### Brief R Tutorial

### Set working directory ###
setwd("C:/Users/sabaker/Documents/Meetings_Conferences/Gradstudent Meetings/RTutorial")

### Install libraries ###
install.packages("xlsx") #or in Rstudio: Tools -> Install Packages... 
library(xlsx)

### Use R as Calculator ###
10^3 + 5
(121 + 27) / (2.5^2
) # R will have a "+" in the command line to show that the statement is not complete
# esc will quit the statement
x=log(2)
exp(x)

### workspace ###
a = 11 # assign basic variables
# notice this adds the variable to the environment tab in RStudio
a
a * 2
a = a + 1

### Clear all variables from memory ###
rm(list=ls())

### Scalars, vectors, and matrices ###
## scalar = single number 0-D
a = 1
## vectors = row of numbers 1-D
b = c(1, 2, 3)
## matrices = row and column 2-D
c = matrix(data=c(9,2,3,4,5,6),ncol=3)

### Built in Functions - R has built in function ###
# mean
mean(x=b) # show how the function is shown in RStudio
mean(b)

### Help & Documentation ###
help(rnorm) # help for rnorm functoin
example(rnorm) # example of how to use the function
# also use the bottom right window in RStudio to look at packages, functions, ect.

# create a normal distribution
rnorm(10) # 10 random numbers with a normal distribution
rnorm(10, mean=1.2, sd=3.4) # change the mean and standard dev

### Scripts ###
# Open new and save with extention ".R"
# Run lines scripts with CRTL+ENTER or click Run
# Run entire script with CTRL+SHIFT + S
# Can run script without opening
source("BriefRTutorial.R") #need to set directory before hand

### Data Structures ###
## Vector = row of numbers, 1-D
vec1 = c(1,4,6,8,10)
vec1
vec1[5]
vec1[3] = 12
vec2 = seq(from=0, to=1, by=0.25)
vec2
sum(vec1)
vec1 + vec2

## Matrices = just a 2-D vector
mat=matrix(data=c(9,2,3,4,5,6),ncol=3) # or specify nrow
mat[1,2] #[row,column]
mat[2,]
mean(mat)

## Data frame = a matrix with names above the columns, eg. timeseries
t = data.frame(x = c(11,12,14), y = c(19,20,21), z = c(10,9,7))
t
mean(t$z)

## Lists = columns can be different lengths, unlike matrices and dataframes
L = list(one=1, two=c(1,2), five=seq(0, 1, length=5))
L
names(L)
L$five + 10

### Classes ###
## Numeric
a = c(1,2,3)
## Character
m = "pear"
## Date
date1=strptime( c("20100225230000","20100226000000", "20100226010000"),format="%Y%m%d%H%M%S")

### Graphics ###
## plot
par(mfrow=c(1,1))
x = rnorm(100)
plot(x)
plot(x, type="l", col="gold") # type = line, col = color
plot(x, type="b", col="blue")

## histogram
par(mfrow=c(2,2)) #change number of plots shown in the window
hist(rnorm(100))
hist(rnorm(100)) #changes every time
hist(rnorm(100))
hist(rnorm(100))
par(mfrow=c(1,1))

## not doing#####
#fancier plotting
t = data.frame(a = c(1,10,5,7,8), b = c(2.5,1.5,9,1,0), c = c(4,3,2,1,0))
plot(t$a, type="l", ylim=range(t),lwd=3, col=rgb(1,0,0,0.3)) #rgb(red, green, blue, alpha
lines(t$b, type="s", lwd=2,col=rgb(0.3,0.4,0.3,0.9)) # type = stair steps
points(t$c, pch=20, cex=4,col=rgb(0,0,1,0.3)) #cex is scale of point, pch = popints used
#####

### Reading and writing data files ###
getwd()
setwd("C:/Users/sabaker/Documents/Meetings_Conferences/Gradstudent Meetings/RTutorial")

d = data.frame(a = c(3,4,5), b = c(12,43,54))
write.table(d, file="tst0.txt", row.names=FALSE)
d2 = read.table(file="tst0.txt", header=TRUE)

### Programming Tools ###
## If-statement
w = 3
if( w < 5 ) {
  d=2 
  } else{
  d=10
  }
d

## For-loop
h = seq(from=1, to=8)
s = c()
for(i in 2:10) {
  s[i] = h[i] * 10
  }
s

## Write your own function
fun1 = function(arg1, arg2 ) {
  w = arg1 ^ 2
  return(arg2 + w)
  }
fun1(arg1 = 3, arg2 = 5)


### Lees Ferry flow example ###
url =  "http://civil.colorado.edu/~balajir/r-session-files/Leesferry-mon-data.txt"

# read data
data = read.table(url)
str(data)
data[,1] #years
data[1,] #year with flows

# name columns and change units
colnames(data) <- c("Year","Jan", "Feb", "Mar", "Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec")
data$Year #years
data[2:13] = data[2:13]*(10^-6) #af to MAF

# Calc the median and mean flows for each month
median = apply(data[2:13], 2, FUN = median) 
mean = apply(data[2:13], 2, FUN = mean) 

# Calc the annual flow for each year
sum = apply(data[2:13],1, FUN = sum)

# Boxplot monthly flows with median/mean, add legend
boxplot(data[2:13],xlab="Months",ylab="Monthly Flow (MAF)")
lines(mean,col="red")
points(median,col="blue")
legend("topright",c("Mean","Median"), col=c("red","blue"), lwd=1, lty=c(1,0), pch=c(NA,1))