xgb_best_script.py 文件源码

def mungeskewed(train, test, numeric_feats):
    ntrain = train.shape[0]
    test['loss'] = 0
    train_test = pd.concat((train, test)).reset_index(drop=True)
    skewed_feats = train[numeric_feats].apply(lambda x: skew(x.dropna()))
    skewed_feats = skewed_feats[skewed_feats > 0.25]
    skewed_feats = skewed_feats.index

    for feats in skewed_feats:
        train_test[feats] = train_test[feats] + 1
        train_test[feats], lam = boxcox(train_test[feats])
    return train_test, ntrain