@@ -365,7 +365,7 @@ You will notice that the largest variation is now aligned with the `X axis`, the
# Example 7: Retrieval and analysis of obesity data
In this example, we will show an analysis similar to the one conducted in Example 5. The only difference here is that we will model all of the data present in the journal. This includes the simultaneous analysis of categorical and number range descriptors present in the journal. We use an [impetuous shell](https://github.com/richardtjornhammar/rixcfgs/blob/master/code/environments/impetuous-shell.nix) and download the required [python file](https://gist.github.com/richardtjornhammar/1b9f5742391b1bcf30f4821a00f30b6a) and execute it in the shell. Now you are done! Was that too fast? ok, so what is this about?
In this example, we will show an analysis similar to the one conducted in Example 4. The only difference here is that we will model all of the data present in the journal. This includes the simultaneous analysis of categorical and number range descriptors present in the journal. We use an [impetuous shell](https://github.com/richardtjornhammar/rixcfgs/blob/master/code/environments/impetuous-shell.nix) and download the required [python file](https://gist.github.com/richardtjornhammar/1b9f5742391b1bcf30f4821a00f30b6a) and execute it in the shell. Now you are done! Was that too fast? ok, so what is this about?
You will see that the python code downloads a data directory (if you're using GNU/Linux), extracts it, curates it and performs the analysis. The directory contains sample data with information about both the platform and the sample properties. In our case a sample can come from any of `6` different platforms and belong to either `lean` or `obese``females` or `males`. We collect the information and skip all but the `GPL8300` platform data. Now we have a journal that describes how well the sample was collected (with integer value ranges) and the sample categories as well as gene transcripts belonging to the samples. We can see that the common property for all samples are that they all are dealing with `obesity`, `adipocyte`, `inflammation` and `gene expression`. The journal now has the form
