Researchers studying chemical properties of wines collected data on a sample of white wines in Northern Portugal. A research goal was to cluster wines based on similar chemical properties.

Using pdist$(),$ calculate a distance matrix for wines. The matrix of input features, X$,$ has already been created.

Use the distance matrix to cluster the wines with centroid linkage.

The code provided creates a dataframe with two features $($free$\_$sulfur$\_$dioxide and sulphates$),$ normalizes the dataframe, and displays the cluster membership of each data point.

import pandas as pd

from scipy.cluster.hierarchy import linkage

from scipy.spatial.distance import pdist

from sklearn.preprocessing import StandardScaler

wine $=$ pd$.$read$\_$csv$(\text{'}$wine$1.$csv$\text{'})$

# Calculate a distance matrix with selected variables

X $=$ wine$[[\text{'}$free$\_$sulfur$\_$dioxide', 'sulphates'$]]$

scaler $=$ StandardScaler$()$

X $=$ pd$.$DataFrame$($scaler$.$fit$\_$transform$($X$))$

# Your code goes here

print$($clusterModel$)$