dpgmm.py 文件源码

def _update_precisions(self, X, z):
        """Update the variational distributions for the precisions"""
        n_features = X.shape[1]
        if self.covariance_type == 'spherical':
            self.dof_ = 0.5 * n_features * np.sum(z, axis=0)
            for k in range(self.n_components):
                # could be more memory efficient ?
                sq_diff = np.sum((X - self.means_[k]) ** 2, axis=1)
                self.scale_[k] = 1.
                self.scale_[k] += 0.5 * np.sum(z.T[k] * (sq_diff + n_features))
                self.bound_prec_[k] = (
                    0.5 * n_features * (
                        digamma(self.dof_[k]) - np.log(self.scale_[k])))
            self.precs_ = np.tile(self.dof_ / self.scale_, [n_features, 1]).T

        elif self.covariance_type == 'diag':
            for k in range(self.n_components):
                self.dof_[k].fill(1. + 0.5 * np.sum(z.T[k], axis=0))
                sq_diff = (X - self.means_[k]) ** 2  # see comment above
                self.scale_[k] = np.ones(n_features) + 0.5 * np.dot(
                    z.T[k], (sq_diff + 1))
                self.precs_[k] = self.dof_[k] / self.scale_[k]
                self.bound_prec_[k] = 0.5 * np.sum(digamma(self.dof_[k])
                                                   - np.log(self.scale_[k]))
                self.bound_prec_[k] -= 0.5 * np.sum(self.precs_[k])

        elif self.covariance_type == 'tied':
            self.dof_ = 2 + X.shape[0] + n_features
            self.scale_ = (X.shape[0] + 1) * np.identity(n_features)
            for k in range(self.n_components):
                diff = X - self.means_[k]
                self.scale_ += np.dot(diff.T, z[:, k:k + 1] * diff)
            self.scale_ = pinvh(self.scale_)
            self.precs_ = self.dof_ * self.scale_
            self.det_scale_ = linalg.det(self.scale_)
            self.bound_prec_ = 0.5 * wishart_log_det(
                self.dof_, self.scale_, self.det_scale_, n_features)
            self.bound_prec_ -= 0.5 * self.dof_ * np.trace(self.scale_)

        elif self.covariance_type == 'full':
            for k in range(self.n_components):
                sum_resp = np.sum(z.T[k])
                self.dof_[k] = 2 + sum_resp + n_features
                self.scale_[k] = (sum_resp + 1) * np.identity(n_features)
                diff = X - self.means_[k]
                self.scale_[k] += np.dot(diff.T, z[:, k:k + 1] * diff)
                self.scale_[k] = pinvh(self.scale_[k])
                self.precs_[k] = self.dof_[k] * self.scale_[k]
                self.det_scale_[k] = linalg.det(self.scale_[k])
                self.bound_prec_[k] = 0.5 * wishart_log_det(
                    self.dof_[k], self.scale_[k], self.det_scale_[k],
                    n_features)
                self.bound_prec_[k] -= 0.5 * self.dof_[k] * np.trace(
                    self.scale_[k])