Question

我有这种格式的csv：

Col1_Status Col1_Value  Col2_Status Col2_Value Col3_Status  Col3__Value
LOW             5           HIGH         5         LOW           5
LOW             8           HIGH         8         LOW           8
HIGH            82          HIGH         8         LOW           7
HIGH            83          NORMAL       8         LOW           7
HIGH            82          NORMAL       8         LOW           7

我想创建一个包含高和低列的新数据框，例如：

Col1_High  Col1_Low Col2_High Col2_Low Col3_High Col3_Low
    82         5        5        NA        NA        5
    83         8        8        NA        NA        8
    82         NA       8        NA        NA        7
    NA         NA       NA       NA        NA        7
    NA         NA       NA       NA        NA        7

最好的方法是什么？

到目前为止，我认为：

#extract the Status Columns from original file into DataFrame
  statusDF <- ret[grepl("Status", colnames(ret))]

  #extract the Value Columns from original file into DataFrame
  originalValueDF <- ret[grepl("Value", colnames(ret))]

  #create new columns attribute_high and attribute_low
  for(i in names(originalValueDF)){
    newValueDF <- originalValueDF[[paste(i, 'High', sep = "_")]]
    newValueDF <- originalValueDF[[paste(i, 'Low', sep = "_")]]
  }

 #populate both columns based on value in attribute status column
 for(i in names(originalValueDF)){
    if (originalValueDF$i == "High"){
      temp <-  # stuck here
    }
  }

任何建议表示赞赏

Answer 1

以下是大量lapply的尝试。我们首先创建一个列表（l1），其中列出了每个＆＃39; High＆＃39;和＆＃39;低＆＃39;状态。但是，这些向量的长度是不同的，因此我们需要将它们全部设置为等于它们的最大值（在我们的例子中为ind）。我们将向量转换为具有2列（高和低）的矩阵，并使用do.call和cbind来获取最终的数据帧。

l1 <- lapply(seq(1, ncol(df), by = 2), function(i) list(HIGH = df[i+1][df[i] == 'HIGH'],
                                                         LOW = df[i+1][df[i] == 'LOW']))
names(l1) <- paste0('Col', seq(length(l1)))

ind <- max(unlist(lapply(l1, function(i) lengths(i))))

do.call(cbind, lapply(lapply(l1, function(i) lapply(i, `length<-`, ind)), function(j)
                    setNames(data.frame(matrix(unlist(j), ncol = 2)), c('High', 'Low'))))

#  Col1.High Col1.Low Col2.High Col2.Low Col3.High Col3.Low
#1        82        5         5       NA        NA        5
#2        83        8         8       NA        NA        8
#3        82       NA         8       NA        NA        7
#4        NA       NA        NA       NA        NA        7
#5        NA       NA        NA       NA        NA        7

Answer 2

ret <- read.table(text="
Col1_Status Col1_Value  Col2_Status Col2_Value Col3_Status  Col3__Value
LOW             5           HIGH         5         LOW           5
LOW             8           HIGH         8         LOW           8
HIGH            82          HIGH         8         LOW           7
HIGH            83          NORMAL       8         LOW           7
HIGH            82          NORMAL       8         LOW           7
", header = TRUE, stringsAsFactors = F)

# fix column headers
names(ret) <- gsub("(_+)", "_", names(ret))

library(stats)

# extract the column prefixes
prefixes <- unique(gsub("_.+", "", names(ret)))
value_names  <- names(ret[grepl("_Value",  names(ret))])
status_names <- names(ret[grepl("_Status", names(ret))])

library(stats)
# get the lwo values - extract the lows, pad with NA's and set the name to _High
high_values  <- sapply(1:length(prefixes),
                       function(i) {
                         result <- ret[which(ret[, status_names][i] == "HIGH"), value_names][[i]]
                         result[(length(result)+1):nrow(ret)+1] <- NA
                         setNames(list(foo = result[1:nrow(ret)]), paste0(prefixes[i], "_High"))})

# get the lwo values - extract the lows, pad with NA's and set the name to _Low
low_values  <- sapply(1:length(prefixes),
                      function(i) {
                        result <- ret[which(ret[, status_names][i] == "LOW"), value_names][[i]]
                        result[(length(result)+1):nrow(ret)+1] <- NA
                        setNames(list(foo = result[1:nrow(ret)]), paste0(prefixes[i], "_Low"))})

# combine
output <- cbind(data.frame(low_values), data.frame(high_values))

output

#   Col1_Low Col2_Low Col3_Low Col1_High Col2_High Col3_High
# 1        5       NA        5        82         5        NA
# 2        8       NA        8        83         8        NA
# 3       NA       NA        7        82         8        NA
# 4       NA       NA        7        NA        NA        NA
# 5       NA       NA        7        NA        NA        NA

根据现有列中的值在Dataframe中创建和填充新列

2 个答案: