Getting Started with R

4/2

[1] 2

6/12

[1] 0.5

4/12

[1] 0.3333333

81/9

[1] 9

sqrt(81)

[1] 9

sqrt(144)

[1] 12

sqrt(16)

[1] 4

log(2)#Natural Log

[1] 0.6931472

log(10)

[1] 2.302585

log(2.72)

[1] 1.000632

Question 1: Compute the log base 5 of 10 and the log of 10.

#Answers for Question 1
log(10,5) #log of 10, base 5

[1] 1.430677

log(10,10)#log of 10, base 10

[1] 1

log(100,4)#log of 100,base 4

[1] 3.321928

#Batting Average=(No. of Hits)/(No. of At Bats)
#What is the batting average of a player that bats 129 hits in 412 at bats?
BA=129/412
BA

[1] 0.3131068

#Alternative Solutions
N_Hits=129
At_Bats=412
BA<-N_Hits/At_Bats
BA

[1] 0.3131068

Batting_Average=round(BA,digits = 3)
Batting_Average

[1] 0.313

#Question_2:What is the batting average of a player that bats 42 hits in 212 at bats?

#Answers
N_Hits=42
At_Bats1=212
Bat_Average<-N_Hits/At_Bats1
BattingAverage=round(Bat_Average,digits = 3)
BattingAverage

[1] 0.198

#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

OBP_Adj=round(OBP,digits = 3)
OBP_Adj

[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=(156+65+3)/(565+65+3+156+7)
OBP_Ad=round(OBP,digits = 3)
OBP_Ad

[1] 0.281

Often you will want to test whether something is less than, greater than or equal to something.

3==8

[1] FALSE

2==3

[1] FALSE

1==1

[1] TRUE

3>=1

[1] TRUE

3>=9

[1] FALSE

3!=4

[1] TRUE

Often you will want to test whether something is less than, greater than or equal to something.

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

[1] FALSE

FALSE|TRUE

[1] TRUE

TRUE & FALSE

[1] FALSE

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

[1] TRUE

2<1|2==3

[1] FALSE

total_bases<-7+4
total_bases*4

[1] 44

Vectors

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(1,3,4,1,6)
runs_per_9innings

[1] 1 3 4 1 6

hits_per_9innings<-c(2,4,6,1,2)
hits_per_9innings

[1] 2 4 6 1 2

#Replicate functions
rep(3,3)

[1] 3 3 3

seq(1,10,by=3)

[1]  1  4  7 10

seq(2,13,by=3)

[1]  2  5  8 11

#adding vectors
pitches_by_innings+strikes_by_innings#+ operator

[1] 21 27 16 34 19

#compare two vectors
pitches_by_innings

[1] 12 15 10 20 10

strikes_by_innings

[1]  9 12  6 14  9

pitches_by_innings==strikes_by_innings

[1] FALSE FALSE FALSE FALSE FALSE

length(pitches_by_innings)

[1] 5

min(pitches_by_innings)

[1] 10

mean(pitches_by_innings)

[1] 13.4

pitches_by_innings[1]

[1] 12

hits_per_9innings[1]

[1] 2

pitches_by_innings[length(pitches_by_innings)]

[1] 10

pitches_by_innings[c(2,3,4)]

[1] 15 10 20

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

[1] "catcher"     "pitcher"     "infielders"  "outfielders"

Data Frames

data.frame(bonus = c(2, 3, 1), active_roster = c("yes", "No", "Yes"), salary = c(1.5, 2.5, 1))

NA
NA

Using Tables

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

x
 No Yes 
  2   3 

NUmerical measures and center of spread

ceo_slaries<-c(12,.4,2,50,8,3,1,4,.25)
mean(ceo_slaries)

[1] 8.961111

var(ceo_slaries)

[1] 251.9386

sd(ceo_slaries)

[1] 15.87257

median(ceo_slaries)

[1] 3

fivenum(ceo_slaries)

[1]  0.25  1.00  3.00  8.00 50.00

Question_5: Get the first element of hits_per_9innings

hits_per_9innings[1]

[1] 2

Question_6: Get the last element of hits_per_9innings

hits_per_9innings[length(hits_per_9innings)]

[1] 2

getMode<-function(x) {
  ux<-unique(x)
  ux[which.max(tabulate(match(x,ux)))]
}

Question_7: Find the most frequent value of hits_per_9innings.

pitches_by_innings

[1] 12 15 10 20 10

getMode(pitches_by_innings)

[1] 10

Question_8 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","Monday","Saturday","Tuesday")
table(game_day)

game_day
  Monday Saturday  Tuesday 
       1        3        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"