Getting started with R

# Addition
1+1

[1] 2

7-8

[1] -1

# Division
2/3

[1] 0.6666667

# Exponentiation
2^3 

[1] 8

# Square root
sqrt(15)

[1] 3.872983

# Logarithms
log(2)

[1] 0.6931472

#Question_1: Compute the log base 5 of 10 and the log of 10.

log10(10)

[1] 1

log(10,5)#Base 5

[1] 1.430677

log(10,10)#Base 10

[1] 1

log(100,4)#Base 4

[1] 3.321928

#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

#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

3 == 8# Does 3 equals 8?

[1] FALSE

3 != 8# Is 3 different from 8?

[1] TRUE

3 <= 8# Is 3 less than or equal to 8?

[1] TRUE

3>4

[1] FALSE

# Logical Disjunction (or)
FALSE | FALSE # False OR False

[1] FALSE

# Logical Conjunction (and)
TRUE & FALSE #True AND False

[1] FALSE

# Negation
! FALSE # Not False

[1] TRUE

# Combination of statements
2 < 3 | 1 == 5 # 2<3 is True, 1==5 is False, True OR False is True

[1] TRUE

#In R, you create a variable and assign it a value using <- as follows

Total_Bases <- 6 + 5
Total_Bases*3

[1] 33

#To see the variables that are currently defined, use ls (as in “list”)

ls()

[1] "BA"                 "Batting_Average"   
[3] "OBP"                "On_Base_Percentage"
[5] "Total_Bases"       

#To delete a variable, use rm (as in “remove”)

rm(Total_Bases)

#Either <- or = can be used to assign a value to a variable, but I prefer <- because is less likely to be confused with the logical operator ==

#The basic type of object in R is a vector, which is an ordered list of values of the same type. You can create a vector using the c() function (as in “concatenate”).

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. 

# replicate function
rep(2, 5)

[1] 2 2 2 2 2

rep(1,4)

[1] 1 1 1 1

# consecutive numbers
1:5

[1] 1 2 3 4 5

2:10

[1]  2  3  4  5  6  7  8  9 10

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

[1] 1 3 5 7 9

seq(2,13,by=3)

[1]  2  5  8 11

# 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

pitches_by_innings

[1] 12 15 10 20 10

# If you want to get the first element:
pitches_by_innings[1]

[1] 12

#Question_5: Get the first element of hits_per_9innings.
pitches_by_innings[length(pitches_by_innings)]

[1] 10

#Question_6: Get the last element of hits_per_9innings.
pitches_by_innings[c(2, 3, 4)]

[1] 15 10 20

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

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

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

[1] 4 9 6 2 8

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

n <- 5

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

[1]  5 10  6  3  4

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

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

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

x
 No Yes 
  2   3 

sals <- c(12, .4, 5, 2, 50, 8, 3, 1, 4, 0.25)
# the average
mean(sals) 

[1] 8.565

# the 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 

# 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 strikes_by_innings.
strikes_by_innings

[1]  9 12  6 14  9

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"