def __init__(self, initial_means, priors=None, covariance_matrices=None,
conv_threshold=1e-6, bias=0.1, normalise=False,
svd_dimensions=None):
"""
Creates an EM clusterer with the given starting parameters,
convergence threshold and vector mangling parameters.
:param initial_means: the means of the gaussian cluster centers
:type initial_means: [seq of] numpy array or seq of SparseArray
:param priors: the prior probability for each cluster
:type priors: numpy array or seq of float
:param covariance_matrices: the covariance matrix for each cluster
:type covariance_matrices: [seq of] numpy array
:param conv_threshold: maximum change in likelihood before deemed
convergent
:type conv_threshold: int or float
:param bias: variance bias used to ensure non-singular covariance
matrices
:type bias: float
:param normalise: should vectors be normalised to length 1
:type normalise: boolean
:param svd_dimensions: number of dimensions to use in reducing vector
dimensionsionality with SVD
:type svd_dimensions: int
"""
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._means = numpy.array(initial_means, numpy.float64)
self._num_clusters = len(initial_means)
self._conv_threshold = conv_threshold
self._covariance_matrices = covariance_matrices
self._priors = priors
self._bias = bias
def cluster(self,
vectors,
assign_clusters=False,
ClusterNum=None,
DisType='cos',
Stype='avg',
trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if ('cos' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = cosine_distance(
vectors[i], vectors[j])
elif ('euc' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = euclidean_distance(
vectors[i], vectors[j])
self._dendrogram = Dendrogram(
[numpy.array(vector, numpy.float64) for vector in vectors])
result = VectorSpaceClusterer.cluster(self, vectors, assign_clusters,
ClusterNum, Stype, trace)
if (2 == len(vectors[0])): # 二维样本则显示可视化结果
self.draw_2D(vectors, result)
return result
def cluster(self, vectors, assign_clusters=False,ClusterNum=None, DisType='euc',Stype='mean',trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if(0==l):
return []
if('cos'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = cosine_distance(vectors[i], vectors[j])
elif('euc'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = euclidean_distance(vectors[i], vectors[j])
result = VectorSpaceClusterer.cluster(self, vectors,assign_clusters,ClusterNum, Stype, trace)
#/////////////////////// 测试，输出距离 /////////////////
# m = 0
# for k,v in self._distMap:
# m +=1
# print v,"\t",
# if (m%7==0):
# print
#/////////////////////////////////////////////////////
if(2==len(vectors[0])): # 二维样本则显示可视化结果
draw_2D_cluster(vectors, result)
return result
def __init__(self,
num_means,
distance,
repeats=1,
conv_test=1e-6,
initial_means=None,
normalise=False,
svd_dimensions=None,
rng=None,
avoid_empty_clusters=False):
"""
:param num_means: the number of means to use (may use fewer)
:type num_means: int
:param distance: measure of distance between two vectors
:type distance: function taking two vectors and returing a float
:param repeats: number of randomised clustering trials to use
:type repeats: int
:param conv_test: maximum variation in mean differences before
deemed convergent
:type conv_test: number
:param initial_means: set of k initial means
:type initial_means: sequence of vectors
:param normalise: should vectors be normalised to length 1
:type normalise: boolean
:param svd_dimensions: number of dimensions to use in reducing vector
dimensionsionality with SVD
:type svd_dimensions: int
:param rng: random number generator (or None)
:type rng: Random
:param avoid_empty_clusters: include current centroid in computation
of next one; avoids undefined behavior
when clusters become empty
:type avoid_empty_clusters: boolean
"""
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._num_means = num_means
self._distance = distance
self._max_difference = conv_test
assert not initial_means or len(initial_means) == num_means
self._means = initial_means
assert repeats >= 1
assert not (initial_means and repeats > 1)
self._repeats = repeats
if rng: self._rng = rng
else: self._rng = random.Random()
self._avoid_empty_clusters = avoid_empty_clusters
def __init__(self, num_means, distance, repeats=1,
conv_test=1e-6, initial_means=None,
normalise=False, svd_dimensions=None,
rng=None, avoid_empty_clusters=False):
"""
:param num_means: the number of means to use (may use fewer)
:type num_means: int
:param distance: measure of distance between two vectors
:type distance: function taking two vectors and returing a float
:param repeats: number of randomised clustering trials to use
:type repeats: int
:param conv_test: maximum variation in mean differences before
deemed convergent
:type conv_test: number
:param initial_means: set of k initial means
:type initial_means: sequence of vectors
:param normalise: should vectors be normalised to length 1
:type normalise: boolean
:param svd_dimensions: number of dimensions to use in reducing vector
dimensionsionality with SVD
:type svd_dimensions: int
:param rng: random number generator (or None)
:type rng: Random
:param avoid_empty_clusters: include current centroid in computation
of next one; avoids undefined behavior
when clusters become empty
:type avoid_empty_clusters: boolean
"""
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._num_means = num_means
self._distance = distance
self._max_difference = conv_test
assert not initial_means or len(initial_means) == num_means
self._means = initial_means
assert repeats >= 1
assert not (initial_means and repeats > 1)
self._repeats = repeats
if rng: self._rng = rng
else: self._rng = random.Random()
self._avoid_empty_clusters = avoid_empty_clusters
def __init__(self,
initial_means,
priors=None,
covariance_matrices=None,
conv_threshold=1e-6,
bias=0.1,
normalise=False,
svd_dimensions=None):
"""
Creates an EM clusterer with the given starting parameters,
convergence threshold and vector mangling parameters.
:param initial_means: the means of the gaussian cluster centers
:type initial_means: [seq of] numpy array or seq of SparseArray
:param priors: the prior probability for each cluster
:type priors: numpy array or seq of float
:param covariance_matrices: the covariance matrix for each cluster
:type covariance_matrices: [seq of] numpy array
:param conv_threshold: maximum change in likelihood before deemed
convergent
:type conv_threshold: int or float
:param bias: variance bias used to ensure non-singular covariance
matrices
:type bias: float
:param normalise: should vectors be normalised to length 1
:type normalise: boolean
:param svd_dimensions: number of dimensions to use in reducing vector
dimensionsionality with SVD
:type svd_dimensions: int
"""
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._means = numpy.array(initial_means, numpy.float64)
self._num_clusters = len(initial_means)
self._conv_threshold = conv_threshold
self._covariance_matrices = covariance_matrices
self._priors = priors
self._bias = bias
def cluster(self,
vectors,
assign_clusters=False,
ClusterNum=None,
DisType='euc',
Stype='mean',
trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if (0 == l):
return []
if ('cos' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = cosine_distance(
vectors[i], vectors[j])
elif ('euc' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = euclidean_distance(
vectors[i], vectors[j])
result = VectorSpaceClusterer.cluster(self, vectors, assign_clusters,
ClusterNum, Stype, trace)
#/////////////////////// 测试，输出距离 /////////////////
# m = 0
# for k,v in self._distMap:
# m +=1
# print v,"\t",
# if (m%7==0):
# print
#/////////////////////////////////////////////////////
if (2 == len(vectors[0])): # 二维样本则显示可视化结果
draw_2D_cluster(vectors, result)
return result
def cluster(self, vectors, assign_clusters=False, DisType='cos',Stype='avg',trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if('cos'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = cosine_distance(vectors[i], vectors[j])
elif('euc'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = euclidean_distance(vectors[i], vectors[j])
self._dendrogram = Dendrogram(
[numpy.array(vector, numpy.float64) for vector in vectors])
result = VectorSpaceClusterer.cluster(self, vectors,assign_clusters, Stype, trace)
return result
def __init__(self, num_clusters=None, normalise=True, svd_dimensions=None):
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._num_clusters = num_clusters
self._groups_values = None
self._distMap = {}
def __init__(self, num_clusters=None, normalise=True, svd_dimensions=None):
VectorSpaceClusterer.__init__(self, normalise, svd_dimensions)
self._num_clusters = num_clusters
self._groups_values = None
self._distMap ={}