ICU-Sepsis
基于MIMIC-III构建的脓毒症患者表格MDP环境，用于强化学习算法评估。
基本信息
资源简介
ICU-Sepsis
【数据集背景】
本数据集源站标题为《icu-sepsis/icu-sepsis》。源站首次发布：2024-02-29。
【数据内容】
源站原始描述：ICU-Sepsis is a lightweight, yet challenging RL environment that models the treatment of sepsis in the ICU. # The ICU-Sepsis Environment The **ICU-Sepsis** environment is a reinforcement learning environment that simulates the treatment of sepsis in an intensive care unit (ICU). The environment is introduced in the paper ICU-Sepsis: A Benchmark MDP Built from Real Medical Data, accepted at the Reinforcement Learning Conference, 2024. ICU-Sepsis is built using the MIMIC-III Dataset, based on the…
【主题与分类】
主题标签：applied-reinforcement-learning、reinforcement-learning、reinforcement-learning-environments。
【适用方向】
结构化表格数据可直接用于统计建模、特征工程与队列分析。
【获取与许可】
源站页面：https://github.com/icu-sepsis/icu-sepsis
使用许可：MIT。
【使用注意】
· 源站最后修改于 2024-10-23，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/icu-sepsis/icu-sepsis.git
curl -L -o repo.zip https://github.com/icu-sepsis/icu-sepsis/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
Python installation and quickstart
ICU-Sepsis can be used with Python 3.10 or later, with gymnasium 0.28.1 or
later, and gym 0.21.0 or later.
Installation with pip
The environment can be installed using the pip command:
pip install icu-sepsis
Installation from source
To install the environment from source, clone the repository and navigate to
the packages directory, and install the icu_sepsis package locally:
git clone https://github.com/icu-sepsis/icu-sepsis.git
cd icu-sepsis/packages/
pip install icu_sepsis/
Uninstalling
To uninstall, use the pip uninstall command:
pip uninstall icu_sepsis -y
Quickstart
The environment can be loaded with the Gym or Gymnasium packages and follows
the standard Gym API. The following code snippet demonstrates how to create
the environment, reset it, and take a step:
import gymnasium as gym
import icu_sepsis
env = gym.make(''Sepsis/ICU-Sepsis-v2'')
state, info = env.reset()
print(''Initial state:'', state)
print(''Extra info:'', info)
next_state, reward, terminated, truncated, info = env.step(0)
print(''\nTaking action 0:'')
print(''Next state:'', next_state)
print(''Reward:'', reward)
print(''Terminated:'', terminated)
print(''Truncated:'', truncated)
You can also run the script examples/quickstart.py to verify that the
installation was successful.
数据加载示例（表格/文本类）
import pandas as pd, glob, os
files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
