one_way_fs.py 文件源码

def h2o_f_classif(X, feature_names, target_feature):
    """Compute the ANOVA F-value for the provided sample.
    This method is adapted from ``sklearn.feature_selection.f_classif``
    to function on H2OFrames.

    Parameters
    ----------

    X : ``H2OFrame``, shape=(n_samples, n_features)
        The feature matrix. Each feature will be tested 
        sequentially.

    feature_names : array_like (str), optional (default=None)
        The list of names on which to fit the transformer.

    target_feature : str, optional (default=None)
        The name of the target feature (is excluded from the fit)
        for the estimator.


    Returns
    -------

    f : float
        The computed F-value of the test.

    prob : float
        The associated p-value from the F-distribution.
    """
    frame = check_frame(X, copy=False)

    # first, get unique values of y
    y = X[target_feature]
    _, unq = _unq_vals_col(y)

    # if y is enum, make the unq strings..
    unq = unq[_] if not y.isfactor()[0] else [str(i) for i in unq[_]]

    # get the masks
    args = [frame[y == k, :][feature_names] for k in unq]
    f, prob = h2o_f_oneway(*args)
    return f, prob


# The following function is a rewriting (of the sklearn rewriting) of 
# scipy.stats.f_oneway. Contrary to the scipy.stats.f_oneway implementation 
# it does not copy the data while keeping the inputs unchanged. Furthermore,
# contrary to the sklearn implementation, it does not use np.ndarrays, rather
# amending 1d H2OFrames inplace.