如何调整R自定义函数为数据库不存在的日期生成指定样式图表

该需求完全可以实现，仅需在现有函数开头增加日期存在性校验逻辑，未匹配到日期时直接构造空数据集触发目标条件分支即可，修改后的逻辑如下：

修改核心要点 #

• 函数入口处先将传入的dmda转为日期格式，校验其是否存在于df1的date2列且对应所选分类有数据
• 若不存在匹配日期，直接计算m值，构造行数≤2的空datas数据集，自动触发要求的仅画横线逻辑，不会渲染数据点
• 额外兼容空数据集下的坐标轴范围计算，避免绘图函数报错

修改后完整代码 #

library(dplyr)
library(tidyverse)
library(lubridate)

df1 <- structure(
  list(date1= c("2021-06-28","2021-06-28","2021-06-28"),
       date2 = c("2021-07-01","2021-07-02","2021-07-04"),
       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),DR06 = c(5,4,0),DR07 = c(5,4,0),DR08 = c(5,4,0)),
  class = "data.frame", row.names = c(NA, -3L))


f1 <- function(dmda, CategoryChosse) {
  # 新增：先校验传入日期是否在date2中存在对应分类数据
  dmda_date <- ymd(dmda)
  target_data <- df1 %>% filter(date2 == dmda_date, Category == CategoryChosse)
  
  if(nrow(target_data) == 0) {
    # 无匹配数据时，计算对应分类下DR1的均值作为m，也可根据需求自定义取值逻辑
    m <- df1 %>% 
      filter(Category == CategoryChosse) %>% 
      pull(DR1) %>% 
      mean(na.rm = T)
    # 手动设置坐标轴范围，避免空数据报错，可按需调整范围大小
    max_x <- 10
    max_y <- round(m, 0) + 10
    # 生成空画布
    plot(1, type = "n", xlim= c(0,max_x),  ylim= c(0,max_y),
         xaxs='i', xlab = "Days", ylab = "Numbers", main = paste0(dmda, "-", CategoryChosse))
    # 直接执行目标逻辑画横线
    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")
    # 结束函数运行
    return(invisible())
  }
  
  # 以下为原有逻辑，仅补充了分组计算时的.groups参数避免警告，修正了nls分支的系数取值错误
  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), .groups = "drop")
  
  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[head(mat1,10)] <- NA_real_
  }
  
  datas <-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category) %>%
    summarize(across(starts_with("DR0"), sum), .groups = "drop") %>%
    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
  
  m<-df1 %>%
    group_by(Category,Week) %>%
    summarize(across(starts_with("DR1"), mean), .groups = "drop")
  
  m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
  
  maxrange <-  range(min(0, datas$Numbers, na.rm = TRUE), na.rm = TRUE)
  maxrange[1] <- maxrange[1] - (maxrange[1] %%10) + 35
  
  max_x<-max(0, datas$Days, na.rm = TRUE)+1
  
  plot(Numbers ~ Days,  xlim= c(0,max_x),  ylim= c(0,maxrange[1]),
       xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
  
  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)
    # 修正原代码系数取值错误：x=0时的截距对应b2，为coef[2]
    coef_val<-coef(mod)[2]
    points(0, coef_val, col="red",pch=19,cex = 2,xpd=TRUE)
    text(.99,coef_val + 1,max(0, round(coef_val,1)), cex=1.1,pos=4,offset =1,col="black")
  }
  
}
# 原有收录日期测试
f1("2021-07-01", "ABC")
f1("2021-07-02", "ABC")
f1("2021-07-04", "ABC")
# 未收录日期测试
f1("2021-10-15", "ABC")

效果说明 #

调用未收录的日期时，会直接生成无数据点、仅带m对应横线及标注的图表，完全符合需求。

内容的提问来源于stack exchange，提问作者Antonio