def __init__(self, **params):
'''
Parameters
----------
ms_h : float, sets the bandwidth of the mean shift algorithm, defaults to None, whereby the algorithm automatically
determines the bandwidth
automatic_ms_h : bool, if True forces the algorithm to determine its own bandwidth, overrides any ms_h setting
ms_sub : float, sets the percentage (0 < ms_sub <= 100) of the data points supplied to self.__call__ that are used to compute the ms seed
points
rho_threshold : float, ratio of 2nd largest to largest cluster eigenvalues, above which cluster centers are
removed from the output
'''
super(lpcMeanShift, self).__init__()
self._lpcParameters = { 'ms_h': None,
'automatic_ms_h': False,
'ms_sub': 30,
'rho_threshold': 0.2
}
self._prm_list = [self._lpcParameters]
self.user_prm = None #extension of parameter set disallowed
self._type_check.update({ 'ms_h': lambda x: (x is None) or lpcMeanShift._positivityCheck(x) or (isinstance(x, list) and all(map(lpcMeanShift._positivityCheck, x)) ) ,
'automatic_ms_h': (bool,),
'ms_sub': lambda x: lpcMeanShift._positivityCheck and x <= 100,
'rho_threshold': lambda x: lpcMeanShift._positivityCheck and x < 1
})
self.set(**params)
if self._lpcParameters['automatic_ms_h'] or self._lpcParameters['ms_h'] is None :
self._meanShift = MeanShift()
else:
self._meanShift = MeanShift(bandwidth = mean(self._lpcParameters['ms_h']))
def calculate_cluster(lena, lena_mat, quantile):
bandwidth = estimate_bandwidth(lena_mat, quantile=quantile, n_samples=500)
ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
ms.fit(lena_mat)
labels = ms.labels_
cluster_centers = ms.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
lena_clustered = lena.copy()
lena_clustered_value = lena.copy()
lena_mat_clustered = lena_mat.copy()
lena_mat_clustered_value = lena_mat.copy()
for point, pointb, value in zip(lena_mat_clustered, lena_mat_clustered_value, labels):
point[2] = value
pointb[2] = cluster_centers[value, 2]
lena_clustered[point[0], point[1]] = value
lena_clustered_value[point[0], point[1]] = cluster_centers[value, 2]
image = {"image": lena_clustered_value,
"quantile": quantile,
"clusters": n_clusters_}
return image
def calculate_cluster(camera, camera_mat, quantile):
bandwidth = estimate_bandwidth(camera_mat,
quantile=quantile,
n_samples=500)
ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
ms.fit(camera_mat)
labels = ms.labels_
cluster_centers = ms.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
camera_clustered = camera.copy()
camera_clustered_value = camera.copy()
camera_mat_clustered = camera_mat.copy()
camera_mat_clustered_value = camera_mat.copy()
for point, pointb, value in zip(camera_mat_clustered,
camera_mat_clustered_value, labels):
point[2] = value
pointb[2] = cluster_centers[value, 2]
camera_clustered[point[0], point[1]] = value
camera_clustered_value[point[0], point[1]] = cluster_centers[value, 2]
image = {
"image": camera_clustered_value,
"quantile": quantile,
"clusters": n_clusters_
}
return image
def meanshift(desc, quantile, hs=16, hr=16, copy=True):
"""
Do nothing for now...
"""
if copy:
desc = desc.copy()
desc[:, :2] /= hs
desc[:, 2:] /= hr
bandwidth = estimate_bandwidth(desc, quantile=quantile, n_samples=500)
ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
ms.fit(desc)
ms.cluster_centers_[:, :2] *= hs
ms.cluster_centers_[:, 2:] *= hr
return ms
def setScaleParameters(self, ms_h = None):
'''This is for initially setting the scale parameters, and only has an effect if
self._lpcParamters['automatic_ms_h'] is False
Parameters
----------
ms_h : float or None, sets the bandwidth of meanshift algorithm, default (None) has no effect
'''
if not self._lpcParameters['automatic_ms_h'] and ms_h is not None:
self.set_in_dict('ms_h', ms_h, self._lpcParameters)
bandwidth = mean(self._lpcParameters['ms_h'])
self._meanShift = MeanShift(bandwidth = bandwidth)
class lpcMeanShift(PrmDictBase):
'''
Wrapper around the scikit-learn class sklearn.cluster.MeanShift to approximately mimic the behavior of the LPCM CRAN package
Callable that generates n starting points based on local density modes of X. Seed points for modes are given by x0;
ms.h controls the kernel bandwidth (original CRAN package allowed x0 as a vector with separate bandwidth per dimension,
the sklearn MeanShift class allows only a scalar bandwidth, so the mean is taken), ms.sub is the percentage of data points
that should be used a seeds for selecting local density modes
'''
@staticmethod
def _positivityCheck(x):
return isinstance(x, (int, float)) and x > 0
def _removeNonTracklikeClusterCenters(self):
'''NOTE : Much of this code is copied from LPCMImpl.followXSingleDirection (factor out?)
'''
labels = self._meanShift.labels_
labels_unique = unique(labels)
cluster_centers = self._meanShift.cluster_centers_
rsp = lpcRandomStartPoints()
cluster_representatives = []
for k in range(len(labels_unique)):
cluster_members = labels == k
cluster_center = cluster_centers[k]
cluster = self._Xi[cluster_members,:]
mean_sub = cluster - cluster_center
cov_x = dot(transpose(mean_sub), mean_sub)
eigen_cov = eigh(cov_x)
sorted_eigen_cov = zip(eigen_cov[0],map(ravel,vsplit(eigen_cov[1].transpose(),len(eigen_cov[1]))))
sorted_eigen_cov.sort(key = lambda elt: elt[0], reverse = True)
rho = sorted_eigen_cov[1][0] / sorted_eigen_cov[0][0] #Ratio of two largest eigenvalues
if rho < self._lpcParameters['rho_threshold']:
cluster_representatives.append(cluster_center)
else: #append a random element of the cluster
random_cluster_element = rsp(cluster, 1)[0]
cluster_representatives.append(random_cluster_element)
return array(cluster_representatives)
def __init__(self, **params):
'''
Parameters
----------
ms_h : float, sets the bandwidth of the mean shift algorithm, defaults to None, whereby the algorithm automatically
determines the bandwidth
automatic_ms_h : bool, if True forces the algorithm to determine its own bandwidth, overrides any ms_h setting
ms_sub : float, sets the percentage (0 < ms_sub <= 100) of the data points supplied to self.__call__ that are used to compute the ms seed
points
rho_threshold : float, ratio of 2nd largest to largest cluster eigenvalues, above which cluster centers are
removed from the output
'''
super(lpcMeanShift, self).__init__()
self._lpcParameters = { 'ms_h': None,
'automatic_ms_h': False,
'ms_sub': 30,
'rho_threshold': 0.2
}
self._prm_list = [self._lpcParameters]
self.user_prm = None #extension of parameter set disallowed
self._type_check.update({ 'ms_h': lambda x: (x is None) or lpcMeanShift._positivityCheck(x) or (isinstance(x, list) and all(map(lpcMeanShift._positivityCheck, x)) ) ,
'automatic_ms_h': (bool,),
'ms_sub': lambda x: lpcMeanShift._positivityCheck and x <= 100,
'rho_threshold': lambda x: lpcMeanShift._positivityCheck and x < 1
})
self.set(**params)
if self._lpcParameters['automatic_ms_h'] or self._lpcParameters['ms_h'] is None :
self._meanShift = MeanShift()
else:
self._meanShift = MeanShift(bandwidth = mean(self._lpcParameters['ms_h']))
def __call__(self, X, n = None, x0 = None):
'''
Generates n seed points for the lpc algorithm.
X, 2 dimensional [#points, #dimension of points] array containing the data for which local density modes is to calculated
n, required number of seed points, if n = None, returns exactly the local density modes, otherwise lpcRandomStartPoints is called with x0 equal
to the local density modes (local density modes are the cluster centers)
x0, 2-dimensional array containing #rows equal to number of explicitly defined mean shift seed points and #columns equal
to dimension of the individual data points (called number of features in MeanShift docs).
Returns the lpc seed points as a 2 dimensional [#seed points, #dimension of seed points] array
'''
self._Xi = X
if x0 is None:
N = self._Xi.shape[0]
ms_sub = float(self._lpcParameters['ms_sub'])
#guarantees ms_sub <= ms_sub % of N <= 10 * ms_sub seed points (could give the option of using seed point binning in MeanShift)
Nsub = int(min(max(ms_sub, floor(ms_sub * N / 100)), 10 * ms_sub))
ms_seeds = self._Xi[sample(xrange(0, N), Nsub),:]
else:
ms_seeds = x0
self._meanShift.seeds = ms_seeds
self._meanShift.fit(self._Xi)
cluster_respresentatives = self._removeNonTracklikeClusterCenters()
if len(cluster_respresentatives) == 0:
cluster_respresentatives = None
lpcRSP = lpcRandomStartPoints()
if n is None:
return lpcRSP(self._Xi, n = 2, x0 = cluster_respresentatives)
else:
return lpcRSP(self._Xi, n = n, x0 = cluster_respresentatives)
def setScaleParameters(self, ms_h = None):
'''This is for initially setting the scale parameters, and only has an effect if
self._lpcParamters['automatic_ms_h'] is False
Parameters
----------
ms_h : float or None, sets the bandwidth of meanshift algorithm, default (None) has no effect
'''
if not self._lpcParameters['automatic_ms_h'] and ms_h is not None:
self.set_in_dict('ms_h', ms_h, self._lpcParameters)
bandwidth = mean(self._lpcParameters['ms_h'])
self._meanShift = MeanShift(bandwidth = bandwidth)
def getClusterLabels(self):
return self._meanShift.labels_
'LassoLarsCV':LassoLarsCV(), 'LassoLarsIC':LassoLarsIC(), 'LatentDirichletAllocation':LatentDirichletAllocation(), 'LedoitWolf':LedoitWolf(), 'LinearDiscriminantAnalysis':LinearDiscriminantAnalysis(), 'LinearRegression':LinearRegression(), 'LinearSVC':LinearSVC(), 'LinearSVR':LinearSVR(), 'LocallyLinearEmbedding':LocallyLinearEmbedding(), 'LogisticRegression':LogisticRegression(), 'LogisticRegressionCV':LogisticRegressionCV(), 'MDS':MDS(), 'MLPClassifier':MLPClassifier(), 'MLPRegressor':MLPRegressor(), 'MaxAbsScaler':MaxAbsScaler(), 'MeanShift':MeanShift(), 'MinCovDet':MinCovDet(), 'MinMaxScaler':MinMaxScaler(), 'MiniBatchDictionaryLearning':MiniBatchDictionaryLearning(), 'MiniBatchKMeans':MiniBatchKMeans(), 'MiniBatchSparsePCA':MiniBatchSparsePCA(), 'MultiTaskElasticNet':MultiTaskElasticNet(), 'MultiTaskElasticNetCV':MultiTaskElasticNetCV(), 'MultiTaskLasso':MultiTaskLasso(), 'MultiTaskLassoCV':MultiTaskLassoCV(), 'MultinomialNB':MultinomialNB(), 'NMF':NMF(), 'NearestCentroid':NearestCentroid(), 'NearestNeighbors':NearestNeighbors(), 'Normalizer':Normalizer(), 'NuSVC':NuSVC(),
