VisualizationWithR/lection1/Commands.R

# Install R
# # apt install r-base
# # snap install rstudio
#
# Online:
# https://cran.r-project.org
# https://posit.co


# --------------------------------------------------------------------------
# Slide 4, 5: Installing R
# --------------------------------------------------------------------------

# Some samples
1 + 2
4 * 7
(2 + 3) * 9
2 ^ 3
11 %% 3
11 %/% 3
print("Hello World")
print("Hello World", quote=FALSE)
print(81 / 3)
q()

# --------------------------------------------------------------------------
# Slide 5: Installing R Studio
# --------------------------------------------------------------------------
1 + 2
4 * 7
print("Hello World")


# --------------------------------------------------------------------------
# Slide 6: Running R on Posit Cloud
# --------------------------------------------------------------------------
1 + 2
4 * 7
print("Hello World")

# Some random values:
rnorm(10)
help("rnorm")

# Variables
a <- 3
b <- 5
c <- a * b
print(c)

# Vectors
seq(3, 5, 0.2)
u <- c(1,3,5)
v <- rnorm(3)
v + 5
w <- 7:9
u + w
u - w
u * w
u %*% w
u %o% w
abs(v)
log(w)
log(abs(v))

m <- matrix(1:12, 3, 4)
t(m)
m %*% c(1,2,3,4)

t(sapply(v, function (x) c(x, x * x)))




# Acessing and changing vectors
u[1]
u[2]
u[3]
u
u[2] <- 7
u
u[4] <- 9
u
u[7] <- 11
u
u[1:3]
u[2:5]
u[4:11]
u[is.na(u)] <- 0
u
u[u < 6]
u[u > 6] <- u[u > 6] * 2

# Calculating mean
s <- 0
for (x in w)
{
  s <- s + x
}
s / length(w)

mean(w)


# summing up all positive / negative values
s1 <- 0
s2 <- 0
for (x in v)
{
  if ( x >= 0 )
  {
    s1 <- s1 + x
  }
  else
  {
    s2 <- s2 + x
  }
}
print(c(s1, s2))

sum(v[v >= 0])
sum(v[v < 0])


# Plotting
plot(w, v)
plot(w, v, "l")
help("plot")

# --------------------------------------------------------------------------
# Slide 8: Packages in R
# --------------------------------------------------------------------------
# Install needed package for plotting.
# Needed only once after installing R
install.packages("ggplot2")


# Activate "ggplot2" package.
# Needed only once per session or script.
library(ggplot2)

qplot(data=iris, Sepal.Width, Sepal.Length)
qplot(data=iris, Sepal.Width, Sepal.Length, colour=Species)
qplot(data=iris, Sepal.Width, Sepal.Length, colour=Species, facets = .~ Species)


qplot(data=diamonds, carat, price, colour=clarity, facets = . ~ clarity)

# --------------------------------------------------------------------------
# Slide 9: the daily life of a data scientist
# --------------------------------------------------------------------------

# Datasets
head(iris)
length(iris)
summary(iris)
iris["Sepal.Width"]
iris[c("Sepal.Lenght", "Sepal.Width")]
iris$Sepal.Width
iris$Sepal.Width[1:10]
hist(iris$Sepal.Width)
hist(iris$Sepal.Length)
boxplot(iris$Sepal.Length ~ iris$Species)
plot(iris$Sepal.Width, iris$Sepal.Length)



# Diamonds dataset
myData <- read.csv("diamonds.csv")
summary(myData)
plot(myData$carat, myData$price)

ggplot(data=myData, aes(x=carat, y=price)) + geom_point()
ggplot(data=myData, aes(x=carat, y=price, color=clarity)) + geom_point()
ggplot(data=myData[myData$carat < 2.5,], aes(x=carat, y=price, color=clarity)) + geom_point(alpha=0.1) + geom_smooth()