# Vessel Count Category vs. Trade Share

Now, let’s investigate whether ports with higher vessel counts also tend to play a larger role in their country’s maritime imports and exports.

You computed the variable `VESSEL_COUNT_CATEGORY`, which classifies each port as "low", "medium", or "high" based on its total vessel count. Each port also has two columns: `SHARE_COUNTRY_MARITIME_IMPORT` and `SHARE_COUNTRY_MARITIME_EXPORT`, representing the share of that port in its country’s total maritime imports and exports, respectively.

***

### **🔧 Your tasks:**

Your task is to visualize and interpret the relationship between vessel count category and trade share:

* [ ] **Create boxplots** for both import and export shares, grouped by `VESSEL_COUNT_CATEGORY`. They should look something like this (here, outliers aren't show for the purpose of visualization:

<figure><img src="https://2669499530-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnYNN3nXNuXMJpHACcH73%2Fuploads%2FjO6trRQLSntAaf0mN8Y1%2Fimage.png?alt=media&#x26;token=1fa73c8e-d016-406d-98e6-f1d0d31e70c4" alt="" width="375"><figcaption></figcaption></figure>

***

**Interpretation Questions:**

* [ ] 🤔 What do the boxplots reveal about the relationship between vessel traffic and a port’s importance in national trade?
* [ ] &#x20;🤔 Are the distributions similar for imports and exports, or do you notice differences between them?
* [ ] &#x20;🤔 What is your takeway from the distribution of the "high" category?

> <img src="https://2669499530-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnYNN3nXNuXMJpHACcH73%2Fuploads%2Ft1yAGmUambZeYVQvPSeu%2Fp.png?alt=media&#x26;token=01872756-9ca8-44f9-9ec1-1ff5f70ce561" alt="" data-size="line">
>
> You really just need to use matplotlib's `boxplot()`. There is no need for actual grouping on the dataset, you simply need to set the `x` and `y` options of the boxplot. To remove the outliers from the boxplots, set `showfliers` option to false.
