KY diabetes

##讀取資料，data.frame(xtabs挑選資料項目X軸項目命名
dta <-read.csv("C:/tmp/diabetes_mell.csv",sep=",", header = T, stringsAsFactors = FALSE)[,c(6,7,8,9)]
head(dta)

##    gender     race diabetes           BMI
## 1   Males    White       No    Overweight
## 2   Males    Black       No Normal weight
## 3   Males    Black       No Normal weight
## 4 Females    Black      Yes    Overweight
## 5   Males Hispanic       No    Overweight
## 6 Females    White       No    Overweight

##建立項目
dta_v3 <- data.frame(xtabs(data = dta, ~ race + gender + diabetes + BMI))
##查看資料，多了Freq
head(dta_v3)

##       race  gender diabetes           BMI Freq
## 1    Black Females       No Normal weight  347
## 2 Hispanic Females       No Normal weight  712
## 3    White Females       No Normal weight  998
## 4    Black   Males       No Normal weight  429
## 5 Hispanic   Males       No Normal weight  706
## 6    White   Males       No Normal weight  873

library(lattice)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(ggplot2)
library(magrittr)

## 
## Attaching package: 'magrittr'

## The following object is masked from 'package:tidyr':
## 
##     extract

library(ggalluvial)
##運用老師上教的指令帶入ggplot圖
p<- ggplot(dta_v3, 
       aes(axis1=race,
           axis2=gender, 
           axis3=diabetes, 
           y=Freq)) +
  scale_x_discrete(limits=c("race", 
                            "gender", 
                            "diabetes"), 
                   expand=c(.1, .01)) +
  labs(x='BMI', 
       y='SEQN') +
  geom_alluvium(aes(fill=BMI)) +
  geom_stratum() + 
  geom_text(stat="stratum", 
            infer.label=TRUE) +
  scale_fill_manual(values=c('gray60','hotpink'))+
  theme_minimal() +
  ggtitle("Subjects stratified by diabetes in overall population")

p