##  Code for Book: Applied Statistical Analysis in R for Psychology and Human factors
##  (c) Shane T. Mueller, Ph.D.
##  Michigan Technological University
##  shanem@mtu.edu
##
##  Textbook and videos available at http://pages.mtu.edu/~shanem/psy5210
##
##
## This file contains example software code relevant for Chapter 1 (Introduction)
## The code in this file may be used and shared freely with or without attribution.





## Some basic arithmetic:
 3 + 3
 9 * 6*3.45
 9 + 6*3.45
 (9 + 6)*3.45
 (9 + 6)^3.45
 (9 + 6)^3.45/33.0
 (9 + 6)^3.45/0


 
 ##Numbers and vectors
 
 3+1
 c(1,3,5)
 1:20
 
 
##First graphics
 
par(mfcol=c(1,3),las=1)
x <- runif(100)
plot(x)
barplot(x)
hist(x)


##Second example.
par(mfrow=c(1,1),las=1)  #reset viewport
tmp <- runif(100)*.2
tmp2 <- tmp + 3
y <- x + tmp2
plot(x,y)
cor(x,y)


##############################
## Functions

xycorr < cor(x,y)
xycorr

plot(x,y,pch=16)


##################################
## Data arrays, frames, matrices:
m <- matrix(runif(100),10,10)
print(round(m,3))


##change to a data frame:
n <- as.data.frame(m)
print(n)
View(n)






## Accessing Sub-elements:
print(x[20])
print(m[1,])   ##get first row
print(m[,3])   ##get third column
print(m[1,3])  ##get a specific element

print(n$V2)
print(n[,2])


##Access by name and recoding:

lookup <- c(A = "Alfa", B = "Bravo",  C  = "Charlie",
            D = "Delta")
lookup["B"]
lookup[c("A","A","C","B","D")]





##add new data column:
n$new <- 43 #This puts 43 in each row
print(n)
n$new2 <- c(44,45) #this recycles the shorter list to fill
print(n)
n$new3 <- 1:10


##Data types:
c(1,3,3,44,5)
typeof(5)
typeof(as.integer(5))

33.0
1.223
c(1,3,3,44.3,5)
typeof(33.0)

##character strings:
bb <- "HELLO"
c("one","two","three")
typeof("H")

##logicals:
a <- c(TRUE,FALSE)
typeof(T)


##Factors:
factor1 <- as.factor(c("greg","jan","marsha","bobby",
                       "tom","cindy","peter"))



##changing types:
bb <- as.factor(c(5.5,1,2,3.2,3.3))

as.character(bb)
as.numeric(bb)
as.numeric(as.character(bb))


##transforming between numbers and factors:
doses <- c(0,2000,50,2000,50,2000,0,50,50)
dosefactor <- as.factor(doses)
benefit <- c(5,6,20,3,18,2,4,22,17)
dosefactor



##simple filtering:
set.seed(1111)
x <- rnorm(100)
y <- x + runif(100,-.3,.3)
tmp <- (x>.5)
x[tmp]
x[!tmp]

##Using filtering to make complex plots:
plot(x[tmp],y[tmp],col="darkgreen",xlim=c(0,1),ylim=c(0,1))
points(x[!tmp],y[!tmp],col="red",pch=16)

##add some additinoal lines:

plot(x[tmp],y[tmp],col="darkgreen",xlim=c(0,1),ylim=c(0,1),
     xaxt="n",yaxt="n",xlab="",ylab="")
points(x[!tmp],y[!tmp],col="red",pch=16)
axis(1,0:10/10)
axis(2,0:10/10,las=1)
abline(0,1,lty=1)
abline(.5,0,lty=3)
abline(v=.5,lty=3)


## Using filters to specify aspects of a plot:
c("red","darkgreen")[tmp+1]

plot(x,y,pch=18,col=c("red","darkgreen")[tmp+1])

plot(x,y,col=c("red","darkgreen")[tmp+1], 
     pch=c(1,16)[1+(y>.5)])





##############################################################
##  Exercises:
## Compute your height in inches, by multiplying your height in feet by 12 and adding the remainder
## Compute your height in meters, using the identity that 1 inch = .0254 meters.
## Compute the average height in meters of at least three people (one who is 5 foot 2, one
## who is 6 feet 5 inches, one who is 4 feet 8.5 inches).


## Suppose I were 5 feet, 9 inches tall.

12*5+9        ##height in feet
(12*5+9)*.0254 ##height in meters
((5*12+2) + (6*12+5) + (4*12+8.5))/3 * .0254


##############################################
##Exercise 2.
##Create z1, a set of 100 random numbers like we did above, but make it less highly correlated 
## with x (try to aim for a correlation of .8).
x <- runif(100)
z1 <- runif(100) * .5 + x
cor(z1, x)
plot(x,z1)

x <- runif(100)
z1 <- runif(100)*1  + 1.5*x
 cor(z1, x)
plot(z1,x)

##Create z2, a set  of 100 random numbers, but make them negatively correlated with x.
z2 <- x -runif(100) * .5 
cor(z2, x)
z2 <- runif(100) * .5 - x
cor(z2, x)
 
##Compute the correlation between z1 and z2
 cor(z1,z2)
 
 ##############################################
 ### Exercise
 ## Create a 10x20 matrix of uniform random numbers.
 x <- matrix(runif(10*20),10,20)
 x
 
 ##############################################
 ### Exercise
 ##  The cex argument sets the size of the symbol.  Use the distance from the origin to impact the size.
 
 #The distance to the origin (0,0) can be computed using the Pythagoras theorem:
 
x <- runif(100)
y <- runif(100)
plot(x,y)
abline(0,0)
abline(v=0)
distance <- sqrt(x ^2 + y^2)
 
# We could use \texttt{dist} directly as the cex argument because the distance will always be less than sqrt(2):
   
 plot(x,y,cex=distance)

## However, we want to do this with two thresholds.  The simplest way to do that is to create a vector if three cex 
## sizes to use: c(.5,1,3), and then a vector to select which ones.
 
 choosepoint1 <- (distance > .4)
 choosepoint2 <- (distance > .8)
 choosepoint <- choosepoint1 + choosepoint2 + 1
 plot(x,y,cex=c(.5,1,3)[choosepoint])

 
#Use the functions plot, points, and lines to create 500 random normal, and highlight the outliers more than 2.5 units from the mean.
##  First, lets create the numbers, plus an 'index' vector that we will use later.
 
 nums <- rnorm(500)
 index <- 1:500

## Now, plot the numbers with open circles:
 plot(index,nums)

# Now, create a filter like we have done before, and overplot the ones we care about.  Here, we filter both the index and the numbers with the filter.  Also pch=16 plots in a solid point.
 
 filter <- abs(nums)>2.5
 points(index[filter],nums[filter],col="red",pch=16)

## Finally:
 segments(0,2.5,500,2.5)
 segments(0,-2.5,500,-2.5)

 ##############################################
 ### Exercise
 ##  Create an R Markdown document. In the document, incorporate the following: section header, 
 ##  section subheader,  numeric bulleted lists, italic and bold text, R code that calculates the mean 
 ## of four numbers, and R code that make a barplot of those four numbers.}
 
 
 
# The following file should address each of these.

# ---
#   title: "R Markdown Example"
#  author: "Shane Mueller"
#  date: "08/31/2016"
#  output: word_document
#  ---
#    # Top-level header
#    
#    ### Subsection title 
#    This is is normal text.  You can also do:
#    
#    * **bold**
#    * *italic*
#    
#    Or:
#    1. First
#  2. Second
#  3. Third
#  
#  ## Display and execute code
#  This will both display and execute the code:
#    ```{r}
#  (33+55+192+12)/4
#  barplot(c(33,55,192,12))
#  ```

 
 
## Issues/questions from class discussion forum

 
## basics of RStudio interface:
## * differences between run, source, source/echo/etc.
## * managing panes of rstudio
## breakpoints/debugging
##
 
##### 
## more on factors:
 
x <- factor(sample(letters,5))
x2 <- x[1:4] 
x2 
##compare these:
x3 <- as.factor(x2)
x4 <- factor(x2)

x5 <- factor(x,levels=letters)

##what will this do?
as.numeric(x2)

##what will this do?
as.numeric(x5)


str(x2)



## selecting/filtering
## we will cover this again next week:
tmp <- c(T,F,F,T,T,T,F)
colors <- c("red","darkgreen")
colors[c(1)]
colors[c(1,1)]
colors[c(1,2,2,1)]

colors[tmp]
as.numeric(tmp)
as.numeric(tmp)+1
tmp+1
colors[tmp+1]

##filter by value
x <- runif(10)
x
x < .5
x[x<.5]