def predict_proba(self, X, XErr, priorStar=None):
if priorStar is not None:
self._priorStar = priorStar
logLStar = logsumexp(self.clfStar.logprob_a(X, XErr), -1)
logLGal = logsumexp(self.clfGal.logprob_a(X, XErr), -1)
logposteriorStar = logLStar + np.log(self._priorStar)
logposteriorGal = logLGal + np.log(1.0 - self._priorStar)
posteriorStar = np.exp(logposteriorStar)
posteriorGal = np.exp(logposteriorGal)
posteriorStar /= posteriorStar + posteriorGal
return posteriorStar
def test_logsumexp():
np.random.seed(0)
X = np.random.random((100, 100))
for axis in (None, 0, 1):
np_result = np.log(np.sum(np.exp(X), axis=axis))
aML_result = logsumexp(X, axis=axis)
assert_array_almost_equal(np_result, aML_result)
def score_samples(self, X, Xerr):
"""Return the per-sample likelihood of the data under the model.
Compute the log probability of X under the model and
return the posterior distribution (responsibilities) of each
mixture component for each element of X.
Parameters
----------
X: array_like, shape (n_samples, n_features)
List of n_features-dimensional data points. Each row
corresponds to a single data point.
Xerr: array_like
errors, shape = (n_samples, n_features, n_features)
Returns
-------
logprob : array_like, shape (n_samples,)
Log probabilities of each data point in X.
responsibilities : array_like, shape (n_samples, n_components)
Posterior probabilities of each mixture component for each
observation
"""
X = np.asarray(X)
if X.ndim == 1:
X = X[:, np.newaxis]
if X.size == 0:
return np.array([]), np.empty((0, self.n_components))
if X.shape[1] != self.mu.shape[1]:
raise ValueError('The shape of X is not compatible with self')
#### offending line
## have to check if there is the self.weights_ these are the weights of
## the different gaussians that are being mixed
#### original line from scikit learn GMM
## check the types of return of log_multivariate_normal_density
## - [x] check the types of return of self.alphas - same as gmm.weights_
##
## lpr = (log_multivariate_normal_density(X, self.means_, self.covars_,
## self.covariance_type)
## logprob_a computes the log multivariate gaussian for one gaussian at
## time and give return of N(x|mu, V) but the algorithm might be smart
## enough to
## original code computes an array of instead
## - need to find the corresponding
## mu and V for each components to compute
## [N(x|mu_1, V_1), N(x|mu_2, V_2), ..., N(x|mu_n_comp, V_n_comp)]
## following line is supposed to add in so each log P of a particular
## normal in the mixture add with the log weight of that log
lpr = (self.logprob_a(X, Xerr) + np.log(self.alpha))
logprob = logsumexp(lpr, axis=1)
responsibilities = np.exp(lpr - logprob[:, np.newaxis])
return logprob, responsibilities
def test_logsumexp():
np.random.seed(0)
X = np.random.random((100, 100))
for axis in (None, 0, 1):
np_result = np.log(np.sum(np.exp(X), axis=axis))
aML_result = logsumexp(X, axis=axis)
assert_array_almost_equal(np_result, aML_result)
def score_samples(self, X, Xerr):
"""Return the per-sample likelihood of the data under the model.
Compute the log probability of X under the model and
return the posterior distribution (responsibilities) of each
mixture component for each element of X.
Parameters
----------
X: array_like, shape (n_samples, n_features)
List of n_features-dimensional data points. Each row
corresponds to a single data point.
Xerr: array_like
errors, shape = (n_samples, n_features, n_features)
Returns
-------
logprob : array_like, shape (n_samples,)
Log probabilities of each data point in X.
responsibilities : array_like, shape (n_samples, n_components)
Posterior probabilities of each mixture component for each
observation
"""
X = np.asarray(X)
if X.ndim == 1:
X = X[:, np.newaxis]
if X.size == 0:
return np.array([]), np.empty((0, self.n_components))
if X.shape[1] != self.mu.shape[1]:
raise ValueError('The shape of X is not compatible with self')
#### offending line
## have to check if there is the self.weights_ these are the weights of
## the different gaussians that are being mixed
#### original line from scikit learn GMM
## check the types of return of log_multivariate_normal_density
## - [x] check the types of return of self.alphas - same as gmm.weights_
##
## lpr = (log_multivariate_normal_density(X, self.means_, self.covars_,
## self.covariance_type)
## logprob_a computes the log multivariate gaussian for one gaussian at
## time and give return of N(x|mu, V) but the algorithm might be smart
## enough to
## original code computes an array of instead
## - need to find the corresponding
## mu and V for each components to compute
## [N(x|mu_1, V_1), N(x|mu_2, V_2), ..., N(x|mu_n_comp, V_n_comp)]
## following line is supposed to add in so each log P of a particular
## normal in the mixture add with the log weight of that log
lpr = (self.logprob_a(X, Xerr) + np.log(self.alpha))
logprob = logsumexp(lpr, axis=1)
responsibilities = np.exp(lpr - logprob[:, np.newaxis])
return logprob, responsibilities
def computeStellarPosteriors(X,
XErr,
ngStar=None,
ngGal=None,
priorStar=0.5,
magMin=None,
magMax=None,
extMax=None):
clfStar, clfGal = loadXDFits(ngStar=ngStar,
ngGal=ngGal,
magMin=magMin,
magMax=magMax,
extMax=extMax)
logLStar = logsumexp(clfStar.logprob_a(X, XErr), -1)
logLGal = logsumexp(clfGal.logprob_a(X, XErr), -1)
logposteriorStar = logLStar + np.log(priorStar)
logposteriorGal = logLGal + np.log(1.0 - priorStar)
posteriorStar = np.exp(logposteriorStar)
posteriorGal = np.exp(logposteriorGal)
posteriorStar /= posteriorStar + posteriorGal
return posteriorStar
def logL(self, X, Xerr):
"""Compute the log-likelihood of data given the model
Parameters
----------
X: array_like
data, shape = (n_samples, n_features)
Xerr: array_like
errors, shape = (n_samples, n_features, n_features)
Returns
-------
logL : float
log-likelihood
"""
return np.sum(logsumexp(self.logprob_a(X, Xerr), -1))
def logL(self, X, Xerr):
"""Compute the log-likelihood of data given the model
Parameters
----------
X: array_like
data, shape = (n_samples, n_features)
Xerr: array_like
errors, shape = (n_samples, n_features, n_features)
Returns
-------
logL : float
log-likelihood
"""
return np.sum(logsumexp(self.logprob_a(X, Xerr), -1))
def score(self, X, Xerr):
"""Compute the score of data given the model
Provides the mean log-likelihood of the data in X based on the
model as a score for scikit-learn cross-validation.
Parameters
----------
X: array_like, shape = (n_samples, n_features)
Input data.
Xerr: array_like, shape = (n_samples, n_features, n_features)
Error on input data.
Returns
-------
score : float
Score (log-likelihood).
"""
if self.V is None or self.mu is None or self.weights is None:
raise StandardError("Model parameters not set.")
logprob = self.GMM.logprob_a(X,Xerr)
logLs = logsumexp(logprob,axis=-1)
return np.mean(logLs)
