模拟家庭收入、区域、年龄、血压及多属性的大规模数据集生成的R代码和一份10000人数据集，可以用于学习机器学习

# 加载必要的包 library(dplyr) # 设置随机种子以确保结果可重复 set.seed(42) # 定义样本数量 n <- 10000 # 生成家庭收入，假设收入在3万到15万美元之间 income <- round(runif(n, min = 30000, max = 150000), 0) # 生成区域，假设有四个区域: 东部, 西部, 南部, 北部 region <- sample(c("East", "West", "South", "North"), size = n, replace = TRUE) # 生成年龄，假设年龄在18到80岁之间 age <- round(runif(n, min = 18, max = 80), 0) # 生成收缩压，假设收缩压在90到180 mmHg之间 systolic_bp <- round(runif(n, min = 90, max = 180), 0) # 生成舒张压，假设舒张压在60到120 mmHg之间 diastolic_bp <- round(runif(n, min = 60, max = 120), 0) # 生成性别，假设有两个性别: 男, 女 gender <- sample(c("Male", "Female"), size = n, replace = TRUE) # 生成体重，假设体重在50到120公斤之间 weight <- round(runif(n, min = 50, max = 120), 1) # 生成身高，假设身高在150到200厘米之间 height <- round(runif(n, min = 150, max = 200), 1) # 生成婚姻状态，假设有三种状态: 未婚, 已婚, 离婚 marital_status <- sample(c("Single", "Married", "Divorced"), size = n, replace = TRUE) # 生成教育水平，假设有四个等级: 高中, 本科, 硕士, 博士 education <- sample(c("High School", "Bachelor's", "Master's", "PhD"), size = n, replace = TRUE) # 生成种族，假设有四个种族: 白人, 黑人, 亚裔, 拉丁裔 ethnicity <- sample(c("White", "Black", "Asian", "Hispanic"), size = n, replace = TRUE) # 生成现居地，假设有五个城市: 纽约, 洛杉矶, 芝加哥, 休斯顿, 迈阿密 current_residence <- sample(c("New York", "Los Angeles", "Chicago", "Houston", "Miami"), size = n, replace = TRUE) # 生成血糖水平，假设血糖水平在70到180 mg/dL之间 blood_sugar <- round(runif(n, min = 70, max = 180), 1) # 创建数据框 data <- data.frame( Income = income, Region = region, Age = age, Systolic_BP = systolic_bp, Diastolic_BP = diastolic_bp, Gender = gender, Weight = weight, Height = height, Marital_Status = marital_status, Education = education, Ethnicity = ethnicity, Current_Residence = current_residence, Blood_Sugar = blood_sugar ) # 查看数据 View(data) # 保存数据到CSV文件 # write.csv(data, "simulated_health_data.csv", row.names = FALSE) # 提示保存完成 # cat("数据已保存为 'simulated_health_data.csv'")