Occurrence and Co-occurrence of Pokemon Types with Chord Diagrams

Preamble¶

Introduction¶

In this section, we're going to use the Pokémon for Data Mining and Machine Learning dataset to visualise the occurrences and co-occurrence of Pokémon types.

The Dataset¶

The dataset documentation states that we can expect 23 variables per each of the 721 Pokémon of the first six generations.

Let's download the mirrored dataset and have a look for ourselves.

It looks good so far, but let's confirm the 23 variables against 721 samples from the documentation.

Perfect, that's exactly what we were expecting.

Data Wrangling¶

We need to do a bit of data wrangling before we can visualise our data. We can see from the columns names that the Pokémon types are split between the columns Type_1 and Type_2.

So let's select just these two columns and work with a list containing only them as we move forward.

Unlike the previous section, this visualisation will also include every occurrence of a type, not just the co-occurrences. Let's extract these single-typed instances before continuing.

Without further investigation, we can see that we have at least a few NaN values in the table above. We are only interested in co-occurrence of types, so we can remove all samples which contain a NaN value.

Our chord diagram will need two inputs: the co-occurrence matrix, and a list of names to label the segments.

We can build a co-occurrence matrix with the following approach. We'll start by creating a list with every type pairing in its original and reversed form.

Which we can now use to create the matrix.

We can list this using a DataFrame for better presentation.

We extracted our single-typed instances earlier. Here is the frequency of these occurrences.

Let's add these to our matrix along the diagonal. We are lucky that our matrix is of size $ 18 \times 18 $, and our single_typed list is of size $18$.

We can confirm they've been added by displaying the matrix through a DataFrame once again.

Now for the names of our types.

Chord Diagram¶

Time to visualise the occurrences and co-occurrence of types using a chord diagram. We are going to use a list of custom colours that represent the types.

Finally, we can put it all together.

Conclusion¶

In this section, we demonstrated how to conduct some data wrangling on a downloaded dataset to prepare it for a chord diagram. Our chord diagram is interactive, so you can use your mouse or touchscreen to investigate the occurrences and co-occurrences!