Networkx is a python package for working with graphs and networks. Networkx is capable of creating a graph from within a python script, but you may also want to load a graphs from file. This post looks at some of the ways networkx allows you to load graphs from file, and gives some simple examples… Read More »
Networkx is a python package for creating, visualising and analysing graph networks. This post gives a simple networkx example to show how it works. A simple Networkx Example A graph network is built from nodes – the entities of interest, and edges – the relationships between those nodes. To create a graph we need to… Read More »
Making predictions is easy, but getting them right is difficult. An essential part of predictive analytics is model validation – checking the quality of predictions. Those post looks at a simple model validation technique you can use with your machine learning models. Once you have trained your predictive model it needs to make good predictions… Read More »
The ROC Curve is a commonly used method for and evaluating the performance of classification models. ROC curves use a combination the false positive rate (i.e. occurrences that were predicted positive, but actually negative) and true positive rate (i.e. occurrences that were correctly predicted) to build up a summary picture of the classification performance. ROC… Read More »
This post looks at how to build a simple classification model with the python machine learning library scikit-learn. Building a simple classification model is fairly easy with sci-kit learn, and this post explores some of the default behaviour and sign-posts some extra work that we would want to to ensure robust predictions. I’ve tried to… Read More »