1 setwd("/media/mandy/Samsung_T1/mpicbs/2015kurs2")
   2 
   3 
   4 ##################################################
   5 ################ First Session ###################
   6 ##################################################
   7 x <- rnorm(100, mean = 2, sd = 4)
   8 
   9 xx <- density(x)
  10 
  11 plot(x)
  12 
  13 ls()
  14 objects()
  15 
  16 library()
  17 head(installed.packages)
  18 
  19 
  20 ##################################################
  21 ############## Objects and Functions #############
  22 ##################################################
  23 
  24 
  25 ### str()
  26 require(ggplot2)
  27 example(scale_colour_brewer)
  28 
  29 ls()
  30 str(dsamp)
  31 str(d)
  32 
  33 ##################################################
  34 ################### Vectors  #####################
  35 ##################################################
  36 
  37 ## Coercion - Exercises
  38 c(1, FALSE)
  39 c("a", 1)
  40 c(list(1), "a")
  41 c(TRUE, 1L)
  42 
  43 1 == "1"
  44 -1 < FALSE
  45 "one" < 2
  46 
  47 
  48 v1 <- c(1L,1L,2L)
  49 v2 <- seq(0,5,by = 0.5)
  50 v3 <- rep(c(F,T),times = c(2,5))
  51 v4 <- letters[sample(1:5)]
  52 
  53 length(v1)
  54 length(v2)
  55 
  56 lapply(list(v1,v2,v3,v4), typeof)
  57 
  58 
  59 
  60 
  61 ## What happens to a factor when you modify its levels?
  62 f1 <- factor(letters)
  63 summary(f1)
  64 levels(f1) <- rev(levels(f1))
  65 summary(f1)
  66 
  67 f2 <- rev(factor(letters))
  68 summary(f2)
  69 
  70 f3 <- factor(letters, levels = rev(letters))
  71 summary(f3)
  72 
  73 f4 <- c(f2,f3)
  74 summary(f4)
  75 
  76 
  77 ##################################################
  78 ################ Data Frames  ####################
  79 ##################################################
  80 
  81 ## combining data frames
  82 ### rbind
  83 
  84 x <- data.frame(id=1:3,score=rnorm(3))
  85 y <- data.frame(id=13:15,score=rnorm(3))
  86 rbind(x,y)
  87 
  88 
  89 ## cbind
  90 x <- data.frame(id=1:5,score1=rnorm(5))
  91 y <- data.frame(score2=rnorm(5),score3=rnorm(5))
  92 cbind(x,y)
  93 
  94 
  95 ## merge
  96 (d1 <- data.frame(id=LETTERS[c(1,2,3)],day1=sample(10,3)))
  97 (d2 <- data.frame(id=LETTERS[c(1,3,5,6)],day2=sample(10,4)))
  98 
  99 merge(d1,d2)
 100 
 101 merge(d1,d2,all.x = T)
 102 
 103 merge(d1,d2,all.y = T)
 104 
 105 zz <- merge(d1,d2,all = T)
 106 
 107 
 108 ## exercises merging
 109 
 110 m1 <- data.frame(id = 1:10,
 111                  m1 = rnorm(10),
 112                  m2 = runif(10))
 113 
 114 m2 <- data.frame(id2 = sample(1:20,size = 10),
 115                  m2 = rnorm(10, mean = 5),
 116                  m3 = rt(10,df = 4))
 117 
 118 require(lubridate)
 119 subjdata <- data.frame(id = 1:20,
 120                        bd = ymd("19900101") + ddays(sample.int(3500)),
 121                        sex = sample(c("m","f"),20,replace = T))
 122 
 123 
 124 ## indexing 
 125 
 126 ## indexing with positive integers
 127 letters[1:3]
 128 letters[c(1:3,1:3)]
 129 
 130 
 131 ## logical indexing
 132 x <- c(1,2,3,NA)
 133 x[!is.na(x)]
 134 
 135 ## indexing in combination with assignment
 136 x[is.na(x)] <- 0
 137 x
 138 
 139 ## logical indexing on data frames
 140 library(MASS)
 141 painters[painters$Colour >= 17,]
 142 
 143 ## logical indexing on data frames (rows) combined with indexing with integers (columns)
 144 painters[painters$Colour >= 17 & painters$Composition > 10, c(1,2,3)]
 145 
 146 
 147 ## use of %in%
 148 painters[painters$School %in% c("A","C","D"),]
 149 
 150 ## use of which
 151 which(painters$School %in% c("A","C","D"))
 152 
 153 ## indexing with character vector
 154 painters[1:3,c("Drawing","Expression")]
 155 
 156 ## negative indeces
 157 x <- c(5,8,6,7,1,5,3)
 158 (z <- x[-1])
 159 
 160 
 161 ##########################################################
 162 ###################### Exercises Indexing ################
 163 ##########################################################
 164 
 165 ########## part A
 166 
 167 ## run the following commands!
 168 ## try to understand whats going on in each case!
 169 x <- c(2, 7, 0, 9, 10, 23, 11, 4, 7, 8, 6, 0)
 170 x[4]
 171 x[3:5]
 172 x[c(1, 5, 8)]
 173 x[x > 10]
 174 x[(1:6) * 2]
 175 all(x > 0)
 176 x[x == 0] <- 1
 177 x
 178 
 179 all(x > 0)
 180 ifelse(round(x/2) == x/2, "even", "odd")
 181 
 182 sum(x > 4)
 183 
 184 ## Display every third element in x
 185 
 186 
 187 
 188 ## Display elements that are less than 10,
 189 ## but greater than 4
 190 
 191 
 192 
 193 ## Modify the vector x, replacing by 10 all values
 194 ## that are greater than 10
 195 
 196 
 197 
 198 ## Modify the vector x, multiplying by 2 all
 199 ## elements that are smaller than 5
 200 
 201 
 202 
 203 ## Create a new vector y with elements 0,1,0,1, . . .
 204 ## (12 elements) and a vector z that equals x when y=0
 205 ## and 3x when y=1.
 206 ## (You can do it using ifelse, but there are other possibilities)
 207 
 208 
 209 
 210 ##################################################
 211 ################ Reading Data ####################
 212 ##################################################
 213 
 214 read.table("week1/data/fishercats.txt",  
 215            sep=" ",header=T)
 216 
 217 
 218 winer <- read.table( 
 219     "http://socserv.socsci.mcmaster.ca/jfox/Courses/R/ICPSR/Winer.txt",
 220     header=T)
 221 
 222 
 223 mydata <- read.delim("clipboard",na.strings=".")
 224 
 225 
 226 data(airquality)
 227 aq <-edit(airquality)
 228 
 229 fix(airquality)
 230 
 231 ## read excel
 232 library(XLConnect)
 233 my.wb <- loadWorkbook("week1/data/Duncan.xls")
 234 sheets <- getSheets(my.wb)
 235 content <- readWorksheet(my.wb, sheet=1)
 236 head(content)
 237 
 238 require(readxl)
 239 x <- read_excel("week1/data/Duncan.xls")
 240 
 241 
 242 ##################################################
 243 ################ Apply family ####################
 244 ##################################################
 245 
 246 lapply(mtcars,mean)
 247 sapply(mtcars,mean)
 248 
 249 
 250 x <- 1:12
 251 dim(x) <- c(2,2,3)
 252 apply(x,3,quantile) #calculate the quantiles for each 2x2 matrix
 253 
 254 
 255 tapply(mtcars$mpg,mtcars$cyl,mean)
 256 
 257 tapply(mtcars$mpg,list(mtcars$cyl,mtcars$vs),mean)
 258