Skip to content

Instantly share code, notes, and snippets.

@vwm
vwm / README.md
Last active October 2, 2019 18:54

This dataset originates from R for Data Science's Tidy Tuesday weekly event for June 18, 2019. It describes the count of birds heard or seen each year around Christmas in the Hamilton area of Ontario.

A grouped version of the data is included which summarizes counts by year.

@vwm
vwm / README.md
Last active September 17, 2019 23:32
Television Show Ratings

This dataset originates from R for Data Science's Tidy Tuesday weekly event for January 8, 2019. It describes television show ratings by season, genre, and release date.

Questions for consideration:

  • Do certain genres garner better ratings when combined with other genres? (Are there "good" or "bad" genre pairings that become evident?)
  • Is there a correlation between the release date and rating?
  • How do ratings tend to change across seasons? (Does this rating change differ across genres?)

Genre is categorical. Rating and share are quantitative.

@vwm
vwm / README.md
Last active September 18, 2019 19:54
Student to Teacher Ratios

This dataset originates from R for Data Science's Tidy Tuesday weekly event for May 7, 2019. It describes student to teacher ratios by country, year, and educational level.

A cleaned version of the dataset which replaces "NA" ratios with zeroes is included.

Questions for consideration:

  • How does educational level correlate to ratio?
  • Which countries have the largest disparity of ratios across different educational levels?
  • Which countries have improved their ratios the most over time?

Country and educational level are categorical. Ratio is quantitative.

@vwm
vwm / README.md
Last active October 24, 2019 01:40
Franchise Revenues

This dataset originates from R for Data Science's Tidy Tuesday weekly event for July 2, 2019. It describes franchise revenue by revenue category, the original media source, and the year the franchise was created.

Alternate versions of this dataset are included:

  • A grouped version of the dataset which summarizes total franchise revenue
  • A combined version of the dataset which features both the summarized total and the original category-specific revenue
  • A combined, top 20 version that adds different revenue scales and instances of zero revenue

Questions for consideration:

  • How does revenue by revenue category change over time?
  • How does the age of a franchise correlate with its total revenue?