Initialize GMM with sklearn python
I want to create a GMM sklearn object with a predefined set of means, weights and covariances (on a grid).
I managed it:
from sklearn.mixture import GaussianMixture
import numpy as np
def get_grid_gmm(subdivisions=[10,10,10], variance=0.05 ):
n_gaussians = reduce(lambda x, y: x*y,subdivisions)
step = [ 1.0/(2*subdivisions[0]), 1.0/(2*subdivisions[1]), 1.0/(2*subdivisions[2])]
means = np.mgrid[ step[0] : 1.0-step[0]: complex(0,subdivisions[0]),
step[1] : 1.0-step[1]: complex(0,subdivisions[1]),
step[2] : 1.0-step[2]: complex(0,subdivisions[2])]
means = np.reshape(means,[-1,3])
covariances = variance*np.ones_like(means)
weights = (1.0/n_gaussians)*np.ones(n_gaussians)
gmm = GaussianMixture(n_components=n_gaussians, covariance_type='spherical' )
gmm.weights_ = weights
gmm.covariances_ = covariances
gmm.means_ = means
return gmm
def main():
xx = np.random.rand(100,3)
gmm = get_grid_gmm()
y= gmm.predict_proba(xx)
if __name__ == "__main__":
main()
The problem is that there is no method gmm.predict_proba()
that I need to use later. How can I overcome this?
UPDATE : I updated the code to be a complete example that shows the error
UPDATE2
I have updated the code as per the comments and answers
from sklearn.mixture import GaussianMixture
import numpy as np
def get_grid_gmm(subdivisions=[10,10,10], variance=0.05 ):
n_gaussians = reduce(lambda x, y: x*y,subdivisions)
step = [ 1.0/(2*subdivisions[0]), 1.0/(2*subdivisions[1]), 1.0/(2*subdivisions[2])]
means = np.mgrid[ step[0] : 1.0-step[0]: complex(0,subdivisions[0]),
step[1] : 1.0-step[1]: complex(0,subdivisions[1]),
step[2] : 1.0-step[2]: complex(0,subdivisions[2])]
means = np.reshape(means,[3,-1])
covariances = variance*np.ones(n_gaussians)
cov_type = 'spherical'
weights = (1.0/n_gaussians)*np.ones(n_gaussians)
gmm = GaussianMixture(n_components=n_gaussians, covariance_type=cov_type )
gmm.weights_ = weights
gmm.covariances_ = covariances
gmm.means_ = means
from sklearn.mixture.gaussian_mixture import _compute_precision_cholesky
gmm.precisions_cholesky_ = _compute_precision_cholesky(covariances, cov_type)
gmm.precisions_ = gmm.precisions_cholesky_ ** 2
return gmm
def main():
xx = np.random.rand(100,3)
gmm = get_grid_gmm()
_, y = gmm._estimate_log_prob(xx)
y = np.exp(y)
if __name__ == "__main__":
main()
There are no more errors, but _estimate_log_prob and predict_proba do not give the same result for the set GMM. Why might this be?
source to share
Since you are not training the model, but simply using a function to evaluate, you do not need to use an object, but you can use the same function they use under the hood. You can try _estimate_log_gaussian_prob
. This is what they do internally, I think.
Look at the source:
specifically in the base class https://github.com/scikit-learn/scikit-learn/blob/ab93d657eb4268ac20c4db01c48065b5a1bfe80d/sklearn/mixture/base.py#L342
which calls a specific method which in turn calls the function https://github.com/scikit-learn/scikit-learn/blob/ab93d657eb4268ac20c4db01c48065b5a1bfe80d/sklearn/mixture/gaussian_mixture.py#L671
source to share