Activity 4

#Addition
2+3

[1] 5

#Subtraction
5-2

[1] 3

#Division
2/9

[1] 0.2222222

#Exponentiation
2^9

[1] 512

#Square root
sqrt(7)

[1] 2.645751

#Logarithms
log(2)

[1] 0.6931472

log(2.72, base = 2.72)

[1] 1

log10(10)

[1] 1

log10(100)

[1] 2

log(10, base = 5)

[1] 1.430677

#Batting Average=(No. of Hits)/(No. of At Bats)
#What is the batting average of a player that bats 29 hits in 112 at bats?
BA=(29)/(112)
BA

[1] 0.2589286

Batting_Average=round(BA,digits = 3)
Batting_Average

[1] 0.259

#Question_2:What is the batting average of a player that bats 42 hits in 212 at bats?
BA= (42)/212
BA

[1] 0.1981132

#Question_2:What is the batting average of a player that bats 42 hits in 212 at bats?
#On Base Percentage
#OBP=(H+BB+HBP)/(At Bats+BB+HBP+SF)
#Let us compute the OBP for a player with the following general stats
#AB=515,H=172,BB=84,HBP=5,SF=6
OBP=(172+84+5)/(515+84+5+6)
OBP

[1] 0.4278689

On_Base_Percentage=round(OBP,digits = 3)
On_Base_Percentage

[1] 0.428

#Question_3:Compute the OBP for a player with the following general stats:
AB=565
H=156
BB=65
HBP=3
SF=7
OBP=(H+BB+HBP)/(AB+BB+HBP+SF)
OBP

[1] 0.35

#equal
3==8

[1] FALSE

#different
3!=8

[1] TRUE

#less than or equal
3<=8

[1] TRUE

#greater
3>8

[1] FALSE

#LOGICAL OPERATORS
#OR
FALSE | FALSE

[1] FALSE

#AND
TRUE & FALSE

[1] FALSE

#NEGATION
! FALSE

[1] TRUE

#COMBINATION OF STATEMENTS
2<3 | 1==5

[1] TRUE

Total_Bases <- 6+5
Total_Bases*3

[1] 33

ls()

 [1] "AB"                 "BA"                 "Batting_Average"   
 [4] "BB"                 "H"                  "HBP"               
 [7] "OBP"                "On_Base_Percentage" "SF"                
[10] "Total_Bases"       

#remove variable
rm(Total_Bases)

pitches_by_innings <- c(12, 15, 10, 20, 10) 
pitches_by_innings

[1] 12 15 10 20 10

strikes_by_innings <- c(9, 12, 6, 14, 9)
strikes_by_innings

[1]  9 12  6 14  9

#Question_4: Define two vectors,runs_per_9innings and hits_per_9innings, each with five elements. 
runs_per_9innings <- c(5, 2, 3, 4, 5)
hits_per_9innings <- c(2, 3, 4, 5, 6)
runs_per_9innings

[1] 5 2 3 4 5

hits_per_9innings

[1] 2 3 4 5 6

# replicate function
rep(2, 5)

[1] 2 2 2 2 2

# consecutive numbers
1:5

[1] 1 2 3 4 5

# sequence from 1 to 10 with a step of 2
seq(1, 10, by=2)

[1] 1 3 5 7 9

#add vectors
pitches_by_innings+strikes_by_innings

[1] 21 27 16 34 19

# compare vectors
pitches_by_innings == strikes_by_innings

[1] FALSE FALSE FALSE FALSE FALSE

# find length of vector
length(pitches_by_innings)

[1] 5

# find minimum value in vector
min(pitches_by_innings)

[1] 10

# find average value in vector
mean(pitches_by_innings)

[1] 13.4

#You can access parts of a vector by using [. Recall what the value is of the vector pitches_by_innings.
# If you want to get the first element:
pitches_by_innings[1]

[1] 12

#Question_5: Get the first element of hits_per_9innings.
hits_per_9innings[1]

[1] 2

#If you want to get the last element of pitches_by_innings without explicitly typing the number of elements of pitches_by_innings, make use of the length function, which calculates the length of a vector:
pitches_by_innings[length(pitches_by_innings)]

[1] 10

#Question_6: Get the last element of hits_per_9innings.
hits_per_9innings[length(hits_per_9innings)]

[1] 6

pitches_by_innings[c(2, 3, 4)]

[1] 15 10 20

player_positions <- c("catcher", "pitcher", "infielders", "outfielders")

#data frame
data.frame(bonus = c(2, 3, 1),#in millions 
           active_roster = c("yes", "no", "yes"), 
           salary = c(1.5, 2.5, 1))#in millions 

#random sample
sample(1:10, size=5)

[1] 10  4  9  1  8

bar <- data.frame(var1 = LETTERS[1:10], var2 = 1:10)
# Check data frame
bar

#Suppose you want to select a random sample of size 5. First, define a variable n with the size of the sample, i.e. 5

n <- 5

#Now, select a sample of size 5 from the vector with 1 to 10 (the number of rows in bar). Use the function nrow() to find the number of rows in bar instead of manually entering that number.

#Use : to create a vector with all the integers between 1 and the number of rows in bar.

samplerows <- sample(1:nrow(bar), size=n) 
# print sample rows
samplerows

[1]  1  4  9 10  3

#The variable samplerows contains the rows of bar which make a random sample from all the rows in bar. Extract those rows from bar with

# extract rows
barsample <- bar[samplerows, ]
# print sample
print(barsample)

   var1 var2
1     A    1
4     D    4
9     I    9
10    J   10
3     C    3

#The code above creates a new data frame called barsample with a random sample of rows from bar.

#In a single line of code:

bar[sample(1:nrow(bar), n), ]

#Table
x <- c("Yes","No","No","Yes","Yes") 
table(x)

x
 No Yes 
  2   3 

#Numerical measures of center and spread
sals <- c(12, .4, 5, 2, 50, 8, 3, 1, 4, 0.25)
#the average
mean(sals)

[1] 8.565

#variance
var(sals)

[1] 225.5145

#the standard deviation
sd(sals)

[1] 15.01714

#the median
median(sals)

[1] 3.5

# Tukey's five number summary, usefull for boxplots
# five numbers: min, lower hinge, median, upper hinge, max
fivenum(sals)

[1]  0.25  1.00  3.50  8.00 50.00

# summary statistics
summary(sals)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.250   1.250   3.500   8.565   7.250  50.000 

#Mode
#In R we can write our own functions, and a first example of a function is shown below in order to compute the mode of a vector of observations x
# Function to find the mode, i.e. most frequent value
getMode <- function(x) {
     ux <- unique(x)
     ux[which.max(tabulate(match(x, ux)))]
 }

# Most frequent value in pitches_by_innings
getMode(pitches_by_innings)

[1] 10

#Question_7: Find the most frequent value of hits_per_9innings.
getMode(hits_per_9innings)

[1] 2

#There is no mode so it is returning the first value
getMode(strikes_by_innings)

[1] 9

#Question_8: Summarize the following survey with the `table()` command:
#What is your favorite day of the week to watch baseball? A total of 10 fans submitted this survey.
#Saturday, Saturday, Sunday, Monday, Saturday,Tuesday, Sunday, Friday, Friday, Monday
game_day<-c("Saturday", "Saturday", "Sunday", "Monday", "Saturday","Tuesday", "Sunday", "Friday", "Friday", "Monday")
table(game_day)

game_day
  Friday   Monday Saturday   Sunday  Tuesday 
       2        2        3        2        1 

#Question_9: What is the most frequent answer recorded in the survey? Use the getMode function to compute results. 
getMode(game_day)

[1] "Saturday"