Campaign Bumper Sticker Analysis

This analysis compares Presidential bumper sticker font sizes by candidates since 1996. What do bumper stickers say about a candidate, their party or their chance of success? Enjoy?

Naive Bayes Classifier in Tableau (no R/Py)

Building machine learning algorithms or predictive models in Tableau requires R or Python integration or to push the model into your ETL process. This can be difficult for some organizations who don't have this capability or want to avoid stale models. This post details how to build a Naive Bayes classification model entirely in Tableau that can scale as you feed it new data. 

Naive Bayes is a probabilistic classification model based on Bayes theorem. It can be used to predict the probability of an outcome based on multiple independent conditions. It is incredibly flexible, extensible, and simple. Naive Bayes classification models can be used to detect fraud, predict attrition, or diagnose medical conditions. Really it can potentially be used to determine the probability of any event occurring


The example detailed below is a proof of concept using Titanic passenger training data from a Kaggle challenge. Below is a detailed tutorial on how to build a model in Tableau and how to apply to new data.



To build a Naive Bayes classification model in Tableau you need to create A LOT of calculated fields (nearly 30 for this example), train your model, and then blend it with a new data set in order to predict outcomes. But once this is initially setup you can implement the model in your Tableau Server environment, feed the model new data, and produce new predictions automatically. You can produce a probability for every new data point fed into your database; assuming the input variables don't change significantly. 

How To Create a Gauge Chart in Tableau (UPDATED)

A while back I wrote a post on how to create a gauge chart in Tableau. At the time I felt bad about writing it because I thought it was a bad chart. I have since come around on the gauge. See my previous post on bullets vs gauges for mobile dashboards. And this created some convo on the Twitters about the merits of the gauge. But I think it's an unfairly maligned chart type.
So I think this should be an available chart type to create simply in Tableau. But the old approach I outlined required too much data re-shaping. So at last year's Tableau Conference I presented a new way of creating a gauge that required no data re-shaping. Just a bit of math. Outlined below are updated steps for creating a gauge in Tableau.


Most Popular Beatles Songs

This data visualization shows the popularity of Beatles songs using the Spotify API. I then assigned each song to a songwriter using Wikipedia data from an old Beatles project.


This is a new type of visualization I am calling a Marimekko Slope Plot. It combines several chart types and communicates a lot of information. The bar width shows the sample size (number of songs) by a discrete category (songwriter). The dots show a distribution of points (songs) with ability to compare across discrete categories (songwriter). Finally it show trends over time through the area chart slope (song popularity trend). I will post later about other applications of this chart and how it was created in Tableau.

Triangle Maps in Tableau

This triangle map was inspired by a UK election map in the Financial Times created by Billy Ehrenberg. This map below shows voting results in Wisconsin by county comparing 2012 to 2016 and where Clinton lost compared to Obama. If you are interested in a how-to post let me know in the comments below. Data source: Wikipedia.


div#ContactForm1 { display: none !important; }