R語言缺失值處理

缺失值

1. is.na 確實(shí)值位置判斷
注意: 缺失值被認(rèn)為是不可比較的，即便是與缺失值自身的比較。這意味著無法使用比較運(yùn)算
符來檢測缺失值是否存在。例如，邏輯測試myvar == NA的結(jié)果永遠(yuǎn)不會(huì)為TRUE。作為
替代，你只能使用處理缺失值的函數(shù)（如本節(jié)中所述的那些）來識(shí)別出R數(shù)據(jù)對象中的缺
失值。
2. na.omit() 刪除不完整觀測

manyNAs

manyNAs(data, nORp = 0.2)
Arguments

data
A data frame with the data set.

nORp
A number controlling when a row is considered to have too many NA values (defaults to 0.2, i.e. 20% of the columns). If no rows satisfy the constraint indicated by the user, a warning is generated.
按照比例判斷缺失.
3. knnImputation K近鄰填補(bǔ)
library(DMwR)
knnImputation(data, k = 10, scale = T, meth = "weighAvg", distData = NULL)

Arguments

Details
This function uses the k-nearest neighbours to fill in the unknown (NA) values in a data set. For each case with any NA value it will search for its k most similar cases and use the values of these cases to fill in the unknowns.

If meth=’median’ the function will use either the median (in case of numeric variables) or the most frequent value (in case of factors), of the neighbours to fill in the NAs. If meth=’weighAvg’ the function will use a weighted average of the values of the neighbours. The weights are given by exp(-dist(k,x) where dist(k,x) is the euclidean distance between the case with NAs (x) and the neighbour k

例子:

#首先讀入程序包并對數(shù)據(jù)進(jìn)行清理
library(DMwR)
data(algae)
algae <- algae[-manyNAs(algae), ]
clean.algae <- knnImputation(algae[,1:12],k=10)

> head(clean.algae)
  season  size  speed mxPH mnO2     Cl    NO3     NH4    oPO4     PO4 Chla   a1
1 winter small medium 8.00  9.8 60.800  6.238 578.000 105.000 170.000 50.0  0.0
2 spring small medium 8.35  8.0 57.750  1.288 370.000 428.750 558.750  1.3  1.4
3 autumn small medium 8.10 11.4 40.020  5.330 346.667 125.667 187.057 15.6  3.3
4 spring small medium 8.07  4.8 77.364  2.302  98.182  61.182 138.700  1.4  3.1
5 autumn small medium 8.06  9.0 55.350 10.416 233.700  58.222  97.580 10.5  9.2
6 winter small   high 8.25 13.1 65.750  9.248 430.000  18.250  56.667 28.4 15.1
4. centralImputation()中心插值

用非缺失樣本的中位數(shù)(median)對缺失數(shù)據(jù)進(jìn)行插值

data(algae)
cleanAlgae <- centralImputation(algae)
summary(cleanAlgae)
5. complete.cases() 尋找完整數(shù)據(jù)集

x <- airquality[, -1] # x is a regression design matrix
y <- airquality[,  1] # y is the corresponding response
#驗(yàn)證是否complete.cases結(jié)果與is.na一樣
stopifnot(complete.cases(y) != is.na(y))
#x,y共同的非缺失行的bool結(jié)果
ok <- complete.cases(x, y)
#共有幾個(gè)缺失樣本
sum(!ok) # how many are not "ok" ?
#得到非缺失樣本
x <- x[ok,]
y <- y[ok]
6. na.fail()是否有遺漏值

DF <- data.frame(x = c(1, 2, 3), y = c(0, 10, NA))
na.fail(DF)

Error in na.fail.default(DF) : 對象里有遺漏值