用最后一个不是 NA 的值填充 NA 列值（na.locf by column）
Fill in NA column values with the last value that was not NA (na.locf by column)
我正在清理我的数据，dput 如下所示。
DF <- structure(list(toberevised = c("[Money amounts are in thousands of dollars]",
NA, NA, NA, "Item", NA, NA, NA, NA, "Number of returns", "Number of joint returns",
"Number with paid preparer's signature", "Number of exemptions",
"Adjusted gross income (AGI) [3]", "Salaries and wages in AGI: [4] Number",
"Salaries and wages in AGI: Amount", "Taxable interest: Number",
"Taxable interest: Amount", "Ordinary dividends: Number", "Ordinary dividends: Amount"
), ...2 = c("UNITED STATES [2]", NA, NA, NA, "All returns", NA,
NA, "1", NA, "135257620", "52607676", "80455243", "273738434",
"7364640131", "114060887", "5161583318", "59553985", "161324824",
"31158675", "164247298"), ...3 = c(NA, NA, NA, NA, "Under", ",000 [1]",
NA, "2", NA, "92150166", "20743943", "53622647", "159649737",
"1797097083", "75422766", "1541276272", "28527550", "39043002",
"13174923", "23867893"), ...4 = c(NA, NA, "Size of adjusted gross income",
NA, "50000", "under", "75000", "3", NA, "18221115", "11329459",
"11025624", "44189517", "1119634632", "16299827", "896339313",
"10891905", "16353293", "5255958", "12810282"), ...5 = c(NA,
NA, NA, NA, "75000", "under", "100000", "4", NA, "10499106",
"8296546", "6260725", "28555195", "905336768", "9520214", "721137490",
"7636612", "12852148", "4095938", "11524298"), ...6 = c(NA, NA,
NA, NA, "100000", "under", "200000", "5", NA, "10797979", "9193700",
"6678965", "30919226", "1429575727", "9782173", "1083175205",
"9092673", "23160862", "5824522", "25842394"), ...7 = c(NA, NA,
NA, NA, "200000", "or more", NA, "6", NA, "3589254", "3044028",
"2867282", "10424759", "2112995921", "3035907", "919655038",
"3405245", "69915518", "2807334", "90202431")), row.names = c(NA,
-20L), class = c("tbl_df", "tbl", "data.frame"))
在第一行和第三行中，我想使用 zoo 中的 na.locf 之类的东西，但不是在行上而是在列上，这样 DF 就变成了。
DF[1,3:7] <- "UNITED STATES [2]"
DF[1,5:7] <- "Size of adjusted gross income"
按行应用na.locf：
DF[] <- t(apply(DF, 1, zoo::na.locf, na.rm = FALSE))
DF
# A tibble: 20 x 7
# toberevised ...2 ...3 ...4 ...5 ...6 ...7
# <chr> <chr> <chr> <chr> <chr> <chr> <chr>
# 1 [Money amounts are in th… UNITED ST… UNITED ST… UNITED STATES … UNITED STATES … UNITED STATES … UNITED STATES…
# 2 NA NA NA NA NA NA NA
# 3 NA NA NA Size of adjust… Size of adjust… Size of adjust… Size of adjus…
# 4 NA NA NA NA NA NA NA
# 5 Item All retur… Under 50000 75000 100000 200000
# 6 NA NA ,000 [… under under under or more
# 7 NA NA NA 75000 100000 200000 200000
# 8 NA 1 2 3 4 5 6
# 9 NA NA NA NA NA NA NA
#10 Number of returns 135257620 92150166 18221115 10499106 10797979 3589254
#11 Number of joint returns 52607676 20743943 11329459 8296546 9193700 3044028
#12 Number with paid prepare… 80455243 53622647 11025624 6260725 6678965 2867282
#13 Number of exemptions 273738434 159649737 44189517 28555195 30919226 10424759
#14 Adjusted gross income (A… 7364640131 1797097083 1119634632 905336768 1429575727 2112995921
#15 Salaries and wages in AG… 114060887 75422766 16299827 9520214 9782173 3035907
#16 Salaries and wages in AG… 5161583318 1541276272 896339313 721137490 1083175205 919655038
#17 Taxable interest: Number 59553985 28527550 10891905 7636612 9092673 3405245
#18 Taxable interest: Amount 161324824 39043002 16353293 12852148 23160862 69915518
#19 Ordinary dividends: Num… 31158675 13174923 5255958 4095938 5824522 2807334
#20 Ordinary dividends: Amou… 164247298 23867893 12810282 11524298 25842394 90202431
按照@G 的建议。 Grothendieck na.locf0 是一个更好的候选人。
DF[] <- t(apply(DF, 1, zoo::na.locf0))
我正在清理我的数据，dput 如下所示。
DF <- structure(list(toberevised = c("[Money amounts are in thousands of dollars]",
NA, NA, NA, "Item", NA, NA, NA, NA, "Number of returns", "Number of joint returns",
"Number with paid preparer's signature", "Number of exemptions",
"Adjusted gross income (AGI) [3]", "Salaries and wages in AGI: [4] Number",
"Salaries and wages in AGI: Amount", "Taxable interest: Number",
"Taxable interest: Amount", "Ordinary dividends: Number", "Ordinary dividends: Amount"
), ...2 = c("UNITED STATES [2]", NA, NA, NA, "All returns", NA,
NA, "1", NA, "135257620", "52607676", "80455243", "273738434",
"7364640131", "114060887", "5161583318", "59553985", "161324824",
"31158675", "164247298"), ...3 = c(NA, NA, NA, NA, "Under", ",000 [1]",
NA, "2", NA, "92150166", "20743943", "53622647", "159649737",
"1797097083", "75422766", "1541276272", "28527550", "39043002",
"13174923", "23867893"), ...4 = c(NA, NA, "Size of adjusted gross income",
NA, "50000", "under", "75000", "3", NA, "18221115", "11329459",
"11025624", "44189517", "1119634632", "16299827", "896339313",
"10891905", "16353293", "5255958", "12810282"), ...5 = c(NA,
NA, NA, NA, "75000", "under", "100000", "4", NA, "10499106",
"8296546", "6260725", "28555195", "905336768", "9520214", "721137490",
"7636612", "12852148", "4095938", "11524298"), ...6 = c(NA, NA,
NA, NA, "100000", "under", "200000", "5", NA, "10797979", "9193700",
"6678965", "30919226", "1429575727", "9782173", "1083175205",
"9092673", "23160862", "5824522", "25842394"), ...7 = c(NA, NA,
NA, NA, "200000", "or more", NA, "6", NA, "3589254", "3044028",
"2867282", "10424759", "2112995921", "3035907", "919655038",
"3405245", "69915518", "2807334", "90202431")), row.names = c(NA,
-20L), class = c("tbl_df", "tbl", "data.frame"))
在第一行和第三行中，我想使用 zoo 中的 na.locf 之类的东西，但不是在行上而是在列上，这样 DF 就变成了。
DF[1,3:7] <- "UNITED STATES [2]"
DF[1,5:7] <- "Size of adjusted gross income"
按行应用na.locf：
DF[] <- t(apply(DF, 1, zoo::na.locf, na.rm = FALSE))
DF
# A tibble: 20 x 7
# toberevised ...2 ...3 ...4 ...5 ...6 ...7
# <chr> <chr> <chr> <chr> <chr> <chr> <chr>
# 1 [Money amounts are in th… UNITED ST… UNITED ST… UNITED STATES … UNITED STATES … UNITED STATES … UNITED STATES…
# 2 NA NA NA NA NA NA NA
# 3 NA NA NA Size of adjust… Size of adjust… Size of adjust… Size of adjus…
# 4 NA NA NA NA NA NA NA
# 5 Item All retur… Under 50000 75000 100000 200000
# 6 NA NA ,000 [… under under under or more
# 7 NA NA NA 75000 100000 200000 200000
# 8 NA 1 2 3 4 5 6
# 9 NA NA NA NA NA NA NA
#10 Number of returns 135257620 92150166 18221115 10499106 10797979 3589254
#11 Number of joint returns 52607676 20743943 11329459 8296546 9193700 3044028
#12 Number with paid prepare… 80455243 53622647 11025624 6260725 6678965 2867282
#13 Number of exemptions 273738434 159649737 44189517 28555195 30919226 10424759
#14 Adjusted gross income (A… 7364640131 1797097083 1119634632 905336768 1429575727 2112995921
#15 Salaries and wages in AG… 114060887 75422766 16299827 9520214 9782173 3035907
#16 Salaries and wages in AG… 5161583318 1541276272 896339313 721137490 1083175205 919655038
#17 Taxable interest: Number 59553985 28527550 10891905 7636612 9092673 3405245
#18 Taxable interest: Amount 161324824 39043002 16353293 12852148 23160862 69915518
#19 Ordinary dividends: Num… 31158675 13174923 5255958 4095938 5824522 2807334
#20 Ordinary dividends: Amou… 164247298 23867893 12810282 11524298 25842394 90202431
按照@G 的建议。 Grothendieck na.locf0 是一个更好的候选人。
DF[] <- t(apply(DF, 1, zoo::na.locf0))