Bena345/diabetes-readmission

---
license: mit
language:
- en
tags:
- medical
pretty_name: Diabetes Readmissions
---

# Data source:
Clore,John, Cios,Krzysztof, DeShazo,Jon, and Strack,Beata. (2014).
Diabetes 130-US hospitals for years 1999-2008. UCI Machine Learning
Repository. https://doi.org/10.24432/C5230J.

# Basic data preprocessing was based on this [notebook](https://github.com/csinva/imodels-data/blob/master/notebooks_fetch_data/00_get_datasets_custom.ipynb).

# To load raw train and test sets

from datasets import load_dataset

train_set = load_dataset(dataset_name, data_files="train.csv")

test_set = load_dataset(dataset_name, data_files="test.csv")

# To load preprocessed train set

from datasets import load_dataset

preprocessed_train_set = load_dataset(dataset_name, data_files="preprocessed_train_set.csv")

原始信息汇总

数据集概述

数据来源

• 作者: Clore, John, Cios, Krzysztof, DeShazo, Jon, 和 Strack, Beata
• 年份: 2014年
• 数据集名称: Diabetes 130-US hospitals for years 1999-2008
• 来源: UCI Machine Learning Repository
• DOI: https://doi.org/10.24432/C5230J

数据加载

• 原始训练集和测试集加载: python from datasets import load_dataset

  train_set = load_dataset(dataset_name, data_files="train.csv") test_set = load_dataset(dataset_name, data_files="test.csv")

• 预处理训练集加载: python from datasets import load_dataset

  preprocessed_train_set = load_dataset(dataset_name, data_files="preprocessed_train_set.csv")

搜集汇总

背景与挑战

背景概述

该数据集包含糖尿病患者的医疗记录，重点关注再入院情况，但存在数据列不匹配的问题。数据来源于1999-2008年间130家美国医院，包含多种医疗相关字段。