当所有列都有 0 值时调整条件

Question

下面的代码根据我在date2 上选择的日期/类别生成图表。这几天是 30/06、01/07 和 02/07。对于 30/06 和 01/07，我可以正常生成，如您在附图中看到的那样，但不能用于 02/07。这是因为我所有的列都有 0 值，最终会在datas 中产生问题。所以我需要如果所有列都是 0，我希望我的图表考虑代码的这种情况：

if (nrow(datas)<=2){
abline(h=m,lwd=2) 
points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
text(.1,m+ .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}

所以我的图表没有点，只有m 中的线。

下面的可执行代码

library(dplyr)

df1 <- structure(
  list(date1= c("2021-06-28","2021-06-28","2021-06-28"),
       date2 = c("2021-06-30","2021-07-01","2021-07-02"),
       Category = c("ABC","ABC","ABC"),
       Week= c("Wednesday","Wednesday","Wednesday"),
       DR1 = c(4,1,0),
       DR01 = c(4,1,0), DR02= c(4,2,0),DR03= c(9,5,0),
       DR04 = c(5,4,0),DR05 = c(5,4,0)),
  class = "data.frame", row.names = c(NA, -3L))


f1 <- function(dmda, CategoryChosse) {
  
  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week')) %>%
    mutate(across(matches("^DR0\\d+$"), ~.x + 
                    get(paste0(cur_column(), '_PV')),
                  .names = '{col}_{col}_PV')) %>%
    select(date1:Category, DR01_DR01_PV:last_col())
  
  SPV<-data.frame(SPV)
  
  mat1 <- df1 %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(starts_with("DR0")) %>%
    pivot_longer(cols = everything()) %>%
    arrange(desc(row_number())) %>%
    mutate(cs = cumsum(value)) %>%
    filter(cs == 0) %>%
    pull(name)
  
  (dropnames <- paste0(mat1,"_",mat1, "_PV"))
  
  SPV <- SPV %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(-any_of(dropnames))
  
  datas<-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category) %>%
    summarize(across(starts_with("DR0"), sum)) %>%
    pivot_longer(cols= -Category, names_pattern = "DR0(.+)", values_to = "val") %>%
    mutate(name = readr::parse_number(name))
  colnames(datas)[-1]<-c("Days","Numbers")
  
  datas <- datas %>% 
    group_by(Category) %>% 
    slice((as.Date(dmda) - min(as.Date(df1$date1) [
      df1$Category == first(Category)])):max(Days)+1) %>%
    ungroup
  
  
  plot(Numbers ~ Days,  xlim= c(0,45), ylim= c(0,30),
       xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
  
  m<-df1 %>%
    group_by(Category,Week) %>%
    summarize(across(starts_with("DR1"), mean))
  
  m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
  
  if (nrow(datas)<=2){
    abline(h=m,lwd=2) 
    points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,m+ .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else if(any(table(datas$Numbers) >= 3) & length(unique(datas$Numbers)) == 1){
    yz <- unique(datas$Numbers)
    lines(c(0,datas$Days), c(yz, datas$Numbers), lwd = 2)
    points(0, yz, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,yz+ .5,round(yz,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else{
    mod <- nls(Numbers ~ b1*Days^2+b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
    new.data <- data.frame(Days = with(datas, seq(min(Days),max(Days),len = 45)))
    new.data <- rbind(0, new.data)
    lines(new.data$Days,predict(mod,newdata = new.data),lwd=2)
    coef<-coef(mod)[2]
    points(0, coef, col="red",pch=19,cex = 2,xpd=TRUE)
    text(.99,coef + 1,max(0, round(coef,1)), cex=1.1,pos=4,offset =1,col="black")
  }
}


f1("2021-06-30", "ABC")
f1("2021-07-01", "ABC")
f1("2021-07-02", "ABC")

Answer 1

DR0 列在最后一种情况下被删除，这会导致错误，因为 summarise 正在循环通过这些列 summarize(across(starts_with("DR0"), sum))。一种选择是创建条件检查，即如果没有 DR0 列，则将这些列添加为 NA 并且它应该可以正常工作

f1 <- function(dmda, CategoryChosse) {
  
  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week')) %>%
    mutate(across(matches("^DR0\\d+$"), ~.x + 
                    get(paste0(cur_column(), '_PV')),
                  .names = '{col}_{col}_PV')) %>%
    select(date1:Category, DR01_DR01_PV:last_col())
  
  SPV<-data.frame(SPV)
  
  mat1 <- df1 %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(starts_with("DR0")) %>%
    pivot_longer(cols = everything()) %>%
    arrange(desc(row_number())) %>%
    mutate(cs = cumsum(value)) %>%
    filter(cs == 0) %>%
    pull(name)
  
  (dropnames <- paste0(mat1,"_",mat1, "_PV"))
  
  SPV <- SPV %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(-any_of(dropnames))
  
  if(length(grep("DR0", names(SPV))) == 0) {
    SPV[mat1] <- NA_real_
  }
 
  datas <-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category) %>%
    summarize(across(starts_with("DR0"), sum)) %>%
    pivot_longer(cols= -Category, names_pattern = "DR0(.+)", values_to = "val") %>%
    mutate(name = readr::parse_number(name))
  colnames(datas)[-1]<-c("Days","Numbers")
 

  datas <- datas %>% 
    group_by(Category) %>% 
    slice((as.Date(dmda) - min(as.Date(df1$date1) [
      df1$Category == first(Category)])):max(Days)+1) %>%
    ungroup
  
  
  
  plot(Numbers ~ Days,  xlim= c(0,45), ylim= c(0,30),
       xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
  
 m<-df1 %>%
   group_by(Category,Week) %>%
   summarize(across(starts_with("DR1"), mean))
 
 m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
 
 if (nrow(datas)<=2){
   abline(h=m,lwd=2) 
   points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
   text(.1,m+ .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
 
 else if(any(table(datas$Numbers) >= 3) & length(unique(datas$Numbers)) == 1){
   yz <- unique(datas$Numbers)
   lines(c(0,datas$Days), c(yz, datas$Numbers), lwd = 2)
   points(0, yz, col = "red", pch = 19, cex = 2, xpd = TRUE)
   text(.1,yz+ .5,round(yz,1), cex=1.1,pos=4,offset =1,col="black")}
 
 else{
   mod <- nls(Numbers ~ b1*Days^2+b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
   new.data <- data.frame(Days = with(datas, seq(min(Days),max(Days),len = 45)))
   new.data <- rbind(0, new.data)
   lines(new.data$Days,predict(mod,newdata = new.data),lwd=2)
   coef<-coef(mod)[2]
   points(0, coef, col="red",pch=19,cex = 2,xpd=TRUE)
   text(.99,coef + 1,max(0, round(coef,1)), cex=1.1,pos=4,offset =1,col="black")
 }
 
}

-测试

f1("2021-07-02", "ABC")

-输出