R Notebook

4+3

[1] 7

4-3

[1] 1

4==3

[1] FALSE

3^2

[1] 9

sqrt(4)

[1] 2

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

log(10)#1n, natural log, base e=2.72

[1] 2.302585

log10(10)

[1] 1

log10(100)

[1] 2

log10(1000)

[1] 3

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

#Question_1

log(10,base=5)

[1] 1.430677

log(10)#ln of 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
Batting_Average1=round(BA_1,digits = 3)
Batting_Average1

[1] 0.198

On_Base_Percentage=round(OBP,digits = 3)
On_Base_Percentage

[1] 0.35

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

#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_Percentage2=round(OBP,digits =3)
On_Base_Percentage2

[1] 0.35

Total_Bases<-136+ 214
Total_Bases

[1] 350

ls()

 [1] "BA"                  "BA_1"                "Batting_Average"     "Batting_Average1"    "contract_length"     "contract_years"     
 [7] "contracts_mean"      "contracts_median"    "contracts_n"         "contracts_sd"        "contracts_w1sd"      "contracts_w2sd"     
[13] "contracts_w3sd"      "firstbase"           "firstbaseTest"       "game_day"            "getMode"             "HR_before"          
[19] "model1"              "model2"              "model3"              "model4"              "model5"              "model6"             
[25] "model7"              "n_1"                 "n_2"                 "n_3"                 "n_4"                 "n_seasons"          
[31] "n_soto_seasons"      "OBP"                 "On_Base_Percentage"  "On_Base_Percentage2" "pitches_by_innings"  "players_positions"  
[37] "predictTest"         "Robert_HRs"          "salary_ave"          "salary_ave_2"        "sals"                "soccer_positions"   
[43] "Soto_Walks_6"        "Soto_Walks_Before"   "SSE"                 "strikes_by_innings"  "Total_Bases"         "wanted_BB"          
[49] "wanted_HR"           "Wins_Season"         "x"                   "x_4"                 "y_1"                 "y_2"                
[55] "y_3"                 "y_4"                

rm(Total_Bases)

ls()

 [1] "BA"                  "BA_1"                "Batting_Average"     "Batting_Average1"    "contract_length"     "contract_years"     
 [7] "contracts_mean"      "contracts_median"    "contracts_n"         "contracts_sd"        "contracts_w1sd"      "contracts_w2sd"     
[13] "contracts_w3sd"      "firstbase"           "firstbaseTest"       "game_day"            "getMode"             "HR_before"          
[19] "model1"              "model2"              "model3"              "model4"              "model5"              "model6"             
[25] "model7"              "n_1"                 "n_2"                 "n_3"                 "n_4"                 "n_seasons"          
[31] "n_soto_seasons"      "OBP"                 "On_Base_Percentage"  "On_Base_Percentage2" "pitches_by_innings"  "players_positions"  
[37] "predictTest"         "Robert_HRs"          "salary_ave"          "salary_ave_2"        "sals"                "soccer_positions"   
[43] "Soto_Walks_6"        "Soto_Walks_Before"   "SSE"                 "strikes_by_innings"  "wanted_BB"           "wanted_HR"          
[49] "Wins_Season"         "x"                   "x_4"                 "y_1"                 "y_2"                 "y_3"                
[55] "y_4"                

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(5,6,9,7,14)
strikes_by_innings

[1]  5  6  9  7 14

#Question_4: Define two vectors,runs_per_9innings and hits_per_9innings, each with five elements.

rep(2,5)

[1] 2 2 2 2 2

1:6

[1] 1 2 3 4 5 6

seq(3,10,3)

[1] 3 6 9

strikes_by_innings

[1]  5  6  9  7 14

Wins_Season

[1] 94 88 96 87 79

pitches_by_innings

[1] 12 15 10 20 10

strikes_by_innings+pitches_by_innings

[1] 17 21 19 27 24

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

pitches_by_innings[3]

[1] 10

pitches_by_innings[1]

[1] 12

pitches_by_innings[5]

[1] 10

pitches_by_innings[length(pitches_by_innings)]

[1] 10

pitches_by_innings[c(2,3,4)]

[1] 15 10 20

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

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

soccer_positions<- c("goalkeepers","defenders","midfielders", "forwards")
soccer_positions

[1] "goalkeepers" "defenders"   "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(1:9, size=2)

[1] 6 3

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

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

table(x)

x
 no yes 
  3   7 

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(Wins_Season)

[1] 94

Wins_Season

[1] 94 88 96 87 79

#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"