### -----------------------------------------------------------------------
### Programmieren mit statistischer Software (SoSe 2017)
### -----------------------------------------------------------------------


## ----better1a------------------------------------------------------------
bli <- read.csv2("better-life-index.csv",
                 stringsAsFactors = FALSE)

## ----better1b------------------------------------------------------------
head(names(bli))

## ----better1c------------------------------------------------------------
## summary(bli)
## str(bli)
## head(bli)

## ----char1---------------------------------------------------------------
t <- c("The quick brown fox", "jumps over the lazy dog")  # bevorzugt
t
t2 <- c('The quick brown fox', 'jumps over the lazy dog')
t2

## ----char2---------------------------------------------------------------
t3 <- c('The quick brown fox', 'jumps over the "lazy" dog')
t3
t4 <- c("The quick brown fox", "jumps over the 'lazy' dog")
t4

## ----char3---------------------------------------------------------------
# ?Quotes
# \n   newline
# \t	 tab

## ----char4---------------------------------------------------------------
length(t)

## ----char5---------------------------------------------------------------
nchar(t)

## ----char6---------------------------------------------------------------
#?paste
paste("Today is", date())
paste("Today is", date(), sep = ": ")

## ----char7---------------------------------------------------------------
paste("A", 1:6, sep = "")
# aequivalent
paste0("A", 1:6)

## ----char8---------------------------------------------------------------
paste("A", 1:6, collapse=",", sep="")
paste(t, collapse = " ")
paste(t, collapse = " ... ")

## ----fun1----------------------------------------------------------------
#?sprintf   
sprintf("%s is %f feet tall", "Sven", 7.1) 

## ----fun2----------------------------------------------------------------
#?tolower          
tolower(t)
#?toupper         
toupper(t)

## ----fun3----------------------------------------------------------------
#?strtrim         
strtrim(t, c(5,10))

## ----fun4----------------------------------------------------------------
#?strwrap         
strwrap(t, width=5)
strwrap(t, width=10)
strwrap(t, width=2)

## ----fun5----------------------------------------------------------------
#?abbreviate   
abbreviate(names.arg=t, minlength = 4)
abbreviate(names.arg=t, minlength = 10)
abbreviate(names.arg=t, minlength = 2)

## ----match1--------------------------------------------------------------
#?match                       
match(c("a","y"), letters)
match(c("a", 1), letters)

## ----match2--------------------------------------------------------------
c("a",1) %in% letters         

## ----match3--------------------------------------------------------------
#?pmatch          
pmatch("med", c("mean", "mode"))
pmatch("med", c("mean", "median", "mode"))
pmatch("med", c("mean", "median", "mode", "median2"))

## ----match4--------------------------------------------------------------
#?charmatch        
charmatch("med", c("mean", "mode"))
charmatch("med", c("mean", "median", "mode"))
charmatch("med", c("mean", "median", "mode", "median2"))

## ----match5--------------------------------------------------------------
#names(bli)

match(c("Housing_Rooms.per.person",
        "Environment_Air.pollution"), 
      names(bli))

## ----match6--------------------------------------------------------------
match(c("Housing_Rooms.per.person", "Housing_Rooms.per.person_xxx",
        "Environment_Air.pollution"), 
      names(bli))

( c("Housing_Rooms.per.person", "Housing_Rooms.per.person_xxx",
  "Environment_Air.pollution") %in% 
names(bli) )

## ----sub1----------------------------------------------------------------
#?substr
# substr(x, start, stop) 

## ----sub2----------------------------------------------------------------
substr(t, 5, 10)
substr(t, 4, 11)

substr(t[2], 21, 23)
substr(t[2], 21, 23) <- "cat"
t

## ----sub3----------------------------------------------------------------
substr(t[2], 21, 23) <- "zo"
t
substr(t[2], 21, 23) <- "zoxx"               
t

# substring(text, first, last = 1000000L)

## ----sub4----------------------------------------------------------------
substring(t[2], 21)
substring(t[2], 21) <- "bee"
t
substring(t[2], 21) <- "zoxx"     
t

## ----sub5----------------------------------------------------------------
substr(bli$Income_Households.income,
       start = 1,
       stop = nchar(bli$Income_Households.income) - 4)

Income_Households.income_num <-
  as.numeric(
    substr(bli$Income_Households.income,
           start = 1,
           stop = nchar(bli$Income_Households.income) - 4)
    )

## ----regex1--------------------------------------------------------------
#?regex  

## ----regex2--------------------------------------------------------------
t2 <- c("Programmieren", "mit", "statistischer", "Software", "SS2017")
# ?grep
# grep(pattern, x, ignore.case = FALSE, perl = FALSE, value = FALSE,
#      fixed = FALSE, useBytes = FALSE, invert = FALSE)

## ----regex3--------------------------------------------------------------
grep("a", t2)
grep("[[:alpha:]]", t2)
grep("[[:digit:]]", t2)

## ----regex4--------------------------------------------------------------
grepl("a", t2)
grepl("[[:alpha:]]", t2)
grepl("[[:digit:]]", t2)

## ----regex5--------------------------------------------------------------
t3 <- c("2012-07-10", "2012-01-20", "May 5, 2012")

grep("\\d{4}-\\d{2}-\\d{2}", t3)
grepl("\\d{4}-\\d{2}-\\d{2}", t3)

## ----regex6--------------------------------------------------------------
#?regexpr
# regexpr(pattern, text, ignore.case = FALSE, perl = FALSE,
#         fixed = FALSE, useBytes = FALSE)

## ----regex7--------------------------------------------------------------
regexpr("a", t2)

## ----regex8--------------------------------------------------------------
regexpr("[[:alpha:]]", t2)

## ----regex9--------------------------------------------------------------
regexpr("[[:digit:]]", t2)

## ----regex10-------------------------------------------------------------
# gregexpr("a", t2)
# gregexpr("[[:alpha:]]", t2)
# gregexpr("[[:digit:]]", t2)

## ----sub6----------------------------------------------------------------
# sub(pattern, replacement, x, ignore.case = FALSE, perl = FALSE,
#     fixed = FALSE, useBytes = FALSE)
sub("(\\d{4})-\\d{2}-\\d{2}", "\\1", t3)
sub("(\\d{4})-(\\d{2})-(\\d{2})", "\\3.\\2.\\1", t3)

gsub("(\\d{4})-\\d{2}-\\d{2}", "\\1", t3)
gsub("(\\d{4})-(\\d{2})-(\\d{2})", "\\3.\\2.\\1", t3)

## ----split1--------------------------------------------------------------
#?strsplit
# strsplit(x, split, fixed = FALSE, perl = FALSE, useBytes = FALSE)

## ----split2--------------------------------------------------------------
x <- c(as = "asfef", qu = "qwerty", "yuiop[", "b", "stuff.blah.yech")
strsplit(x, "e")

## ----split3--------------------------------------------------------------
t4 <- c("89. Derdiyok fuer Schuerrle",
        "69. Kohr fuer L. Bender")

## ----split4--------------------------------------------------------------
#?regexec
m <- regexec("(\\d\\d)\\. (.+) fuer (.+)", t4)
#?regmatches          # Extract or Replace Matched Substrings
regmatches(t4, m)

## ----daten1--------------------------------------------------------------
grep("Income_", names(bli))

## ----daten2--------------------------------------------------------------
sub("(\\d+) .+", "\\1", bli$Income_Households.income)

## ----daten3--------------------------------------------------------------
satisfaction <- data.frame(
  letter = substr(bli$COUNTRY, 1, 1),
  value  = as.numeric(
    sub("(.+) rate", "\\1", bli$Life.Satisfaction_Life.Satisfaction)))

# satisfaction

# barplot(sapply(split(satisfaction$value, satisfaction$letter), mean))

## ----daten4--------------------------------------------------------------
# Objekt mit Nummer der Iteration im Namen 
for(i in 1:3){
  name <- paste0("res",i)
  assign(name,i)
}
res1
res2
res3