Predict Student Performance - baseline学习

已于 2023-07-21 15:51:52 修改
阅读量207 收藏
点赞数
分类专栏： 数据竞赛 文章标签： python 人工智能 深度学习
于 2023-05-14 22:51:54 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_38812492/article/details/130672881
版权

关注我的公众号YueTan进行交流探讨
欢迎关注数据比赛方案仓库 https://github.com/hongyingyue/Competition-solutions

通过学习以上baseline进行学习

  • xgboost版本也很重要，从1.4升级到1.6后，能够提升0.08

背景

针对某个level_group的特征，其中把train_df[‘event_name’]长变宽数据，进行提取特征

# reference: https://www.kaggle.com/code/cdeotte/random-forest-baseline-0-664/notebook
def feature_engineer(train):
    dfs = []
    for c in count_var:
        tmp = train.groupby(['session_id','level_group'])[c].agg('nunique')
        tmp.name = tmp.name + '_nunique'
        dfs.append(tmp)
    for c in mean_var:
        tmp = train.groupby(['session_id','level_group'])[c].agg('mean')
        dfs.append(tmp)
    for c in event_var:
        tmp = train.groupby(['session_id','level_group'])[c].agg('sum')
        tmp.name = tmp.name + '_sum'
        dfs.append(tmp)
    df = pd.concat(dfs,axis=1)
    df = df.fillna(-1)
    df = df.reset_index()
    df = df.set_index('session_id')
    return df

目标: 由于一个level_group有多个问题，因此针对每个level_group建立的特征分布用不同模型去拟合问题

train_x = df_tr.iloc[train_index]
train_x = train_x.loc[train_x.level_group == grp]
train_users = train_x.index.values
train_y = train_label.loc[train_label.q==t].set_index('session').loc[train_users]

阈值：针对预测提交为类别的任务，阈值非常关键

scores = []; thresholds = []
best_score = 0; best_threshold = 0

for threshold in np.arange(0.4,0.81,0.01):
    print(f'{threshold:.02f}, ',end='')
    preds = (oof.values.reshape((-1))>threshold).astype('int')
    m = f1_score(true.values.reshape((-1)), preds, average='macro')   
    scores.append(m)
    thresholds.append(threshold)
    if m>best_score:
        best_score = m
        best_threshold = threshold

polars

https://www.kaggle.com/code/pourchot/simple-xgb
其中，最后一个baseline采用polars编写，在数据越来越大的今天，polars可以加速cpu大数据量的计算

特征

columns = [

    pl.col("page").cast(pl.Float32),
    (
        (pl.col("elapsed_time") - pl.col("elapsed_time").shift(1)) 
         .fill_null(0)
         .clip(0, 1e9)
         .over(["session_id", "level_group"])
         .alias("elapsed_time_diff")
    ),
    (
        (pl.col("screen_coor_x") - pl.col("screen_coor_x").shift(1)) 
         .abs()
         .over(["session_id", "level_group"])
        .alias("location_x_diff") 
    ),
    (
        (pl.col("screen_coor_y") - pl.col("screen_coor_y").shift(1)) 
         .abs()
         .over(["session_id", "level_group"])
        .alias("location_y_diff") 
    ),
    pl.col("fqid").fill_null("fqid_None"),
    pl.col("text_fqid").fill_null("text_fqid_None")
]

特征解析

# 单特征
columns = [
    pl.col("page").cast(pl.Float32),
    (
        (pl.col("elapsed_time") - pl.col("elapsed_time").shift(1))
        .fill_null(0)
        .clip(0, 1e9)
        .over(["session_id", "level"])
        .alias("elapsed_time_diff")
    ),
    (
        (pl.col("screen_coor_x") - pl.col("screen_coor_x").shift(1))
        .abs()
        .over(["session_id", "level"])
    ),
    (
        (pl.col("screen_coor_y") - pl.col("screen_coor_y").shift(1))
        .abs()
        .over(["session_id", "level"])
    ),
    pl.col("fqid").fill_null("fqid_None"),
    pl.col("text_fqid").fill_null("text_fqid_None")

]

group 特征

def feature_engineer(x, grp, use_extra, feature_suffix):
    aggs = [
        pl.col("index").count().alias(f"session_number_{feature_suffix}"),  # session长度

        *[pl.col(c).drop_nulls().n_unique().alias(f"{c}_unique_{feature_suffix}") for c in CATS], # 类别的nunique

        *[pl.col(c).std().alias(f"{c}_std_{feature_suffix}") for c in NUMS],  # 数量的统计
        *[pl.col(c).mean().alias(f"{c}_mean_{feature_suffix}") for c in NUMS],
        *[pl.col(c).min().alias(f"{c}_min_{feature_suffix}") for c in NUMS],
        *[pl.col(c).max().alias(f"{c}_max_{feature_suffix}") for c in NUMS],
        *[pl.col(c).sum().alias(f"{c}_sum_{feature_suffix}") for c in NUMS],

        *[pl.col("fqid").filter(pl.col("fqid") == c).count().alias(f"{c}_fqid_counts{feature_suffix}")  # fqid 精细展开的每一个count
          for c in fqid_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("fqid") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for  # fqid下的时间差的，std
          c in fqid_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("fqid") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for
          c in fqid_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("fqid") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for
          c in fqid_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("fqid") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for
          c in fqid_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("fqid") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for
          c in fqid_lists],


        *[pl.col("text_fqid").filter(pl.col("text_fqid") == c).count().alias(f"{c}_text_fqid_counts{feature_suffix}") for  # text_fqid的精细展开的count
          c in text_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("text_fqid") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for  # text_fqid的每一个的耗时的std
          c in text_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("text_fqid") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for
          c in text_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("text_fqid") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for
          c in text_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("text_fqid") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for
          c in text_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("text_fqid") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for
          c in text_lists],

        *[pl.col("room_fqid").filter(pl.col("room_fqid") == c).count().alias(f"{c}_room_fqid_counts{feature_suffix}")  # room_fqid的精细展开的count
          for c in room_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("room_fqid") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for
          c in room_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("room_fqid") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for
          c in room_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("room_fqid") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for
          c in room_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("room_fqid") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for
          c in room_lists],
        *[pl.col("elapsed_time_diff").filter(pl.col("room_fqid") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for
          c in room_lists],

        *[pl.col("event_name").filter(pl.col("event_name") == c).count().alias(f"{c}_event_name_counts{feature_suffix}")  # event
          for c in event_name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("event_name") == c).std().alias(f"{c}_ET_std_{feature_suffix}")for
          c in event_name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("event_name") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for
          c in event_name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("event_name") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for
          c in event_name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("event_name") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for
          c in event_name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("event_name") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for
          c in event_name_feature],

        *[pl.col("name").filter(pl.col("name") == c).count().alias(f"{c}_name_counts{feature_suffix}") for c in  # name
          name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("name") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for c in
          name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("name") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for c in
          name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("name") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for c in
          name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("name") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for c in
          name_feature],
        *[pl.col("elapsed_time_diff").filter(pl.col("name") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for c in
          name_feature],

        *[pl.col("level").filter(pl.col("level") == c).count().alias(f"{c}_LEVEL_count{feature_suffix}") for c in LEVELS],  # level
        *[pl.col("elapsed_time_diff").filter(pl.col("level") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for c in
          LEVELS],
        *[pl.col("elapsed_time_diff").filter(pl.col("level") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for c in
          LEVELS],
        *[pl.col("elapsed_time_diff").filter(pl.col("level") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for c in
          LEVELS],
        *[pl.col("elapsed_time_diff").filter(pl.col("level") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for c in
          LEVELS],
        *[pl.col("elapsed_time_diff").filter(pl.col("level") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for c in
          LEVELS],

        *[pl.col("level_group").filter(pl.col("level_group") == c).count().alias(f"{c}_LEVEL_group_count{feature_suffix}") for c in
          level_groups],
        *[pl.col("elapsed_time_diff").filter(pl.col("level_group") == c).std().alias(f"{c}_ET_std_{feature_suffix}") for c in
          level_groups],
        *[pl.col("elapsed_time_diff").filter(pl.col("level_group") == c).mean().alias(f"{c}_ET_mean_{feature_suffix}") for c in
          level_groups],
        *[pl.col("elapsed_time_diff").filter(pl.col("level_group") == c).max().alias(f"{c}_ET_max_{feature_suffix}") for c in
          level_groups],
        *[pl.col("elapsed_time_diff").filter(pl.col("level_group") == c).min().alias(f"{c}_ET_min_{feature_suffix}") for c in
          level_groups],
        *[pl.col("elapsed_time_diff").filter(pl.col("level_group") == c).sum().alias(f"{c}_ET_sum_{feature_suffix}") for c in
          level_groups],

        *[pl.col("index").filter((pl.col("level") == c) & (pl.col('room_fqid') == d)).count().alias(f"{c}{d}_level_room_count{feature_suffix}") for c in LEVELS for d in room_lists],


    ]

    df = x.groupby(['session_id'], maintain_order=True).agg(aggs).sort("session_id")

    if use_extra:
        if grp == '5-12':
            aggs = [
                pl.col("elapsed_time").filter((pl.col("text")=="Here's the log book.")
                                              |(pl.col("fqid")=='logbook.page.bingo'))
                    .apply(lambda s: s.max()-s.min()).alias("logbook_bingo_duration"),
                pl.col("index").filter(
                    (pl.col("text") == "Here's the log book.") | (pl.col("fqid") == 'logbook.page.bingo')).apply(
                    lambda s: s.max() - s.min()).alias("logbook_bingo_indexCount"),
                pl.col("elapsed_time").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'reader')) | (
                                pl.col("fqid") == "reader.paper2.bingo")).apply(lambda s: s.max() - s.min()).alias(
                    "reader_bingo_duration"),
                pl.col("index").filter(((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'reader')) | (
                            pl.col("fqid") == "reader.paper2.bingo")).apply(lambda s: s.max() - s.min()).alias(
                    "reader_bingo_indexCount"),
                pl.col("elapsed_time").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'journals')) | (
                                pl.col("fqid") == "journals.pic_2.bingo")).apply(lambda s: s.max() - s.min()).alias(
                    "journals_bingo_duration"),
                pl.col("index").filter(((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'journals')) | (
                            pl.col("fqid") == "journals.pic_2.bingo")).apply(lambda s: s.max() - s.min()).alias(
                    "journals_bingo_indexCount"),
            ]
            tmp = x.groupby(["session_id"], maintain_order=True).agg(aggs).sort("session_id")
            df = df.join(tmp, on="session_id", how='left')

        if grp == '13-22':
            aggs = [
                pl.col("elapsed_time").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'reader_flag')) | (
                                pl.col("fqid") == "tunic.library.microfiche.reader_flag.paper2.bingo")).apply(
                    lambda s: s.max() - s.min() if s.len() > 0 else 0).alias("reader_flag_duration"),
                pl.col("index").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'reader_flag')) | (
                                pl.col("fqid") == "tunic.library.microfiche.reader_flag.paper2.bingo")).apply(
                    lambda s: s.max() - s.min() if s.len() > 0 else 0).alias("reader_flag_indexCount"),
                pl.col("elapsed_time").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'journals_flag')) | (
                                pl.col("fqid") == "journals_flag.pic_0.bingo")).apply(
                    lambda s: s.max() - s.min() if s.len() > 0 else 0).alias("journalsFlag_bingo_duration"),
                pl.col("index").filter(
                    ((pl.col("event_name") == 'navigate_click') & (pl.col("fqid") == 'journals_flag')) | (
                                pl.col("fqid") == "journals_flag.pic_0.bingo")).apply(
                    lambda s: s.max() - s.min() if s.len() > 0 else 0).alias("journalsFlag_bingo_indexCount")
            ]
            tmp = x.groupby(["session_id"], maintain_order=True).agg(aggs).sort("session_id")
            df = df.join(tmp, on="session_id", how='left')

    return df.to_pandas()

时间特征

def time_feature(train):
    train["year"] = train["session_id"].apply(lambda x: int(str(x)[:2])).astype(np.uint8)
    train["month"] = train["session_id"].apply(lambda x: int(str(x)[2:4])+1).astype(np.uint8)
    train["day"] = train["session_id"].apply(lambda x: int(str(x)[4:6])).astype(np.uint8)
    train["hour"] = train["session_id"].apply(lambda x: int(str(x)[6:8])).astype(np.uint8)
    train["minute"] = train["session_id"].apply(lambda x: int(str(x)[8:10])).astype(np.uint8)
    train["second"] = train["session_id"].apply(lambda x: int(str(x)[10:12])).astype(np.uint8)


    return train

base-nn

https://www.kaggle.com/code/abaojiang/lb-0-694-tconv-with-4-features-training-part

据称只使用4个特征

  • Difference of elapsed_time
  • event_name
  • name
  • room_fqid

业务过程

  • https://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/384796

结合上面的帖子，和某个用户行为来看游戏是如何进行的
尤其要注意区分几个level之间，以及理解下如何算答对答错的

一开始是： 在这里插入图片描述

YueTann
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
专栏目录
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

YueTann

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值