Getting Started With R Part 2

#Case-scenario 1
#This is the fourth season of outfielder Luis Robert with the Chicago White Socks. If during the first three seasons he hit 11, 13, and 12 home runs, how many does he need on this season for his overall average to be at least 20?

#Solution
# 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

# Find standard deviation
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 

#Question 1
#Now, I must complete the problem below which represents a similar case scenario. 

#This is the sixth season of outfielder Juan Soto in the majors. If during the first five seasons he received 79, 108,41,145, and 135 walks, how many does he need on this season for his overall number of walks per season to be at least 100?

# Walks for Juan Soto
Soto_walks <- c(79, 108, 41, 145, 135)
n_seasons  <- 6
desired_walks <- 100

# Sum of the first five seasons
sum_first5 <- sum(Soto_walks)

# Solve for x6
x_6 <- n_seasons * desired_walks - sum_first5
x_6

[1] 92

#Case-scenario 2
The average salary of 10 baseball players is 72,000 dollars a week and the average salary of 4 soccer players is 84,000. Find the mean salary of all 14 professional players.

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

#The average salary of 7 basketball players is 102,000 dollars a week and the average salary of 9 NFL players is 91,000. Find the mean salary of all 16 professional players.

n_bb  <- 7     # number of basketball players
y_bb  <- 102000 # average basketball salary
n_nfl <- 9     # number of NFL players
y_nfl <- 91000  # average NFL salary

# Combine
combined_mean <- (n_bb*y_bb + n_nfl*y_nfl)/(n_bb + n_nfl)
combined_mean

[1] 95812.5

#Case-scenario 3
#The frequency distribution below lists the number of active players in the Barclays Premier League and the time left in their contract.

Years   Number of players
6   28
5   72
4   201
3   109
2   56
1   34

Q1.Find the mean,the median and the standard deviation.

Q2. What percentage of the data lies within one standard deviation of the mean?

Q3. What percentage of the data lies within two standard deviations of the mean?

Q4. What percent of the data lies within three standard deviations of the mean?

Q5. Draw a histogram to illustrate the data.

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

## Within 2 sd
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(0,225),
   breaks = 5)

# 1) Read the CSV file

doubles_data <- read.csv("doubles_hit.csv", header = TRUE)

# 2) Extract the relevant column

my_doubles <- doubles_data$doubles  

# 3) Calculate basic statistics

doubles_mean   <- mean(my_doubles)    # Mean
doubles_median <- median(my_doubles)  # Median
doubles_sd     <- sd(my_doubles)      # Standard Deviation
doubles_n      <- length(my_doubles)  # Number of observations

# Print out results
doubles_mean

[1] 23.55

doubles_median

[1] 23.5

doubles_sd

[1] 13.37371

doubles_n

[1] 100

# 4) Calculate % of data within 1, 2, and 3 SDs of the mean using absolute value ensures we look at both sides of the mean.
doubles_w1sd <- sum(abs(my_doubles - doubles_mean) / doubles_sd < 1) / doubles_n
doubles_w2sd <- sum(abs(my_doubles - doubles_mean) / doubles_sd < 2) / doubles_n
doubles_w3sd <- sum(abs(my_doubles - doubles_mean) / doubles_sd < 3) / doubles_n

doubles_w1sd

[1] 0.58

doubles_w2sd

[1] 1

doubles_w3sd

[1] 1

# Optionally compare to Empirical Rule (68%, 95%, 99.7%)
doubles_w1sd - 0.68

[1] -0.1

doubles_w2sd - 0.95

[1] 0.05

doubles_w3sd - 0.9973

[1] 0.0027

# 5) Draw a histogram of the doubles hit

hist(my_doubles,
     main  = "Histogram of Doubles Hit",
     xlab  = "Number of Doubles",
     breaks = 10   
     )