如何调整R代码跳过全零异常行，正常生成输出表格

核心修改逻辑 #

• 在return_coef函数入口处新增全零行校验，只要当前传入的日期、分类对应的行所有DR相关列数值总和为0，直接返回NA跳过后续计算
• 为nls拟合增加异常捕获逻辑，避免其他偶发拟合错误导致程序整体中断
• 最终输出可以按需保留NA标注异常行，或直接过滤掉异常行

修改后可直接运行的完整代码 #

library(dplyr)
library(lubridate)
library(tidyr)
library(readr)

df1 <- structure(
  list(date1= c("2021-06-28","2021-06-28","2021-06-28","2021-06-28"),
       date2 = c("2021-06-30","2021-06-30","2021-07-01","2021-07-01"),
       Category = c("FDE","ABC","FDE","ABC"),
       Week= c("Wednesday","Wednesday","Friday","Friday"),
       DR1 = c(4,1,6,1),
       DR01 = c(4,1,4,3), DR02= c(4,2,6,0),DR03= c(9,5,4,0),
       DR04 = c(5,4,3,3),DR05 = c(5,4,5,0),
       DR06 = c(2,4,3,3),DR07 = c(2,5,4,0),
       DR08 = c(3,4,5,0),DR09 = c(2,3,4,0)),
  class = "data.frame", row.names = c(NA, -4L))

# 异常测试数据集，取消注释即可验证效果
#df1 <- structure(
#  list(date1= c("2021-06-28","2021-06-28","2021-06-28","2021-06-28"),
#       date2 = c("2021-06-30","2021-06-30","2021-07-01","2021-07-01"),
#       Category = c("FDE","ABC","FDE","ABC"),
#       Week= c("Wednesday","Wednesday","Friday","Friday"),
#       DR1 = c(4,1,6,0),
#       DR01 = c(4,1,4,0), DR02= c(4,2,6,0),DR03= c(9,5,4,0),
#       DR04 = c(5,4,3,0),DR05 = c(5,4,5,0),
#       DR06 = c(2,4,3,0),DR07 = c(2,5,4,0),
#       DR08 = c(3,4,5,0),DR09 = c(2,3,4,0)),
#  class = "data.frame", row.names = c(NA, -4L))

return_coef <- function(dmda, CategoryChosse) {
  # 新增：全零行判断，匹配到直接返回NA跳过后续计算
  target_row <- df1 %>% filter(date2 == dmda, Category == CategoryChosse)
  dr_cols_sum <- sum(target_row %>% select(starts_with("DR")))
  if (dr_cols_sum == 0) {
    return(NA_real_)
  }
  
  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))
  
  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
  
  # 新增：拟合异常捕获，避免其他偶发错误中断程序
  tryCatch({
    mod <- nls(Numbers ~ b1*Days^2+b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
    return(as.numeric(coef(mod)[2]))
  }, error = function(e) {
    return(NA_real_)
  })
}

# 生成结果
res <- cbind(df1[2:3], coef = mapply(return_coef, df1$date2, df1$Category))
# 如需直接删除异常行，取消注释执行下面一行即可
# res <- na.omit(res)

print(res)

运行效果 #

使用注释中的异常测试数据集运行时，输出结果如下：

date2 Category coef
1 2021-06-30      FDE    4
2 2021-06-30      ABC    1
3 2021-07-01      FDE    6
4 2021-07-01      ABC   NA

全零异常行会返回NA，其余正常行计算结果不受影响，按需过滤NA即可实现跳过异常行的需求。

内容的提问来源于stack exchange，提问作者user16774617