We can now implement the Gaussian mixture algorithm using the Scikit-Learn implementation. The direct approach has already been shown in Chapter 2, Introduction to Semi-Supervised Learning. The dataset is generated to have three cluster centers and a moderate overlap due to a standard deviation equal to 1.5:
from sklearn.datasets import make_blobsnb_samples = 1000X, Y = make_blobs(n_samples=nb_samples, n_features=2, centers=3, cluster_std=1.5, random_state=1000)
The corresponding plot is shown in the following diagram:
The Scikit-Learn implementation is based on the GaussianMixture class