kgrid.py 文件源码

def cv_LinearRegression_ci( xM, yV, n_splits = 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_splits, 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