Lab 5

library(ggplot2)

data <- read.csv("DodgersData.csv",
                 stringsAsFactors = FALSE)

head(data)

##   month day attend day_of_week opponent temp  skies day_night cap shirt
## 1   APR  10  56000     Tuesday  Pirates   67 Clear        Day  NO    NO
## 2   APR  11  29729   Wednesday  Pirates   58 Cloudy     Night  NO    NO
## 3   APR  12  28328    Thursday  Pirates   57 Cloudy     Night  NO    NO
## 4   APR  13  31601      Friday   Padres   54 Cloudy     Night  NO    NO
## 5   APR  14  46549    Saturday   Padres   57 Cloudy     Night  NO    NO
## 6   APR  15  38359      Sunday   Padres   65 Clear        Day  NO    NO
##   fireworks bobblehead
## 1        NO         NO
## 2        NO         NO
## 3        NO         NO
## 4       YES         NO
## 5        NO         NO
## 6        NO         NO

names(data)

##  [1] "month"       "day"         "attend"      "day_of_week" "opponent"   
##  [6] "temp"        "skies"       "day_night"   "cap"         "shirt"      
## [11] "fireworks"   "bobblehead"

Question 1: Attendance

median_attendance <- median(data$attend, na.rm = TRUE)
mean_attendance <- mean(data$attend, na.rm = TRUE)

median_attendance

## [1] 40284

mean_attendance

## [1] 41040.07

Question 2: Histogram

ggplot(data, aes(x = attend)) +
  geom_histogram(
    binwidth = 5000,
    fill = "blue",
    color = "white"
  ) +
  labs(
    title = "Distribution of Dodgers Game Attendance",
    x = "Attendance",
    y = "Number of Games"
  ) +
  theme_minimal()