####Lecture02 = Introduction to R########

#Getting help with R

help()

help(seq)

?mean

help(package="agricolae")
help(package="ExpDes")
help(package="ggplot2")

#help.search( )

help.search("histogram")
help.search("dispersão")
help.search("t.test")
help.search("anova")

#install packages

install.packages("BGLR")
install.packages("MASS")
install.packages("lme4")

install.packages(c("ggplot2", "dplyr", "tidyr"))

#library package

library("ggplot2")
library("lme4")
require("devtools")

# swirl package

install.packages("swirl")
require("swirl")
swirl()
#bye( ): to exit swirl

#R Help on the Internet
#https://search.r-project.org/
#http://www.rseek.org

#Mailing Lists
#https://www.r-project.org/mail.html


#R as a calculator

##arithmetic operators
#sum
1+4
2+5

#subtract
6-3
8-4

#divide
10/2 
10/3

#multiplication
2*3 
4*1.2

#exponential
2^2 
2**2

#square root
sqrt(16) 
sqrt(64)
9^0.5 #or
sqrt(9)

#log
log(10)
log(10,base = 10)
log(10,base = 2)

#-----------

##comparison operators

3*2==5 #equal to (# caution: ’==’ is different than ’=’)

4!=1 #not equal to

10>4 #greater than

3<5 #less than

10>=10 #greater than or equal to

12<=10 #less than or equal to

10!=5 #different than

a <- 5
b <- 3

a == b
a != b
a < b
a > b
a <= b
a >= b

#-----------

#parentheses are important

4*5+2-3/8 
4*(5+2)-(3/8) 
4*(5+2-3/8)
((4*5)+2-3)/8

#--------------

#Summary Statistics

d <- c(10, 8, 12, 7, 6, 9, 8, 13, 10, 7)

mean(d)

median(d)

var(d)

sd(d)

#==========
#Simple functions

##logical operators

40 & 5 > 30 
40 | 5 > 30 

1<0 
1==0 
1>0 

p <- TRUE
q <- FALSE
p & q
p | q


#Functions

#?functionname

?log

?seq

?rep

#seq(  ) function

x <- seq(1, 10)
x

seq(from=0, to=100, by=3) #we can write in this way, or
seq(0,100,3) #make sequence

#Create a sequence of integers from 1 to 10
x <- seq(1, 10)
x

#Create a sequence of integers from 0 to 20, in increments of 2:
y <- seq(0, 20, by = 2)
y

#Create a descending sequence from 10 to 1:
z <- seq(10, 1, by = -1)
z

#rep function

?rep
rep(x=1,times=3) #or
rep(1,3)

# Repeat value 3 five times
x <- rep(3, times = 5)
x

#Repeat vector [1, 2, 3] twice:

y <- c(1, 2, 3)
z <- rep(y, times = 2)
z



#=========

#R creating objects

x=10

x*2
x^5
x+2

# or
x<-10
x*2
x^5
x+2

x<-5
x*5
x^5
x+1

x_name = "name"
x_name

#To see which type your object is

class(x)
class(x_name)

#=========


#R Data Types

#Vectors

#Numerical Vector
x<- c(1, 2, 3, 4, 5)
x

#Character Vector (Strings)
y<-c("apple","banana","orange","grape")
y

#Logical Vector (Boolean)
z<- c(TRUE, FALSE, TRUE, FALSE)
z

#Vector with Numeric Sequence
x<- seq(1, 10)
x

#Repeating Vector
x<- rep(0, times = 5)
x

#Vector with Randomly Generated Values
x<- runif(5)
x


#Vector Manipulation

#Two vectors of same length can be added, subtracted, multiplied or divided giving the result as a vector output.

# Create two vector
v1 <- c(3,8,4,5,0,11)
v2 <- c(4,11,0,8,1,2)

# Vector addition
v <- v1+v2
v

# Vector subtraction
v <- v1-v2
v

# Vector multiplication
v <- v1*v2
v

# Vector division
v <- v1/v2
v

#Math on vectors

x <- c(10, 20, 40, 80)
x + 10

x * 2

y <- c(0, -10, 5, -20)
x + y


#Vector Element Sorting

v <- c(3,8,4,5,0,11,-9,304)

# Sort the elements of the vector
v <- sort(v)
v

# Sorting character vectors
v <- c("Red","Blue","Yellow","Violet")
v <- sort(v)
v

# Naming Vectors

yield <- c(150, 200, 225)
names(yield) <- c("Piracicaba", "Limeira", "Campinas")
yield

yield["Piracicaba"]


# Vectors (continue) Examples:

x = c(1.5,2.1,2.5,3.4,4.3,6.1) #A vector with numeric value
y = c("A","A","B","B","C","C") #A vector with character values
str(x)
str(y)

sum(x) #the sum of the vector objects
mean(x) #the mean of the vector objects
var(x) #the variance between the vector objects
sum(y) #returns error, because y is not numeric

#To do

#Exercise 1
x <- runif(10)
x
sum(x)
mean(x)
var(x)

#all numbers less than 0.05
x[x<0.05]

#all numbers are greater than or equal to 0.5
x[x>=0.5]

#Exercise 2
seq(1,10,0.1) #Creates a vector from 1 to 10 by 0.1 of interval

sample(seq(1,10,0.1),4) #Sample from the seq(1,10,0.1) 4 numbers


#=========


#Matrices

#A Matrix is created using the matrix() function
?matrix

# Create a 2x3 matrix from a vector
x<- c(1, 2, 3, 4, 5, 6)
y<- matrix(x, nrow = 2, ncol = 3)
y


matrix(0, 2, 3)

(vals <- 1:6)

(x <- matrix(vals, 2, 3))

dim(x)

#or

(vals <- 1:6)

(y <- matrix(vals, 2, 3, byrow = TRUE))

dim(y)


# Elements are arranged sequentially by row
M <- matrix(c(3:14), nrow = 4, ncol = 3, byrow = TRUE)
M

# Elements are arranged sequentially by column
N <- matrix(c(3:14), nrow = 4, ncol = 3, byrow = FALSE)
N

# Define the column and row names
rownames = c("row1", "row2", "row3", "row4")
colnames = c("col1", "col2", "col3")

x <- matrix(c(3:14), nrow = 4, ncol = 3, byrow = TRUE, dimnames = list(rownames, colnames))
x

#Accessing Elements of a Matrix

# Access the element at 3rd column and 1st row
x[1,3]

# Access the element at 2nd column and 4th row
x[4,2]

# Access only the  2nd row
x[2, ]

# Access only the 3rd column
x[,3]


#Mathematical Operations with Matrices

#Matrix Addition & Subtraction

# Create two 2x3 matrices

matrix1 <- matrix(c(3, 9, -1, 4, 2, 6), nrow = 2)
matrix1

matrix2 <- matrix(c(5, 2, 0, 9, 3, 4), nrow = 2)
matrix2

# Add the matrices
M <- matrix1 + matrix2
M

# Subtract the matrices
M <- matrix1 - matrix2
M


# Multiply the matrices
M <- matrix1 * matrix2
M


# Divide the matrices
M <- matrix1 / matrix2
M

#Matrix Algebra
matrix1 <- matrix(c(3, 9, -1, 4), nrow = 2)
matrix1

#Transposed Matrix
y <- t(matrix1)
y

#Matrix Determinant
y <-det(matrix1)
y

#Inverse of matrix
y<- solve(matrix1)
y



#To do

#Create matrices M and N in R

v1 <- c(5,9)
v2 <- c(-4,1)
v3 <- c(8,0)

M <- rbind(v1, v2, v3)
M

v1 <- c(-4,1)
v2 <- c(-2,0)
v3 <- c(0,5)

N <- rbind(v1, v2, v3)
N

#Get the transpose of M and N

t(M)

t(N)

#Add M and N

result <- M+N
result

#Subtract N from M

result1 <- N-M
result1

###cbind

v1 <- c(5,9)
v2 <- c(-4,1)
v3 <- c(8,0)

M <- cbind(v1, v2, v3)
M

v1 <- c(-4,1)
v2 <- c(-2,0)
v3 <- c(0,5)

N <- cbind(v1, v2, v3)
N

#---------

##Data frame

?data.frame

# Criar um data frame com três colunas
name <- c("Ana", "João", "Maria")
age <- c(25, 30, 28)
score <- c(85, 90, 88)

df <- data.frame(name, age, score)
df

df <- data.frame(
  Ind = c(1:10),
  Yield = c(1.80, 1.77, 1.71, 1.65, 1.66, 1.63, 1.77, 2.58, 2.15, 1.56),
  Resis = c(TRUE, FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, FALSE, FALSE)
)


#=========

#Graphic Plotting

#Scatter Plot

?plot
# Data vectors
x <- c(1, 2, 3, 4, 5)
y <- c(3, 5, 7, 8, 10)

# Create the scatter plot
plot(x, y, main = "Maize summer", xlab = "yield", ylab = "years", col = "blue",pch = 19)

####
x <- seq(0, 20, 0.5)
y <- x^2
plot(x, y, main = "Scatterplot example")


#Histogram

temperatures <- c(67 ,72 ,74 ,62 ,76 ,66 ,65 ,59 ,61 ,69 )

# histogram of temperatures vector
result <- hist(temperatures,
               main = "Histogram of Temperature",
               xlab = "Temperature in degrees Fahrenheit")


#BoxPlots

age_class <- c(21,22,24,18,19,27,22,22,23,21,23,21)
summary(age_class)

boxplot(age_class, main="Boxplot: age_class", col="Pink")

#Barplots


#Example:

max.temp <- c(22, 27, 26, 24, 23, 26, 28)

barplot(max.temp,
        main = "Maximum Temperatures in a Week",
        xlab = "Degree Celsius",
        ylab = "Day",
        names.arg = c("Sun", "Mon", "Tue", "Wed", "Thu", "Fri", "Sat"),
        col = "Blue")

#HeatMaps

#Create an example matrix
matriz <- matrix(rnorm(100), nrow = 10)

#Create a matrix heatmap
heatmap(matriz, col = heat.colors(256), main = "Example of HeatMap")


#Working Directory
getwd()
setwd("C:/Users/Usuario/Desktop/Rtest")
#or
setwd("C:\\Users\\Usuario\\Desktop\\Rtest")

#File formattig


#Importing data into R

#read.table(filename,header=FALSE,sep = "")

#Example

X<-read.table("C:\\Users\\Usuario\\Desktop\\Rtest\\data1.csv", header = T, sep = ";")
X

#Exporting data from R

#write.table

write.table(X, file = "C:\\Users\\Usuario\\Desktop\\Rtest\\result.csv")


#Fitting Regression Model

?lm

Y <- c(6.5,5.8,7.8,8.1,10.4,12.3,13.1,17.4,20.1,24.5,25.5,27.1) # response variable
X <- c(1.4,1.5,1.7,1.9,2.1,2.2,2.4,3.2,3.7,4.2,4.8,5.2)       # explanatory variable
dados <- data.frame(Y,X)
dados

modelo.regressao <- lm(Y ~ X, data= dados)

summary(modelo.regressao)  # To obtain the coefficients of the linear regression line

anova(modelo.regressao)    # ANOVA

plot (Y ~ X,pch=16 ,data = dados)
abline(modelo.regressao,col="Red") # This function fits the model line to the data