『Data Science』R语言学习笔记，基础语法

Matrices can be subsetted in the usual way with (i,j) type indices.

> x <- matrix(1:6,3)

> x[1,2]
[1] 3

> x[1,]
[1] 1 3 5

> x[,2]
[1] 3 4

> x[1,drop = FALSE]
     [,1]
[1,]    3

> x[1,1] [,2] [,3]
[1,]    1    3    5

Partial Matching

Partial matching of names is allowed with [[ and $.

> x <- list(aardvark = 1:5)

> x$a
[1] 1 2 3 4 5

> x[["a"]]
NULL

> x[["a",exact = FALSE]]
[1] 1 2 3 4 5

Removing NA Values

> x <- c(1,4,5)

> bad <- is.na(x)

> x[!bad]
[1] 1 2 4 5

Use built-in function complete.cases() to get a logical vector indicating which cases are complete,i.e.,have no missing values.

> x <- c(1,5)
> y <- c("a","f")

> good <- complete.cases(x,y)

> good
[1]  TRUE  TRUE FALSE  TRUE FALSE  TRUE

> x[good]
[1] 1 2 4 5
> y[good]
[1] "a" "b" "d" "f"

From data frame

> airquality[1:6,]                    ## call a matrix 
  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5   ## there a NA value in this vector
6    28      NA 14.9   66     5   6   ## there a NA value in this vector

> good <- complete.cases(airquality)  ## as there a NA value in 6s/7s row,so it is filtered.

> airquality[good,][1:6,]
  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4   
7    23     299  8.6   65     5   7
8    19      99 13.8   59     5   8

Vectorized Operations

• many operations in R are vectorized making code more efficient,concise,and easier to read.

> x <- 1:4; y <- 6:9

> x + y
[1]  7  9 11 13

> x > 2
[1] FALSE FALSE  TRUE  TRUE

> y >= 2
[1] TRUE TRUE TRUE TRUE

> y == 8
[1] FALSE FALSE  TRUE FALSE

> x * y
[1]  6 14 24 36

> x / y
[1] 0.1666667 0.2857143 0.3750000 0.4444444

Logic Control

if-else

> if (x > 3) {
+     y <- 10
+ } else {
+     y <- 0
+ }

For

> x <- c("a","d")
> for (i in 1:4) {
+     print(x[i])
+ }
[1] "a"
[1] "b"
[1] "c"
[1] "d"

> for(i in seq_along(x)) {
+     print(x[i])
+ }
[1] "a"
[1] "b"
[1] "c"
[1] "d"

> for(letter in x){
+     print(letter)
+ }
[1] "a"
[1] "b"
[1] "c"
[1] "d"

> for(i in 1:4) print(x[i])
[1] "a"
[1] "b"
[1] "c"
[1] "d"

While

> count <- 0
> while(count < 10) {
+     print(count)
+     count <- count + 1
+ }
[1] 0
[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9

> z <- 5
> while(z >=3 && z <= 10) {
+     print(z)
+     coin <- rbinom(1,1,0.5)
+     
+     if(coin == 1) {
+         z <- z + 1
+     } else {
+         z <- z - 1
+     }
+ }
[1] 5
[1] 4
[1] 3
[1] 4
[1] 5
[1] 4
[1] 5
[1] 4
[1] 3

Repeat

> x0 <- 1
> tol <- 1e-8
> repeat {
+     x1 <- computeEstimate()
+     if(abs(x1 - x0) < tol) {
+         break
+     } else {
+         x0 <- x1
+     }
+ }

> for(i in 1:100) {
+     if(i <= 20) {
+         next        ## jump into next loop
+     }
+ }

Function

> add2 <- function(x,y) {
+   x + y
+ }

> add2(2,3)
[1] 5

> above <- function(x,n = 10) {
+   use <- x >n
+   x[use]
+ }

> x <- 1:20
> above(x,10)
 [1] 11 12 13 14 15 16 17 18 19 20

> columnmean <- function(y,removeNA = TRUE) {
+   nc <- ncol(y)
+   means <- numeric(nc)
+   for(i in 1:nc) {
+     means[i] <- mean(y[,i],na.rm = removeNA)
+   }
+   means                       ## return result
+ }

> columnmean(airquality)        ## compute the mean of values of columns of `airqulity`.
[1]  42.129310 185.931507   9.957516  77.882353   6.993464  15.803922

The ... Argument

（编辑：核心网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!