Calculate metrics to evaluate how well these rules performed using the
evaluate() and classification_stats() functions from this chapter.
Build a clustering model to distinguish between red and white wine by their
chemical properties:
a) Combine the red and white wine datasets (data/winequality-red.csv
and data/winequality-white.csv, respectively) and add a column for the
kind of wine (red or white).
b) Perform some initial EDA.
c) Build and fit a pipeline that scales the data and then uses k-means clustering to
make two clusters. Be sure not to use the quality column.
d) Use the Fowlkes-Mallows Index (the fowlkes_mallows_score() function
is in sklearn.metrics) to evaluate how well k-means is able to make the
distinction between red and white wine.
e) Find the center of each cluster.