Problema
Actualmente, el ensamblador apilado tiene su propia configuración para CV. IterativeAlgorithm
llama a la utilidad
El divisor de datos configurado de forma predeterminada en el ensamblador apilado no establece shuffle=True
, lo que podría provocar un rendimiento deficiente si el conjunto de datos de entrada tiene un orden. Tampoco tendrá la misma configuración para otros parámetros como n_folds
, que no es ideal.
Además, esta diferencia nos impide admitir sklearn 0.24.0 . La solución de este problema debería permitirnos admitir esa versión.
Reparar
Hagamos que automl pase su divisor de datos a través de IterativeAlgorithm
al ensamblador apilado.
@ angela97lin ¿tiene sentido mi explicación / hubo alguna razón por la que decidimos no hacer esto cuando estábamos configurando el apilamiento? :)
@dsherry ¡Creo que tu explicación tiene sentido! IIRC cuando estábamos configurando el apilamiento y estábamos tratando de hacerlo más eficiente / hacer que el apilamiento se ejecutara más rápido, queríamos usar por defecto algo que no tuviera demasiados pliegues, de ahí la línea self._default_cv(n_splits=3, random_state=random_state)
donde tomamos el predeterminado especificado por scikit-learn, y codificado n_splits
a 3.
Profundizó un poco más en esto y traté de tejer el método de división de datos utilizado por AutoML con el componente de conjunto apilado. Sin embargo, me encontré con este problema (después de abordar las actualizaciones de API necesarias para que nuestra clase TrainingValidationSplit
funcione):
estimator = WrappedSKClassifier(pipeline=LogisticRegressionBinaryPipeline(parameters={'Imputer':{'categorical_impute_strategy': 'm...Logistic Regression Classifier':{'penalty': 'l2', 'C': 1.0, 'n_jobs': -1, 'multi_class': 'auto', 'solver': 'lbfgs'},}))
X = 0 1 2 3 4
0 0.965469 0.041236 0.028701 0.659165 0.213375
1 0.043831...978 0.079577
48 0.376344 0.920154 0.314640 0.180086 0.197598
49 0.682661 0.046529 0.400513 0.412513 0.751464
y = array([1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0])
<strong i="7">@_deprecate_positional_args</strong>
def cross_val_predict(estimator, X, y=None, *, groups=None, cv=None,
n_jobs=None, verbose=0, fit_params=None,
pre_dispatch='2*n_jobs', method='predict'):
"""Generate cross-validated estimates for each input data point
The data is split according to the cv parameter. Each sample belongs
to exactly one test set, and its prediction is computed with an
estimator fitted on the corresponding training set.
Passing these predictions into an evaluation metric may not be a valid
way to measure generalization performance. Results can differ from
:func:`cross_validate` and :func:`cross_val_score` unless all tests sets
have equal size and the metric decomposes over samples.
Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
estimator : estimator object implementing 'fit' and 'predict'
The object to use to fit the data.
X : array-like of shape (n_samples, n_features)
The data to fit. Can be, for example a list, or an array at least 2d.
y : array-like of shape (n_samples,) or (n_samples, n_outputs), \
default=None
The target variable to try to predict in the case of
supervised learning.
groups : array-like of shape (n_samples,), default=None
Group labels for the samples used while splitting the dataset into
train/test set. Only used in conjunction with a "Group" :term:`cv`
instance (e.g., :class:`GroupKFold`).
cv : int, cross-validation generator or an iterable, default=None
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 5-fold cross validation,
- int, to specify the number of folds in a `(Stratified)KFold`,
- :term:`CV splitter`,
- An iterable yielding (train, test) splits as arrays of indices.
For int/None inputs, if the estimator is a classifier and ``y`` is
either binary or multiclass, :class:`StratifiedKFold` is used. In all
other cases, :class:`KFold` is used.
Refer :ref:`User Guide <cross_validation>` for the various
cross-validation strategies that can be used here.
.. versionchanged:: 0.22
``cv`` default value if None changed from 3-fold to 5-fold.
n_jobs : int, default=None
Number of jobs to run in parallel. Training the estimator and
predicting are parallelized over the cross-validation splits.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
verbose : int, default=0
The verbosity level.
fit_params : dict, defualt=None
Parameters to pass to the fit method of the estimator.
pre_dispatch : int or str, default='2*n_jobs'
Controls the number of jobs that get dispatched during parallel
execution. Reducing this number can be useful to avoid an
explosion of memory consumption when more jobs get dispatched
than CPUs can process. This parameter can be:
- None, in which case all the jobs are immediately
created and spawned. Use this for lightweight and
fast-running jobs, to avoid delays due to on-demand
spawning of the jobs
- An int, giving the exact number of total jobs that are
spawned
- A str, giving an expression as a function of n_jobs,
as in '2*n_jobs'
method : {'predict', 'predict_proba', 'predict_log_proba', \
'decision_function'}, default='predict'
The method to be invoked by `estimator`.
Returns
-------
predictions : ndarray
This is the result of calling `method`. Shape:
- When `method` is 'predict' and in special case where `method` is
'decision_function' and the target is binary: (n_samples,)
- When `method` is one of {'predict_proba', 'predict_log_proba',
'decision_function'} (unless special case above):
(n_samples, n_classes)
- If `estimator` is :term:`multioutput`, an extra dimension
'n_outputs' is added to the end of each shape above.
See Also
--------
cross_val_score : Calculate score for each CV split.
cross_validate : Calculate one or more scores and timings for each CV
split.
Notes
-----
In the case that one or more classes are absent in a training portion, a
default score needs to be assigned to all instances for that class if
``method`` produces columns per class, as in {'decision_function',
'predict_proba', 'predict_log_proba'}. For ``predict_proba`` this value is
0. In order to ensure finite output, we approximate negative infinity by
the minimum finite float value for the dtype in other cases.
Examples
--------
>>> from sklearn import datasets, linear_model
>>> from sklearn.model_selection import cross_val_predict
>>> diabetes = datasets.load_diabetes()
>>> X = diabetes.data[:150]
>>> y = diabetes.target[:150]
>>> lasso = linear_model.Lasso()
>>> y_pred = cross_val_predict(lasso, X, y, cv=3)
"""
X, y, groups = indexable(X, y, groups)
cv = check_cv(cv, y, classifier=is_classifier(estimator))
splits = list(cv.split(X, y, groups))
test_indices = np.concatenate([test for _, test in splits])
if not _check_is_permutation(test_indices, _num_samples(X)):
> raise ValueError('cross_val_predict only works for partitions')
E ValueError: cross_val_predict only works for partitions
../venv/lib/python3.7/site-packages/sklearn/model_selection/_validation.py:845: ValueError
Este es un error que se produce cuando intentamos llamar a:
clf = StackedEnsembleClassifier(input_pipelines=[logistic_regression_binary_pipeline_class(parameters={})], cv=TrainingValidationSplit())
clf.fit(X, y)
La razón de esto es porque scikit-learn valida que el cv pasado es de hecho un método de validación cruzada; no está contento con divisiones individuales como TrainingValidationSplit
donde algunos de los datos nunca estarán en los datos de prueba (ya que solo hay una división).
Como tal, creo que el mejor plan por ahora es hacer lo más fácil para admitir scikit-learn 0.24 y establecer el cv predeterminado shuffle=True
. Podemos revisar esto si creemos que es útil. ¿Pensamientos, @dsherry?
Relacionado: https://stackoverflow.com/questions/41753795/sklearn-timeseriessplit-cross-val-predict-only-works-for-partitions