# book chapter introduction to R code
# chapter page 1
myresult <- 10 # this is all a comment
myresult

# section 2 Showing the value and structure of an object str()
# str() = structure NOT string as in some other programming languages
str(myresult)

# chapter page 2 section 3
sum1 <- 2 + 6 + 3
sum1

sum2 <- 2 + 6 + 
3
sum2

sum3 <- 2 + 6 +
 + 3
 sum3

sum4 <- 2 + 6
 + 3
sum4
###
 myresult2 <- 20;   myresult3 <- 50 ;    myresult4 <- 100 ;   myresult5 <- 700 

 #### section 5 joining individual values c()

x<- c(71, 68, 68, 66, 67, 70, 71, 70, 73, 72, 65, 66)
y <- c(69, 64, 65, 63, 65, 62, 65, 64, 66, 59, 62)
x; y
x[2]
x <- x[-2]
x
x_time2 <-  2 * x
x_time2

# obtain summary stats.
summary(x)
summary(y) 

# section 6 dataframes and lists
mydataframe=data.frame(x_axis=x, y_axis=y)
mydataframe

summary(mydataframe)

names(mydataframe)   # returns names of columns
mydataframe$y_axis   # returns the values for the y_axis column
mydataframe[1]       # returns the values for the first column, same as mydataframe[,1]
mydataframe[1,]      # returns the values for the first row

######### factor creation and manipulation
# factor consists of element each has a internal value (numeric)
# and a optional label (character) 
# in factor() function you specify the labels, internal values assigned automatically 
# and sequentially starting at 1. 
# internal values still 1's and 2's in all three below:
# example 1
grouping_var <- factor(c(1,1,1,1,2,2,2,2))
grouping_var
str(grouping_var)  # structure function
# example 2
grouping_string <- factor(c("one","one","one","one","two","two","two","two"))
grouping_string
str(grouping_string)
# example 3 
grouping_gap <- factor(c(5,5,5,5,10,10,10,10))
grouping_gap
str(grouping_gap)
# using gl() to create factors:
grouping_var2 <- gl(2,8, labels= c("control", "treat"))
grouping_var2

# note that just requesting the factor name
# produces the list of labels applies to each of the interal values:
# i.e. grouping_var2
# [1] control control control control control control control control treat  
#[10] treat   treat   treat   treat   treat   treat   treat  
# Levels: control treat

#extraction
# extracting internal values easy as already numeric
numeric1<- as.numeric(grouping_var)
numeric1
numeric12<- as.numeric(grouping_string)
numeric12
numeric13<- as.numeric(grouping_gap)
numeric13
# check they are numeric
is.numeric(numeric13)
str(numeric13)
# extracting labels need to convert:
# if labels do not look like numbers just get NA's 
# na example:
as.numeric(levels(grouping_var2))[as.integer(grouping_var2)]
# working example:
as.numeric(levels(grouping_gap))[as.integer(grouping_gap)]


####################
values<- as.numeric(as.character(grouping_var2))
values

as.numeric(levels(grouping_var2))[as.integer(grouping_var2)]
as.numeric(levels(f))[as.integer(f)]

#################
# section 8 editing a dataframe

variable1<- c(2,5,7) 
variable2<- c(24,36,20)
mydataframe2 <- data.frame(happiness=variable1, age=variable2)
mydataframe2
mydataframe2[1]        # returns the values for the first column, 
mydataframe2[,1]       # same as  above
mydataframe2[1,]       #  row
mydataframe2
mydataframe2[2, ] <- 44  # change all values in second row to 44
mydataframe2
mydataframe2[ ,1] <- 100  # change all values in first column to 100
mydataframe2   # change  value in first column first row  to 3
mydataframe2[ 1,1] <- 3
mydataframe2

#######################
#  column actions
# changing the name for the first column
names (mydataframe2) [1] <- "var_renamed"
# create three new columns for the dataframe
mydataframe2["newvar1"] <- 1
mydataframe2["newvar2"] <- 0 
mydataframe2["newvar3"] <- 50
mydataframe2
# remove the newvar2 variable
mydataframe2["newvar2"] <- NULL
mydataframe2
##################
# section 9	Creating a new dataframe from a subset of columns 
# Creating new dataframe from subset of columns
# select only two columns called "age" and "newvar3" 
#  to form a new dataframe called newdataframe_subset, 
newdataframe_subset<- mydataframe2[, c("age", "newvar3")] 
newdataframe_subset
##################
# section 10 Creating new dataframe from subset of rows
# can select specific rows based upon some criteria. 
# Say we wanted to only select rows where the var_renamed vector only has a value of 100. 
newdataframe_subrows <- mydataframe2[mydataframe2$"var_renamed" ==100, ]
newdataframe_subrows
##################
# section 11 Loading data and giving it focus - attach()
mydataframe <- read.delim("http://www.robin-beaumont.co.uk/virtualclassroom/stats/basics/coursework/data/pain_medication.dat", header=TRUE) 
# In contrast, if you have a local copy 
# you need to replace the forward slashes  '/'  with double back slashes '\\' thus:

mydataframe <- read.delim("D:\\folder\\folder\\pain_medication.dat", header=TRUE)

# If you can't remember the place or name where you have the 
# file you can annotate the above R code to:
mydataframe <-  read.table(file=file.choose())
##################
# section 12 Seeing and Setting the Working Directory
# seeing:
getwd()
# returns [1] "C:/Users/robin/Documents" 
# setting:
setwd("D:/r scripts")

####  .Rprofile options
# see; http://www.dummies.com/how-to/content/how-to-configure-r.html
# see; http://stackoverflow.com/questions/5085774/how-to-modify-and-save-rprofile-site-under-windows
# To Set the working directory in R permanently see; 
http://faculty.chicagobooth.edu/robert.gramacy/teaching/ara/setcwd.pdf
# 1. Open the Rprofile.site file on text editor (notepad)
# 2. Add the line: setwd("<the desired working directory >") to the end of theRprofile.site file and add a new line (i.e. hit the enter key) 
# example from above pdf:
# Things you might want to change
# options(papersize="a4")
# options(editor="notepad")
# options(pager="internal")
# set the default help type
# options(help_type="text")
 options(help_type="html")
# set a site library
# .Library.site <- file.path(chartr("\\", "/", R.home()), 
"site-library")
# set a CRAN mirror
# local({r <- getOption("repos")
# r["CRAN"] <- "http://my.local.cran"
# options(repos=r)})
setwd("C:\\Programming\\R\\Data\\RegressionClassData")

# NOTICE THE EXTRA EMPTY LINE AFTER THE setwd() COMMAND.
##################
# section 13 Saving and loading your data in R format
# saving: 
save(mydataframe,file="mydata.rda") 
# To load the dataframe use the load() function: 
load("mydata.Rda")

##################
# section 14 Saving your data as a text file
# To write a tab delimited file, with the names of each column at the top:
write.table(mydataframe,"d:/basics/coursework/data/pain_medication.dat", header=TRUE, sep = "\t")
# To write a comma separated file with the names of each column at the top:
write.csv(mydataframe, "d:/basics/coursework/data/pain_medication.dat", header=TRUE)