features.py 文件源码

def remove_lv_features(model, X):
    r"""Remove low-variance features.

    Parameters
    ----------
    model : alphapy.Model
        Model specifications for removing features.
    X : numpy array
        The feature matrix.

    Returns
    -------
    X_reduced : numpy array
        The reduced feature matrix.

    References
    ----------
    You can find more information on low-variance feature selection here [LV]_.

    .. [LV] http://scikit-learn.org/stable/modules/feature_selection.html#variance-threshold

    """

    logger.info("Removing Low-Variance Features")

    # Extract model parameters

    lv_remove = model.specs['lv_remove']
    lv_threshold = model.specs['lv_threshold']
    predict_mode = model.specs['predict_mode']

    # Remove low-variance features

    if lv_remove:
        logger.info("Low-Variance Threshold  : %.2f", lv_threshold)
        logger.info("Original Feature Count  : %d", X.shape[1])
        if not predict_mode:
            selector = VarianceThreshold(threshold=lv_threshold)
            selector.fit(X)
            support = selector.get_support()
            model.feature_map['lv_support'] = support
        else:
            support = model.feature_map['lv_support']
        X_reduced = X[:, support]
        logger.info("Reduced Feature Count   : %d", X_reduced.shape[1])
    else:
        X_reduced = X
        logger.info("Skipping Low-Variance Features")

    return X_reduced