on_error': True, 'store_history': True, 'user_expressions': {}}, 'header': {'date': datetime.datetime(2022, 10, 11, 13, 38, 13, 16000, tzinfo=tzutc()), 'msg_id': '9ef5094f-a023-46d2-bc95-96e97d6fb1ab', 'msg_type': 'execute_request', 'session': '9d7f8445-ab7d-44de-8ece-2962f6804115', 'username': '', 'version': '5.2'}, 'metadata': {'cellId': '374194c9-20cc-4172-9ef1-a3c9987f840a', 'deletedCells': [], 'recordTiming': False}, 'msg_id': '9ef5094f-a023-46d2-bc95-96e97d6fb1ab', 'msg_type': 'execute_request', 'parent_header': {}})
    395             except Exception:
    396                 self.log.debug("Unable to signal in pre_handler_hook:", exc_info=True)
    397             try:
    398                 result = handler(self.shell_stream, idents, msg)
    399                 if inspect.isawaitable(result):
--> 400                     await result
        result = <coroutine object Kernel.execute_request>
    401             except Exception:
    402                 self.log.error("Exception in message handler:", exc_info=True)
    403             except KeyboardInterrupt:
    404                 # Ctrl-c shouldn't crash the kernel here.

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/kernelbase.py in execute_request(self=<ipykernel.ipkernel.IPythonKernel object>, stream=<zmq.eventloop.zmqstream.ZMQStream object>, ident=[b'9d7f8445-ab7d-44de-8ece-2962f6804115'], parent={'buffers': [], 'content': {'allow_stdin': True, 'code': 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', 'silent': False, 'stop_on_error': True, 'store_history': True, 'user_expressions': {}}, 'header': {'date': datetime.datetime(2022, 10, 11, 13, 38, 13, 16000, tzinfo=tzutc()), 'msg_id': '9ef5094f-a023-46d2-bc95-96e97d6fb1ab', 'msg_type': 'execute_request', 'session': '9d7f8445-ab7d-44de-8ece-2962f6804115', 'username': '', 'version': '5.2'}, 'metadata': {'cellId': '374194c9-20cc-4172-9ef1-a3c9987f840a', 'deletedCells': [], 'recordTiming': False}, 'msg_id': '9ef5094f-a023-46d2-bc95-96e97d6fb1ab', 'msg_type': 'execute_request', 'parent_header': {}})
    719                 user_expressions,
    720                 allow_stdin,
    721             )
    722 
    723         if inspect.isawaitable(reply_content):
--> 724             reply_content = await reply_content
        reply_content = <coroutine object IPythonKernel.do_execute>
    725 
    726         # Flush output before sending the reply.
    727         sys.stdout.flush()
    728         sys.stderr.flush()

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/ipkernel.py in do_execute(self=<ipykernel.ipkernel.IPythonKernel object>, code='ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', silent=False, store_history=True, user_expressions={}, allow_stdin=True, cell_id='374194c9-20cc-4172-9ef1-a3c9987f840a')
    385                         store_history=store_history,
    386                         silent=silent,
    387                         cell_id=cell_id,
    388                     )
    389                 else:
--> 390                     res = shell.run_cell(code, store_history=store_history, silent=silent)
        res = undefined
        code = 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)'
        store_history = True
        silent = False
    391         finally:
    392             self._restore_input()
    393 
    394         if res.error_before_exec is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/ipykernel/zmqshell.py in run_cell(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, *args=('ens = mlens_opt.fit(x_train, y_train, x_test, y_test)',), **kwargs={'silent': False, 'store_history': True})
    523         )
    524         self.payload_manager.write_payload(payload)
    525 
    526     def run_cell(self, *args, **kwargs):
    527         self._last_traceback = None
--> 528         return super().run_cell(*args, **kwargs)
        args = ('ens = mlens_opt.fit(x_train, y_train, x_test, y_test)',)
        kwargs = {'silent': False, 'store_history': True}
    529 
    530     def _showtraceback(self, etype, evalue, stb):
    531         # try to preserve ordering of tracebacks and print statements
    532         sys.stdout.flush()

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_cell(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, raw_cell='ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', store_history=True, silent=False, shell_futures=True)
   2953         result : :class:`ExecutionResult`
   2954         """
   2955         result = None
   2956         try:
   2957             result = self._run_cell(
-> 2958                 raw_cell, store_history, silent, shell_futures)
        raw_cell = 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)'
        store_history = True
        silent = False
        shell_futures = True
   2959         finally:
   2960             self.events.trigger('post_execute')
   2961             if not silent:
   2962                 self.events.trigger('post_run_cell', result)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/interactiveshell.py in _run_cell(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, raw_cell='ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', store_history=True, silent=False, shell_futures=True)
   2998             runner = self.loop_runner
   2999         else:
   3000             runner = _pseudo_sync_runner
   3001 
   3002         try:
-> 3003             return runner(coro)
        runner = <function _pseudo_sync_runner>
        coro = <coroutine object InteractiveShell.run_cell_async>
   3004         except BaseException as e:
   3005             info = ExecutionInfo(raw_cell, store_history, silent, shell_futures)
   3006             result = ExecutionResult(info)
   3007             result.error_in_exec = e

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/async_helpers.py in _pseudo_sync_runner(coro=<coroutine object InteractiveShell.run_cell_async>)
     73 
     74     Credit to Nathaniel Smith
     75 
     76     """
     77     try:
---> 78         coro.send(None)
        coro.send = <built-in method send of coroutine object>
     79     except StopIteration as exc:
     80         return exc.value
     81     else:
     82         # TODO: do not raise but return an execution result with the right info.

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_cell_async(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, raw_cell='ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', store_history=True, silent=False, shell_futures=True, transformed_cell='ens = mlens_opt.fit(x_train, y_train, x_test, y_test)\n', preprocessing_exc_tuple=None)
   3224                 interactivity = "none" if silent else self.ast_node_interactivity
   3225                 if _run_async:
   3226                     interactivity = 'async'
   3227 
   3228                 has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
-> 3229                        interactivity=interactivity, compiler=compiler, result=result)
        interactivity = 'last_expr'
        compiler = <ipykernel.compiler.XCachingCompiler object>
   3230 
   3231                 self.last_execution_succeeded = not has_raised
   3232                 self.last_execution_result = result
   3233 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_ast_nodes(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, nodelist=[<_ast.Assign object>], cell_name='/tmp/ipykernel_88346/411782330.py', interactivity='none', compiler=<ipykernel.compiler.XCachingCompiler object>, result=<ExecutionResult object at 7fe0273f0250, executi...rue silent=False shell_futures=True> result=None>)
   3439                         mod = ast.Interactive([node])
   3440                     with compiler.extra_flags(getattr(ast, 'PyCF_ALLOW_TOP_LEVEL_AWAIT', 0x0) if self.autoawait else 0x0):
   3441                         code = compiler(mod, cell_name, mode)
   3442                         code = self._update_code_co_name(code)
   3443                         asy = compare(code)
-> 3444                     if (await self.run_code(code, result,  async_=asy)):
        self.run_code = <bound method InteractiveShell.run_code of <ipykernel.zmqshell.ZMQInteractiveShell object>>
        code = <code object <module> at 0x7fe02b17d5d0, file "/tmp/ipykernel_88346/411782330.py", line 1>
        result = <ExecutionResult object at 7fe0273f0250, executi...rue silent=False shell_futures=True> result=None>
        asy = False
   3445                         return True
   3446 
   3447             # Flush softspace
   3448             if softspace(sys.stdout, 0):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_code(self=<ipykernel.zmqshell.ZMQInteractiveShell object>, code_obj=<code object <module> at 0x7fe02b17d5d0, file "/tmp/ipykernel_88346/411782330.py", line 1>, result=<ExecutionResult object at 7fe0273f0250, executi...rue silent=False shell_futures=True> result=None>, async_=False)
   3519                     code = compile('last_expr', 'fake', "single")
   3520                     exec(code, {'last_expr': last_expr})
   3521                 elif async_ :
   3522                     await eval(code_obj, self.user_global_ns, self.user_ns)
   3523                 else:
-> 3524                     exec(code_obj, self.user_global_ns, self.user_ns)
        code_obj = <code object <module> at 0x7fe02b17d5d0, file "/tmp/ipykernel_88346/411782330.py", line 1>
        self.user_global_ns = {'CH_CONFIGS': ['ch_A_B'], 'CLASS_TARGET': 'genus_sex_vctrck', 'FEATURES': ['melspec_db_2_hires_lomels_htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk'], 'GENUS_SEX_CLASS_VCTRCK': 'genus_sex_vctrck', 'In': ['', 'from libs.config.mosquito.mosquito_config import GENUS_SEX_CLASS_VCTRCK', "RANDOM_SEED = 1\nCH_CONFIGS = ['ch_A_B']\nTEST_PRO..._htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk']", 'import logging\nimport sys\nsys.path.append("../.....sifier\nfrom sklearn.metrics import accuracy_score', "LOG_FORMAT = '%(asctime)s,%(msecs)d %(levelname)...:%S',\n                        level=logging.INFO)", "exp_conf = MlExpConf(CLASS_TARGET, CH_CONFIGS, '...    # strat_cols=STRAT_COLS\n                    )", 'channel_data = load_data.get_data(FEATURES, exp_...ws=True, remove_null_cols=False, normalize=False)', "x_train = channel_data['ch_A_B']['x_train']\ny_train = channel_data['y_train']", "x_test = channel_data['ch_A_B']['x_test'].values\ny_test = channel_data['y_test']", '# mlens_opt = MlensClassifier()\nmlens_opt = Mlen...tune_base_learners=True, tune_meta_learners=True)', 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', 'preds = ens.predict(x_test)', 'print(accuracy_score(y_test, preds))', "RANDOM_SEED = 1\nCH_CONFIGS = ['ch_A_B']\nTEST_PRO..._htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk']", "exp_conf = MlExpConf(CLASS_TARGET, CH_CONFIGS, '...    # strat_cols=STRAT_COLS\n                    )", 'channel_data = load_data.get_data(FEATURES, exp_...ws=True, remove_null_cols=False, normalize=False)', "x_train = channel_data['ch_A_B']['x_train']\ny_train = channel_data['y_train']", "x_test = channel_data['ch_A_B']['x_test'].values\ny_test = channel_data['y_test']", '# mlens_opt = MlensClassifier()\nmlens_opt = Mlen...tune_base_learners=True, tune_meta_learners=True)', 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)'], 'LOG_FORMAT': '%(asctime)s,%(msecs)d %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s', 'MlExpConf': <class 'libs.classes.ml_exp_conf.MlExpConf'>, 'MlensClassifier': <class 'libs.training.ensemble.mlens_classifier.MlensClassifier'>, 'Out': {}, 'PRINT_STATS': True, ...}
        self.user_ns = {'CH_CONFIGS': ['ch_A_B'], 'CLASS_TARGET': 'genus_sex_vctrck', 'FEATURES': ['melspec_db_2_hires_lomels_htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk'], 'GENUS_SEX_CLASS_VCTRCK': 'genus_sex_vctrck', 'In': ['', 'from libs.config.mosquito.mosquito_config import GENUS_SEX_CLASS_VCTRCK', "RANDOM_SEED = 1\nCH_CONFIGS = ['ch_A_B']\nTEST_PRO..._htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk']", 'import logging\nimport sys\nsys.path.append("../.....sifier\nfrom sklearn.metrics import accuracy_score', "LOG_FORMAT = '%(asctime)s,%(msecs)d %(levelname)...:%S',\n                        level=logging.INFO)", "exp_conf = MlExpConf(CLASS_TARGET, CH_CONFIGS, '...    # strat_cols=STRAT_COLS\n                    )", 'channel_data = load_data.get_data(FEATURES, exp_...ws=True, remove_null_cols=False, normalize=False)', "x_train = channel_data['ch_A_B']['x_train']\ny_train = channel_data['y_train']", "x_test = channel_data['ch_A_B']['x_test'].values\ny_test = channel_data['y_test']", '# mlens_opt = MlensClassifier()\nmlens_opt = Mlen...tune_base_learners=True, tune_meta_learners=True)', 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)', 'preds = ens.predict(x_test)', 'print(accuracy_score(y_test, preds))', "RANDOM_SEED = 1\nCH_CONFIGS = ['ch_A_B']\nTEST_PRO..._htk', 'ext_temp', 'mfcc_2_midres_lomels_no_htk']", "exp_conf = MlExpConf(CLASS_TARGET, CH_CONFIGS, '...    # strat_cols=STRAT_COLS\n                    )", 'channel_data = load_data.get_data(FEATURES, exp_...ws=True, remove_null_cols=False, normalize=False)', "x_train = channel_data['ch_A_B']['x_train']\ny_train = channel_data['y_train']", "x_test = channel_data['ch_A_B']['x_test'].values\ny_test = channel_data['y_test']", '# mlens_opt = MlensClassifier()\nmlens_opt = Mlen...tune_base_learners=True, tune_meta_learners=True)', 'ens = mlens_opt.fit(x_train, y_train, x_test, y_test)'], 'LOG_FORMAT': '%(asctime)s,%(msecs)d %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s', 'MlExpConf': <class 'libs.classes.ml_exp_conf.MlExpConf'>, 'MlensClassifier': <class 'libs.training.ensemble.mlens_classifier.MlensClassifier'>, 'Out': {}, 'PRINT_STATS': True, ...}
   3525             finally:
   3526                 # Reset our crash handler in place
   3527                 sys.excepthook = old_excepthook
   3528         except SystemExit as e:

...........................................................................
/tmp/ipykernel_88346/411782330.py in <module>()
----> 1 ens = mlens_opt.fit(x_train, y_train, x_test, y_test)

...........................................................................
/home/bastian/git/python/libs/training/ensemble/mlens_classifier.py in fit(self=MlensClassifier(tune_base_learners=False, tune_meta_learners=True, random_seed=1), x_train=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), y_train=array([2, 2, 1, ..., 2, 2, 0]), x_test=array([[  7.1236587 ,   8.4514475 ,  -4.9251547 ...3.888027  ,
        -12.220552  ,   0.        ]]), y_test=array([3, 3, 2, 0, 3, 0, 3, 2, 0, 0, 1, 2, 0, 1,...1, 0, 1, 0,
       2, 3, 1, 1, 1, 1, 3, 2, 3, 1]))
    174             x_train, y_train,
    175             meta_learners,
    176             param_dicts=param_dicts,
    177             preprocessing=preprocess,
    178             # TODO use parameter
--> 179             n_iter=2  # bump this up to do a larger grid search
    180         )
    181         print(pd.DataFrame(evl.results))
    182         ens = self._generate_super_learner(evl, in_layer_proba, in_layer_class)
    183         ens.fit(x_train, y_train)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in fit(self=<mlens.model_selection.model_selection.Evaluator object>, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), y=array([2, 2, 1, ..., 2, 2, 0]), estimators=[('rf', RandomForestClassifier(random_state=1)), ('svc', SVC())], param_dicts={'rf': {'max_depth': <scipy.stats._distn_infrastructure.rv_frozen object>, 'max_features': <scipy.stats._distn_infrastructure.rv_frozen object>}, 'svc': {'C': <scipy.stats._distn_infrastructure.rv_frozen object>}}, n_iter=2, preprocessing={'class': [('layer-1', SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False))], 'proba': [('layer-1', SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False))]})
    487             class instance with stored estimator evaluation results in
    488             the ``results`` attribute.
    489         """
    490         job = set_job(estimators, preprocessing)
    491         self._initialize(job, estimators, preprocessing, param_dicts, n_iter)
--> 492         self._fit(X, y, job)
        self._fit = <bound method BaseEval._fit of <mlens.model_selection.model_selection.Evaluator object>>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]])
        y = array([2, 2, 1, ..., 2, 2, 0])
        job = 'preprocess-evaluate'
    493         self._get_results()
    494         return self
    495 
    496     def _initialize(self, job, estimators, preprocessing, param_dicts, n_iter):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in _fit(self=<mlens.model_selection.model_selection.Evaluator object>, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), y=array([2, 2, 1, ..., 2, 2, 0]), job='preprocess-evaluate')
    175         parallel(delayed(subtask, not _threading)()
    176                  for task in generator for subtask in task(args, inp))
    177 
    178     def _fit(self, X, y, job):
    179         with ParallelEvaluation(self.backend, self.n_jobs) as manager:
--> 180             manager.process(self, job, X, y)
        manager.process = <bound method ParallelEvaluation.process of <mlens.parallel.backend.ParallelEvaluation object>>
        self = <mlens.model_selection.model_selection.Evaluator object>
        job = 'preprocess-evaluate'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]])
        y = array([2, 2, 1, ..., 2, 2, 0])
    181 
    182     def collect(self, path, case):
    183         """Collect cache estimators"""
    184         if case == 'transformers':

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelEvaluation object>, caller=<mlens.model_selection.model_selection.Evaluator object>, case='preprocess-evaluate', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), y=array([2, 2, 1, ..., 2, 2, 0]), path=None, **kwargs={})
    851         with Parallel(n_jobs=self.n_jobs, temp_folder=tf, max_nbytes=None,
    852                       mmap_mode='w+', verbose=self.verbose,
    853                       backend=self.backend) as parallel:
    854 
    855             caller.indexer.fit(self.job.predict_in, self.job.targets, self.job.job)
--> 856             caller(parallel, self.job.args(**kwargs), case)
        caller = <mlens.model_selection.model_selection.Evaluator object>
        parallel = Parallel(n_jobs=-1)
        self.job.args = <bound method Job.args of <mlens.parallel.backend.Job object>>
        kwargs = {}
        case = 'preprocess-evaluate'

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in __call__(self=<mlens.model_selection.model_selection.Evaluator object>, parallel=Parallel(n_jobs=-1), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}, 'dir': [('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'fit', 'main': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}}, case='preprocess-evaluate')
    149         if 'evaluate' in case:
    150             if self.verbose >= 2:
    151                 safe_print(self._print_eval_start(), file=f)
    152                 t1 = time()
    153 
--> 154             self._run('estimators', parallel, args)
        self._run = <bound method BaseEval._run of <mlens.model_selection.model_selection.Evaluator object>>
        parallel = Parallel(n_jobs=-1)
        args = {'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}, 'dir': [('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'fit', 'main': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}}
    155             self.collect(args['dir'], 'estimators')
    156 
    157             if self.verbose >= 2:
    158                 print_time(t1, '{:<13} done'.format('Evaluation'), file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/model_selection/model_selection.py in _run(self=<mlens.model_selection.model_selection.Evaluator object>, case='estimators', parallel=Parallel(n_jobs=-1), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}, 'dir': [('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'fit', 'main': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}})
    171         else:
    172             generator = self._learners
    173             inp = 'main'
    174 
    175         parallel(delayed(subtask, not _threading)()
--> 176                  for task in generator for subtask in task(args, inp))
        generator = [EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6), EvalLearner(attr='predict', backend='threading',...   scorer=make_scorer(accuracy_score), verbose=6)]
        args = {'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}, 'dir': [('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'fit', 'main': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...8.847113  ,
         14.94697   ,   0.05878035]]), 'y': array([2, 2, 1, ..., 2, 2, 0])}}
    177 
    178     def _fit(self, X, y, job):
    179         with ParallelEvaluation(self.backend, self.n_jobs) as manager:
    180             manager.process(self, job, X, y)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object BaseEval._run.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

---------------------------------------------------------------------------
Sub-process traceback:
---------------------------------------------------------------------------
JoblibValueError                                   Tue Oct 11 15:54:32 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.EvalSubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.EvalSubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.EvalSubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.EvalSubLearner object>
        self.job = 'fit'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self=<mlens.parallel.learner.EvalSubLearner object>, path=[('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>)])
    332         if self.scorer is None:
    333             raise ValueError("Cannot generate CV-scores without a scorer")
    334         t0 = time()
    335         transformers = self._load_preprocess(path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
        self._predict = <bound method EvalSubLearner._predict of <mlens.parallel.learner.EvalSubLearner object>>
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
    338 
    339         o = IndexedEstimator(estimator=self.estimator,
    340                              name=self.name_index,
    341                              index=self.index,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), score_preds=None)
    351 
    352     def _predict(self, transformers, score_preds=None):
    353         """Sub-routine to with sublearner"""
    354         # Train set
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
        self.in_index = ((0, 1899),)
    357 
    358         # Validation set
    359         self.test_score_, self.test_pred_time_ = self._score_preds(
    360             transformers, self.out_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), index=((0, 1899),))
    361 
    362     def _score_preds(self, transformers, index):
    363         # Train scores
    364         xtemp, ytemp = slice_array(self.in_array, self.targets, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
        xtemp = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        ytemp = array([2, 2, 1, ..., 2, 0, 3])
        transformers.transform = <bound method Pipeline.transform of Pipeline(nam...se,
       verbose=False))],
     return_y=True)>
    367 
    368         t0 = time()
    369 
    370         if self.error_score is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    129             Preprocessed input data
    130 
    131         y : array-like of shape [n_samples, ], optional
    132             Original or preprocessed targets, depending on the transformers.
    133         """
--> 134         return self._run(False, True, X, y)
        self._run = <bound method Pipeline._run of Pipeline(name='pi...se,
       verbose=False))],
     return_y=True)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
    135 
    136     def fit_transform(self, X, y=None):
    137         """Fit and transform pipeline.
    138 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), fit=False, process=True, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
     64         for tr_name, tr in self._pipeline:
     65             if fit:
     66                 tr.fit(X, y)
     67 
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr = SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False)
     70 
     71         if process:
     72             if self.return_y:
     73                 return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), x=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    230 def transform(tr, x, y):
    231     """Try transforming with X and y. Else, transform with only X."""
    232     try:
    233         x = tr.transform(x)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
        x = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr.transform = <bound method BaseEnsemble.transform of SuperLea...corer=None, shuffle=False,
       verbose=False)>
    236 
    237     return x, y
    238 
    239 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]), **kwargs={})
    555                 return self.predict(X, **kwargs), y
    556 
    557             # Asked to reproduce predictions during fit, here we need to
    558             # account for that in model selection mode,
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        self._backend.transform = <bound method Sequential.transform of Sequential...n=True)])],
   verbose=0)],
      verbose=False)>
        kwargs = {}
    561             if X.shape[0] != y.shape[0]:
    562                 r = y.shape[0] - X.shape[0]
    563                 y = y[r:]
    564             return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), **kwargs={})
    232         if not self.__fitted__:
    233             NotFittedError("Instance not fitted.")
    234 
    235         f, t0 = print_job(self, "Transforming")
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
        out = undefined
        self._predict = <bound method Sequential._predict of Sequential(...n=True)])],
   verbose=0)],
      verbose=False)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        kwargs = {}
    238 
    239         if self.verbose:
    240             print_time(t0, "{:<35}".format("Transform complete"),
    241                        file=f, flush=True)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), job='transform', **kwargs={})
    261             data.
    262         """
    263         r = kwargs.pop('return_preds', True)
    264         with ParallelProcessing(self.backend, self.n_jobs,
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
        out = undefined
        manager.stack = <bound method ParallelProcessing.stack of <mlens.parallel.backend.ParallelProcessing object>>
        self = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        job = 'transform'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        r = True
        kwargs = {}
    267 
    268         if not isinstance(out, list):
    269             out = [out]
    270         out = [p.squeeze() for p in out]

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), job='transform', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=None, path=None, return_preds=True, warm_start=False, split=True, **kwargs={})
    668             Prediction array(s).
    669         """
    670         out = self.initialize(
    671             job=job, X=X, y=y, path=path, warm_start=warm_start,
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
        self.process = <bound method ParallelProcessing.process of <mlens.parallel.backend.ParallelProcessing object>>
        caller = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        out = {}
        kwargs = {}
    674 
    675     def process(self, caller, out, **kwargs):
    676         """Process job.
    677 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), out=None, **kwargs={})
    713                       backend=self.backend) as parallel:
    714 
    715             for task in caller:
    716                 self.job.clear()
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
        self._partial_process = <bound method ParallelProcessing._partial_proces...lens.parallel.backend.ParallelProcessing object>>
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        parallel = Parallel(n_jobs=-1)
        kwargs = {}
    719 
    720                 if task.name in return_names:
    721                     out.append(self.get_preds(dtype=_dtype(task)))
    722 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self=<mlens.parallel.backend.ParallelProcessing object>, task=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), parallel=Parallel(n_jobs=-1), **kwargs={})
    734         task.setup(self.job.predict_in, self.job.targets, self.job.job)
    735 
    736         if not task.__no_output__:
    737             self._gen_prediction_array(task, self.job.job, self.__threading__)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        self.job.args = undefined
        kwargs = {}
        parallel = Parallel(n_jobs=-1)
    740 
    741         if not task.__no_output__ and getattr(task, 'n_feature_prop', 0):
    742             self._propagate_features(task)
    743 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}, 'dir': [('sc.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('sc.0.2', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'transform', 'main': {'P': array([[2.60052562e-01, 1.77754706e-03, 5.693393... 1.20693236e-04, 9.98786032e-01]], dtype=float32), 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}}, parallel=Parallel(n_jobs=-1))
    147         if self.verbose >= 2:
    148             safe_print(msg.format('Learners ...'), file=f, end=e2)
    149             t1 = time()
    150 
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
        self.learners = [Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None)]
    153                  for sublearner in learner(args, 'main'))
    154 
    155         if self.verbose >= 2:
    156             print_time(t1, 'done', file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object Layer.__call__.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in retrieve(self=Parallel(n_jobs=-1))
    739 %s""" % (this_report, exception.message)
    740                     # Convert this to a JoblibException
    741                     exception_type = _mk_exception(exception.etype)[0]
    742                     exception = exception_type(report)
    743 
--> 744                     raise exception
        exception = undefined
    745 
    746     def __call__(self, iterable):
    747         if self._jobs:
    748             raise ValueError('This Parallel instance is already running')

JoblibValueError: JoblibValueError
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    885         # indeed has already been destroyed, so that exceptions in
    886         # _bootstrap_inner() during normal business hours are properly
    887         # reported.  Also, we only suppress them for daemonic threads;
    888         # if a non-daemonic encounters this, something else is wrong.
    889         try:
--> 890             self._bootstrap_inner()
        self._bootstrap_inner = <bound method Thread._bootstrap_inner of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    891         except:
    892             if self._daemonic and _sys is None:
    893                 return
    894             raise

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in _bootstrap_inner(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    921                 _sys.settrace(_trace_hook)
    922             if _profile_hook:
    923                 _sys.setprofile(_profile_hook)
    924 
    925             try:
--> 926                 self.run()
        self.run = <bound method Thread.run of <DummyProcess(Thread-404, started daemon 140600733968128)>>
    927             except SystemExit:
    928                 pass
    929             except:
    930                 # If sys.stderr is no more (most likely from interpreter

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/threading.py in run(self=<DummyProcess(Thread-404, started daemon 140600733968128)>)
    865         from the args and kwargs arguments, respectively.
    866 
    867         """
    868         try:
    869             if self._target:
--> 870                 self._target(*self._args, **self._kwargs)
        self._target = <function worker>
        self._args = (<_queue.SimpleQueue object>, <_queue.SimpleQueue object>, None, (), None, False)
        self._kwargs = {}
    871         finally:
    872             # Avoid a refcycle if the thread is running a function with
    873             # an argument that has a member that points to the thread.
    874             del self._target, self._args, self._kwargs

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/multiprocessing/pool.py in worker(inqueue=<_queue.SimpleQueue object>, outqueue=<_queue.SimpleQueue object>, initializer=None, initargs=(), maxtasks=None, wrap_exception=False)
    116             util.debug('worker got sentinel -- exiting')
    117             break
    118 
    119         job, i, func, args, kwds = task
    120         try:
--> 121             result = (True, func(*args, **kwds))
        result = None
        func = <mlens.externals.joblib._parallel_backends.SafeFunction object>
        args = ()
        kwds = {}
    122         except Exception as e:
    123             if wrap_exception and func is not _helper_reraises_exception:
    124                 e = ExceptionWithTraceback(e, e.__traceback__)
    125             result = (False, e)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/_parallel_backends.py in __call__(self=<mlens.externals.joblib._parallel_backends.SafeFunction object>, *args=(), **kwargs={})
    345     def __init__(self, func):
    346         self.func = func
    347 
    348     def __call__(self, *args, **kwargs):
    349         try:
--> 350             return self.func(*args, **kwargs)
        self.func = <mlens.externals.joblib.parallel.BatchedCalls object>
        args = ()
        kwargs = {}
    351         except KeyboardInterrupt:
    352             # We capture the KeyboardInterrupt and reraise it as
    353             # something different, as multiprocessing does not
    354             # interrupt processing for a KeyboardInterrupt

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.EvalSubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.EvalSubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.EvalSubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.EvalSubLearner object>
        self.job = 'fit'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in fit(self=<mlens.parallel.learner.EvalSubLearner object>, path=[('class.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('class.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.1.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.rf.0.0.2', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('proba.svc.0.0.2', <mlens.parallel.learner.IndexedEstimator object>)])
    332         if self.scorer is None:
    333             raise ValueError("Cannot generate CV-scores without a scorer")
    334         t0 = time()
    335         transformers = self._load_preprocess(path)
    336         self._fit(transformers)
--> 337         self._predict(transformers)
        self._predict = <bound method EvalSubLearner._predict of <mlens.parallel.learner.EvalSubLearner object>>
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
    338 
    339         o = IndexedEstimator(estimator=self.estimator,
    340                              name=self.name_index,
    341                              index=self.index,

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _predict(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), score_preds=None)
    351 
    352     def _predict(self, transformers, score_preds=None):
    353         """Sub-routine to with sublearner"""
    354         # Train set
    355         self.train_score_, self.train_pred_time_ = self._score_preds(
--> 356             transformers, self.in_index)
        transformers = Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True)
        self.in_index = ((0, 1899),)
    357 
    358         # Validation set
    359         self.test_score_, self.test_pred_time_ = self._score_preds(
    360             transformers, self.out_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _score_preds(self=<mlens.parallel.learner.EvalSubLearner object>, transformers=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), index=((0, 1899),))
    361 
    362     def _score_preds(self, transformers, index):
    363         # Train scores
    364         xtemp, ytemp = slice_array(self.in_array, self.targets, index)
    365         if transformers:
--> 366             xtemp, ytemp = transformers.transform(xtemp, ytemp)
        xtemp = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        ytemp = array([2, 2, 1, ..., 2, 0, 3])
        transformers.transform = <bound method Pipeline.transform of Pipeline(nam...se,
       verbose=False))],
     return_y=True)>
    367 
    368         t0 = time()
    369 
    370         if self.error_score is not None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in transform(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    129             Preprocessed input data
    130 
    131         y : array-like of shape [n_samples, ], optional
    132             Original or preprocessed targets, depending on the transformers.
    133         """
--> 134         return self._run(False, True, X, y)
        self._run = <bound method Pipeline._run of Pipeline(name='pi...se,
       verbose=False))],
     return_y=True)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
    135 
    136     def fit_transform(self, X, y=None):
    137         """Fit and transform pipeline.
    138 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/handles.py in _run(self=Pipeline(name='pipeline-11',
     pipeline=[('la...lse,
       verbose=False))],
     return_y=True), fit=False, process=True, X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
     64         for tr_name, tr in self._pipeline:
     65             if fit:
     66                 tr.fit(X, y)
     67 
     68             if len(self._pipeline) > 1 or process:
---> 69                 X, y = transform(tr, X, y)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr = SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False)
     70 
     71         if process:
     72             if self.return_y:
     73                 return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in transform(tr=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), x=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]))
    230 def transform(tr, x, y):
    231     """Try transforming with X and y. Else, transform with only X."""
    232     try:
    233         x = tr.transform(x)
    234     except TypeError:
--> 235         x, y = tr.transform(x, y)
        x = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        y = array([2, 2, 1, ..., 2, 0, 3])
        tr.transform = <bound method BaseEnsemble.transform of SuperLea...corer=None, shuffle=False,
       verbose=False)>
    236 
    237     return x, y
    238 
    239 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=SuperLearner(array_check=None, backend=None, fol...scorer=None, shuffle=False,
       verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=array([2, 2, 1, ..., 2, 0, 3]), **kwargs={})
    555                 return self.predict(X, **kwargs), y
    556 
    557             # Asked to reproduce predictions during fit, here we need to
    558             # account for that in model selection mode,
    559             # blend ensemble will cut X in observation size so need to adjust y
--> 560             X = self._backend.transform(X, **kwargs)
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        self._backend.transform = <bound method Sequential.transform of Sequential...n=True)])],
   verbose=0)],
      verbose=False)>
        kwargs = {}
    561             if X.shape[0] != y.shape[0]:
    562                 r = y.shape[0] - X.shape[0]
    563                 y = y[r:]
    564             return X, y

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in transform(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), **kwargs={})
    232         if not self.__fitted__:
    233             NotFittedError("Instance not fitted.")
    234 
    235         f, t0 = print_job(self, "Transforming")
    236 
--> 237         out = self._predict(X, 'transform', **kwargs)
        out = undefined
        self._predict = <bound method Sequential._predict of Sequential(...n=True)])],
   verbose=0)],
      verbose=False)>
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        kwargs = {}
    238 
    239         if self.verbose:
    240             print_time(t0, "{:<35}".format("Transform complete"),
    241                        file=f, flush=True)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/ensemble/base.py in _predict(self=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), job='transform', **kwargs={})
    261             data.
    262         """
    263         r = kwargs.pop('return_preds', True)
    264         with ParallelProcessing(self.backend, self.n_jobs,
    265                                 max(self.verbose - 4, 0)) as manager:
--> 266             out = manager.stack(self, job, X, return_preds=r, **kwargs)
        out = undefined
        manager.stack = <bound method ParallelProcessing.stack of <mlens.parallel.backend.ParallelProcessing object>>
        self = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        job = 'transform'
        X = array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])
        r = True
        kwargs = {}
    267 
    268         if not isinstance(out, list):
    269             out = [out]
    270         out = [p.squeeze() for p in out]

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in stack(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), job='transform', X=array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]]), y=None, path=None, return_preds=True, warm_start=False, split=True, **kwargs={})
    668             Prediction array(s).
    669         """
    670         out = self.initialize(
    671             job=job, X=X, y=y, path=path, warm_start=warm_start,
    672             return_preds=return_preds, split=split, stack=True)
--> 673         return self.process(caller=caller, out=out, **kwargs)
        self.process = <bound method ParallelProcessing.process of <mlens.parallel.backend.ParallelProcessing object>>
        caller = Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False)
        out = {}
        kwargs = {}
    674 
    675     def process(self, caller, out, **kwargs):
    676         """Process job.
    677 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in process(self=<mlens.parallel.backend.ParallelProcessing object>, caller=Sequential(backend='threading', dtype=<class 'nu...on=True)])],
   verbose=0)],
      verbose=False), out=None, **kwargs={})
    713                       backend=self.backend) as parallel:
    714 
    715             for task in caller:
    716                 self.job.clear()
    717 
--> 718                 self._partial_process(task, parallel, **kwargs)
        self._partial_process = <bound method ParallelProcessing._partial_proces...lens.parallel.backend.ParallelProcessing object>>
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        parallel = Parallel(n_jobs=-1)
        kwargs = {}
    719 
    720                 if task.name in return_names:
    721                     out.append(self.get_preds(dtype=_dtype(task)))
    722 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/backend.py in _partial_process(self=<mlens.parallel.backend.ParallelProcessing object>, task=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), parallel=Parallel(n_jobs=-1), **kwargs={})
    734         task.setup(self.job.predict_in, self.job.targets, self.job.job)
    735 
    736         if not task.__no_output__:
    737             self._gen_prediction_array(task, self.job.job, self.__threading__)
    738 
--> 739         task(self.job.args(**kwargs), parallel=parallel)
        task = Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0)
        self.job.args = <bound method Job.args of <mlens.parallel.backend.Job object>>
        kwargs = {}
        parallel = Parallel(n_jobs=-1)
    740 
    741         if not task.__no_output__ and getattr(task, 'n_feature_prop', 0):
    742             self._propagate_features(task)
    743 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/layer.py in __call__(self=Layer(backend='threading', dtype=<class 'numpy.f...='sc', raise_on_exception=True)])],
   verbose=0), args={'auxiliary': {'P': None, 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}, 'dir': [('sc.0.1', <mlens.parallel.learner.IndexedEstimator object>), ('sc.0.2', <mlens.parallel.learner.IndexedEstimator object>)], 'job': 'transform', 'main': {'P': array([[2.60052562e-01, 1.77754706e-03, 5.693393... 1.20693236e-04, 9.98786032e-01]], dtype=float32), 'X': array([[ -0.7725007 ,   0.13594785,  -5.245197  ...5.025976  ,
        -21.679056  ,   0.        ]])}}, parallel=Parallel(n_jobs=-1))
    147         if self.verbose >= 2:
    148             safe_print(msg.format('Learners ...'), file=f, end=e2)
    149             t1 = time()
    150 
    151         parallel(delayed(sublearner, not _threading)()
--> 152                  for learner in self.learners
        self.learners = [Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None), Learner(attr='predict_proba', backend='threading...a=True, raise_on_exception=True,
    scorer=None)]
    153                  for sublearner in learner(args, 'main'))
    154 
    155         if self.verbose >= 2:
    156             print_time(t1, 'done', file=f)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=-1), iterable=<generator object Layer.__call__.<locals>.<genexpr>>)
    788             if pre_dispatch == "all" or n_jobs == 1:
    789                 # The iterable was consumed all at once by the above for loop.
    790                 # No need to wait for async callbacks to trigger to
    791                 # consumption.
    792                 self._iterating = False
--> 793             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=-1)>
    794             # Make sure that we get a last message telling us we are done
    795             elapsed_time = time.time() - self._start_time
    796             self._print('Done %3i out of %3i | elapsed: %s finished',
    797                         (len(self._output), len(self._output),

---------------------------------------------------------------------------
Sub-process traceback:
---------------------------------------------------------------------------
ValueError                                         Tue Oct 11 15:54:29 2022
PID: 88346Python 3.7.12: /home/bastian/.conda/envs/machine_learning/bin/python
...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in __call__(self=<mlens.externals.joblib.parallel.BatchedCalls object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        self.items = [(<mlens.parallel.learner.SubLearner object>, (), {})]
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
    130     def __init__(self, iterator_slice):
    131         self.items = list(iterator_slice)
    132         self._size = len(self.items)
    133 
    134     def __call__(self):
--> 135         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <mlens.parallel.learner.SubLearner object>
        args = ()
        kwargs = {}
    136 
    137     def __len__(self):
    138         return self._size
    139 

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in __call__(self=<mlens.parallel.learner.SubLearner object>)
    119         else:
    120             self.processing_index = ''
    121 
    122     def __call__(self):
    123         """Launch job"""
--> 124         return getattr(self, self.job)()
        self = <mlens.parallel.learner.SubLearner object>
        self.job = 'transform'
    125 
    126     def fit(self, path=None):
    127         """Fit sub-learner"""
    128         if path is None:

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in transform(self=<mlens.parallel.learner.SubLearner object>, path=None)
    162             f = "stdout" if self.verbose < 10 - 3 else "stderr"
    163             print_time(t0, msg, file=f)
    164 
    165     def transform(self, path=None):
    166         """Predict with sublearner"""
--> 167         return self.predict(path)
        self.predict = <bound method SubLearner.predict of <mlens.parallel.learner.SubLearner object>>
        path = None
    168 
    169     def _fit(self, transformers):
    170         """Sub-routine to fit sub-learner"""
    171         xtemp, ytemp = slice_array(self.in_array, self.targets, self.in_index)

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in predict(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    152     def predict(self, path=None):
    153         """Predict with sublearner"""
    154         if path is None:
    155             path = self.path
    156         t0 = time()
--> 157         transformers = self._load_preprocess(path)
        transformers = undefined
        self._load_preprocess = <bound method SubLearner._load_preprocess of <mlens.parallel.learner.SubLearner object>>
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
    158 
    159         self._predict(transformers, False)
    160         if self.verbose:
    161             msg = "{:<30} {}".format(self.name_index, "done")

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/learner.py in _load_preprocess(self=<mlens.parallel.learner.SubLearner object>, path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)])
    180         self.fit_time_ = time() - t0
    181 
    182     def _load_preprocess(self, path):
    183         """Load preprocessing pipeline"""
    184         if self.preprocess is not None:
--> 185             obj = load(path, self.preprocess_index, self.raise_on_exception)
        obj = undefined
        path = [('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)]
        self.preprocess_index = 'sc.0.2'
        self.raise_on_exception = True
    186             return obj.estimator
    187         return
    188 
    189     def _predict(self, transformers, score_preds):

...........................................................................
/home/bastian/.conda/envs/machine_learning/lib/python3.7/site-packages/mlens/parallel/_base_functions.py in load(path=[('sc.0.0', <mlens.parallel.learner.IndexedEstimator object>)], name='sc.0.2', raise_on_exception=True)
     24         obj = _load(f, raise_on_exception)
     25     elif isinstance(path, list):
     26         obj = [tup[1] for tup in path if tup[0] == name]
     27         if not obj:
     28             raise ValueError(
---> 29                 "No preprocessing pipeline in cache. Auxiliary Transformer "
     30                 "have not cached pipelines, or cached to another sub-cache.")
     31         elif not len(obj) == 1:
     32             raise ValueError(
     33                 "Could not load unique preprocessing pipeline. "

ValueError: No preprocessing pipeline in cache. Auxiliary Transformer have not cached pipelines, or cached to another sub-cache.
___________________________________________________________________________
___________________________________________________________________________
bastian-f commented 1 year ago

I don't know if it helps, but if I put an empty dictionary as param_dicts, I get warnings like this:

UserWarning: No valid parameters found for class.svc. Will fit and score once with given parameter settings.

But then it works. Of course, without tuning the metalearners.