def dist_mat(self, metric='euclidean', transpose=True):
'''
Return a MD square distance matrix corresponding to distance between rows
'''
import distances
if transpose: data = self.transpose()
else: data = self.transpose()
mat, row_labels, col_labels = data.to_matrix()
D_mat = distances.pdist(mat, metric)
D = MatrixDictionary()
D.from_matrix(D_mat, row_labels, row_labels)
return D
def dist_mat(self, metric ='euclidean', transpose = True):
'''
Return a MD square distance matrix corresponding to distance between rows
'''
import distances
if transpose: data = self.transpose()
else: data = self.transpose()
mat, row_labels, col_labels = data.to_matrix()
D_mat = distances.pdist(mat, metric)
D = MatrixDictionary()
D.from_matrix(D_mat, row_labels, row_labels)
return D
def plot_dist_mat(self, metric ='euclidean', file = None, transpose = True, show_labels = False, **kwargs):
import distances
from heatmap_clust import clust_data, heatmap_clust
matrix, row_labels, col_labels = self.to_matrix()
if transpose:
mat = matrix.transpose()
labels = map(lambda s: s.split('_')[-1], col_labels)
else:
mat = matrix
labels = map(lambda s: s.split('_')[-1], row_labels)
D = distances.pdist(mat, metric)
if show_labels: heatmap_clust(D, file = file, labels =labels, **kwargs)
else: heatmap_clust(D, file = file, **kwargs)
def plot_dist_mat(self, metric ='euclidean', file = None, transpose = True, show_labels = False, **kwargs):
import distances
from heatmap_clust import clust_data, heatmap_clust
matrix, row_labels, col_labels = self.to_matrix()
if transpose:
mat = matrix.transpose()
labels = map(lambda s: s.split('_')[-1], col_labels)
else:
mat = matrix
labels = map(lambda s: s.split('_')[-1], row_labels)
D = distances.pdist(mat, metric)
if show_labels: heatmap_clust(D, file = file, labels =labels, **kwargs)
else: heatmap_clust(D, file = file, **kwargs)
def fuzzy_clustering(self, k, r = 2, metric = 'euclidean', rows = True):
'''
Perform fuzzy c-means clustering on rows or cols.
k = number of clusters.
r = fuzziness exponent. Less fuzzy as r -> 1.
'''
import scipy.cluster.hierarchy as sch
from R_utilities import c_means
import distances
if rows: matrix, row_labels, col_labels = self.to_matrix()
else: matrix, row_labels, col_labels = self.transpose().to_matrix()
D = distances.pdist(matrix, metric)
## cluster each row and return a dict of cluster membership
memb, memb_hard, stats = c_means(D,k,r, diss = True)
membership = MatrixDictionary()
membership.from_matrix(memb, row_labels, range(1,k+1))
membership_hard = {}
for row, m in zip(row_labels, memb_hard): membership_hard[row] = m
return membership, membership_hard, stats
def fuzzy_clustering(self, k, r = 2, metric = 'euclidean', rows = True):
'''
Perform fuzzy c-means clustering on rows or cols.
k = number of clusters.
r = fuzziness exponent. Less fuzzy as r -> 1.
'''
import scipy.cluster.hierarchy as sch
from R_utilities import c_means
import distances
if rows: matrix, row_labels, col_labels = self.to_matrix()
else: matrix, row_labels, col_labels = self.transpose().to_matrix()
D = distances.pdist(matrix, metric)
## cluster each row and return a dict of cluster membership
memb, memb_hard, stats = c_means(D,k,r, diss = True)
membership = MatrixDictionary()
membership.from_matrix(memb, row_labels, range(1,k+1))
membership_hard = {}
for row, m in zip(row_labels, memb_hard): membership_hard[row] = m
return membership, membership_hard, stats
