这是一个预测收入水平的数据集，通过性别、年龄、教育水平等13个属性来预测收入水平。收入水平分为9个级别，即1-9。
\n训练集的最后一列为类别标签，共14列。测试集共13列。
\n13个属性依次表示：性别、婚姻状况、年龄、教育程度、职业、工作年限、双收入、家庭成员、18岁以下、户主状况、家庭类型、民族类别、语言。\n\n* sample-test.csv为提交示例。\n* test.csv为测试集。\n* train.csv为训练集。", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# 多分类任务\n本次竞赛的目的是能够实现对已给数据集的多分类任务。\n# 赛制介绍\n本次比赛系机器学习方向2017级《机器学习框架》课程内部第一次竞赛。\n#赛程安排\n时间：2019.11.12-2019.11.19\n流程：\n1.每位同学注册一个kaggle账号，并登入，然后打开指定链接，参与比赛每位同学可以查看相应的竞赛要求和数据集。\n2.从该平台下载数据集，本地调试算法，并在该平台上提交结果，提交完成后，即得相应的分数并可以查看公共排名结果。\n\n3.每人每天有且仅有二次提交机会，高分成绩直接覆盖低分成绩。\n\n4.比赛提供标准训练集（含标签），仅供参赛选手训练算法模型；提供标准测试数据集（无标签），供参赛选手提交评测结果参与排名。比赛中严禁使用外部数据集，一经发现，成绩作废。\n\n5.比赛中需要使用代码管理工具对代码进行管理，并在提交结果之后存储当前代码作为提交成绩依据的记录，比赛结束公布最终排名时需提交取得最高成绩的代码。\n\n6.比赛截止时，将对所有参赛队伍代码进行审核，识别并剔除只靠人工标注而没有算法贡献的队伍与使用重复代码参赛的队伍。\n\n7.比赛截止时，将取得最高成绩的代码和对应文档上传至雪梨教育平台对应任务。（注意：文档需有对问题解决过程、难点解决过程和核心代码分析等问题的体现。）\n\n8.比赛结束后，随机抽取20%-50%的学生进行答辩。\n\n9.3次竞赛结束后，根据加权结果颁发盖有学院章的证书和奖品。\n\n# 成绩评定\n1. 最终排名占竞赛成绩50%，相关文档占竞赛成绩50%。\n2. 本次竞赛结束后，取前5名颁发优秀奖，取后5名颁发谦虚奖。", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:
\r\nThe evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:
\r\n\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]
\r\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.
\r\nFor every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).
\r\nThe file should contain a header and have the following format:
\r\nAuthorId,DuplicateAuthorIds", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }
1,1
8,8
9,9 10
10,10 9
etc.