R Notebook

# Home-runs so far
HR_before <- c(11, 13, 12)
# Average Number of Home-runs per season wanted
wanted_HR <- 20
# Number of seasons
n_seasons <- 4
# Needed Home-runs on season 4
x_4 <- n_seasons*wanted_HR - sum(HR_before)
# Minimum number of Home-runs needed by Robert
x_4

[1] 44

# Robert's performance
Robert_HRs <- c(11, 13, 12,44)
# Find mean
mean(Robert_HRs)

[1] 20

sd(Robert_HRs)

[1] 16.02082

# Find the maximum number of home-runs during the four seasons period
max(Robert_HRs)

[1] 44

# Find the minimum number of home-runs during the four seasons period
min(Robert_HRs)

[1] 11

summary(Robert_HRs)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  11.00   11.75   12.50   20.00   20.75   44.00 

n_1 <- 10
n_2 <- 4
y_1 <- 72000
y_2 <- 84000
# Mean salary overall
salary_ave <-  (n_1*y_1 + n_2*y_2)/(n_1+n_2)
salary_ave

[1] 75428.57

Soto_Walks<-c(79,108,41,145,135)
wanted_walks<-100
number_seasons<-6
#Needed Wlks on season 6
walks_6<-number_seasons*wanted_walks-sum(Soto_Walks)
walks_6

[1] 92

n_1

[1] 10

n_2<-4
y_1<-72000
y_2<84000

[1] FALSE

#Mean Salary Overall
salary_ave<-(n_1*y_1+n_2*y_2)/(n_1+n_2)
salary_ave

[1] 75428.57

bp_1<-7
fp_1<-9
w_1<-102000
w_2<-91000
#Mean Salary Overall
w_salary_ave<-(bp_1*w_1+fp_1*w_2)/(bp_1+fp_1)
w_salary_ave

[1] 95812.5

getwd ()

[1] "C:/Users/benav/Downloads"

contract_length <- read.table("allcontracts.csv", header = TRUE, sep = ",")
contract_years <- contract_length$years

# Mean 
contracts_mean  <- mean(contract_years)
contracts_mean

[1] 3.458918

# Median
contracts_median <- median(contract_years)
contracts_median

[1] 3

# Find number of observations
contracts_n <- length(contract_years)
# Find standard deviation
contracts_sd <- sd(contract_years)

contracts_w1sd <- sum((contract_years - contracts_mean)/contracts_sd < 1)/ contracts_n
# Percentage of observation within one standard deviation of the mean
contracts_w1sd

[1] 0.8416834

## Difference from empirical 
contracts_w1sd - 0.68

[1] 0.1616834

contracts_w2sd <- sum((contract_years - contracts_mean)/ contracts_sd < 2)/contracts_n
contracts_w2sd

[1] 1

## Difference from empirical 
contracts_w2sd - 0.95

[1] 0.05

## Within 3 sd 
contracts_w3sd <- sum((contract_years - contracts_mean)/ contracts_sd < 3)/contracts_n
contracts_w3sd

[1] 1

## Difference from empirical 
contracts_w3sd - 0.9973

[1] 0.0027

# Create histogram
hist(contract_years,xlab = "Years Left in Contract",col = "green",border = "red", xlim = c(0,8), ylim = c(0,250),
   breaks = 3)

boxplot(contract_years,main= "Years Left in Contract" ,ylab="Years")

boxplot(contract_years,main="Years Left in Contract",ylab="years",col= "lightblue",
        border = "blue",horizontal = FALSE)

doubles<-read.table("doubles_hit.csv",header = TRUE,sep = ",")
doubles_hit<-doubles$doubles_hit

doubles_hit_mean<-mean(doubles_hit)
doubles_hit_mean

[1] 23.55

double_hit_median<-median(doubles_hit)
doubles_hit_mean

[1] 23.55

doubles_hit_n<-length(doubles_hit)
doubles_hit_sd<-sd(doubles_hit)

doubles_hit_w3sd<-sum((doubles_hit-doubles_hit_mean)/doubles_hit_sd<1)/doubles_hit_n
doubles_hit_w3sd

[1] 0.79

doubles_hit_w3sd-0.9973

[1] -0.2073

hist(doubles_hit,xlab = "Number of Doubles",col = "blue" , border = "lightblue", xlim = c (0,60),ylim = c (0,50),breaks=5)