2016-10-17.Rt

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R ist freie Software und kommt OHNE JEGLICHE GARANTIE.
Sie sind eingeladen, es unter bestimmten Bedingungen weiter zu verbreiten.
Tippen Sie 'license()' or 'licence()' für Details dazu.

R ist ein Gemeinschaftsprojekt mit vielen Beitragenden.
Tippen Sie 'contributors()' für mehr Information und 'citation()',
um zu erfahren, wie R oder R packages in Publikationen zitiert werden können.

Tippen Sie 'demo()' für einige Demos, 'help()' für on-line Hilfe, oder
'help.start()' für eine HTML Browserschnittstelle zur Hilfe.
Tippen Sie 'q()', um R zu verlassen.

> options(STERM='iESS', str.dendrogram.last="'", editor='emacsclient', show.error.locations=TRUE)
> 
+ . + + . + + . + 
> ##### First Session 2016
> 
> ### logical vector
> lv <- c(TRUE, TRUE, FALSE, rep(TRUE, 7))

> # lv[7:9] <- c(FALSE, FALSE)
> mode(lv)
[1] "logical"

> sum(lv)
[1] 9

> sum(lv)/length(lv)
[1] 0.9

> ### integer
> iv <- c(2L, 5L, as.integer(seq(2, 16, by = 2)))

> mode(iv)
[1] "numeric"

> 1:7
[1] 1 2 3 4 5 6 7

> is.integer(iv)
[1] TRUE

> seq()
[1] 1

> ### double (numeric)
> dv <- numeric(10)

> set.seed(1)

> dv <- c(seq(2, 16, by = 2.5), rnorm(4))

> rnorm(10, 5, 0.2)
 [1] 5.065902 4.835906 5.097486 5.147665 5.115156 4.938922 5.302356 5.077969
 [9] 4.875752 4.557060

> rnorm(10, 5, 0.2)
 [1] 5.224986 4.991013 4.996762 5.188767 5.164244 5.118780 5.183795 5.156427
 [9] 5.014913 4.602130

> set.seed(10)

> rnorm(10, 5, 0.2)
 [1] 5.003749 4.963149 4.725734 4.880166 5.058909 5.077959 4.758385 4.927265
 [9] 4.674665 4.948704

> rnorm(10, 5, 0.2)
 [1] 5.220356 5.151156 4.952353 5.197489 5.148278 5.017869 4.809011 4.960970
 [9] 5.185104 5.096596

> dv
 [1]  2.0000000  4.5000000  7.0000000  9.5000000 12.0000000 14.5000000
 [7] -0.6264538  0.1836433 -0.8356286  1.5952808

> ### character vector
> cv <- c("sdf", rep("SLU", 3))

> cv
[1] "sdf" "SLU" "SLU" "SLU"

> letters[7:9]
[1] "g" "h" "i"

> cv <- letters[iv]

> sample(LETTERS, 30, replace = TRUE)
 [1] "H" "F" "A" "S" "G" "E" "A" "M" "C" "U" "J" "Y" "G" "M" "E" "P" "L" "M" "K"
[20] "N" "A" "C" "M" "K" "V" "T" "O" "L" "C" "F"

> mode(cv)
[1] "character"

> ### combine it
> t1 <- c(cv, iv)

> is.character(c(cv, iv))
[1] TRUE

> t1[c(2, 15)]
[1] "e" "6"

> t1[c(2, 15)] <- NA

> iv1 <- (NA_real_)

> mode(NA)
[1] "logical"

> mode(NA_character_)
[1] "character"

> ### list
> vector(mode = "list", length = 3)
[[1]]
NULL

[[2]]
NULL

[[3]]
NULL


> l1 <- list(cv, iv, dv)

> length(l1)
[1] 3

> l1[[2]][2]
[1] 5

> class(l1)
[1] "list"

> l1[2]
[[1]]
 [1]  2  5  2  4  6  8 10 12 14 16


> class(l1[2])
[1] "list"

> length(l1[2])
[1] 1

> l1[[2]]
 [1]  2  5  2  4  6  8 10 12 14 16

> class(l1[[2]])
[1] "integer"

> length(l1[[2]])
[1] 10

> unlist(l1)
 [1] "b"                  "e"                  "b"                 
 [4] "d"                  "f"                  "h"                 
 [7] "j"                  "l"                  "n"                 
[10] "p"                  "2"                  "5"                 
[13] "2"                  "4"                  "6"                 
[16] "8"                  "10"                 "12"                
[19] "14"                 "16"                 "2"                 
[22] "4.5"                "7"                  "9.5"               
[25] "12"                 "14.5"               "-0.626453810742332"
[28] "0.183643324222082"  "-0.835628612410047" "1.59528080213779"  

> l2 <- list(x = l1, y = runif(10))

> length(l2[["x"]])
[1] 3

> l2[["x"]]
[[1]]
 [1] "b" "e" "b" "d" "f" "h" "j" "l" "n" "p"

[[2]]
 [1]  2  5  2  4  6  8 10 12 14 16

[[3]]
 [1]  2.0000000  4.5000000  7.0000000  9.5000000 12.0000000 14.5000000
 [7] -0.6264538  0.1836433 -0.8356286  1.5952808


> l2[[1]]
[[1]]
 [1] "b" "e" "b" "d" "f" "h" "j" "l" "n" "p"

[[2]]
 [1]  2  5  2  4  6  8 10 12 14 16

[[3]]
 [1]  2.0000000  4.5000000  7.0000000  9.5000000 12.0000000 14.5000000
 [7] -0.6264538  0.1836433 -0.8356286  1.5952808


> names(l2)
[1] "x" "y"

> ##### Coffee now :-) #####
> 
> ### Questions
> ## Komma = .
> 2.5
[1] 2.5

> ## list workspace: ls()
> ls()
[1] "cv"  "dv"  "iv"  "iv1" "l1"  "l2"  "lv"  "t1" 

> ### Your turn: create a list l3 where 
> ### x is a vector from 1 to 15 and
> ### y is a vector from 10 to 1
> 
> l3 <- list(x = 1:15, y = 10:1)

> l3
$x
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

$y
 [1] 10  9  8  7  6  5  4  3  2  1


> list(x = seq(1, 15), y = rev(1:10))
$x
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

$y
 [1] 10  9  8  7  6  5  4  3  2  1


> rev(letters)
 [1] "z" "y" "x" "w" "v" "u" "t" "s" "r" "q" "p" "o" "n" "m" "l" "k" "j" "i" "h"
[20] "g" "f" "e" "d" "c" "b" "a"

> unlist(l1[-1])
 [1]  2.0000000  5.0000000  2.0000000  4.0000000  6.0000000  8.0000000
 [7] 10.0000000 12.0000000 14.0000000 16.0000000  2.0000000  4.5000000
[13]  7.0000000  9.5000000 12.0000000 14.5000000 -0.6264538  0.1836433
[19] -0.8356286  1.5952808

> ### data.frame
> length(iv)
[1] 10

> length(cv)
[1] 10

> stopifnot(length(iv) == length(cv))

> # stopifnot(length(iv) == 15)
> df1 <- data.frame(x = iv, y = cv,
+                   stringsAsFactors = FALSE)

> df1
    x y
1   2 b
2   5 e
3   2 b
4   4 d
5   6 f
6   8 h
7  10 j
8  12 l
9  14 n
10 16 p

> cv[2] <- "x"

> cv
 [1] "b" "x" "b" "d" "f" "h" "j" "l" "n" "p"

> df1
    x y
1   2 b
2   5 e
3   2 b
4   4 d
5   6 f
6   8 h
7  10 j
8  12 l
9  14 n
10 16 p

> df1[2, 2]
[1] "e"

> str(df1)
'data.frame':	10 obs. of  2 variables:
 $ x: int  2 5 2 4 6 8 10 12 14 16
 $ y: chr  "b" "e" "b" "d" ...

> df2 <- data.frame(iv, cv, dv, lv)

> df2
   iv cv         dv    lv
1   2  b  2.0000000  TRUE
2   5  x  4.5000000  TRUE
3   2  b  7.0000000 FALSE
4   4  d  9.5000000  TRUE
5   6  f 12.0000000  TRUE
6   8  h 14.5000000  TRUE
7  10  j -0.6264538  TRUE
8  12  l  0.1836433  TRUE
9  14  n -0.8356286  TRUE
10 16  p  1.5952808  TRUE

> str(df2)
'data.frame':	10 obs. of  4 variables:
 $ iv: int  2 5 2 4 6 8 10 12 14 16
 $ cv: Factor w/ 9 levels "b","d","f","h",..: 1 9 1 2 3 4 5 6 7 8
 $ dv: num  2 4.5 7 9.5 12 ...
 $ lv: logi  TRUE TRUE FALSE TRUE TRUE TRUE ...

> df2[2:3, 2]
[1] x b
Levels: b d f h j l n p x

> df2[5, 2:4]
  cv dv   lv
5  f 12 TRUE

> df2[5, ]
  iv cv dv   lv
5  6  f 12 TRUE

> df2[ ,2]
 [1] b x b d f h j l n p
Levels: b d f h j l n p x

> df2[-5, ]
   iv cv         dv    lv
1   2  b  2.0000000  TRUE
2   5  x  4.5000000  TRUE
3   2  b  7.0000000 FALSE
4   4  d  9.5000000  TRUE
6   8  h 14.5000000  TRUE
7  10  j -0.6264538  TRUE
8  12  l  0.1836433  TRUE
9  14  n -0.8356286  TRUE
10 16  p  1.5952808  TRUE

> df2[6, 2]
[1] h
Levels: b d f h j l n p x

> names(df2)
[1] "iv" "cv" "dv" "lv"

> is.list(df2)
[1] TRUE

> class(df2)
[1] "data.frame"

> df2[[2]]
 [1] b x b d f h j l n p
Levels: b d f h j l n p x

> df2[[2]] == df2[, 2]
 [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

> all(df2[[2]] == df2[, 2])
[1] TRUE

> sum(df2[[2]] != df2[, 2])
[1] 0

> all(df2[[2]] == factor(cv))
[1] TRUE

> all(df2[[2]] == cv)
[1] TRUE

> all.equal(df2[[2]], df2[, 2])
[1] TRUE

> str(df2)
'data.frame':	10 obs. of  4 variables:
 $ iv: int  2 5 2 4 6 8 10 12 14 16
 $ cv: Factor w/ 9 levels "b","d","f","h",..: 1 9 1 2 3 4 5 6 7 8
 $ dv: num  2 4.5 7 9.5 12 ...
 $ lv: logi  TRUE TRUE FALSE TRUE TRUE TRUE ...

> df2$cv
 [1] b x b d f h j l n p
Levels: b d f h j l n p x

> ### special values
> t2 <- dv

> t2[5] <- NA

> t2[9] <- 0

> t2
 [1]  2.0000000  4.5000000  7.0000000  9.5000000         NA 14.5000000
 [7] -0.6264538  0.1836433  0.0000000  1.5952808

> summary(t2)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
-0.6265  0.1836  2.0000  4.2950  7.0000 14.5000       1 

> sum(t2)
[1] NA

> sum(dv)
[1] 49.81684

> sum(t2, na.rm = TRUE)
[1] 38.65247

> sum(t2[-5])
[1] 38.65247

> 12 / t2
 [1]   6.0000000   2.6666667   1.7142857   1.2631579          NA   0.8275862
 [7] -19.1554426  65.3440578         Inf   7.5221867

> 0 / 0
[1] NaN

> t3 <- 12 / t2

> mean(t3, na.rm = TRUE)
[1] Inf

> median(t3, na.rm = TRUE)
[1] 2.666667

> t4 <- NULL

> is.null(NULL)
[1] TRUE

> length(NULL)
[1] 0

> length(NA)
[1] 1

> c(t4, iv)
 [1]  2  5  2  4  6  8 10 12 14 16

> length(c(t4, iv))
[1] 10

> c(NA, iv)
 [1] NA  2  5  2  4  6  8 10 12 14 16

> length(c(NA, iv))
[1] 11

> ##### Afternoon
> subset(df2, cv == "b")
  iv cv dv    lv
1  2  b  2  TRUE
3  2  b  7 FALSE

> subset(df2, iv > 8)
   iv cv         dv   lv
7  10  j -0.6264538 TRUE
8  12  l  0.1836433 TRUE
9  14  n -0.8356286 TRUE
10 16  p  1.5952808 TRUE

> subset(df2, lv)
   iv cv         dv   lv
1   2  b  2.0000000 TRUE
2   5  x  4.5000000 TRUE
4   4  d  9.5000000 TRUE
5   6  f 12.0000000 TRUE
6   8  h 14.5000000 TRUE
7  10  j -0.6264538 TRUE
8  12  l  0.1836433 TRUE
9  14  n -0.8356286 TRUE
10 16  p  1.5952808 TRUE

> df2[!lv, ]
  iv cv dv    lv
3  2  b  7 FALSE

> seq(0, 20, by = 0.5)
 [1]  0.0  0.5  1.0  1.5  2.0  2.5  3.0  3.5  4.0  4.5  5.0  5.5  6.0  6.5  7.0
[16]  7.5  8.0  8.5  9.0  9.5 10.0 10.5 11.0 11.5 12.0 12.5 13.0 13.5 14.0 14.5
[31] 15.0 15.5 16.0 16.5 17.0 17.5 18.0 18.5 19.0 19.5 20.0

> round(seq(0, 20, by = 0.5))
 [1]  0  0  1  2  2  2  3  4  4  4  5  6  6  6  7  8  8  8  9 10 10 10 11 12 12
[26] 12 13 14 14 14 15 16 16 16 17 18 18 18 19 20 20

> mean(seq(0, 20, by = 0.5))
[1] 10

> mean(round(seq(0, 20, by = 0.5)))
[1] 10

> round(rnorm(10), 2)
 [1]  1.09 -0.76 -0.83  0.83 -0.97 -0.03  0.23 -0.30 -0.68  0.66

> round(rnorm(10), digits = 2) # not needed
 [1] -0.40 -0.33  1.37  2.14  0.51  0.79 -0.90  0.53 -0.65  0.29

> round(digits = 2, x = rnorm(10))
 [1] -1.24 -0.46 -0.83  0.34  1.07  1.22  0.74 -0.48  0.56 -1.25

> ceiling(seq(0, 20, by = 0.5))
 [1]  0  1  1  2  2  3  3  4  4  5  5  6  6  7  7  8  8  9  9 10 10 11 11 12 12
[26] 13 13 14 14 15 15 16 16 17 17 18 18 19 19 20 20

> ceiling(325.3)
[1] 326

> floor(seq(0, 20, by = 0.5))
 [1]  0  0  1  1  2  2  3  3  4  4  5  5  6  6  7  7  8  8  9  9 10 10 11 11 12
[26] 12 13 13 14 14 15 15 16 16 17 17 18 18 19 19 20

> paste(cv, 3)
 [1] "b 3" "x 3" "b 3" "d 3" "f 3" "h 3" "j 3" "l 3" "n 3" "p 3"

> paste(cv, 3, sep = "-")
 [1] "b-3" "x-3" "b-3" "d-3" "f-3" "h-3" "j-3" "l-3" "n-3" "p-3"

> paste(cv, 3, sep = "")
 [1] "b3" "x3" "b3" "d3" "f3" "h3" "j3" "l3" "n3" "p3"

> paste0(cv, 3)
 [1] "b3" "x3" "b3" "d3" "f3" "h3" "j3" "l3" "n3" "p3"

> paste0("run", 1:10)
 [1] "run1"  "run2"  "run3"  "run4"  "run5"  "run6"  "run7"  "run8"  "run9" 
[10] "run10"

> paste0("b", 0:5, collapse = "+")
[1] "b0+b1+b2+b3+b4+b5"

> seq_along(cv)
 [1]  1  2  3  4  5  6  7  8  9 10

> seq_len(5)
[1] 1 2 3 4 5

> seq_len(length(cv)) # redundant
 [1]  1  2  3  4  5  6  7  8  9 10

> ### functions
> summary(df2) # generic
       iv              cv          dv              lv         
 Min.   : 2.00   b      :2   Min.   :-0.8356   Mode :logical  
 1st Qu.: 4.25   d      :1   1st Qu.: 0.5366   FALSE:1        
 Median : 7.00   f      :1   Median : 3.2500   TRUE :9        
 Mean   : 7.90   h      :1   Mean   : 4.9817   NA's :0        
 3rd Qu.:11.50   j      :1   3rd Qu.: 8.8750                  
 Max.   :16.00   l      :1   Max.   :14.5000                  
                 (Other):3                                    

> unclass(df2$cv)
 [1] 1 9 1 2 3 4 5 6 7 8
attr(,"levels")
[1] "b" "d" "f" "h" "j" "l" "n" "p" "x"

> 2^(0:10)
 [1]    1    2    4    8   16   32   64  128  256  512 1024

> (1:10)*4
 [1]  4  8 12 16 20 24 28 32 36 40

> foo <- function(){
+   cat("Hello SLU\n")
+ }

> foo()
Hello SLU

> foo
function(){
  cat("Hello SLU\n")
}

> foo1 <- function(x){
+   cat(paste("Hello", x, "\n"))
+ }

> foo1("Haleh")
Hello Haleh 

> foo1(4)
Hello 4 

> foo1(1:4)
Hello 1 
 Hello 2 
 Hello 3 
 Hello 4 

> foo1(c("Laura", "Haleh"))
Hello Laura 
 Hello Haleh 

> foo2 <- function(x = "Ruben"){
+   writeLines(paste0("Hello ", x, "!"))
+ }

> foo2(c("Laura", "Haleh"))
Hello Laura!
Hello Haleh!

> foo2()
Hello Ruben!

> ### 1 inch = 2.54 cm
> ### inch2cm
> inch2cm <- function(x){
+   # stopifnot(is.numeric(x))
+   if(!is.numeric(x)) {
+     stop(paste(x, "is not numeric!"))
+   }
+   res <- x * 2.54
+   res
+ }

> inch2cm(1:10)
 [1]  2.54  5.08  7.62 10.16 12.70 15.24 17.78 20.32 22.86 25.40

> # inch2cm("a")
> 
> data(trees)

> trees[,1]
 [1]  8.3  8.6  8.8 10.5 10.7 10.8 11.0 11.0 11.1 11.2 11.3 11.4 11.4 11.7 12.0
[16] 12.9 12.9 13.3 13.7 13.8 14.0 14.2 14.5 16.0 16.3 17.3 17.5 17.9 18.0 18.0
[31] 20.6

> inch2cm(trees[,1])
 [1] 21.082 21.844 22.352 26.670 27.178 27.432 27.940 27.940 28.194 28.448
[11] 28.702 28.956 28.956 29.718 30.480 32.766 32.766 33.782 34.798 35.052
[21] 35.560 36.068 36.830 40.640 41.402 43.942 44.450 45.466 45.720 45.720
[31] 52.324

> trees$Girth_cm <- inch2cm(trees[,1])

> head(trees)
  Girth Height Volume Girth_cm
1   8.3     70   10.3   21.082
2   8.6     65   10.3   21.844
3   8.8     63   10.2   22.352
4  10.5     72   16.4   26.670
5  10.7     81   18.8   27.178
6  10.8     83   19.7   27.432

> ### loops
> s1 <- function(x){
+   res <- 0
+   for(i in seq_along(x)){
+     res <- res + x[i]
+   }
+   res
+ }

> s1(3:4)
[1] 7

> sum(3:4)
[1] 7

> s2 <- function(x){
+   res <- 0
+   i <- 1
+   while(i <= length(x)){
+     res <- res + x[i]
+     i <- i + 1
+   }
+   res
+ }

> s2(3:4)
[1] 7

> lapply(l1, length)
[[1]]
[1] 10

[[2]]
[1] 10

[[3]]
[1] 10


> lapply(l1[2:3], mean)
[[1]]
[1] 7.9

[[2]]
[1] 4.981684


> unlist(lapply(l1[2:3], mean))
[1] 7.900000 4.981684

> sapply(l1[2:3], mean)
[1] 7.900000 4.981684

> lapply(l1[2:3], inch2cm)
[[1]]
 [1]  5.08 12.70  5.08 10.16 15.24 20.32 25.40 30.48 35.56 40.64

[[2]]
 [1]  5.080000 11.430000 17.780000 24.130000 30.480000 36.830000 -1.591193
 [8]  0.466454 -2.122497  4.052013

>