# AWS Challenge 2020 Phase 2 — Data

来源：https://www.kaggle.com/competitions/aws-challenge-2020-phase-2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Train and Test Folders
The dataset is split into a train folder (aws-challenge-phase2-train) and test folder (aws-challenge-phase2-test).

For each folder, there are five csv files:

- casevisitsyn – visits and encounters
- labresultsyn – lab tests and results
- patientdemosyn – patient demographics
- surgicalsyn – surgery and procedures
- medicationordersyn – medication orders

# Dataset Description
A detailed description of the dataset can be found in **MedicalSyn-Dataset-Description.pdf**. Do note that the number of rows stated differ as that mentioned in the pdf due to the train-test split. Some columns such as **Deceased_Ind** and **Death_Date** in the test set of **patientdemosyn.csv** are deleted as they are the target metric for Phase 2.

# Diagnosis and Complications
The list of codes for diagnosis and complications relevant for this competition can be found in **Challenge-Statement.pdf**. 
The list of relevant surgery codes associated with complications can be found in **DHL surgery codes.xlsx**.

# Submission
The submission file format is **submission.csv**. The values of the column **Time\_To\_Death** is set as default to 0, and will need to be amended to the correct number of years to death (Please see Overview > Evaluation for more information). Do note that the **Patient\_No** column only has unique values, and only contains a subset of **Patient No** in the test dataset.

To check accuracy of your prediction of number of years to death in the training dataset, the correct values are given in **train\_time\_to\_death.csv**