[NeurIPS 2020] Data Science for COVID-19 (DS4C)

### A portion of our dataset has been accepted in NeurIPS 2020. See this [paper](https://www.cmu.edu/dietrich/causality/CameraReadys-accepted%20papers/55%5CCameraReady%5Cpaper.pdf) for more details

## Context
COVID-19 has infected more than 10,000 people in South Korea.
KCDC (Korea Centers for Disease Control & Prevention) announces the information of COVID-19 quickly and transparently.
We make a structured dataset based on the report materials of KCDC and local governments.
Also, we analyze and visualize the data using various data mining or visualization techniques.

## Official Kernels
- [[DS4C] What is this dataset (Detailed Description)](https://www.kaggle.com/kimjihoo/ds4c-what-is-this-dataset-detailed-description)
- [[DS4C] EDA with Floating Population Data](https://www.kaggle.com/incastle/ds4c-eda-with-floating-population-data)
- [[DS4C] Who spreads the corona virus?](https://www.kaggle.com/incastle/ds4c-who-spreads-the-corona-virus)
- [[DS4C] time series geospatial EDA using folium.](https://www.kaggle.com/mbnb8317/ds4c-time-series-geospatial-eda-using-folium)
- [[DS4C]Tutorial : All about folium (ing..) + 한국어 설명](https://www.kaggle.com/mbnb8317/ds4c-tutorial-all-about-folium-ing)
- [[DS4C] Korea, Wonderland? (Fight against COVID-19)](https://www.kaggle.com/kimjihoo/ds4c-korea-wonderland-fight-against-covid-19)

## Update
- We have stopped updating the dataset.
- PatientRoute.csv is currently not available because of privacy issue.

## Acknowledgements
Thanks sincerely to all the members of KCDC and local governments.
**Source of data**: [KCDC](http://www.cdc.go.kr/) (Korea Centers for Disease Control & Prevention)

***

> **DS4C (Data Science for COVID-19) Project** [(Github)](https://github.com/ThisIsIsaac/Data-Science-for-COVID-19)
1. To reprocess information provided by KCDC and local governments for easy data analysis
2. To find meaningful patterns by applying various data mining or visualization techniques
- **Chief Research Director**
- [Jihoo Kim](https://www.kaggle.com/kimjihoo)
- [JoongKun Lee](https://github.com/ThisIsIsaac)
- **Senior Research Engineer**
- [SeoJin Jang](https://www.kaggle.com/sarah5398)
- [SeongHan Ryoo](https://www.kaggle.com/incastle)
- [YeonJun In](https://www.kaggle.com/mbnb8317)
- [WonCheol Lee](https://www.kaggle.com/leewoncheol)
- [DongHwan Jang](https://github.com/DongHwanJang)
- [Jimi Kim](https://github.com/kjm0623v)
- [MuHwan Kim](https://github.com/minty99) (absent)
- **Research Engineer**
- [BoYoung Song](https://www.kaggle.com/bysong)
- [KyeongWook Jang](https://www.kaggle.com/jeeudev)
- [MinSeok Jung](https://www.kaggle.com/msjung)
- [SangWook Park](https://www.kaggle.com/kvmoke)
- [TaeHyeong Park](https://www.kaggle.com/asdjfalksjdh)
- [WanSik Choi](https://www.kaggle.com/wansook0316)
- [YouNa Jung](https://www.kaggle.com/younajung)

- **Former Maintainer**
- [JuHwan Park](https://www.kaggle.com/parkjuhwan)
- [Won Hwang](https://github.com/mangocode96)
- **Logo Designer**
- [RinChong Kim](http://indesignlab.creatorlink.net)

***

## Partnership
### 1) Competition
- [COVID-19 Visualization & AI Competition](https://dacon.io/competitions/official/235590/overview/) (DACON)
- 2020.03.29 ~ 2020.05.10
- Winners' Code
[1st Place](https://dacon.io/competitions/official/235590/codeshare/949)
[2nd Place](https://dacon.io/competitions/official/235590/codeshare/997)
[3rd Place](https://dacon.io/competitions/official/235590/codeshare/1001)
- [Post-Corona Data Visualization Competition](https://dacon.io/competitions/official/235618/overview/) (KT)
- 2020.07.01 ~ 2020.07.31
- Winners' Code
[1st Place](https://dacon.io/competitions/official/235618/codeshare/1448)
[2nd Place](https://dacon.io/competitions/official/235618/codeshare/1457)
[3rd Place](https://dacon.io/competitions/official/235618/codeshare/1434)
[4th Place](https://dacon.io/competitions/official/235618/codeshare/1363)
[5th Place](https://dacon.io/competitions/official/235618/codeshare/1430)
- [Transport Big Data Online Hackathon](https://dacon.io/competitions/official/235622/overview/) (Ministry of Land, Infrastructure and Transport)
- 2020.07.14 ~ 2020.09.04
- Winners' Code
[1st Place](https://dacon.io/competitions/official/235622/codeshare/1603)
[2nd Place](https://dacon.io/competitions/official/235622/codeshare/1621)
[3rd Place](https://dacon.io/competitions/official/235622/codeshare/1620)
[4th Place](https://dacon.io/competitions/official/235622/codeshare/1606)
[5th Place](https://dacon.io/competitions/official/235622/codeshare/1607)

<img src="https://user-images.githubusercontent.com/50820635/87323213-6f6eed00-c569-11ea-9ca0-965b984e25de.PNG">
### 2) Research
- [Maggie Munkhjargal](https://www.linkedin.com/in/maggie-munkhjargal-md-ph-d-candidate-473a0163/) (Harvard T.H. Chan School of Public Health)
- [Gwang-Jin Kim](https://www.linkedin.com/in/gwang-jin-kim-374b8867/) (University of Freiburg)
- [Sofia K. Mettler](https://www.linkedin.com/in/sofia-kyonhi-mettler-ab23981b2/) (Swiss Federal Institute of Technology, University of Zurich)
- [Myung-Bae Park](https://silvermed.pcu.ac.kr/_silvermed/sub02/sub020401.html) (Department of Gerontology Health and Welfare, Pai Chai University)
- [Jinhee Lee](https://www.ywmc.or.kr/web/www/psychiatry/doc) (Department of Psychiatry, Yonsei University Wonju College of Medicine)
- [Sun Kim](https://www.linkedin.com/in/sun-kim-035585124/) (Harvard T.H. Chan School of Public Health)
- [Ardiansyah Ardiansyah](https://www.linkedin.com/in/ardiansyahdotid) (Chonnam National University)
- [Atina Husnayain](https://www.medrxiv.org/content/10.1101/2020.04.23.20077552v1) (College of Medical Science and Technology, Taipei Medical University)
- [Carlos Saez](https://avillach-lab.hms.harvard.edu/people/carlos-s%C3%A1ez) (Universitat Politècnica de València &amp; Harvard Medical School)
- [Dimitrios E. Kouzoukas](https://www.linkedin.com/in/dimitrios-kouzoukas/) (Edward Hines, Jr. VA Hospital &amp; Loyola University Chicago)
- [Tanima Bose](https://www.linkedin.com/in/tanima-bose-phd-6ab5263a/?originalSubdomain=de) (Ludwig-Maximilian University of Munich)
- [Keumseok Peter Koh](https://www.geog.hku.hk/k-koh) (Faculty of Social Sciences, The University of Hong Kong)

<img src="https://user-images.githubusercontent.com/50820635/83261173-e8062e00-a1f5-11ea-9968-1259e1b704d1.PNG">
### 3) Media
- News articles
- [ZDNet Korea](https://www.zdnet.co.kr/view/?no=20200305141041) (2020.03.05)
- [The Electronic Times](https://www.etnews.com/20200306000213) (2020.03.06)
- [The Korea Economic Daily](https://www.hankyung.com/it/article/202003100677i) (2020.03.10)
- [The Washington Post](https://www.washingtonpost.com/graphics/2020/world/coronavirus-south-korea-church/?itid=ap_youjinshin) (2020.03.25)
- Blog posts
- [Databricks](https://databricks.com/blog/2020/04/14/covid-19-datasets-now-available-on-databricks.html) (2020.04.14)
- [DataRobot](https://www.datarobot.com/blog/predicting-days-to-recovery-of-covid-19-patients/) (2020.05.08)

<img src="https://user-images.githubusercontent.com/50820635/83264205-bb084a00-a1fa-11ea-8e9b-ccd024985887.PNG">
### 4) Sponsor
- Google Korea ([Soonson Kwon](https://kldp.org/~kss/))
- Slack Technologies ([Andy Pflaum](https://www.linkedin.com/in/andypflaum/))
- Notion Labs
<img src="https://user-images.githubusercontent.com/50820635/77623631-c4b7cc00-6f83-11ea-85d8-fc0c25d28af2.PNG">
### 5) Partner
- [Big Leader Institute](http://bigleader.net/)
- [MINDs Lab](https://mindslab.ai:8080/kr/company)
- [SK Telecom Geovision](http://b2b.tworld.co.kr/bizts/solution/solutionTemplate.bs?solutionId=0022)
- [Databricks](https://redash-demo.dev.databricks.com/public/dashboards/iGnxBLpGi7lSTZlH4AwlwmPmEZZo1FKJNKBtUm2Y?org_slug=default)
- [CoronaBoard](https://coronaboard.kr/)
<img src="https://user-images.githubusercontent.com/50820635/89502126-72bf6680-d7ff-11ea-926b-9e7ee6d414b8.PNG">

本数据集的一部分已入选于NeurIPS 2020。详情请参阅此[论文](https://www.cmu.edu/dietrich/causality/CameraReadys-accepted%20papers/55%5CCameraReady%5Cpaper.pdf)。

COVID-19疫情已感染超过10,000名韩国民众。韩国疾病控制与预防中心（KCDC）迅速且透明地发布了COVID-19的相关信息。我们基于KCDC及地方政府提供的报告材料，构建了结构化的数据集。此外，我们运用多种数据挖掘或可视化技术对数据进行分析与可视化。

官方核仁：
- [[DS4C] 本数据集的详细介绍](https://www.kaggle.com/kimjihoo/ds4c-what-is-this-dataset-detailed-description)
- [[DS4C] 基于浮动人口数据的EDA](https://www.kaggle.com/incastle/ds4c-eda-with-floating-population-data)
- [[DS4C] 谁传播了冠状病毒？](https://www.kaggle.com/incastle/ds4c-who-spreads-the-corona-virus)
- [[DS4C] 使用folium进行时间序列地理空间EDA](https://www.kaggle.com/mbnb8317/ds4c-time-series-geospatial-eda-using-folium)
- [[DS4C] 教程：关于folium的所有内容（进行中）+ 韩语说明](https://www.kaggle.com/mbnb8317/ds4c-tutorial-all-about-folium-ing)
- [[DS4C] 韩国，仙境？（抗击COVID-19）](https://www.kaggle.com/kimjihoo/ds4c-korea-wonderland-fight-against-covid-19)

更新：
- 我们已停止更新数据集。
- 由于隐私问题，PatientRoute.csv目前不可用。

致谢：
衷心感谢韩国疾病控制与预防中心（KCDC）和地方政府的所有成员。
**数据来源**：[KCDC](http://www.cdc.go.kr/)（韩国疾病控制与预防中心）

***
> **DS4C（COVID-19数据科学项目**） [(Github)](https://github.com/ThisIsIsaac/Data-Science-for-COVID-19)
1. 对KCDC和地方政府的提供的信息进行重新处理，以便于数据分析
2. 通过应用各种数据挖掘或可视化技术，寻找有意义的模式
- **首席研究总监**
- [Jihoo Kim](https://www.kaggle.com/kimjihoo)
- [JoongKun Lee](https://github.com/ThisIsIsaac)
- **高级研究工程师**
- [SeoJin Jang](https://www.kaggle.com/sarah5398)
- [SeongHan Ryoo](https://www.kaggle.com/incastle)
- [YeonJun In](https://www.kaggle.com/mbnb8317)
- [WonCheol Lee](https://www.kaggle.com/leewoncheol)
- [DongHwan Jang](https://github.com/DongHwanJang)
- [Jimi Kim](https://github.com/kjm0623v)
- [MuHwan Kim](https://github.com/minty99)（缺席）
- **研究工程师**
- [BoYoung Song](https://www.kaggle.com/bysong)
- [KyeongWook Jang](https://www.kaggle.com/jeeudev)
- [MinSeok Jung](https://www.kaggle.com/msjung)
- [SangWook Park](https://www.kaggle.com/kvmoke)
- [TaeHyeong Park](https://www.kaggle.com/asdjfalksjdh)
- [WanSik Choi](https://www.kaggle.com/wansook0316)
- [YouNa Jung](https://www.kaggle.com/younajung)

- **前任维护者**
- [JuHwan Park](https://www.kaggle.com/parkjuhwan)
- [Won Hwang](https://github.com/mangocode96)
- **标志设计师**
- [RinChong Kim](http://indesignlab.creatorlink.net)

## 合作
### 1) 比赛
- [COVID-19可视化与AI竞赛](https://dacon.io/competitions/official/235590/overview/)（DACON）
- 2020.03.29 ~ 2020.05.10
- 冠军代码
[1st Place](https://dacon.io/competitions/official/235590/codeshare/949)
[2nd Place](https://dacon.io/competitions/official/235590/codeshare/997)
[3rd Place](https://dacon.io/competitions/official/235590/codeshare/1001)
- [后冠状病毒数据可视化竞赛](https://dacon.io/competitions/official/235618/overview/)（KT）
- 2020.07.01 ~ 2020.07.31
- 冠军代码
[1st Place](https://dacon.io/competitions/official/235618/codeshare/1448)
[2nd Place](https://dacon.io/competitions/official/235618/codeshare/1457)
[3rd Place](https://dacon.io/competitions/official/235618/codeshare/1434)
[4th Place](https://dacon.io/competitions/official/235618/codeshare/1363)
[5th Place](https://dacon.io/competitions/official/235618/codeshare/1430)
- [交通大数据在线黑客松](https://dacon.io/competitions/official/235622/overview/)（国土交通省）
- 2020.07.14 ~ 2020.09.04
- 冠军代码
[1st Place](https://dacon.io/competitions/official/235622/codeshare/1603)
[2nd Place](https://dacon.io/competitions/official/235622/codeshare/1621)
[3rd Place](https://dacon.io/competitions/official/235622/codeshare/1620)
[4th Place](https://dacon.io/competitions/official/235622/codeshare/1606)
[5th Place](https://dacon.io/competitions/official/235622/codeshare/1607)