Add short part to challenge 1, episode 7 to answer objective

Objective: "Understand when to use hierarchical clustering on high-dimensional data"

_episodes_rmd/07-hierarchical.Rmd

@@ -264,14 +264,17 @@ dendrogram showing how the data is partitioned into clusters. But how do we inte
 > Use `hclust()` to implement hierarchical clustering using the
 > distance matrix `dist_m` and 
 > the `complete` linkage method and plot the results as a dendrogram using
-> `plot()`.
+> `plot()`. Why is hierarchical clustering and the resulting dendrogram useful for performing clustering this case?
 >
 > > ## Solution:
 > >
 > > ```{r plotclustex, fig.cap=" "}
 > > clust <- hclust(dist_m, method = "complete")
 > > plot(clust)
 > > ```
+> > Hierarchical clustering is particularly useful (compared to K-means) when we do not know the number of clusters 
+> > before we perform clustering. It is useful in this case since we have assumed we do not already know what a suitable 
+> > number of clusters may be.
 > {: .solution}
 {: .challenge}