News

This article is by Susan CS and originally appeared on the Alteryx Data Science Blog here: https://community.alteryx.com/t5/Data-Science-Blog/Repairing-Broken-Models-or-Not-During-a-Pandemic/ba-p/558570

What do you do when you have an amazing, even award-winning, model based on years of work that is suddenly wrecked by a global pandemic?

Sound familiar?

Well, if you’re with the Delphi research group at Carnegie Mellon University, you pick yourself up and move on to think creatively about the next big problem.

This article is by Ben Moss and originally appeared on the Alteryx Data Science Blog here: https://community.alteryx.com/t5/Data-Science-Blog/Alteryx-Your-Discover-Weekly-A-Practical-Application-of-K/ba-p/564059

 
Carly Rae Jepsen or Napalm Death
So, let’s review how we can apply KNN in Alteryx in order to allow us to determine whether a track is by either pop artist Carly Rae Jepsen or grindcore band Napalm Death.

This article is by Ben Moss and originally appeared on the Alteryx Data Science Blog here: https://community.alteryx.com/t5/Data-Science-Blog/Alteryx-Your-Discover-Weekly-A-Practical-Application-of-K/ba-p/563359

What Is K-Nearest Neighbours (KNN)? 
The Wikipedia definition is:
In pattern recognition, the k-nearest neighbors algorithm (k-NN) is a non-parametric method used for classification and regression.

This article is by Robert Lenius and originally appeared on the Alteryx Engine Works Blog here: https://community.alteryx.com/t5/Engine-Works-Blog/Verifying-Tax-IDs-With-REGEX/ba-p/529729

Have you ever found yourself putting data into some online application only to have it fire back that the format is incorrect? This could be things like a phone number, address, or in the bad example on the right, a name .

Typically, this is done through regular expressions, also known as REGEX functions.

This article is by CP Lewis and originally appeared on the Alteryx Engine Works Blog here: https://community.alteryx.com/t5/Engine-Works-Blog/Automate-the-Repetitive-Stuff-to-Free-Yourself-Up-to-Focus-on/ba-p/526300

You know how amazing it would be to free up some of your time and look into more advanced topics in Alteryx or look into crazy, off the wall problems? You are not alone! I have wanted to continue looking into this and that in my spare time but for the longest time, I couldn’t. Why you might ask? I didn’t know how to automate my work from end to end and had to continue to manually do things.

This article is by Joshua Burkhow and originally appeared on the Alteryx Engine Works Blog here: https://community.alteryx.com/t5/Engine-Works-Blog/5-MORE-Useful-Design-Patterns-in-Alteryx-You-Need-to-Master/ba-p/520943

 
Solution #6: Keeping Sort Order After a Summarize, Unique or Other Tools

Use Case:

You have data that you want to summarize or get rid of duplicates and in developing a workflow realize that the data gets automatically sorted on the output, but you would like to keep the order that the data is in or some order other than what is given, even with aggregation!

You can simply do this by adding a Record ID tool, and in the case of a Summarize tool, just use the Sort Order column as a ‘First’ or in the case of using the Unique tool just sort on that column after the Unique tool.

This article is by Dan Putler and originally appeared on the Alteryx Data Science Blog here: https://community.alteryx.com/t5/Data-Science-Blog/Blending-Fine-Wine-with-Alteryx-An-Optimization-Tutorial/ba-p/517428

The Optimization Tool has been a part of the Alteryx predictive tool suite for a few years now, but there has been a fairly limited discussion of how it works under the hood, the types of problems it can address, and the different ways the tool can be configured and used (exceptions to this are excellent articles by Philip Mannering, SydneyF, and JoeM).

There are actually numerous types of optimization methods.

2020.1 WHAT'S NEW?

Take your thrill of solving to a whole new level and make a resolution to turn more actionable insights into business outcomes with the 2020.1 Re.Solve release. Start your decade off on the right foot by experiencing new updates that will change the way you solve, interpret your data, and break down barriers within your organization.

This article is by Dan Putler and originally appeared on the Alteryx Data Science Blog here: https://community.alteryx.com/t5/Data-Science-Blog/Getting-to-Know-Optimization-Linear-Programming/ba-p/513793

Linear programming is the oldest of the mathematical programming algorithms, dating to the late 1930s. The method can either minimize or maximize a linear function of one or more variables subject to a set of inequality constraints.

This article is by Sean Adams and originally appeared on the Alteryx Engine Works Blog here: https://community.alteryx.com/t5/Engine-Works-Blog/Beyond-Single-Pass-Analytics-What-Changes-With-Scale/ba-p/513519

When we begin with analytics, either as a new practice within your firm, or starting a team in a new area–much of your work may initially be what I call "single-pass analytics," where the data goes from source, to prep, straight to the end-point.