A basic example to pull in data from a tidytuesday repo, demonstrate DataFramesMeta syntax, and make a plot

julia_tidytuesday.jl

using CSV, HTTP, DataFramesMeta, Plots, Dates
theme(:ggplot2)
plotlyjs()

file1 = "https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-10/nyt_titles.tsv"

df = CSV.read(HTTP.get(file1).body, DataFrame)

# who is the author with the most weeks on the best seller list?
top_authors = @chain df begin
    groupby([:author])
    @combine(:total_weeks=sum(:total_weeks))
    sort(:total_weeks, rev=true)
    first(5)
end

bar(top_authors.author, top_authors.total_weeks, 
    title="Top 5 Authors by # Weeks on Bestseller List")

top_authors_list = top_authors.author

# How did this change over time?

top_authors_over_time = @chain df begin
                            groupby([:year, :author])
                            @combine(:total_weeks = sum(:total_weeks))
                            @rsubset(:author ∈ top_authors_list)
                            @transform(:year = Date.(:year))
                            @orderby(:year)
                        end

auth = top_authors_list[1]
tempdf = top_authors_over_time[top_authors_over_time.author.==auth, :]
a = plot(tempdf.year, tempdf.total_weeks, label=auth)
for author in top_authors_list[2:5]
    tempdf = top_authors_over_time[top_authors_over_time.author.==author, :]
    a = plot!(tempdf.year, tempdf.total_weeks, label=author)
end
display(a)