R Language Learning Note (16): Handling Missing values

#识别缺失值install. Packages ("Vim") data (sleep,package= "vim") #列出没有缺失值的行sleep [Complete.cases (Sleep),]# Lists rows sleep[!complete.cases (sleep) with one or more missing values,] #有多少个缺失值sum (Is.na (sleep$dream)) #sleep The data for a percentage of the $dream is mean with missing values ( Is.na (Sleep$dream)) #数据集中多个行包含缺失值mean (!complete.cases (Sleep)) #探索缺失值install. Packages ("mice") the library (MICE) data ( Sleep,package= "Vim") Md.pattern (Sleep) #图形探索library ("Vim") Aggr (Sleep,prop=false,numbers=true)

Matrixplot (Sleep)

Marginplot (Sleep[c ("Gest", "Dream")],pch=c ("Col=c", "Red", "blue")

#用相关性探索缺失值x <-as.data.frame (is.na (Sleep)) head (sleep,n=5) head (x,n=5) Y<-x[which (Apply (X,2,sum) >0)] Cor (y)

Nond Dream Sleep Span Gest
Nond 1.00 0.91 0.49 0.02-0.14
Dream 0.91 1.00 0.20 0.04-0.13
Sleep 0.49 0.20 1.00-0.07-0.07
Span 0.02 0.04-0.07 1.00 0.20
gest-0.14-0.13-0.07 0.20 1.00

Cor (sleep,y,use= "Pairwise.complete.obs")

Nond Dream Sleep Span Gest
BODYWGT 0.23 0.22 0.002-0.06-0.05
BRAINWGT 0.18 0.16 0.008-0.08-0.07
Nond na na na-0.04-0.05
Dream-0.19 NA-0.189 0.12 0.23
sleep-0.08-0.08 NA 0.10 0.04
Span 0.08 0.06 0.005 NA-0.07
Gest 0.20 0.05 0.160-0.17 NA
Pred 0.05-0.07 0.202 0.02-0.20
EXP 0.25 0.13 0.261-0.19-0.19
Danger 0.07-0.07 0.209-0.07-0.20

#行删除newdata <-mydata[complete.cases (MyData),]newdata<-na.omit (MyData) options (Digits=1) Cor (na.omit (sleep)) FIT<-LM (Dream~span+gest,data=na.omit (Sleep)) Summary (FIT) #多重插补library (MICE) data (sleep,package= "VIM") imp<- Mice (sleep,seed=1234) Fit<-with (IMP,LM (dream~span+gest)) Pooled<-pool (FIT) Summary (Pooled) impimp$imp$ Dreamdataset3<-complete (imp,action=3) dataset3  #多重删补后的结果

BODYWGT brainwgt nond Dream Sleep Span Gest Pred Exp Danger
1 7e+03 6e+03 2 0.5 3 39 645 3 5 3
2 1e+00 7e+00 6 2.0 8 4 42 3 1 3
3 3e+00 4e+01 11 1.5 12 14 60 1 1 1
4 9e-01 6e+00 13 3.4 16 2 25 5 2 3
5 3e+03 5e+03 2 1.8 4 69 624 3 5 4
6 1e+01 2e+02 9 0.7 10 27 180 4 4 4
7 2e-02 3e-01 16 3.9 20 19 35 1 1 1
8 2e+02 2e+02 5 1.0 6 30 392 4 5 4
9 3e+00 3e+01 11 3.6 14 28 63 1 2 1
5E+01 4e+02 8 1.4 10 50 230 1 1 1
4E-01 6e+00 11 1.5 12 7 112 5 4 4
5E+02 4e+02 3 0.7 4 30 281 5 5 5
6E-01 2e+00 8 2.7 10 18 46 2 1 2
2E+02 4e+02 3 0.5 3 40 365 5 5 5
7E-02 1e+00 6 2.1 8 4 42 1 1 1
3e+00 2e+01 9 0.0 9 50 28 2 2 2
8e-01 4e+00 7 4.1 11 6 42 2 2 2
2E-01 5e+00 10 1.2 11 10 120 2 2 2
1E+00 2e+01 5 1.3 6 34 28 1 2 1
6E+01 8e+01 12 6.1 18 7 21 1 1 1
5E+02 7e+02 11 0.3 11 28 400 5 5 5
3E+01 1e+02 3 0.5 4 20 148 5 5 5
1E-01 1e+00 11 3.4 14 4 16 3 1 2
2E+02 4e+02 8 3.6 12 39 252 1 4 1
8E+01 3e+02 5 1.5 6 41 310 1 3 1
4E+01 1e+02 11 2.0 13 16 63 1 1 1
1E-01 4e+00 10 3.4 14 9 28 5 1 3
1e+00 6e+00 7 0.8 8 8 68 5 3 4
5E+02 7e+02 2 0.8 3 46 336 5 5 5
1E+02 2e+02 7 3.4 11 22 100 1 1 1
4E+01 6e+01 3 0.6 4 16 33 3 5 4
5E-03 1e-01 8 1.4 9 3 22 5 2 4
1E-02 2e-01 18 2.0 20 24 50 1 1 1
6E+01 1e+03 6 1.9 8 100 267 1 1 1
1E-01 3e+00 8 2.4 11 13 30 2 1 1
1e+00 8e+00 8 2.8 11 4 45 3 1 3
PNS 2e-02 4e-01 12 1.3 13 3 19 4 1 3
5E-02 3e-01 11 2.0 13 2 30 4 1 3
2e+00 6e+00 14 5.6 19 5 12 2 1 1
4e+00 1e+01 14 3.1 17 6 120 2 1 1
2E+02 5E+02 8 1.0 8 24 440 5 5 5
5E-01 2e+01 15 1.8 17 12 140 2 2 2
1E+01 1e+02 10 0.9 11 20 170 4 4 4
2e+00 1e+01 12 1.8 14 13 17 2 1 2
2E+02 2e+02 6 1.9 8 27 115 4 4 4
2e+00 1e+01 8 0.9 8 18 31 5 5 5
4e+00 4e+01 11 1.5 12 14 63 2 2 2
3E-01 2e+00 11 2.6 13 5 21 3 1 3
4e+00 5e+01 7 2.4 10 10 52 1 1 1
7E+00 2e+02 8 1.2 10 29 164 2 3 2
Wuyi 8e-01 1e+01 6 0.9 7 7 225 2 2 2
4e+00 2e+01 5 0.5 5 6 225 3 2 3
1E+01 1e+02 2 0.5 3 17 150 5 5 5
6E+01 2e+02 3 0.6 4 20 151 5 5 5
1e+00 1e+01 8 2.6 11 13 90 2 2 2
6E-02 1e+00 8 2.2 10 4 100 3 1 2
9E-01 3e+00 11 2.3 13 4 60 2 1 2
2e+00 1e+01 5 0.5 5 8 200 3 1 3
1E-01 2e+00 13 2.6 16 2 46 3 2 2
4e+00 6e+01 10 0.6 10 24 210 4 3 4
4e+00 4e+00 13 6.6 19 3 14 2 1 1
4e+00 2e+01 18 0.5 19 13 38 3 1 1

#成对删除cor (sleep,use= "Pairwise.complete.obs")

R Language Learning Note (16): Handling Missing values