EM.py

'''
https://towardsdatascience.com/gaussian-mixture-models-d13a5e915c8e
'''

import numpy as np
from sklearn.datasets.samples_generator import make_blobs
from sklearn.mixture import GaussianMixture
from matplotlib import pyplot as plt
import seaborn as sns
sns.set()

X, y = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)
plt.scatter(X[:,0], X[:,1])

n_components = np.arange(1, 21)
models = [GaussianMixture(n, covariance_type='full', random_state=0).fit(X) for n in n_components]
plt.plot(n_components, [m.bic(X) for m in models], label='BIC')
plt.plot(n_components, [m.aic(X) for m in models], label='AIC')
plt.legend(loc='best')
plt.xlabel('n_components');

gmm = GaussianMixture(n_components=4)
gmm.fit(X)

labels = gmm.predict(X)
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis');

gmm.predict_proba(X)