mstz/toxicity
收藏Hugging Face2023-04-16 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/mstz/toxicity
下载链接
链接失效反馈官方服务：
资源简介：
---
language:
- en
tags:
- toxicity
- tabular_classification
- binary_classification
- multiclass_classification
- UCI
pretty_name: Toxicity
size_categories:
- n<1K
task_categories:
- tabular-classification
configs:
- encoding
- income
- income-no race
- race
license: cc
---
# Adult
The [Toxicity dataset](https://archive-beta.ics.uci.edu/dataset/728/toxicity) from the [UCI ML repository](https://archive.ics.uci.edu/ml/datasets).
The dataset includes 171 molecules designed for functional domains of a core clock protein, CRY1, responsible for generating circadian rhythm.
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-------------------|---------------------------|-----------------------------------------------------------------|
| toxicity | Binary classification | Is the molecule toxic? |
# Usage
```python
from datasets import load_dataset
dataset = load_dataset("mstz/toxicity")["train"]
```
提供机构：
mstz
原始信息汇总
数据集概述
基本信息
- 名称: Toxicity
- 来源: UCI ML repository
- 语言: 英语
- 标签:
- toxicity
- tabular_classification
- binary_classification
- multiclass_classification
- 大小分类: n<1K
- 任务分类: tabular-classification
- 许可证: cc
数据集内容
- 描述: 包含171种分子，这些分子设计用于核心时钟蛋白CRY1的功能域，CRY1负责生成昼夜节律。
配置与任务
- 配置: toxicity
- 任务: Binary classification
- 描述: 判断分子是否具有毒性。
使用示例
python from datasets import load_dataset
dataset = load_dataset("mstz/toxicity")["train"]
