Intro: basics 02

#creating a matrix
#matrix(data = NA, nrow = 1, ncol = 1, byrow = FALSE,dimnames = NULL)
?matrix

#creatng a vector, use the function c
codes <- c(380,124,818)
#for character vectors use quotes to avoid returning an error
country <- c("italy","canada","egypt")
codes <- c(italy = 380, canada = 124 ,egypt = 818)

print(codes)

#names can be assigned to vecors using the names function
names(codes) <- country
#another function to create vectors is 'seq', example
#this will print out 1  10
seq(1,10)
#this will print out only the odd numbers because we specified that the sequence should start from 1 and end at 10 in increments of 2
seq(1,10,2)
#this prodeces integers
class(seq(1,10))
#subsetting a vector to access a specific part of it, use square brackets
#can acess one element of the vector
codes[2]
#can access several elements of the vector
codes[c(1,3)]
codes[1:2]
codes[1:3]
#access a specific name in the vector, use quotes
codes["canada"]

#coercion is an attempt by R to be flexible with data types,
#vectors must always be the same type but R can coerce a vector before throwing out an error message
#example
x <- c(1,"canada",3)
# 1 and 3 are retruned as character strings, when the class of the vector X is checekd it returns as character
class(x)
#R coerced the data into a character string 

#r can force a specific coercion
x <- 20:36
y <- as.character(x)
#can use as.muneric to turn them back frm character to numenric
as.numeric(y)

#Create a vector containing all the positive odd numbers smaller than 100.
# The numbers should be in ascending order
seq(1,100,2)

#length.out lets us generate sequences that are increasing by the same amount but are of the prespecified length.
seq(1,100,length.out = 10)

#You can create an integer by adding the letter L after a whole number
class(3L)
#For most practical purposes, integers and numerics are indistinguishable,
3-3L
#integers tae up less space

library(dslabs)
data(murders)

#the function sort sorts vectors in increasing order
sort(murders$total)

#The function order takes a vector as input and returns the vector of indexes that sorts the input vector
x <- c(31, 4, 15, 92, 65)
sort(x)

index <- order(x)
x[index]
#this is the index that puts x in order
order(x)
# this returns 2,3,1,5,5
#the second item (4) is the smallest so it comes 1st

#using the dslabs data set to answer the question of wich state has the most murders
#We first obtain the index that orders the vectors according to murder totals and 
index <- order(murders$total)
#then index the state names vector
murders$abb[index]

#[1] "VT" "ND" "NH" "WY" "HI" "SD" "ME" "ID" "MT" "RI" "AK" "IA" "UT" "WV" "NE" "OR" "DE"
#[18] "MN" "KS" "CO" "NM" "NV" "AR" "WA" "CT" "WI" "DC" "OK" "KY" "MA" "MS" "AL" "IN" "SC"
#[35] "TN" "AZ" "NJ" "VA" "NC" "MD" "OH" "MO" "LA" "IL" "GA" "MI" "PA" "NY" "FL" "TX" "CA"

#so california has the most murders and vermont has the least
  
#the function max can be used to find the largest value
max(murders$total)
#this gives us the max of the total murders

#which.max gives the index where the max number is
i_max <- which.max(murders$total)
i_max
#this returns 5
#now we subset the murders data set to access the object in the vector that matches with 5
murders$state[i_max]
#its cali

i_min <- which.min(murders$total)
murders$abb[i_min]

#its VT

#the function rank returns a vector with the rank of the first entry, second entry, etc., of the input vector
x
# 31 4 15 92 65
rank(x)
#3 1 2 5 4, returns this 

#31 is the third smallest value so it returns a 3, 4 is the smallest so it gets 1

# Access population values from the dataset and store it in pop
pop <- murders$population
# Sort the object and save it in the same object 
pop<- sort(pop)
# Report the smallest population size 
pop[1]

# Access population from the dataset and store it in pop
pop <- murders$population
# Use the command order to find the vector of indexes that order pop and store in object ord
ord <- order(murders$population)
# Find the index number of the entry with the smallest population size,subset
ord[1]

# Define a variable states to be the state names from the murders data frame

states <- (murders$state)
# Define a variable ranks to determine the population size ranks 
ranks <- rank(murders$population)

# Define a variable ind to store the indexes needed to order the population values
ind <- order(murders$population)

# Create a data frame my_df with the state name and its rank and ordered from least populous to most 
my_df <- data.frame(name = states[ind], rank = ranks[ind])

# Using new dataset 
library(dslabs)
data(na_example)

# Checking the structure 
str(na_example)

# Find out the mean of the entire dataset 
mean(na_example)

# Use is.na to create a logical index ind that tells which entries are NA
ind <- is.na(na_example)
# Determine how many NA ind has using the sum function
sum(ind)

#in R arithmetic operations on vectors occur element wise
murder_rate <- murders$total/murders$population * 100000

#order states by murder rate in decreasing order
murders$state[order(murder_rate, decreasing = TRUE)]

# Calculate the average murder rate in the US 
mean(murder_rate)

name <- c("Mandi", "Amy", "Nicole", "Olivia")
distance <- c(0.8, 3.1, 2.8, 4.0)
time <- c(10, 30, 40, 50)

time/60
distance/(time/60)