R Notebook

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

4+3

[1] 7

4-3

[1] 1

4==3

[1] FALSE

3^2

[1] 9

sqrt(4)

[1] 2

log(10)

[1] 2.302585

log10(10)

[1] 1

log10(100)

[1] 2

log10(1000)

[1] 3

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

log(10, base = 5)

[1] 1.430677

log(10)

[1] 2.302585

log10(10)

[1] 1

#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_1=(42)/212
Battling_Average1=round(BA_1, digits = 3)
Battling_Average1

[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

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 = (156+65+3)/(565+65+3+7)
On_base_percent2 = round(OBP, digits = 3)
On_base_percent2

[1] 0.35

3==5

[1] FALSE

3==8

[1] FALSE

3==3

[1] TRUE

3==2+1

[1] TRUE

4!=4

[1] FALSE

2!=4

[1] TRUE

TRUE | FALSE

[1] TRUE

TRUE & FALSE

[1] FALSE

!FALSE

[1] TRUE

!TRUE

[1] FALSE

!FALSE & FALSE | TRUE

[1] TRUE

!FALSE & !TRUE | TRUE

[1] TRUE

2 > 5 | 1 == 3

[1] FALSE

11 > 7 | 4 == 3

[1] TRUE

Total_Bases <- 136 + 214 
Total_Bases

[1] 350

ls()

[1] "BA"                 "BA_1"               "Batting_Average"    "Battling_Average1" 
[5] "OBP"                "On_base_percent2"   "On_Base_Percentage"

rm(Total_Bases)

ls()

[1] "BA"                 "BA_1"               "Batting_Average"    "Battling_Average1" 
[5] "OBP"                "On_base_percent2"   "On_Base_Percentage"

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

[1] 12 15 10 20 10

Wins_Season <- c(94, 88 , 96, 87, 79)
Wins_Season

[1] 94 88 96 87 79

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(13, 10, 8, 5, 9)
hits_per_9innings <- c(10, 10, 9, 7, 12)
runs_per_9innings

[1] 13 10  8  5  9

hits_per_9innings

[1] 10 10  9  7 12

rep(2, 5)

[1] 2 2 2 2 2

rep(1,4)

[1] 1 1 1 1

1:5

[1] 1 2 3 4 5

seq(3,10,3)

[1] 3 6 9

pitches_by_innings+strikes_by_innings

[1] 21 27 16 34 19

pitches_by_innings == strikes_by_innings

[1] FALSE FALSE FALSE FALSE FALSE

strikes_by_innings

[1]  9 12  6 14  9

Wins_Season

[1] 94 88 96 87 79

pitches_by_innings

[1] 12 15 10 20 10

strikes_by_innings+pitches_by_innings

[1] 21 27 16 34 19

strikes_by_innings==pitches_by_innings

[1] FALSE FALSE FALSE FALSE FALSE

length(pitches_by_innings)

[1] 5

min(pitches_by_innings)

[1] 10

max(pitches_by_innings)

[1] 20

mean(pitches_by_innings)

[1] 13.4

Question_5: Get the first element of hits_per_9innings.

pitches_by_innings[3]

[1] 10

pitches_by_innings[1]

[1] 12

pitches_by_innings[5]

[1] 10

Question_6: Get the last element of hits_per_9innings.

length(pitches_by_innings)

[1] 5

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"

soccer_positions <- c("Goalkeeper", "defender", "midfielders", "forwards")
soccer_positions

[1] "Goalkeeper"  "defender"    "midfielders" "forwards"   

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

sample(1:13, size=2)

[1]  2 12

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

x <- c("yes", "no", "no", "no", "yes", "yes", "yes", "no", "yes","yes")
x

 [1] "yes" "no"  "no"  "no"  "yes" "yes" "yes" "no"  "yes" "yes"

table(x)

x
 no yes 
  4   6 

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 

# 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_9innings)

[1] 10

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