Activity 4

Basic Calculations

# Addition
2+3

# Division
2/3

# Exponentiation
2^3 

# Square root
sqrt(2)

# Logarithms
log(2)

Question 1: Compute the log base 5 of 10 and the log of 10

log10(5)

log(10)

Computing some offensive metrics in Baseball

#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

Batting_Average=round(BA,digits = 3)
Batting_Average

Question 2: What is the batting average of a player that bats 42 hits in 212 at bats?

#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

On_Base_Percentage=round(OBP,digits = 3)
On_Base_Percentage

Often you will want to test whether something is less than, greater than or equal to something.

#Question_3:Compute the OBP for a player with the following general stats:
#AB=565,H=156,BB=65,HBP=3,SF=7
#OBP=(H+BB+HBP)/(AT Bats+BB=HBP+SF)
OBP = (156+65+3)/(565+65+3+7)
On_Base_Percentage=round(OBP,digits = 3)
On_Base_Percentage

3 == 8# Does 3 equals 8?
3 != 8# Is 3 different from 8?
3 <= 8# Is 3 less than or equal to 8?
3>4

# Logical Disjunction (or)
FALSE | FALSE # False OR False
# Logical Conjunction (and)
TRUE & FALSE #True AND False
# Negation
! FALSE # Not False

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

Assigning Values to Variables

Total_Bases <- 6 + 5
Total_Bases*3

ls()

rm(Total_Bases)

Vector

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

strikes_by_innings <- c(9, 12, 6, 14, 9)
strikes_by_innings

#Question_4: Define two vectors,runs_per_9innings and hits_per_9innings, each with five elements. 
runs_per_9inning<-c(2,5,7,11,13)
hits_per_9innings<-c(11,13,16,18,19)
runs_per_9inning
hits_per_9innings

# replicate function
rep(2, 5)

rep(1,4)

# consecutive numbers
1:5
2:10

# sequence from 1 to 20 with a step of 3
seq(1, 20, by=3)

# add vectors
pitches_by_innings+strikes_by_innings

# compare vectors
pitches_by_innings == strikes_by_innings

# find length of vector
length(pitches_by_innings)

# find average value in vector
mean(pitches_by_innings)

pitches_by_innings

# If you want to get the first element:
pitches_by_innings[1]

#Question_5: Get the first element of hits_per_9innings.
pitches_by_innings[length(pitches_by_innings)]

#Question_6: Get the last element of hits_per_9innings.
pitches_by_innings[c(2, 3, 4)]

player_positions <- c("catcher", "pitcher", "infielders", "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)

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

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

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

Using Tables

x <- c("Yes","No","No","Yes","Yes") 
table(x)

Numerical measures of center and spread

sals <- c(12, .4, 5, 2, 50, 8, 3, 1, 4, 0.25)
# the average
mean(sals) 

# the variance
var(sals)

# the standard deviation
sd(sals)

# the median
median(sals)

# Tukey's five number summary, usefull for boxplots
# five numbers: min, lower hinge, median, upper hinge, max
fivenum(sals)

# summary statistics
summary(sals)

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)))]
 }

# Most frequent value in pitches_by_innings
getMode(pitches_by_innings)

#Question_7: Find the most frequent value of hits_per_9innings.

getMode(hits_per_9innings)

#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")

#Question_9: What is the most frequent answer recorded in the survey? Use the getMode function to compute results. 
getMode(game_day)