###
###		Basic R commands
###

# assignment, objects

x <- 3			# or x = 3

ls()

x <- c(1,2,3,4,5,6,7,8,9,10)
(x <- c(1,2,3,4,5,6,7,8,9,10))

(x <- 1:10)

x[3] <- 4
x[3] <- "four"
x


(y <- as.list(1:10))

y[3]
y[[3]]
y[[3]] <- "four"
y


# --- strings/characters

s <- "abcdefghijklmnopqrstuvwxyz"

require(stringr)			# install.packages("stringr")
?stringr

s[1:4]					# what you expected?
str_sub(s, 1, 4)


# --- matrix

(xx <- matrix(1:10,nrow=5,ncol=2))
?matrix
(xx <- matrix(1:10,nrow=5,ncol=2,byrow=TRUE))

dim(xx)

rowSums(xx)
colSums(xx)

transpose(xx)
t(xx)

2*xx + 3

xx * xx
xx^2


(xtx <- t(xx)%*%xx)

(ev <- eigen(xtx))
names(ev)
ev$values
ev[[1]]

(udv <- svd(xx))
names(udv)
udv$d^2
udv$v
ev$vectors


# --- data frame

x <- 1:10
w <- rnorm(10)
y <- c(1,4,2,5,4,NA,7,3,2,10)

mean(x)
mean(y)
mean(y, na.rm=TRUE)

group <- c("A","A","A","B","A","A","B","B","B","B")

(data <- data.frame(x,w,y,group))
str(data)
typeof(data)

colnames(data)
rownames(data)

colMeans(data)
lapply(data, mean)

my_mean <- function(x) { return( mean(x,na.rm=TRUE) ) }

lapply(data, my_mean)


# --- input/output

getwd()

setwd("~/courses/mich/text_analytics/data/")  # see file.path

data <- read.csv("little_file.csv")
dim(data)
data
data$newVar <- rnorm(4)

write.csv(data, "temp.csv")

system("cat temp.csv")

readLines("temp.csv")   # embedded quotes


# --- regular expression challenge

#   dealing with newlines

txt <- "\nNow this is the first line. \nAnd this is the second.\n Third and last\n"

txt <- str_replace(txt,'^\n','')				
txt <- str_replace(txt,'\n$','.')			# missing last .
txt <- str_replace_all(txt,'\n',' ')