Q1
# Average player count by season
seasonal_trends <- cleaned_data %>%
group_by(season) %>%
summarise(avg_players = mean(avg, na.rm = TRUE))
# Plot the results
library(ggplot2)
ggplot(seasonal_trends, aes(x = season, y = avg_players, fill = season)) +
geom_bar(stat = "identity") +
labs(title = "Average Player Count by Season", x = "Season", y = "Average Player Count")
## Q2 Setup 1
# Load necessary libraries
library(tidyverse)
# Load the dataset
player_data <- read_csv("C:/Users/kyalg/Downloads/games.csv")## Rows: 83631 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): gamename, month, avg_peak_perc
## dbl (4): year, avg, gain, peak
##
## 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.# Step 1: Filter out rows with missing or zero avg values
player_data_filtered <- player_data %>%
filter(!is.na(avg) & avg > 0)
# Step 2: Group by game name and calculate the average avg per game
avg_per_game <- player_data_filtered %>%
group_by(gamename) %>%
summarise(avg_player_count = mean(avg, na.rm = TRUE)) %>% # Calculate mean avg per game
arrange(desc(avg_player_count)) # Sort in descending order
# Step 3: Get the top 100 games
top_100_games <- avg_per_game %>%
slice_head(n = 100) # Select the top 100 rows
# Display the top 100 games
print(top_100_games)## # A tibble: 100 × 2
## gamename avg_player_count
## <chr> <dbl>
## 1 PLAYERUNKNOWN'S BATTLEGROUNDS 482025.
## 2 Dota 2 453732.
## 3 Counter-Strike: Global Offensive 308645.
## 4 Cyberpunk 2077 146416.
## 5 Apex Legends 83044.
## 6 Destiny 2 75035.
## 7 Grand Theft Auto V 64019.
## 8 Team Fortress 2 52885.
## 9 Tom Clancy's Rainbow Six Siege 52743.
## 10 Football Manager 2021 49945.
## # ℹ 90 more rows
