Module 6: Apply 5

Import data

# csv file
data <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2023/2023-02-21/bob_ross.csv')

Apply the following dplyr verbs to your data

Filter rows

filter(data, season == 1)
filter(data, season == 1 & episode == 1)
filter(data, season == 1 | episode == 1)
filter(data, season %in% c(11, 12))

Arrange rows

arrange(data, desc(season), desc(episode))

Select columns

select(data, season:painting_title)
select(data, season, episode, painting_title, colors)
select(data, season, episode, painting_title, colors, color_hex)
select(data, season, episode, painting_title, starts_with("color"))
select(data, season, episode, contains("painting"))
select(data, season, episode, ends_with("src"))
select(data, season, episode, ends_with("src"), everything())

Add columns

# Create a new column: ratio of colors used vs episodes 
mutate(data,
       index_per_episode = painting_index / episode) %>%
# Select season, episode, painting_title, and new column
    select(season:painting_title, index_per_episode)

mutate(data,
       index_per_episode = painting_index / episode) %>%
    select(season:painting_title, index_per_episode)

transmute(data,
          index_per_episode = painting_index / episode)

select(data, painting_index) %>%
    mutate(painting_index_lag1 = lag(painting_index))

select(data, painting_index) %>%
    mutate(painting_index_cumsum = cumsum(painting_index))

Summarize by groups

data

# average painting index
summarize(data, avg_painting_index = mean(painting_index, na.rm = TRUE))

data %>%
    
    # Group by season
    group_by(season) %>%
    
    # Calculate average painting index
    summarize(avg_painting_index = mean(painting_index, na.rm = TRUE)) %>%
    
    # Sort it
    arrange(avg_painting_index)