002_xgb_holdout_item_812_1.py 文件源码

python
阅读 16 收藏 0 点赞 0 评论 0

项目:Instacart 作者: KazukiOnodera 项目源码 文件源码
def split_build_valid():

    train_user['is_valid'] = np.random.choice([0,1], size=len(train_user), 
                                              p=[1-valid_size, valid_size])
    valid_n = train_user['is_valid'].sum()
    build_n = (train_user.shape[0] - valid_n)

    print('build user:{}, valid user:{}'.format(build_n, valid_n))
    valid_user = train_user[train_user['is_valid']==1].user_id
    is_valid = X_train.user_id.isin(valid_user)

    dbuild = xgb.DMatrix(X_train[~is_valid].drop('user_id', axis=1), y_train[~is_valid])
    dvalid = xgb.DMatrix(X_train[is_valid].drop('user_id', axis=1), label=y_train[is_valid])
    watchlist = [(dbuild, 'build'),(dvalid, 'valid')]

    print('FINAL SHAPE')
    print('dbuild.shape:{}  dvalid.shape:{}\n'.format((dbuild.num_row(), dbuild.num_col()),
                                                      (dvalid.num_row(), dvalid.num_col())))

    return dbuild, dvalid, watchlist

#==============================================================================
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号