jgrid.py 文件源码

def cv_LinearRegression_ci(xM, yV, n_folds=5, scoring='median_absolute_error', disp=False):
    """
    metrics.explained_variance_score(y_true, y_pred)    Explained variance regression score function
    metrics.mean_absolute_error(y_true, y_pred) Mean absolute error regression loss
    metrics.mean_squared_error(y_true, y_pred[, ...])   Mean squared error regression loss
    metrics.median_absolute_error(y_true, y_pred)   Median absolute error regression loss
    metrics.r2_score(y_true, y_pred[, ...]) R^2 (coefficient of determination) regression score function.
    """

    if disp:
        print(xM.shape, yV.shape)

    clf = linear_model.LinearRegression()
    kf5_c = model_selection.KFold(n_splits=n_folds, shuffle=True)
    kf5 = kf5_c.split(xM)

    cv_score_l = list()
    ci_l = list()
    for train, test in kf5:
        # clf.fit( xM[train,:], yV[train,:])
        # yV is vector but not a metrix here. Hence, it should be treated as a
        # vector
        clf.fit(xM[train, :], yV[train])

        yVp_test = clf.predict(xM[test, :])

        # Additionally, coef_ and intercept_ are stored.
        ci_l.append((clf.coef_, clf.intercept_))
        if scoring == 'median_absolute_error':
            cv_score_l.append(
                metrics.median_absolute_error(yV[test], yVp_test))
        else:
            raise ValueError("{} scoring is not supported.".format(scoring))

    if disp:  # Now only this flag is on, the output will be displayed.
        print('{}: mean, std -->'.format(scoring),
              np.mean(cv_score_l), np.std(cv_score_l))

    return cv_score_l, ci_l