Question

我正在处理一个大型数据框（30000多个观测值和20个变量），因此无法转置我的数据框。对于某些行，某些列会移至Date-class列的右侧，但不会移至Date-class列的左侧。我尝试根据发生偏移的列编写一个if语句，但是似乎无法绕开它。这是一些示例代码：

structure(list(Site = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("1", "2", "3"), class = "factor"), 
Vial = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L, 
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L, 5L, 6L, 
7L, 8L, 9L, 10L), Date = structure(c(15156, 15156, 15156, 
15156, 15156, 15156, 15156, 15156, 15156, 15156, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, 15156, 15156, 15156, 15156, 
15156, 15156, 15156, 15156, 15156, 15156), class = "Date"), 
Value_1 = c("a", "a", "a", "a", "a", "a", "a", "a", "a", 
"a", "2011-07-01", "2011-07-01", "2011-07-01", "2011-07-01", 
"2011-07-01", "2011-07-01", "2011-07-01", "2011-07-01", "2011-07-01", 
"2011-07-01", "a", "a", "a", "a", "a", "a", "a", "a", "a", 
"a"), Value_2 = c("b", "b", "b", "b", "b", "b", "b", "b", 
"b", "b", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", 
"b", "b", "b", "b", "b", "b", "b", "b", "b", "b"), Value_3 = c("c", 
"c", "c", "c", "c", "c", "c", "c", "c", "c", "b", "b", "b", 
"b", "b", "b", "b", "b", "b", "b", "c", "c", "c", "c", "c", 
"c", "c", "c", "c", "c"), Value_4 = c(NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, "c", "c", "c", "c", "c", "c", "c", "c", 
"c", "c", "d", "d", "d", "d", "d", "d", "d", "d", "d", "d"
)), row.names = c(NA, -30L), class = "data.frame")

请注意，最后一列包含NA的值，也包含值。

Answer 1

我再次敦促上游流程应该是固定的。在此期间，此骇客暂时应该可以正常工作。

nadate <- is.na(x$Date)
newdate <- as.Date(x$Value_1[nadate])
newnotna <- !is.na(newdate)
x$Date[nadate] <- newdate[newnotna]
ind <- seq(which(colnames(x) == "Date") + 1L, ncol(x) - 1L)
x[nadate & newnotna, ind] <- x[nadate & newnotna, ind + 1L]
x[nadate & newnotna, ncol(x)] <- NA
x
#    Site Vial       Date Value_1 Value_2 Value_3 Value_4
# 1     1    1 2011-07-01       a       b       c    <NA>
# 2     1    2 2011-07-01       a       b       c    <NA>
# 3     1    3 2011-07-01       a       b       c    <NA>
# 4     1    4 2011-07-01       a       b       c    <NA>
# 5     1    5 2011-07-01       a       b       c    <NA>
# 6     1    6 2011-07-01       a       b       c    <NA>
# 7     1    7 2011-07-01       a       b       c    <NA>
# 8     1    8 2011-07-01       a       b       c    <NA>
# 9     1    9 2011-07-01       a       b       c    <NA>
# 10    1   10 2011-07-01       a       b       c    <NA>
# 11    2    1 2011-07-01       a       b       c    <NA>
# 12    2    2 2011-07-01       a       b       c    <NA>
# 13    2    3 2011-07-01       a       b       c    <NA>
# 14    2    4 2011-07-01       a       b       c    <NA>
# 15    2    5 2011-07-01       a       b       c    <NA>
# 16    2    6 2011-07-01       a       b       c    <NA>
# 17    2    7 2011-07-01       a       b       c    <NA>
# 18    2    8 2011-07-01       a       b       c    <NA>
# 19    2    9 2011-07-01       a       b       c    <NA>
# 20    2   10 2011-07-01       a       b       c    <NA>
# 21    3    1 2011-07-01       a       b       c       d
# 22    3    2 2011-07-01       a       b       c       d
# 23    3    3 2011-07-01       a       b       c       d
# 24    3    4 2011-07-01       a       b       c       d
# 25    3    5 2011-07-01       a       b       c       d
# 26    3    6 2011-07-01       a       b       c       d
# 27    3    7 2011-07-01       a       b       c       d
# 28    3    8 2011-07-01       a       b       c       d
# 29    3    9 2011-07-01       a       b       c       d
# 30    3   10 2011-07-01       a       b       c       d

这应该足够稳定：如果对同一数据多次运行，则仅此而已。如果$Date列不是NA，则不尝试移动。如果$Value_1没有解析为日期，则没有任何变化。

根据列值向左移动行

1 个答案: