我是个合成器:)。这里我把答案组合成一个函数:

#' keep rows that have a certain number (range) of NAs anywhere/somewhere and delete others
#' @param df a data frame
#' @param col restrict to the columns where you would like to search for NA; eg, 3, c(3), 2:5, "place", c("place","age")
#' \cr default is NULL, search for all columns
#' @param n integer or vector, 0, c(3,5), number/range of NAs allowed.
#' \cr If a number, the exact number of NAs kept
#' \cr Range includes both ends 3<=n<=5
#' \cr Range could be -Inf, Inf
#' @return returns a new df with rows that have NA(s) removed
#' @export
ez.na.keep = function(df, col=NULL, n=0){
    if (!is.null(col)) {
        # R converts a single row/col to a vector if the parameter col has only one col
        # see https://radfordneal.wordpress.com/2008/08/20/design-flaws-in-r-2-%E2%80%94-dropped-dimensions/#comments
        df.temp = df[,col,drop=FALSE]
    } else {
        df.temp = df
    }

    if (length(n)==1){
        if (n==0) {
            # simply call complete.cases which might be faster
            result = df[complete.cases(df.temp),]
        } else {
            # credit: http://stackoverflow.com/a/30461945/2292993
            log <- apply(df.temp, 2, is.na)
            logindex <- apply(log, 1, function(x) sum(x) == n)
            result = df[logindex, ]
        }
    }

    if (length(n)==2){
        min = n[1]; max = n[2]
        log <- apply(df.temp, 2, is.na)
        logindex <- apply(log, 1, function(x) {sum(x) >= min && sum(x) <= max})
        result = df[logindex, ]
    }

    return(result)
}

我更喜欢用下面的方法来检查行中是否包含NAs:

row.has.na <- apply(final, 1, function(x){any(is.na(x))})

这将返回逻辑向量，其中的值表示一行中是否有NA。你可以使用它来查看你需要删除多少行:

sum(row.has.na)

并最终放弃它们

final.filtered <- final[!row.has.na,]

对于过滤具有特定部分NAs的行，它变得有点棘手(例如，您可以将'final[，5:6]'输入到'apply')。 一般来说，Joris Meys的解决方案似乎更优雅。

我的猜测是，这个问题可以用这样一种更优雅的方式解决:

  m <- matrix(1:25, ncol = 5)
  m[c(1, 6, 13, 25)] <- NA
  df <- data.frame(m)
  library(dplyr) 
  df %>%
  filter_all(any_vars(is.na(.)))
  #>   X1 X2 X3 X4 X5
  #> 1 NA NA 11 16 21
  #> 2  3  8 NA 18 23
  #> 3  5 10 15 20 NA

使用{dplyr}包中的filter()函数和across()帮助函数是一种既通用又能产生可读性较好的代码的方法。

library(dplyr)

vars_to_check <- c("rnor", "cfam")

# Filter a specific list of columns to keep only non-missing entries

df %>% 
  filter(across(one_of(vars_to_check),
                ~ !is.na(.x)))

# Filter all the columns to exclude NA
df %>% 
  filter(across(everything(),
                ~ !is.na(.)))

# Filter only numeric columns
df %>%
  filter(across(where(is.numeric),
                ~ !is.na(.)))

类似地，在dplyr包中也有变体函数(filter_all, filter_at, filter_if)，它们完成同样的事情:

library(dplyr)

vars_to_check <- c("rnor", "cfam")

# Filter a specific list of columns to keep only non-missing entries
df %>% 
  filter_at(.vars = vars(one_of(vars_to_check)),
            ~ !is.na(.))

# Filter all the columns to exclude NA
df %>% 
  filter_all(~ !is.na(.))

# Filter only numeric columns
df %>%
  filter_if(is.numeric,
            ~ !is.na(.))

这将返回至少有一个非na值的行。

final[rowSums(is.na(final))<length(final),]

这将返回至少有两个非na值的行。

final[rowSums(is.na(final))<(length(final)-1),]

Tidyr有一个新函数drop_na:

library(tidyr)
df %>% drop_na()
#              gene hsap mmul mmus rnor cfam
# 2 ENSG00000199674    0    2    2    2    2
# 6 ENSG00000221312    0    1    2    3    2
df %>% drop_na(rnor, cfam)
#              gene hsap mmul mmus rnor cfam
# 2 ENSG00000199674    0    2    2    2    2
# 4 ENSG00000207604    0   NA   NA    1    2
# 6 ENSG00000221312    0    1    2    3    2