kgrid.py 文件源码

def cv_LinearRegression_ci_pred_full_Ridge( xM, yV, alpha, n_splits = 5, shuffle=True, disp = False):
    """
    Note - scoring is not used. I may used later. Not it is remained for compatibility purpose.
    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)

    # print( 'alpha of Ridge is', alpha)
    clf = linear_model.Ridge( alpha)
    kf5_c = model_selection.KFold( n_splits=n_splits, shuffle=shuffle)
    kf5 = kf5_c.split( xM)

    cv_score_l = list()
    ci_l = list()
    yVp = yV.copy() 
    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,:])
        yVp[test] = yVp_test

        # Additionally, coef_ and intercept_ are stored.        
        ci_l.append( (clf.coef_, clf.intercept_))
        y_a = np.array( yV[test])[:,0]
        yp_a = np.array( yVp_test)[:,0]
        cv_score_l.extend( np.abs(y_a - yp_a).tolist())

    return cv_score_l, ci_l, yVp.A1.tolist()