Category: R

R

the leading tool
many packages
active community

install.packages("swirl")
library(swirl)
swirl()

> ?mean
> x <- c(0:10, 50)
> x
 [1]  0  1  2  3  4  5  6  7  8  9 10 50
> xm <- mean(x)
> xm
[1] 8.75
> c(xm, mean(x, trim = 0.10))
[1] 8.75 5.50

> subset(statesInfo, state.region == 1)
               X state.abb state.area state.region population income illiteracy life.exp murder
7    Connecticut        CT       5009            1       3100   5348        1.1    72.48    3.1
19         Maine        ME      33215            1       1058   3694        0.7    70.39    2.7
21 Massachusetts        MA       8257            1       5814   4755        1.1    71.83    3.3
29 New Hampshire        NH       9304            1        812   4281        0.7    71.23    3.3
30    New Jersey        NJ       7836            1       7333   5237        1.1    70.93    5.2
32      New York        NY      49576            1      18076   4903        1.4    70.55   10.9
38  Pennsylvania        PA      45333            1      11860   4449        1.0    70.43    6.1
39  Rhode Island        RI       1214            1        931   4558        1.3    71.90    2.4
45       Vermont        VT       9609            1        472   3907        0.6    71.64    5.5
   highSchoolGrad frost  area
7            56.0   139  4862
19           54.7   161 30920
21           58.5   103  7826
29           57.6   174  9027
30           52.5   115  7521
32           52.7    82 47831
38           50.2   126 44966
39           46.4   127  1049
45           57.1   168  9267

Title
========================================================
This is an R Markdown document or RMD. Markdown is a simple formatting syntax for authoring web pages (click the **Help** toolbar button for more details on using R Markdown).

When you click the **Knit HTML** button a web page will be generated that includes both content as well as the output of any embedded R code chunks within the document.

R

> v <- c(1, 3, 5)
> v
[1] 1 3 5
> v[2]
[1] 3
> v[2] <- 10
> v
[1]  1 10  5
> length(v)
[1] 2
1] 2
> v <- seq(1, 10)
> v
 [1]  1  2  3  4  5  6  7  8  9 10
> v <- rep(1:5, times=3)
> v
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
> x <- c(1, 3, 5)
> y <- c(2, 4, 6)
> x*2
[1]  2  6 10
> x + y
[1]  3  7 11
> x > y
[1] FALSE FALSE FALSE
> x %in% y
[1] FALSE FALSE FALSE
> union(x, y)
[1] 1 3 5 2 4 6
> intersect(x, y)
numeric(0)
> setdiff(x, y)
[1] 1 3 5
> setequal(x, y)
[1] FALSE
> x <- c("S", "M", "L", "M", "L")
> x
[1] "S" "M" "L" "M" "L"
> x.fc <- factor(x)
> x.fc
[1] S M L M L
Levels: L M S
> levels(x.fc)
[1] "L" "M" "S"
> x.or <- ordered(x, levels=c("S","M","L"))
> x.or
[1] S M L M L
Levels: S < M < L
> x <- matrix(1:6, nrow=3, ncol=2)
> x
     [,1] [,2]
[1,]    1    4
[2,]    2    5
[3,]    3    6
> 
> x <- matrix(1:6, nrow=3, ncol=2, byrow=TRUE)
> x
     [,1] [,2]
[1,]    1    2
[2,]    3    4
[3,]    5    6
> x <- rbind(c(1, 2), 3:4, 5:6)
> x
     [,1] [,2]
[1,]    1    2
[2,]    3    4
[3,]    5    6
> x <- cbind(c(1,2),3:4,5:6)
> x
     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6
> x + 1
     [,1] [,2] [,3]
[1,]    2    4    6
[2,]    3    5    7
> 1/ x
     [,1]      [,2]      [,3]
[1,]  1.0 0.3333333 0.2000000
[2,]  0.5 0.2500000 0.1666667
> dim(x)
[1] 2 3
> nrow(x)
[1] 2
> ncol(x)
[1] 3
> x
     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6
> x[, 1]
[1] 1 2
> x[2,]
[1] 2 4 6
> x[1, 2]
[1] 3
> x[1, 1:2]
[1] 1 3
> x[1, c(1,2)]
[1] 1 3
> x[1, 2] <- 10
> x
     [,1] [,2] [,3]
[1,]    1   10    5
[2,]    2    4    6
> edit(x)
     col1 col2 col3
[1,]    1   10    5
[2,]    2    4    6
> x2 <- edit(x)
> x
     [,1] [,2] [,3]
[1,]    1   10    5
[2,]    2    4    6
> x <- list(5:10, "abc", matrix(1:6, nrow=2, ncol=3))
> x
[[1]]
[1]  5  6  7  8  9 10

[[2]]
[1] "abc"

[[3]]
     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6

> x[1]
[[1]]
[1]  5  6  7  8  9 10

> x[[1]]
[1]  5  6  7  8  9 10
> x[[3]][1, 2]
[1] 3
x <- read.table("sales.txt", header=TRUE, sep=",", na.strings="*")
sum(x$sales), max(x$sales), mean(x$sales),median(x$sales),sd($sales)
mean(x$DISTANCE, na.rm=TRUE), summary(x$sales), summary(x), str(x)