I am following this sample to do density estimation for the Bayesian Gaussian mixture model below:
bgmm = BayesianGaussianMixture(n_components=10, random_state=7, max_iter=5000).fit(data)
in which data
(as a dataframe) includes 20 columns of numeric data.
I can simply plot the model for two features of bgmm
by
x = np.linspace(-20.0, 30.0) y = np.linspace(-20.0, 40.0) X, Y = np.meshgrid(x, y) XX = np.array([X.ravel(), Y.ravel()]).T Z = -bgmm.score_samples(XX) Z = Z.reshape(X.shape) CS = plt.contour( X, Y, Z, norm=LogNorm(vmin=1.0, vmax=1000.0), levels=np.logspace(0, 3, 10) ) CB = plt.colorbar(CS, shrink=0.8, extend="both") plt.scatter(data[:, 0], data[:, 1], 0.8) plt.show()
But, how can I plot all the clusters in the form of density contours?
Advertisement
Answer
I believe you need to get your data into one big two-column array before fitting, so define a new X_train
that combines all ten pairs of columns into one big pair of columns.
First, convert data
into an array:
data_array = data.to_numpy()
And then reshape into two columns:
X_train = np.reshape(data_array, (10*data_array.shape[0], 2))
and then call the mixture.fit
method with that instead of data
. Then just continue following the sample, using X_train
as they do (and of course use bgmm
instead of clf
).