Select Language

AI社区

公开数据集

微软专业顶石数据集

微软专业顶石数据集

35.53M
367 浏览
0 喜欢
0 次下载
0 条讨论
Business,Education,Software,Finance,Universities and Colleges,Demographics Classification

数据结构 ? 35.53M

    Data Structure ?

    * 以上分析是由系统提取分析形成的结果,具体实际数据为准。

    README.md

    Problem Description ============ - [About the data](#about-the-data) - [Target Variable](#target-variable) - [Submission Format](#submission-format) - [Performance Metric](#performance-metric) - [Features](#features) - [Categories](#categories) - [Example Row](#example-row) ## About the data Your goal is to predict a student's earnings a set number of years after they have enrolled in United States institutions of higher education. The data is compiled from a wide range of sources and [made publicly available by the United States Department of education](https://collegescorecard.ed.gov/). ## Target Variable We're trying to predict the variable `income`, which represents earnings **in thousands of US dollars** a set interval from when the student first enrolled. Submission Format The format for the submission file is two columns with the `row_id` and the `income`. The data type of `income` is a float, **so make sure there is a decimal point in your submission**. For example `0.0` is a valid float. `0` is _not_.
    For example, if you predicted... | row_id | income | |--------|--------| | 2 | 0.0 | | 8 | 0.0 | | 9 | 0.0 | | 10 | 0.0 | | 11 | 0.0 | The first few lines of the `.csv` file that you submit would look like: row_id,income 2,0.0 8,0.0 9,0.0 10,0.0 11,0.0 Performance Metric We're predicting a numeric quantity, so this is a regression problem. To measure regression, we'll use a metric called Root-mean-squared error. It is an error metric, so lower value is better (as opposed to an accuracy metric, where a higher value is better). $$RMSE = qrt{ rac{1}{N} um_{n=1}^{N} (\hat{y}_n - y_n)^2 }$$ Where $\hat{y}_n$ is the predicted earnings and $y_n$ is the actual earnings. The best possible score is 0, but the worst possible score can be infinite. ## Features There are 297 variables in this dataset. Each row in the dataset represents a United States institution of higher education in a specific year. The dataset we are working with covers four particular years, denoted `year_a`, `year_f`, `year_w`, and `year_z` in our dataset. An institution may have a row for all, some, or just for one of the years. We don't provide a unique identifier for an individual institution, just a `row_id` for each row. The variables in the dataset have names that of the form `category__variable`, where `category` is the high level category of the variable (e.g. `academics` or `students`). `variable` is what the specific column contains. Categories - **`academics`** - `program_assoc_agriculture`: Associate degree in Agriculture, Agriculture Operations, And Related Sciences. - `program_assoc_architecture`: Associate degree in Architecture And Related Services. - `program_assoc_biological`: Associate degree in Biological And Biomedical Sciences. - `program_assoc_business_marketing`: Associate degree in Business, Management, Marketing, And Related Support Services. - `program_assoc_communication`: Associate degree in Communication, Journalism, And Related Programs. - `program_assoc_communications_technology`: Associate degree in Communications Technologies/Technicians And Support Services. - `program_assoc_computer`: Associate degree in Computer And Information Sciences And Support Services. - `program_assoc_construction`: Associate degree in Construction Trades. - `program_assoc_education`: Associate degree in Education. - `program_assoc_engineering`: Associate degree in Engineering. - `program_assoc_engineering_technology`: Associate degree in Engineering Technologies And Engineering-Related Fields. - `program_assoc_english`: Associate degree in English Language And Literature/Letters. - `program_assoc_ethnic_cultural_gender`: Associate degree in Area, Ethnic, Cultural, Gender, And Group Studies. - `program_assoc_family_consumer_science`: Associate degree in Family And Consumer Sciences/Human Sciences. - `program_assoc_health`: Associate degree in Health Professions And Related Programs. - `program_assoc_history`: Associate degree in History. - `program_assoc_humanities`: Associate degree in Liberal Arts And Sciences, General Studies And Humanities. - `program_assoc_language`: Associate degree in Foreign Languages, Literatures, And Linguistics. - `program_assoc_legal`: Associate degree in Legal Professions And Studies. - `program_assoc_library`: Associate degree in Library Science. - `program_assoc_mathematics`: Associate degree in Mathematics And Statistics. - `program_assoc_mechanic_repair_technology`: Associate degree in Mechanic And Repair Technologies/Technicians. - `program_assoc_military`: Associate degree in Military Technologies And Applied Sciences. - `program_assoc_multidiscipline`: Associate degree in Multi/Interdisciplinary Studies. - `program_assoc_parks_recreation_fitness`: Associate degree in Parks, Recreation, Leisure, And Fitness Studies. - `program_assoc_personal_culinary`: Associate degree in Personal And Culinary Services. - `program_assoc_philosophy_religious`: Associate degree in Philosophy And Religious Studies. - `program_assoc_physical_science`: Associate degree in Physical Sciences. - `program_assoc_precision_production`: Associate degree in Precision Production. - `program_assoc_psychology`: Associate degree in Psychology. - `program_assoc_public_administration_social_service`: Associate degree in Public Administration And Social Service Professions. - `program_assoc_resources`: Associate degree in Natural Resources And Conservation. - `program_assoc_science_technology`: Associate degree in Science Technologies/Technicians. - `program_assoc_security_law_enforcement`: Associate degree in Homeland Security, Law Enforcement, Firefighting And Related Protective Services. - `program_assoc_social_science`: Associate degree in Social Sciences. - `program_assoc_theology_religious_vocation`: Associate degree in Theology And Religious Vocations. - `program_assoc_transportation`: Associate degree in Transportation And Materials Moving. - `program_assoc_visual_performing`: Associate degree in Visual And Performing Arts. - `program_bachelors_agriculture`: Bachelor's degree in Agriculture, Agriculture Operations, And Related Sciences. - `program_bachelors_architecture`: Bachelor's degree in Architecture And Related Services. - `program_bachelors_biological`: Bachelor's degree in Biological And Biomedical Sciences. - `program_bachelors_business_marketing`: Bachelor's degree in Business, Management, Marketing, And Related Support Services. - `program_bachelors_communication`: Bachelor's degree in Communication, Journalism, And Related Programs. - `program_bachelors_communications_technology`: Bachelor's degree in Communications Technologies/Technicians And Support Services. - `program_bachelors_computer`: Bachelor's degree in Computer And Information Sciences And Support Services. - `program_bachelors_construction`: Bachelor's degree in Construction Trades. - `program_bachelors_education`: Bachelor's degree in Education. - `program_bachelors_engineering`: Bachelor's degree in Engineering. - `program_bachelors_engineering_technology`: Bachelor's degree in Engineering Technologies And Engineering-Related Fields. - `program_bachelors_english`: Bachelor's degree in English Language And Literature/Letters. - `program_bachelors_ethnic_cultural_gender`: Bachelor's degree in Area, Ethnic, Cultural, Gender, And Group Studies. - `program_bachelors_family_consumer_science`: Bachelor's degree in Family And Consumer Sciences/Human Sciences. - `program_bachelors_health`: Bachelor's degree in Health Professions And Related Programs. - `program_bachelors_history`: Bachelor's degree in History. - `program_bachelors_humanities`: Bachelor's degree in Liberal Arts And Sciences, General Studies And Humanities. - `program_bachelors_language`: Bachelor's degree in Foreign Langu
    ×

    帕依提提提温馨提示

    该数据集正在整理中,为您准备了其他渠道,请您使用

    注:部分数据正在处理中,未能直接提供下载,还请大家理解和支持。
    暂无相关内容。
    暂无相关内容。
    • 分享你的想法
    去分享你的想法~~

    全部内容

      欢迎交流分享
      开始分享您的观点和意见,和大家一起交流分享.
    所需积分:0 去赚积分?
    • 367浏览
    • 0下载
    • 0点赞
    • 收藏
    • 分享