hierarchical_clustering_titanic.py

from scipy.cluster.hierarchy import linkage
from scipy.cluster.hierarchy import dendrogram
sample_train,sample_val, gt_train, gt_val = train_test_split(train_df,
                                                             train_df['Survived'],
                                                             test_size=0.05,
                                                             random_state=99)

sample_val_processed = simple_preprocessing(sample_val, train = False)
sample_val_processed = scaler.fit_transform(sample_val_processed)
mergings = linkage(sample_val_processed, method='complete')
fig = plt.figure(figsize = (16,10))

dendrogram(mergings,
           labels=np.array(sample_val['Name']),
           leaf_rotation=90,
           leaf_font_size=10)
plt.show()