intro: R basics

#creating a sequence
print(seq(23,400))

#creating a prompt
?prompt
prompt="Input your name: "
print(prompt)

?run_console

#creating a dataframe
name <- c('John Doe','Peter Gynn','Jolie Hope')
age <- c(21, 23, 26)

data.frame<- c(name,age)
userage <-data.frame

#rounding a number
x <- 0.15 * 19.71
round(x,2)

?round

install.packages("dslabs")
library(dslabs)
install.packages("rtools")

#solving the quadratc formula
#2x^2 -x-4=0
a <- 2
b <- 1
c <- -4

solution_1 <- (-b - sqrt(b^2 - 4*a*c))/(2*a)
solution_2 <- (-b + sqrt(b^2 - 4*a*c))/(2*a)

print(solution_1)
print(solution_2)


#functions are nested
#functions are evaluated from the inside out when you nest them
# R functions are documented

#for variable names, stick to underscores and lower cases.

a <- 3
b <- 2
c <- -1

solution_1
solution_2 
print(solution_1)
print(solution_2)


library(dslabs)
data("murders")

#checking the class of murders dataframe
class(murders)
#structure of murders dataframe
str(murders)

library(help = "stats")

#show the first six lines of murders dataframe
head(murders)
#show names of variables in murders dataframe
names(murders)
#show levels of the factors
levels(murders$region)

# == is a relational vector, it tests for equality
z <- 3 == 2
z
print(class(z))

#You can see the other relational operators by typing:
?Comparison

#turning something into an integer
as.integer()

# We extract the population like this:
p <- murders$population

# This is how we do the same with the square brackets:
o <- murders[["population"]] 

# We can confirm these two are the same
identical(o, p)

# We can see the class of the region variable using class
class(murders$region)

# Determine the number of regions included in this variable using a nested funtion
length(levels(murders$region))

#The function table takes a vector as input and returns the frequency of each unique element in the vector.
# Write one line of code to show the number of states per region
table(murders$region)

#operation to find log base 4 of 1024
log(1024,4)

# The function reorder lets us change the order of the levels of a factor variable based on a summary computed on a numeric vector. 
#create region dataframe
region <- murders$region

#create the value dataframe
value <- murders$total

#reorder the region data by the sum of total murders in "value", from least murders to most murders
region <- reorder(region, value, FUN = sum)
levels(region)

?reorder