r - R 代码中 pivot_longer 函数的问题

Question

我在使用 datas 中的 pivot_longer 函数时遇到问题。你能帮我解决一下吗？

在这个问题中正常工作:How to adjust error when I have 0 values for graph generation .但是，在上一个问题中我没有使用 DTT 列，在当前问题中是。

library(dplyr)

df1 <- structure(
  list(date1= c("2021-06-28","2021-06-28","2021-06-28"),
       date2 = c("2021-06-30","2021-06-30","2021-07-02"),
       DTT= c(NA,NA,"Hol"),
       Week= c("Wednesday","Wednesday","Friday"),
       Category = c("ABC","FDE","ABC"),
       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))


dmda<-"2021-07-02"
CategoryChosse<-"ABC"
DTest<-"Hol"

  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DTT, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week,DTT) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week','DTT')) %>%
    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, DTT==DTest) %>%
    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, DTT==DTest) %>%
    select(-any_of(dropnames))
  
  if(length(grep("DR0", names(SPV))) == 0) {
    SPV[mat1] <- NA_real_
  }
  
  datas <-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category, DTT) %>%
    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")

Error: Can't combine `DTT` <character> and `DR05` <double>.
Run `rlang::last_error()` to see where the error occurred.

Answer 1

pivot_longer 检查列类型，并通过在 cols 中指定 -Category，它将选择所有剩余的列。但是，在 OP 的数据集中，除了其他 numeric 列(“DR0”)之外，还有一个 character 列“DTT”。一个选项是删除“DTT”(通过 %>% select(-DTT) %>% pivot_longer(..)并使用 OP 的代码或使用 cols = starts_with("DR0")

library(dplyr)
library(tidyr)
datas <- SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category, DTT) %>%
    summarize(across(starts_with("DR0"), sum), .groups = "drop") %>%
    pivot_longer(cols= starts_with("DR0"), names_pattern = "DR0(.+)", 
         values_to = "val") %>%
    mutate(name = readr::parse_number(name))

-输出

> head(datas)
# A tibble: 5 × 4
  Category DTT    name   val
  <chr>    <chr> <dbl> <dbl>
1 ABC      Hol       5    NA
2 ABC      Hol       4    NA
3 ABC      Hol       3    NA
4 ABC      Hol       2    NA
5 ABC      Hol       1    NA

关于列名的变化，这里有4列。所以，我们可能需要

colnames(datas)[-c(1, 2)] <- c("Days","Numbers")