Another algorithm that is an alternative to the generic k-means cluster model is the Hierarchical Cluster Model. This algorithm will group data based on hierarchy. In this article, we will learn how to build a Hierarchical Cluster Model in Sklearn.
To build a Hierarchical Cluster Model, we will use the
AgglomerativeClustering class from the
cluster. Then, as usual, we will create an instance of the
AgglomerativeClustering class and pass our features and target to the
fit method to train our model.
from sklearn import datasets from sklearn.preprocessing import StandardScaler from sklearn.cluster import AgglomerativeClustering iris = datasets.load_iris() features = iris.data scaler = StandardScaler() features_std = scaler.fit_transform(features) agglom = AgglomerativeClustering() model = agglom.fit(features_std)