Question

我想在现有数据框中创建一个新列，该列基于同一数据框中另一列中的值并基于特定条件进行填充。

RAVE_ITN_BVAS_ADVIS3$subtype_ANCA_type_abr <-
  apply(
    RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type,
    1,
    FUN = function(x) {
      if (x == "Wegener's Granulomatosis (WG)-PR3") {
        return("GPA_PR3")
      }

      if (x == "Wegener's Granulomatosis (WG)-MPO") {
        return("GPA_MPO")
      }

      if (x == "Microscopic Polyangiitis (MPA)-PR3") {
        return("MPA_PR3")
      }

      if (x == "Microscopic Polyangiitis (MPA)-MPO") {
        return("MPA_MPO")
      }

    }
  )

View(RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type_abr)

我已经尝试了上面的代码（为格式不正确而道歉，stackoverflow似乎最近改变了一切）。

我不断收到错误消息：

Error in apply(RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type, 1, FUN = function(x) { : 
  dim(X) must have a positive length

在此对您的任何帮助将不胜感激，非常感谢。

Answer 1

这是一个奇怪的应用场所。 R还有很多其他功能可以提供帮助。我将查找有关此主题的一些教程。关于堆栈溢出有很多类似的问题。

您的apply的问题是apply取得一个数据帧，然后遍历每一行。您正在尝试使用向量作为apply函数的输入...并且向量没有行...然后函数中的每个x都是一个“命名向量”。您可以使用x["Subtype_ANCA_type"]从命名向量中调用适当的项。但是我不会这样解决问题。只是想解释如何使用Apply，因为这是您提出的问题。

#************************************************************#
# The original question
RAVE_ITN_BVAS_ADVIS3 <- data.frame(
  Subtype_ANCA_type = rep(
    c("Wegener's Granulomatosis (WG)-PR3",
      "Wegener's Granulomatosis (WG)-MPO",
      "Microscopic Polyangiitis (MPA)-PR3",
      "Microscopic Polyangiitis (MPA)-MPO"),
    2
  ),
  stringsAsFactors = FALSE)

RAVE_ITN_BVAS_ADVIS3$subtype_ANCA_type_abr <-
  apply(
    RAVE_ITN_BVAS_ADVIS3,
    1,
    FUN = function(x) {
      if (x["Subtype_ANCA_type"] == "Wegener's Granulomatosis (WG)-PR3") {
        return("GPA_PR3")
      }

      if (x["Subtype_ANCA_type"] == "Wegener's Granulomatosis (WG)-MPO") {
        return("GPA_MPO")
      }

      if (x["Subtype_ANCA_type"] == "Microscopic Polyangiitis (MPA)-PR3") {
        return("MPA_PR3")
      }

      if (x["Subtype_ANCA_type"] == "Microscopic Polyangiitis (MPA)-MPO") {
        return("MPA_MPO")
      }
    }
  )

如果您想手动执行操作（如上述操作），则只需使用[]表示法即可确定将新列数据放置在何处。

#************************************************************#
# Manually add new column for alternative variables
RAVE_ITN_BVAS_ADVIS3 <- data.frame(
  Subtype_ANCA_type = rep(
    c("Wegener's Granulomatosis (WG)-PR3",
      "Wegener's Granulomatosis (WG)-MPO",
      "Microscopic Polyangiitis (MPA)-PR3",
      "Microscopic Polyangiitis (MPA)-MPO"),
    2
  ),
stringsAsFactors = FALSE)

# For the rows in the dataframe where Subtype_ANCA_type == "something", fill the next column.
RAVE_ITN_BVAS_ADVIS3[RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type == "Wegener's Granulomatosis (WG)-PR3" ,"subtype_ANCA_type_abr"] <- "GPA_PR3"
RAVE_ITN_BVAS_ADVIS3[RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type == "Wegener's Granulomatosis (WG)-MPO" ,"subtype_ANCA_type_abr"] <- "GPA_MPO"
RAVE_ITN_BVAS_ADVIS3[RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type == "Microscopic Polyangiitis (MPA)-PR3","subtype_ANCA_type_abr"] <- "MPA_PR3"
RAVE_ITN_BVAS_ADVIS3[RAVE_ITN_BVAS_ADVIS3$Subtype_ANCA_type == "Microscopic Polyangiitis (MPA)-MPO","subtype_ANCA_type_abr"] <- "MPA_MPO"

RAVE_ITN_BVAS_ADVIS3
#                    Subtype_ANCA_type subtype_ANCA_type_abr
# 1  Wegener's Granulomatosis (WG)-PR3               GPA_PR3
# 2  Wegener's Granulomatosis (WG)-MPO               GPA_MPO
# 3 Microscopic Polyangiitis (MPA)-PR3               MPA_PR3
# 4 Microscopic Polyangiitis (MPA)-MPO               MPA_MPO
# 5  Wegener's Granulomatosis (WG)-PR3               GPA_PR3
# 6  Wegener's Granulomatosis (WG)-MPO               GPA_MPO
# 7 Microscopic Polyangiitis (MPA)-PR3               MPA_PR3
# 8 Microscopic Polyangiitis (MPA)-MPO               MPA_MPO

如果要使用很多这些，可能需要制作一个查找表。您甚至可以使用excel或其他来源在csv文件中创建查找表，并使用read.csv读取表。

#************************************************************#
# Add new column from a lookup table
abv_lookup <- data.frame(
  Subtype_ANCA_type = c(
    "Wegener's Granulomatosis (WG)-PR3",
    "Wegener's Granulomatosis (WG)-MPO",
    "Microscopic Polyangiitis (MPA)-PR3",
    "Microscopic Polyangiitis (MPA)-MPO"
  ),
  subtype_ANCA_type_abr = c(
    "GPA_PR3",
    "GPA_MPO",
    "MPA_PR3",
    "MPA_MPO"
  ),
  stringsAsFactors = FALSE
)

RAVE_ITN_BVAS_ADVIS3 <- data.frame(
  Subtype_ANCA_type = rep(
    c("Wegener's Granulomatosis (WG)-PR3",
      "Wegener's Granulomatosis (WG)-MPO",
      "Microscopic Polyangiitis (MPA)-PR3",
      "Microscopic Polyangiitis (MPA)-MPO"),
    2
  ),
  stringsAsFactors = FALSE)

# Merge the two dataframes together by any common columns (Subtype_ANCA_type)
RAVE_ITN_BVAS_ADVIS3 <- merge(RAVE_ITN_BVAS_ADVIS3,abv_lookup)

RAVE_ITN_BVAS_ADVIS3
#                    Subtype_ANCA_type subtype_ANCA_type_abr
# 1 Microscopic Polyangiitis (MPA)-MPO               MPA_MPO
# 2 Microscopic Polyangiitis (MPA)-MPO               MPA_MPO
# 3 Microscopic Polyangiitis (MPA)-PR3               MPA_PR3
# 4 Microscopic Polyangiitis (MPA)-PR3               MPA_PR3
# 5  Wegener's Granulomatosis (WG)-MPO               GPA_MPO
# 6  Wegener's Granulomatosis (WG)-MPO               GPA_MPO
# 7  Wegener's Granulomatosis (WG)-PR3               GPA_PR3
# 8  Wegener's Granulomatosis (WG)-PR3               GPA_PR3

在数据框中使用基于另一列的值创建新列

1 个答案: