Lab 5

Dodger Attendance Analysis

# Load the dataset
DodgersData <- read_csv("DodgersData.csv")

## Rows: 81 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): month, day_of_week, opponent, skies, day_night, cap, shirt, firewor...
## dbl (3): day, attend, temp
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

# Summary Statistics for Attendance
mean_attend <- mean(DodgersData$attend)
median_attend <- median(DodgersData$attend)

# Display calculated values
mean_attend

## [1] 41040.07

median_attend

## [1] 40284

Attendance Distribution Plot

# Boxplot comparing attendance by day vs night games
ggplot(DodgersData, aes(x = day_night, y = attend, fill = day_night)) +
  geom_boxplot() +
  labs(
    title = "Dodgers Attendance: Day vs. Night Games",
    x = "Game Time",
    y = "Attendance"
  ) +
  theme_minimal()