Weekly Viz 2020-12-14

A Statistical Analysis of the Work of Bob Ross

About Makeover Monday

MakeoverMonday is a social data project: “Each week we post a link to a chart, and its data, and then you rework the chart. Maybe you retell the story more effectively, or find a new story in the data. We’re curious to see the different approaches you all take. Whether it’s a simple bar chart or an elaborate infographic, we encourage everyone of all skills to partake. Together we can have broader conversations about and with data.”

Starting from Jan 08, 2018, I decided to put aside one hour on Monday weekly to create some visualization and find some insights from the data.

The datasets are published each week at: MakeoverMonday Datasets.

Makeover Monday 20201214

The original article this week is very interesting – it looks at all the elements Bob Ross (wiki) used in his 381 paintings in his 11-year tv show ‘The Joy of Painting’, and use this dataset to explain statistics concepts like joint probability vs. conditional probability, clustering, etc. I really like the idea of explaining seemly abstract concepts with concrete examples.

My Visualization

In my viz this week, I am also following the same path of explaining conditional probability with heatmap. On the upper right you can switch between frequency and conditional probability – you will find the color pattern different, as two things occur together more does not gurantee that when A exists, B also show up with a high probability (conditional probability).
Besides, a high conditonal probability of item A given item B also does not mean that this pair are more ‘unique’ or ‘valuable’ than the others, especially in the business context. For example, we see the conditional probability of seeing ‘A Tree’ given ‘Barn’ exists is 94%, but this number is high because ‘Barn’ only have 17 occurences in total (on the other hand, 361 for ‘A tree’), while 14 of them have ‘A tree’ in the same painting – this actually leads to a very interesting topic of Market Basket Analysis. In business, we often want to know which two or more items, say, are purchased together more often than the others, thus a grocery store can put them together to boost sales (the famous ‘bear and diaper’ example). You can read more about a market basket analysis implementation in Python here.

–
Please notice that all the visualizations are designed for desktop view, so it is recommended to view them on a desktop device.

–

Insights

• Most elements Ross use frequently in paintings are the natural elements;
• A tree, trees, deciduous trees, etc. are actually the most common elements in Ross’s paintings.

Follow this link to find more weekly vizzes :)