R语言在BRFSS数据中可视化分析探索糖尿病的影响因素

library(ggplot2)library(dplyr)library(Rgraphviz)library(knitr)library(grid)library(gridExtra)

load("brfss2013.RData")

# group and count a feature with discrete valuesfeature_vcounts <- function(df, f) {  df %>%    group_by_at(f) %>%      count()}# method for binning valuesbin_min_sample <- function(p) {  n = 10  a = 10/p  b = 10/(1-p)  max(c(a,b))}# create a new df for simulating binom probability distributionbinom_prob_df <- function(df, f, target) {  new_df <- feature_vcounts(df,f)  new_df$n[new_df[f] == target]/sum(new_df$n)}# filtering df with subgroup valuesubgroup_df <- function(df,f, group) {  filter(df,df[f]==group)}# calc the vector probabilitybinom_prob_vec <- function(v, target) {  sum(v == target)/length(v)}# sample from dfbinom_sample <- function(s,v)  sample(v, size=s, replace=TRUE)# create the binomial sample distributionbinom_sample_dist <- function(df,f,target) {  sample_dist <- c()  for (i in 1:10001) {    prob <- binom_prob_vec(binom_sample(100,df[,f]),target)    sample_dist <- append(sample_dist,prob)}  return(sample_dist)}# convert decimal to percentto_percent <- function(pvalue) {  paste(round(pvalue*100,digits= 2),"%",sep="")}

# Import original file:orig_dim <- dim(brfss2013)# Select only relevant features:weight_diabetes <- brfss2013 %>%   select(sex, X_ageg5yr, weight2,diabete3)# ------------------Cleaning data------------------# 1.Weight strings -> numericweight_diabetes$weight2 <- as.numeric(as.character(weight_diabetes$weight2))new_dim <- dim(weight_diabetes)# 2. Remove Null Weights and Weights over 400weight_diabetes <- na.omit(weight_diabetes)weight_diabetes <- filter(weight_diabetes, weight2 <= 400)# 3. Remove Diabetes Responsestarget <- c("Yes", "No")weight_diabetes <- filter(weight_diabetes, diabete3 %in% target)# 4. Add index and reorderweight_diabetes$index <- seq.int(nrow(weight_diabetes))weight_diabetes <- weight_diabetes[c(4,3,1,2)]clean_dim <- dim(weight_diabetes)# Show data:kable(head(weight_diabetes,n=5), caption="Diabetes Data Set",padding=0, format = "markdown",align="l")

centered <- theme(plot.title = element_text(hjust = 0.5))hist_weight <- ggplot(data=weight_diabetes,aes(weight2,  fill=weight2))+  geom_histogram(fill='salmon',color='white') + ggtitle("Histogram [Weight]") + centeredweight_diabetes$log_weight <- log(weight_diabetes$weight2)hist_log_weight <- ggplot(data=weight_diabetes,aes(log_weight, fill=log_weight))+  geom_histogram(fill='mediumturquoise',color='white') + ggtitle("Histogram [Log_Weight]") + centeredgrid.arrange(hist_weight, hist_log_weight, ncol = 2)