money=c("50000","$50,000","50,000",50000)
class(money)
## [1] "character"
mean(money)
## Warning in mean.default(money): argument is not numeric or logical:
## returning NA
## [1] NA
money1=gsub("\\$","",money)
money1
## [1] "50000" "50,000" "50,000" "50000"
money2=gsub(",","",money1)
money2
## [1] "50000" "50000" "50000" "50000"
money3=as.numeric(money2)
money3
## [1] 50000 50000 50000 50000
mean(money3)
## [1] 50000
ls()
## [1] "money" "money1" "money2" "money3"
rm("money2")
rm(list = ls())
data(mtcars)
str(mtcars)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
tail(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.7 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.5 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.5 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.6 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.6 1 1 4 2
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
table(mtcars$gear)
##
## 3 4 5
## 15 12 5
table(mtcars$cyl)
##
## 4 6 8
## 11 7 14
summary(mtcars$mpg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.42 19.20 20.09 22.80 33.90
library(Hmisc)
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## Loading required package: ggplot2
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:base':
##
## format.pval, round.POSIXt, trunc.POSIXt, units
describe(mtcars$mpg)
## mtcars$mpg
## n missing distinct Info Mean Gmd .05 .10
## 32 0 25 0.999 20.09 6.796 12.00 14.34
## .25 .50 .75 .90 .95
## 15.43 19.20 22.80 30.09 31.30
##
## lowest : 10.4 13.3 14.3 14.7 15.0, highest: 26.0 27.3 30.4 32.4 33.9
summarize(mtcars$mpg,mtcars$cyl,median)
## mtcars$cyl mtcars$mpg
## 1 4 26.0
## 2 6 19.7
## 3 8 15.2
summarize(mtcars$mpg,mtcars$cyl,summary)
## mtcars$cyl mtcars.mpg X1st.Qu. Median Mean X3rd.Qu. Max.
## 1 4 21.4 22.80 26.0 26.66 30.40 33.9
## 2 6 17.8 18.65 19.7 19.74 21.00 21.4
## 3 8 10.4 14.40 15.2 15.10 16.25 19.2
a=sample(150,15,F)
a
## [1] 84 121 31 91 141 144 42 5 133 57 138 62 1 28 24
iris[a,]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 84 6.0 2.7 5.1 1.6 versicolor
## 121 6.9 3.2 5.7 2.3 virginica
## 31 4.8 3.1 1.6 0.2 setosa
## 91 5.5 2.6 4.4 1.2 versicolor
## 141 6.7 3.1 5.6 2.4 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 42 4.5 2.3 1.3 0.3 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 133 6.4 2.8 5.6 2.2 virginica
## 57 6.3 3.3 4.7 1.6 versicolor
## 138 6.4 3.1 5.5 1.8 virginica
## 62 5.9 3.0 4.2 1.5 versicolor
## 1 5.1 3.5 1.4 0.2 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 24 5.1 3.3 1.7 0.5 setosa
rnorm(15,10,5)
## [1] 7.791940 8.673322 9.450006 1.384519 12.593717 9.959854 8.084755
## [8] 11.661243 10.393114 7.339284 3.160930 12.492351 9.705864 3.552195
## [15] 12.423059
c=mean(seq(1:150))
c
## [1] 75.5
d=sd(seq(1:150))
d
## [1] 43.44537
e=rnorm(15,c,d)
e
## [1] 65.087672 68.987699 28.277697 29.684220 68.436212 113.336327
## [7] 9.631312 15.853962 22.791236 87.269415 116.418454 132.651133
## [13] 106.269797 120.968167 77.956584
f=round(e,0)
f
## [1] 65 69 28 30 68 113 10 16 23 87 116 133 106 121 78
f2=ifelse(f<=0,1,f)
f3=ifelse(f>150,150,f2)
unique(f3)
## [1] 65 69 28 30 68 113 10 16 23 87 116 133 106 121 78
iris[f,]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 65 5.6 2.9 3.6 1.3 versicolor
## 69 6.2 2.2 4.5 1.5 versicolor
## 28 5.2 3.5 1.5 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 68 5.8 2.7 4.1 1.0 versicolor
## 113 6.8 3.0 5.5 2.1 virginica
## 10 4.9 3.1 1.5 0.1 setosa
## 16 5.7 4.4 1.5 0.4 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 87 6.7 3.1 4.7 1.5 versicolor
## 116 6.4 3.2 5.3 2.3 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 121 6.9 3.2 5.7 2.3 virginica
## 78 6.7 3.0 5.0 1.7 versicolor
f
## [1] 65 69 28 30 68 113 10 16 23 87 116 133 106 121 78