Feature distributions

The features, except for the transactional amounts, we have in this data are anonymized due to confidentiality issues. Because we do not know what each feature represents and what each feature means, it will be difficult to deduce any intuitive insights from the feature analysis. However, it is still helpful to understand how each of the features is distributed, how the distribution of each feature differs from the others, and whether there is any noticeable pattern we can derive from the set of features.

Let's first take a look at the code. The following code shows how we can compute and visualize the distributions of the features:

// Feature distributionsforeach (string col in df.ColumnKeys){ if (col.Equals("Class") ...

Get C# Machine Learning Projects now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.