Riiid Answer Correctness Prediction

Riiid Answer Correctness Prediction - lgb baseline 学习

news2024/10/5 23:27:21

链接

特征

features = ['user_questions', 'user_mean', 'content_questions', 'content_mean', 'prior_question_elapsed_time']

user_df = train[train.answered_correctly != -1].groupby('user_id').agg({'answered_correctly': ['count', 'mean']}).reset_index()
user_df.columns = ['user_id', 'user_questions', 'user_mean']

content_df = train[train.answered_correctly != -1].groupby('content_id').agg({'answered_correctly': ['count', 'mean']}).reset_index()
content_df.columns = ['content_id', 'content_questions', 'content_mean']

train['prior_question_elapsed_time'].fillna(mean_prior, inplace = True)

得分： 0.75

使用的五个特征含义分别是

用户回答所有问题的个数
用户回答问题的正确率
问题被回答的个数总和
问题被回答的正确率
用户在上一个question bundle中平均消耗时间

在这里插入图片描述

特征2

链接

FEATS = ['answered_correctly_avg_u', 'answered_correctly_sum_u', 'count_u', 'answered_correctly_avg_c', 'part', 'prior_question_had_explanation', 'prior_question_elapsed_time']


def add_user_feats(df, answered_correctly_sum_u_dict, count_u_dict):
    acsu = np.zeros(len(df), dtype=np.int32)
    cu = np.zeros(len(df), dtype=np.int32)
    for cnt,row in enumerate(tqdm(df[['user_id','answered_correctly']].values)):
        acsu[cnt] = answered_correctly_sum_u_dict[row[0]]
        cu[cnt] = count_u_dict[row[0]]
        answered_correctly_sum_u_dict[row[0]] += row[1]
        count_u_dict[row[0]] += 1
    user_feats_df = pd.DataFrame({'answered_correctly_sum_u':acsu, 'count_u':cu})
    user_feats_df['answered_correctly_avg_u'] = user_feats_df['answered_correctly_sum_u'] / user_feats_df['count_u']
    df = pd.concat([df, user_feats_df], axis=1)
    return df

# answered correctly average for each content
content_df = train[['content_id','answered_correctly']].groupby(['content_id']).agg(['mean']).reset_index()
content_df.columns = ['content_id', 'answered_correctly_avg_c']

# changing dtype to avoid lightgbm error
train['prior_question_had_explanation'] = train.prior_question_had_explanation.fillna(False).astype('int8')

得分 0.76

使用的7个特征是

使用的特征是增量特征，截止到目前该用户的回答正确率
截止到目前该用户回答正确的题目个数
截止到目前该用户回答问题所有个数
content在所有回答中的正确率
part
是否有解释
平均消耗时间

特征3

链接

FEATURES = ['prior_question_elapsed_time', 'prior_question_had_explanation', 'part',
	 'answered_correctly_u_avg', 'elapsed_time_u_avg', 'explanation_u_avg',
                'answered_correctly_q_avg', 'elapsed_time_q_avg', 'explanation_q_avg',
                 'answered_correctly_uq_count', 'timestamp_u_recency_1', 'timestamp_u_recency_2', 'timestamp_u_recency_3', 
                'timestamp_u_incorrect_recency']

使用的特征14个

在这里插入图片描述

特征4

https://www.kaggle.com/code/a763337092/lgb1215

features_dict = {
    #'user_id',
    'timestamp':'float16',#
    'user_interaction_count':'int16',
    'user_interaction_timestamp_mean':'float32',
    'lagtime':'float32',#
    'lagtime2':'float32',
    'lagtime3':'float32',
    #'lagtime_mean':'int32',
    'content_id':'int16',
    'task_container_id':'int16',
    'user_lecture_sum':'int16',#
    'user_lecture_lv':'float16',##
    'prior_question_elapsed_time':'float32',#
    'delta_prior_question_elapsed_time':'int32',#
    'user_correctness':'float16',#
    'user_uncorrect_count':'int16',#
    'user_correct_count':'int16',#
    #'content_correctness':'float16',
    'content_correctness_std':'float16',
    'content_correct_count':'int32',
    'content_uncorrect_count':'int32',#
    'content_elapsed_time_mean':'float16',
    'content_had_explanation_mean':'float16',
    'content_explation_false_mean':'float16',
    'content_explation_true_mean':'float16',
    'task_container_correctness':'float16',
    'task_container_std':'float16',
    'task_container_cor_count':'int32',#
    'task_container_uncor_count':'int32',#
    'attempt_no':'int8',#
    'part':'int8',
    'part_correctness_mean':'float16',
    'part_correctness_std':'float16',
    'part_uncor_count':'int32',
    'part_cor_count':'int32',
    'tags0': 'int8',
    'tags1': 'int8',
    'tags2': 'int8',
    'tags3': 'int8',
    'tags4': 'int8',
    'tags5': 'int8',
   # 'tags6': 'int8',
   # 'tags7': 'int8',
#     'tags0_correctness_mean':'float16',
#     'tags1_correctness_mean':'float16',
#     'tags2_correctness_mean':'float16',
#     'tags4_correctness_mean':'float16',
#     'bundle_id':'int16',
#     'bundle_correctness_mean':'float16',
#     'bundle_uncor_count':'int32',
#     'bundle_cor_count':'int32',
    'part_bundle_id':'int32',
    'content_sub_bundle':'int8',
    'prior_question_had_explanation':'int8',
    'explanation_mean':'float16', #
    #'explanation_var',#
    'explanation_false_count':'int16',#
    'explanation_true_count':'int16',#
   # 'community':'int8',
#     'part_1',
#     'part_2',
#     'part_3',
#     'part_4',
#     'part_5',
#     'part_6',
#     'part_7',
#     'type_of_concept',
#     'type_of_intention',
#     'type_of_solving_question',
#     'type_of_starter'
}
categorical_columns= [
    #'user_id',
    'content_id',
    'task_container_id',
    'part',
   # 'community',
    'tags0',
    'tags1',
    'tags2',
    'tags3',
    'tags4',
    'tags5',
    #'tags6',
    #'tags7',
    #'bundle_id',
    'part_bundle_id',
    'content_sub_bundle',
    'prior_question_had_explanation', 
#     'part_1',
#     'part_2',
#     'part_3',
#     'part_4',
#     'part_5',
#     'part_6',
#     'part_7',
#     'type_of_concept',
#     'type_of_intention',
#     'type_of_solving_question',
#     'type_of_starter'
]

features=list(features_dict.keys())

在这里插入图片描述