def check_maxRstat_one_cluster_linkage(self, i):
# Tests maxRstat(Z, R, i) on linkage with one cluster.
Z = np.asarray([[0, 1, 0.3, 4]], dtype=np.double)
R = np.asarray([[0, 0, 0, 0.3]], dtype=np.double)
MD = maxRstat(Z, R, 1)
expectedMD = calculate_maximum_inconsistencies(Z, R, 1)
assert_allclose(MD, expectedMD, atol=1e-15)
def check_maxRstat_one_cluster_linkage(self, i):
# Tests maxRstat(Z, R, i) on linkage with one cluster.
Z = np.asarray([[0, 1, 0.3, 4]], dtype=np.double)
R = np.asarray([[0, 0, 0, 0.3]], dtype=np.double)
MD = maxRstat(Z, R, 1)
expectedMD = calculate_maximum_inconsistencies(Z, R, 1)
assert_allclose(MD, expectedMD, atol=1e-15)
def check_maxRstat_Q_linkage(self, method, i):
# Tests maxRstat(Z, R, i) on the Q data set
X = hierarchy_test_data.Q_X
Z = linkage(X, method)
R = inconsistent(Z)
MD = maxRstat(Z, R, 1)
expectedMD = calculate_maximum_inconsistencies(Z, R, 1)
assert_allclose(MD, expectedMD, atol=1e-15)
def check_maxRstat_Q_linkage(self, method, i):
# Tests maxRstat(Z, R, i) on the Q data set
X = hierarchy_test_data.Q_X
Z = linkage(X, method)
R = inconsistent(Z)
MD = maxRstat(Z, R, 1)
expectedMD = calculate_maximum_inconsistencies(Z, R, 1)
assert_allclose(MD, expectedMD, atol=1e-15)
def check_maxRstat_Q_linkage(self, method, i):
# Tests maxRstat(Z, R, i) on the Q data set
X = eo['Q-X']
Y = pdist(X)
Z = linkage(X, method)
R = inconsistent(Z)
MD = maxRstat(Z, R, 1)
expectedMD = calculate_maximum_inconsistencies(Z, R, 1)
assert_allclose(MD, expectedMD, atol=1e-15)
def process(self, **kwargs) -> Dict[str, Dict[np.ndarray, str]]:
Z = kwargs['Linkage']
IncM = kwargs['IncM']
R = IncM['R']
stat = self.ctrls['Stat'].currentText()
if stat == 'mean':
i = 0
elif stat == 'stdev':
i = 1
elif stat == 'num_links':
i = 2
elif stat == 'inc_coef':
i = 3
MR = hierarchy.maxRstat(Z, R, i)
return {'MaxStat': {'MR': MR, 'stat': stat}}
def silhouette_score(dendroMatrix, distance_metric, linkage_method, labels):
"""
Generate silhoutte score based on hierarchical clustering.
Args:
dendroMatrix: list, occurance of words in different files
distance_metric: string, style of distance metric in the dendrogram
linkage_method: string, style of linkage method in the dendrogram
labels: list, file names
Returns:
silhouetteScore: string, containing the result of silhouette score
silhouetteAnnotation: string, annotation of the silhouette score
score: float, silhouette score
inconsistentMax: float, upper bound of threshold to calculate silhouette score if using Inconsistent criterion
maxclustMax: integer, upper bound of threshold to calculate silhouette score if using Maxclust criterion
distanceMax: float, upper bound of threshold to calculate silhouette score if using Distance criterion
distanceMin: float, lower bound of threshold to calculate silhouette score if using Distance criterion
monocritMax: float, upper bound of threshold to calculate silhouette score if using Monocrit criterion
monocritMin: float, lower bound of threshold to calculate silhouette score if using Monocrit criterion
threshold: float/integer/string, threshold (t) value that users entered, equals to 'N/A' if users leave the field blank
"""
activeFiles = len(labels) - 1
if (
activeFiles > 2
): # since "number of lables should be more than 2 and less than n_samples - 1"
Y = metrics.pairwise.pairwise_distances(dendroMatrix,
metric=distance_metric)
Z = hierarchy.linkage(Y, method=linkage_method)
monocrit = None
# 'maxclust' range
maxclustMax = len(labels) - 1
# 'incosistent' range
R = hierarchy.inconsistent(Z, 2)
inconsistentMax = R[-1][-1]
slen = len('%.*f' % (2, inconsistentMax))
inconsistentMax = float(str(inconsistentMax)[:slen])
# 'distance' range
d = hierarchy.cophenet(Z)
distanceMax = d.max()
slen = len('%.*f' % (2, distanceMax))
distanceMax = float(str(distanceMax)[:slen])
distanceMin = d.min() + 0.01
slen = len('%.*f' % (2, distanceMin))
distanceMin = float(str(distanceMin)[:slen])
# 'monocrit' range
MR = hierarchy.maxRstat(Z, R, 0)
monocritMax = MR.max()
slen = len('%.*f' % (2, monocritMax))
monocritMax = float(str(monocritMax)[:slen])
monocritMin = MR.min() + 0.01
slen = len('%.*f' % (2, monocritMin))
monocritMin = float(str(monocritMin)[:slen])
threshold = request.form['threshold']
if threshold == '':
threshold = str(threshold)
else:
threshold = float(threshold)
if request.form['criterion'] == 'maxclust':
criterion = 'maxclust'
if (threshold == '') or (threshold > maxclustMax):
threshold = len(labels) - 1
else:
threshold = round(float(threshold))
elif request.form['criterion'] == 'distance':
criterion = 'distance'
if (threshold == '') or (threshold > distanceMax) or (threshold <
distanceMin):
threshold = distanceMax
elif request.form['criterion'] == 'inconsistent':
criterion = 'inconsistent'
if (threshold == '') or (threshold > inconsistentMax):
threshold = inconsistentMax
elif request.form['criterion'] == 'monocrit':
criterion = 'monocrit'
monocrit = MR
if (threshold == '') or (threshold > monocritMax) or (threshold <
monocritMin):
threshold = monocritMax
scoreLabel = hierarchy.fcluster(Z,
t=threshold,
criterion=criterion,
monocrit=monocrit)
if len(
set(scoreLabel)
) <= 1: # this means all the files are divided into only 1 or less cluster
silhouetteScore = "Silhouette Score: invalid for only 1 cluster."
silhouetteAnnotation = "because your file are too similar to each other, program classify all of them in the same cluster"
score = 'invalid for only 1 cluster'
inconsistentMax = maxclustMax = distanceMax = distanceMin = monocritMax = monocritMin = threshold = 'N/A'
else:
score = metrics.silhouette_score(Y,
labels=scoreLabel,
metric='precomputed')
score = round(score, constants.ROUND_DIGIT)
inequality = '≤'.decode('utf-8')
silhouetteScore = "Silhouette Score: " + str(
score
) + "\n(-1 " + inequality + " Silhouette Score " + inequality + " 1)"
silhouetteAnnotation = "The best value is 1 and the worst value is -1. Values near 0 indicate overlapping clusters. Negative values generally indicate that a sample has been assigned to the wrong cluster, as a different cluster is more similar."
else:
silhouetteScore = "Silhouette Score: invalid for less than or equal to 2 files."
silhouetteAnnotation = ""
score = 'invalid for less than or equal to 2 files.'
threshold = inconsistentMax = maxclustMax = distanceMax = distanceMin = monocritMax = monocritMin = 'N/A'
return silhouetteScore, silhouetteAnnotation, score, inconsistentMax, maxclustMax, distanceMax, distanceMin, monocritMax, monocritMin, threshold
def silhouette_score(dendroMatrix, distance_metric, linkage_method, labels):
"""
Generate silhoutte score based on hierarchical clustering.
Args:
dendroMatrix: list, occurance of words in different files
distance_metric: string, style of distance metric in the dendrogram
linkage_method: string, style of linkage method in the dendrogram
labels: list, file names
Returns:
silhouetteScore: string, containing the result of silhouette score
silhouetteAnnotation: string, annotation of the silhouette score
score: float, silhouette score
inconsistentMax: float, upper bound of threshold to calculate silhouette score if using Inconsistent criterion
maxclustMax: integer, upper bound of threshold to calculate silhouette score if using Maxclust criterion
distanceMax: float, upper bound of threshold to calculate silhouette score if using Distance criterion
distanceMin: float, lower bound of threshold to calculate silhouette score if using Distance criterion
monocritMax: float, upper bound of threshold to calculate silhouette score if using Monocrit criterion
monocritMin: float, lower bound of threshold to calculate silhouette score if using Monocrit criterion
threshold: float/integer/string, threshold (t) value that users entered, equals to 'N/A' if users leave the field blank
"""
activeFiles = len(labels) - 1
if (activeFiles > 2): # since "number of lables should be more than 2 and less than n_samples - 1"
Y = metrics.pairwise.pairwise_distances(dendroMatrix, metric=distance_metric)
Z = hierarchy.linkage(Y, method=linkage_method)
monocrit = None
# 'maxclust' range
maxclustMax = len(labels) - 1
# 'incosistent' range
R = hierarchy.inconsistent(Z, 2)
inconsistentMax = R[-1][-1]
slen = len('%.*f' % (2, inconsistentMax))
inconsistentMax = float(str(inconsistentMax)[:slen])
# 'distance' range
d = hierarchy.cophenet(Z)
distanceMax = d.max()
slen = len('%.*f' % (2, distanceMax))
distanceMax = float(str(distanceMax)[:slen])
distanceMin = d.min() + 0.01
slen = len('%.*f' % (2, distanceMin))
distanceMin = float(str(distanceMin)[:slen])
# 'monocrit' range
MR = hierarchy.maxRstat(Z, R, 0)
monocritMax = MR.max()
slen = len('%.*f' % (2, monocritMax))
monocritMax = float(str(monocritMax)[:slen])
monocritMin = MR.min() + 0.01
slen = len('%.*f' % (2, monocritMin))
monocritMin = float(str(monocritMin)[:slen])
threshold = request.form['threshold']
if threshold == '':
threshold = str(threshold)
else:
threshold = float(threshold)
if request.form['criterion'] == 'maxclust':
criterion = 'maxclust'
if (threshold == '') or (threshold > maxclustMax):
threshold = len(labels) - 1
else:
threshold = round(float(threshold))
elif request.form['criterion'] == 'distance':
criterion = 'distance'
if (threshold == '') or (threshold > distanceMax) or (threshold < distanceMin):
threshold = distanceMax
elif request.form['criterion'] == 'inconsistent':
criterion = 'inconsistent'
if (threshold == '') or (threshold > inconsistentMax):
threshold = inconsistentMax
elif request.form['criterion'] == 'monocrit':
criterion = 'monocrit'
monocrit = MR
if (threshold == '') or (threshold > monocritMax) or (threshold < monocritMin):
threshold = monocritMax
scoreLabel = hierarchy.fcluster(Z, t=threshold, criterion=criterion, monocrit=monocrit)
if len(set(scoreLabel)) <= 1: # this means all the files are divided into only 1 or less cluster
silhouetteScore = "Silhouette Score: invalid for only 1 cluster."
silhouetteAnnotation = "because your file are too similar to each other, program classify all of them in the same cluster"
score = 'invalid for only 1 cluster'
inconsistentMax = maxclustMax = distanceMax = distanceMin = monocritMax = monocritMin = threshold = 'N/A'
else:
score = metrics.silhouette_score(Y, labels=scoreLabel, metric='precomputed')
score = round(score, constants.ROUND_DIGIT)
inequality = '≤'.decode('utf-8')
silhouetteScore = "Silhouette Score: " + str(
score) + "\n(-1 " + inequality + " Silhouette Score " + inequality + " 1)"
silhouetteAnnotation = "The best value is 1 and the worst value is -1. Values near 0 indicate overlapping clusters. Negative values generally indicate that a sample has been assigned to the wrong cluster, as a different cluster is more similar."
else:
silhouetteScore = "Silhouette Score: invalid for less than or equal to 2 files."
silhouetteAnnotation = ""
score = 'invalid for less than or equal to 2 files.'
threshold = inconsistentMax = maxclustMax = distanceMax = distanceMin = monocritMax = monocritMin = 'N/A'
return silhouetteScore, silhouetteAnnotation, score, inconsistentMax, maxclustMax, distanceMax, distanceMin, monocritMax, monocritMin, threshold
def get_clusters_Hierarchy_clustering(x, hier_dict):
#default value
L_method = 'single'
L_metric = 'euclidean'
t = 0.9
criterionH = 'inconsistent'
depth = 2
R = None
colR = 3
#L_metric can be 'braycurtis’, ‘canberra’, ‘chebyshev’, ‘cityblock’,
#‘correlation’, ‘cosine’, ‘dice’, ‘euclidean’, ‘hamming’, ‘jaccard’,
# ‘kulsinski’, ‘mahalanobis’, ‘matching’, ‘minkowski’,
#‘rogerstanimoto’, ‘russellrao’, ‘seuclidean’, ‘sokalmichener’,
#‘sokalsneath’, ‘sqeuclidean’
#**Note that ‘jensenshannon’,‘yule’may result in a condensed distance matrix which contains infinite value
if 'L_metric' in hier_dict.keys():
L_metric = hier_dict['L_metric']
# L_method can be 'single', 'complete','average','weighted','centroid','median','ward'
if 'L_method' in hier_dict.keys():
L_method = hier_dict['L_method']
if L_method == 'centroid' or L_method == 'median' or L_method == 'ward':
if L_metric != 'euclidean':
L_metric = 'euclidean'
print('\n')
print('*************Note:**************')
print('Method ' + str(L_method) +
' requires the distance metric to be Euclidean')
if 'optimal_ordering' in hier_dict.keys():
optimal_ordering = hier_dict['optimal_ordering']
else:
optimal_ordering = False
Z = linkage(x,
method=L_method,
metric=L_metric,
optimal_ordering=optimal_ordering)
#criterion can be
if 'criterionH' in hier_dict.keys():
criterionH = hier_dict['criterionH']
else:
criterionH = 'inconsistent'
if 'depth' in hier_dict.keys():
depth = hier_dict['depth']
else:
depth = 2
if 't' in hier_dict.keys():
t = hier_dict['t']
#for 'maxclust' or 'maxclust_monocrit' criteria,
#t would be max number of clusters requested.
elif criterionH == 'maxclust_monocrit' or criterionH == 'maxclust':
t = 20
if 'R' in hier_dict.keys():
R = hier_dict['R']
if criterionH == 'inconsistent' or criterionH == 'maxclust_monocrit':
#The inconsistency matrix to use for the 'inconsistent' criterion.
#R is computed if not provided.
if R is None:
R = inconsistent(Z, d=depth)
else:
R = np.asarray(R, order='c')
if criterionH == 'monocrit':
if R is None:
R = inconsistent(Z, d=depth)
#colR is the column of 'R' to use as the statistic
return fcluster(Z,
criterion='monocrit',
t=t,
monocrit=maxRstat(Z, R, colR))
elif criterionH == 'maxclust_monocrit':
return fcluster(Z,
criterion='maxclust_monocrit',
t=t,
monocrit=maxinconsts(Z, R))
else:
return fcluster(Z, criterion=criterionH, depth=depth, R=R, t=t)
def _cluster_by_monocrit(linkage_table: numpy.ndarray, cutoff: float, inconsistent: pandas.DataFrame) -> numpy.ndarray: MR = hierarchy.maxRstat(linkage_table, inconsistent.values, 1) clusters = hierarchy.fcluster(linkage_table, t = cutoff, criterion = 'monocrit', monocrit = MR) return clusters
