Plashkar/diabetes-predict-db

该数据集是为项目sample-diabetes-predict自动处理的，包含多个特征字段，如高血压、高胆固醇、BMI等，目标字段为二分类标签。数据集分为训练集和验证集，分别包含56552和14140个样本。数据集的BCP-47语言代码为unk，表示语言未知。

原始信息汇总

数据集概述

数据集描述

本数据集是为项目“sample-diabetes-predict”自动处理而生成的。

语言

数据集的语言标识符为unk。

数据集结构

数据实例

数据集中的样本示例如下：

json [ { "target": 0, "feat_HighBP": 0.0, "feat_HighChol": 0.0, "feat_CholCheck": 1.0, "feat_BMI": 34.0, "feat_Smoker": 1.0, "feat_Stroke": 0.0, "feat_HeartDiseaseorAttack": 0.0, "feat_PhysActivity": 1.0, "feat_Fruits": 1.0, "feat_Veggies": 1.0, "feat_HvyAlcoholConsump": 0.0, "feat_AnyHealthcare": 1.0, "feat_NoDocbcCost": 0.0, "feat_GenHlth": 3.0, "feat_MentHlth": 0.0, "feat_PhysHlth": 0.0, "feat_DiffWalk": 0.0, "feat_Sex": 0.0, "feat_Age": 6.0, "feat_Education": 6.0, "feat_Income": 7.0 }, { "target": 1, "feat_HighBP": 0.0, "feat_HighChol": 0.0, "feat_CholCheck": 1.0, "feat_BMI": 46.0, "feat_Smoker": 1.0, "feat_Stroke": 0.0, "feat_HeartDiseaseorAttack": 0.0, "feat_PhysActivity": 1.0, "feat_Fruits": 1.0, "feat_Veggies": 1.0, "feat_HvyAlcoholConsump": 0.0, "feat_AnyHealthcare": 1.0, "feat_NoDocbcCost": 0.0, "feat_GenHlth": 2.0, "feat_MentHlth": 1.0, "feat_PhysHlth": 0.0, "feat_DiffWalk": 0.0, "feat_Sex": 1.0, "feat_Age": 10.0, "feat_Education": 6.0, "feat_Income": 5.0 } ]

数据集字段

数据集包含以下字段（特征）：

json { "target": "ClassLabel(num_classes=2, names=[0.0, 1.0], id=None)", "feat_HighBP": "Value(dtype=float64, id=None)", "feat_HighChol": "Value(dtype=float64, id=None)", "feat_CholCheck": "Value(dtype=float64, id=None)", "feat_BMI": "Value(dtype=float64, id=None)", "feat_Smoker": "Value(dtype=float64, id=None)", "feat_Stroke": "Value(dtype=float64, id=None)", "feat_HeartDiseaseorAttack": "Value(dtype=float64, id=None)", "feat_PhysActivity": "Value(dtype=float64, id=None)", "feat_Fruits": "Value(dtype=float64, id=None)", "feat_Veggies": "Value(dtype=float64, id=None)", "feat_HvyAlcoholConsump": "Value(dtype=float64, id=None)", "feat_AnyHealthcare": "Value(dtype=float64, id=None)", "feat_NoDocbcCost": "Value(dtype=float64, id=None)", "feat_GenHlth": "Value(dtype=float64, id=None)", "feat_MentHlth": "Value(dtype=float64, id=None)", "feat_PhysHlth": "Value(dtype=float64, id=None)", "feat_DiffWalk": "Value(dtype=float64, id=None)", "feat_Sex": "Value(dtype=float64, id=None)", "feat_Age": "Value(dtype=float64, id=None)", "feat_Education": "Value(dtype=float64, id=None)", "feat_Income": "Value(dtype=float64, id=None)" }

数据集分割

数据集分为训练集和验证集，分割情况如下：

分割名称	样本数量
训练集	56552
验证集	14140