Getting Started with R

1+1

7-8

[1] -1

(2+5i) + (3-1i)

[1] 5+4i

4/2

[1] 2

2^5

[1] 32

sqrt(25)

[1] 5

sqrt(16)

[1] 4

sqrt(144)

[1] 12

log(2)

log(10)

[1] 2.302585

log(2.72)

[1] 1.000632

log10(10)

[1] 1

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

log(10,5) 

[1] 1.430677

log(10,10)

[1] 1

log(100,4)

[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=(129)/(412)
BA

[1] 0.3131068

#ALternative Solution
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?

#Answer
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_adj = round(OBP, digits = 3)
OBP_adj

[1] 0.281

3==8

[1] FALSE

2==3

[1] FALSE

1==1

[1] TRUE

3>=1

[1] TRUE

3>=9

[1] FALSE

7<=10

[1] TRUE

7<=6

[1] FALSE

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

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

[1] FALSE

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

[1] FALSE

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

[1] TRUE

Total_Bases <- 7 + 4
Total_Bases*4

[1] 44

ls()

 [1] "At_Bats"         "At_Bats1"        "BA"             
 [4] "Bat_Average"     "Batting_Average" "BattingAverage" 
 [7] "N_Hits"          "OBP"             "OBP_adj"        
[10] "OBP_Adj"         "Total_Bases"    

rm(Total_Bases)
   ls()

 [1] "At_Bats"         "At_Bats1"        "BA"             
 [4] "Bat_Average"     "Batting_Average" "BattingAverage" 
 [7] "N_Hits"          "OBP"             "OBP_adj"        
[10] "OBP_Adj"        

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(2,1,0,0,1)
runs_per_9innings

[1] 2 1 0 0 1

hits_per_innings <- c(3,3,4,6,1)
hits_per_innings

[1] 3 3 4 6 1

rep(2, 5)

[1] 2 2 2 2 2

rep(1,4)

[1] 1 1 1 1

1:6

[1] 1 2 3 4 5 6

2:7

[1] 2 3 4 5 6 7

seq(1, 10, by=3)

[1]  1  4  7 10

seq(2,13,by=3)

[1]  2  5  8 11

pitches_by_innings+strikes_by_innings

[1] 21 27 16 34 19

#compare two vecors
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] 12 15 10 20 10

pitches_by_innings[1]

[1] 12

Question_5: Get the first element of hits_per_9innings.

hits_per_innings

[1] 3 3 4 6 1

hits_per_innings[1]

[1] 3

pitches_by_innings[length(pitches_by_innings)]

[1] 10

#Question_6: Get the last element of hits_per_9innings.

hits_per_innings

[1] 3 3 4 6 1

hits_per_innings[length(hits_per_innings)]

[1] 1

pitches_by_innings

[1] 12 15 10 20 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" 
[4] "outfielders"

Data Frames

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

How to make a Random Sample

sample(1:10, size=5)

[1] 10  9  6  1  3

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] 8 1 5 2 9

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

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

NA

Using Tables

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

var(sals)

[1] 225.5145

sd(sals)

[1] 15.01714

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(sals)

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

How about the Mode?

# Function to find the mode, i.e. most frequent value
getMode <- function(x) {
     ux <- unique(x)
     ux[which.max(tabulate(match(x, ux)))]
 }

getMode(pitches_by_innings)

[1] 10

#Question_7: Find the most frequent value of hits_per_9innings.**

getMode(hits_per_innings)

[1] 3

#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"