Attach the ROC plot here. How are ROC plots interpreted in general and specifically for the diabetes case? Do we have a good/bad/ok model?

Load the Pima Diabetes dataset with these settings:

• seed=42
• standardize features
• 70% training split
• 15% validation/test split
• use all features in splits

Check out the PCA plot and attach the plot here. Take a look at the cumulative variance of the first two PCs. Is this value low/ok/high?

What is the recall with regard to the diabetes-positive (class 1) patients? 

Explain the recall vs. precision values of your model with respect to the diabetes positive patients .

Load the Spotify dataset. Select Hierarchical clustering with Ward linkage (leave seed at 10). On the cluster dendrogram, what would be your estimate for the number of groups in the data set? (Hint: it is not 2)

Create a hierarchical clustering model with the number of groups you detected in the dendrogram. Check out the 'Sample from Clusters' section - can you make out the musical genres that the clusters represent?

Attach the silhouette plot here. How do you interpret the plot - what do the positive/negative silhouette numbers mean? Also attach the plot here.

What is the silhouette score of that model? Enter the full number (i.e. with all three decimal digits).

Is the iris dataset balanced with regard to the three flower species?

Look at the percentage of the variance that is explained by the first two PCs. Is that a good/bad value? What in the dataset could explain this value?