Most of the work associated with building a predictive model is associated with either performance tuning or data prepping.
I’m almost half way through prepping some data. It’s not necessary to script this but a script allows me to adjust the data preparation in the future and more importantly to document the sequence of steps that I have taken.
I was recently asked a question about updating display boxes. Display boxes are the building blocks of JMP output windows. Fundamentally there are two methods of updating these display boxes, which I will take a closer look at. (more…)
I’m sure there is a more technically correct term for this: I use the phrase segmented regression to describe the process whereby I select a segment of data within a curve and build a regression model for just that segment.
I have some code to aid the process. The code illustrates how to perform regression on-the-fly as well as how to utilise the MouseTrap function to handle mouse movement events.
An Easter egg is an intentional inside joke, a hidden message, or a secret feature of an interactive work (often, a computer program, video game or DVD menu screen). The name is used to evoke the idea of a traditional Easter egg hunt
The above visualisation is a 3D tree view of a decision tree generated with the Partition platform.
However, if you look under the red triangle hotspot for the platform you won’t find an option to create this output.
I have been investigating the use of logistic regression to model image pixel data. Now I want to take a look at the use of neural networks. In this post I am going to build the simplest possible neural network and compare it against a simple logistic regression.
The problem with the internet is that it gives you too much information, or rather, it takes too long to gather the information. I often cross reference hotel booking sites with TripAdvisor, and its a laborious process. So this evening I decided to streamline my process by writing a script to gather to user reviews into a JMP table and simple report.
In this post I will continue with my so-called hieroglyphics project. This project uses a set of image data that describes handwritten characters. The dataset is frequently used to evaluate machine-learning algorithms. I’m using the dataset to explore a variety of modelling techniques within JMP.
In my last post I used a script to incrementally add terms to my model so that I could explore the performance of the model with increasing complexity. But the order in which I added the terms was based on a heuristic and it wasn’t necessarily optimal. So in this post I want to explore using stepwise regression.
JMP is brilliant for real-time data capture. Add to that the ability to use JSL to construct “industrial” style user-interfaces and its easy to get JMP deployed in an environment that relies on simple to use robust data capture from online measurement systems.
In my last post I built a regression model with a single predictor variable. That variable represented the value of a single pixel from a 28×28 image of a hand written digit. In this post I will look at some model variations based on using a larger number of input variables.