Python sklearn.cross_validation() Examples

def _cv_len(cv, X, y):
    """This method computes the length of a cross validation
    object, agnostic of whether sklearn-0.17 or sklearn-0.18
    is being used.

    Parameters
    ----------

    cv : `sklearn.cross_validation._PartitionIterator` or `sklearn.model_selection.BaseCrossValidator`
        The cv object from which to extract length. If using
        sklearn-0.17, this can be computed by calling `len` on
        ``cv``, else it's computed with `cv.get_n_splits(X, y)`.

    X : pd.DataFrame or np.ndarray, shape(n_samples, n_features)
        The dataframe or np.ndarray being fit in the grid search.

    y : np.ndarray, shape(n_samples,)
        The target being fit in the grid search.

    Returns
    -------

    int
    """
    return len(cv) if not SK18 else cv.get_n_splits(X, y) 

def gen_crossval_idxs(problem, n_folds=2):
        y = problem.ds.target
        rng = 43432
        if hasattr(problem.ds, 'nids'):
            # Ensure that an individual does not appear in both the train
            # and the test dataset
            from ibeis_cnn.dataset import stratified_kfold_label_split
            labels = problem.ds.nids
            _iter = stratified_kfold_label_split(y, labels, n_folds=n_folds, rng=rng)
        else:
            xvalkw = dict(n_folds=n_folds, shuffle=True, random_state=rng)
            import sklearn.cross_validation
            skf = sklearn.cross_validation.StratifiedKFold(y, **xvalkw)
            _iter = skf
            #import sklearn.model_selection
            #skf = sklearn.model_selection.StratifiedKFold(**xvalkw)
            #_iter = skf.split(X=np.empty(len(y)), y=y)
        msg = 'cross-val test on %s' % (problem.ds.name)
        progiter = ut.ProgIter(_iter, length=n_folds, lbl=msg)
        for train_idx, test_idx in progiter:
            yield train_idx, test_idx


# @ut.reloadable_class 

def _set_cv(cv, X, y, classifier):
    """This method returns either a `sklearn.cross_validation._PartitionIterator` or 
    `sklearn.model_selection.BaseCrossValidator` depending on whether sklearn-0.17
    or sklearn-0.18 is being used.

    Parameters
    ----------

    cv : int, `_PartitionIterator` or `BaseCrossValidator`
        The CV object or int to check. If an int, will be converted
        into the appropriate class of crossvalidator.

    X : pd.DataFrame or np.ndarray, shape(n_samples, n_features)
        The dataframe or np.ndarray being fit in the grid search.

    y : np.ndarray, shape(n_samples,)
        The target being fit in the grid search.

    classifier : bool
        Whether the estimator being fit is a classifier

    Returns
    -------

    `_PartitionIterator` or `BaseCrossValidator`
    """
    return check_cv(cv, X, y, classifier) if not SK18 else check_cv(cv, y, classifier) 

def testdata_smk(*args, **kwargs):
    """
    >>> from ibeis.algo.smk.smk_pipeline import *  # NOQA
    >>> kwargs = {}
    """
    import ibeis
    import sklearn
    import sklearn.cross_validation
    # import sklearn.model_selection
    ibs, aid_list = ibeis.testdata_aids(defaultdb='PZ_MTEST')
    nid_list = np.array(ibs.annots(aid_list).nids)
    rng = ut.ensure_rng(0)
    xvalkw = dict(n_folds=4, shuffle=False, random_state=rng)

    skf = sklearn.cross_validation.StratifiedKFold(nid_list, **xvalkw)
    train_idx, test_idx = six.next(iter(skf))
    daids = ut.take(aid_list, train_idx)
    qaids = ut.take(aid_list, test_idx)

    config = {
        'num_words': 1000,
    }
    config.update(**kwargs)
    qreq_ = SMKRequest(ibs, qaids, daids, config)
    smk = qreq_.smk
    #qreq_ = ibs.new_query_request(qaids, daids, cfgdict={'pipeline_root': 'smk', 'proot': 'smk'})
    #qreq_ = ibs.new_query_request(qaids, daids, cfgdict={})
    return ibs, smk, qreq_ 

def _set_cv(cv, estimator=None, X=None, y=None):
        """Set the default CV depending on whether clf
           is classifier/regressor."""
        # Detect whether classification or regression
        if estimator in ['classifier', 'regressor']:
            est_is_classifier = estimator == 'classifier'
        else:
            est_is_classifier = is_classifier(estimator)
        # Setup CV
        if check_version('sklearn', '0.18'):
            from sklearn import model_selection as models
            from sklearn.model_selection import (check_cv,
                                                 StratifiedKFold, KFold)
            if isinstance(cv, (int, np.int)):
                XFold = StratifiedKFold if est_is_classifier else KFold
                cv = XFold(n_splits=cv)
            elif isinstance(cv, str):
                if not hasattr(models, cv):
                    raise ValueError('Unknown cross-validation')
                cv = getattr(models, cv)
                cv = cv()
            cv = check_cv(cv=cv, y=y, classifier=est_is_classifier)
        else:
            from sklearn import cross_validation as models
            from sklearn.cross_validation import (check_cv,
                                                  StratifiedKFold, KFold)
            if isinstance(cv, (int, np.int)):
                if est_is_classifier:
                    cv = StratifiedKFold(y=y, n_folds=cv)
                else:
                    cv = KFold(n=len(y), n_folds=cv)
            elif isinstance(cv, str):
                if not hasattr(models, cv):
                    raise ValueError('Unknown cross-validation')
                cv = getattr(models, cv)
                if cv.__name__ not in ['KFold', 'LeaveOneOut']:
                    raise NotImplementedError('CV cannot be defined with str'
                                              ' for sklearn < .017.')
                cv = cv(len(y))
            cv = check_cv(cv=cv, X=X, y=y, classifier=est_is_classifier)

        # Extract train and test set to retrieve them at predict time
        if hasattr(cv, 'split'):
            cv_splits = [(train, test) for train, test in
                         cv.split(X=np.zeros_like(y), y=y)]
        else:
            # XXX support sklearn.cross_validation cv
            cv_splits = [(train, test) for train, test in cv]

        if not np.all([len(train) for train, _ in cv_splits]):
            raise ValueError('Some folds do not have any train epochs.')

        return cv, cv_splits