Wandering and meeting Sarah, Edouard and Ludovico

This week, I found a link to David Ranzolin’s The Data Analyst as Wanderer: Pre-Exploratory Data Analysis with R. In it David considers “answering questions about the data at two junctures: before you know anything about the data and when you know only very little about the data”.

He used metaphor of wandering to discuss data analysis. He observed “data analysts may wander but are not lost. This post is for data analysts ready to wander over their data (with R)”.

David’s questions are:

  1. What is this?
  2. What’s in this?
  3. What can I do with this?

These sprang to mind when I found Sarah Milstein’s How to Fail When You’re Used to Winning (A guide for managing morale while pushing for innovation). In her post, Sarah observed:

Innovation is a buzzword for our era. It evokes the promise of profiting tomorrow from today’s changes in technology. The word innovation implies a clean, crisp path. That’s a lie. In fact, innovation requires enormous amounts of failure — which then presents leadership challenges.

She adds:

But any team that must experiment constantly will fail a lot, and repeated failure almost always depresses people. (Original emphasis)

This part of her post struck me forcefully:

a certain amount of failure is inevitable. Accountability lies not just in individuals taking responsibility, but in teams having a consistent way to learn from those episodes. (Original emphasis)

Sarah concludes her post with this exhortation:

Your path to succeeding at failure and maintaining morale will not be linear. You’ll stumble along the way and find yourself wanting to pretend you didn’t just trip. But stick with it. Teams that can maintain good spirits during hard times tend to win, and nothing feeds morale like success.

Waldemar Januzczak was the guide in my next phase of wandering. Here in Australia they re-showed his 2009 documentary on Edouard Manet. In part of the documentary he discusses Manet’s Old Musician painting with Juliet Wilson-Bareau. Juliet pointed out Manet’s techniques in the picture and his ability to create texture in his composition.

One example was the shoes of the two young boys:

Juliet’s observation was that by rubbing the existing paint of the shoes rather than adding white, the picture takes on a different perspective.

Juliet’s knowledge of Manet made this granular insight particularly powerful and sent me off thinking about how each of use sees nuances in performance and the data of those performances. She returned me to David’s three questions for wanderers: What is this?; What’s in this?; What can I do with this?.

Fortunately, Ludovico Einaudi was there to help me with these contemplations. One commentator noted of him “For Einaudi, composition can happen in different ways. He improvises at the piano, invents melodies in his mind, but also hears them during his sleep”.

Daniel Keane (2017) said of Ludovico’s music “Throughout its course, one is never sure whether one is listening to something very old or very new.”

I think this sentiment resonates with our experiences of data wandering and why David Ranzolin’s prompts are so helpful.

Photo Credit

Le Vieux Musicien (The Yorck Project, public domain)

What kind of #AFLW Grand Final in 2018?

The 2018 AFLW season concludes this weekend with the Grand Final between the Western Bulldogs and the Brisbane Lions.

I have used both teams’ seven games to identify a median profile of their performances and their opponents in the regular season.

Western Bulldogs


Western Bulldogs and Brisbane

Scoring Scenarios

Western Bulldogs win, game score approximates to 41 v 37 median profile (Western Bulldogs dominate first half, Brisbane lift second half).

Brisbane win, game score approximates to 30 v 16 median profile (strong second quarter defence sets up second half game control for Brisbane).

The score in round 2 when the teams met was 33 v 24 to the Western Bulldogs. (Half time score was 26 v 3.)

Photo Credit

Frame grab (AFL website)

#AFLW 2018: End of Regular Season

My record of the 2018 AFLW season point scoring after the conclusion of the regular season is:

I have excluded the drawn game between GWS and Adelaide. The winning teams are in light blue and the losing teams are in light green.

The visualisation and data matrix for this box plot is provided by BoxPlotR:

The box plot description for figure legend:

Center lines show the medians; box limits indicate the 25th and 75th percentiles as determined by R software; whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles, outliers are represented by dots; data points are plotted as open circles. n = 27 sample points.

Photo Credit

Brisbane Lions (Courier Mail, Twitter)