Python Pool.coord_range方法代码示例

# 需要导入模块: from ZIBMolPy.pool import Pool [as 别名]
# 或者: from ZIBMolPy.pool.Pool import coord_range [as 别名]

#.........这里部分代码省略.........
	# orthogonalize and normalize eigenvectors 
	eigvectors = orthogonalize(eigvalues, eigvectors, corr_node_weights)

	# perform PCCA+
	# First two return-values "c_f" and "indicator" are not needed
	(chi_matrix, rot_matrix) = cluster_by_isa(eigvectors, n_clusters)[2:]

	if(options.optimize_chi):
		print "\n### Optimizing chi matrix ..."
		
		outliers = 5
		mean_weight = np.mean(corr_node_weights)
		threshold = mean_weight/100*outliers
		print "Light-weight node threshold (%d%% of mean corrected node weight): %.4f."%(outliers, threshold)

		# accumulate nodes for optimization
		edges = np.where(np.max(chi_matrix, axis=1) > 0.9999)[0] # edges of simplex
		heavies = np.where( corr_node_weights > threshold)[0] # heavy-weight nodes
		filtered_eigvectors = eigvectors[ np.union1d(edges, heavies) ]

		# perform the actual optimization
		rot_matrix = opt_soft(filtered_eigvectors, rot_matrix, n_clusters)

		chi_matrix = np.dot(eigvectors[:,:n_clusters], rot_matrix)
		
		# deal with light-weight nodes: shift and scale
		for i in np.where(corr_node_weights <= threshold)[0]:
			if(i in edges):
				print "Column %d belongs to (potentially dangerous) light-weight node, but its node is a simplex edge."%(i+1)
				continue
			print "Column %d is shifted and scaled."%(i+1)
			col_min = np.min( chi_matrix[i,:] )
			chi_matrix[i,:] -= col_min
			chi_matrix[i,:] /= 1-(n_clusters*col_min)
			
	qc_matrix = np.dot( np.dot( np.linalg.inv(rot_matrix), np.diag(eigvalues[range(n_clusters)]) ), rot_matrix ) - np.eye(n_clusters)
	cluster_weights = rot_matrix[0]
	
	print "\n### Matrix numerics check"
	print "-- Q_c matrix row sums --"
	print np.sum(qc_matrix, axis=1)
	print "-- cluster weights: first column of rot_matrix --"
	print cluster_weights
	print "-- cluster weights: numpy.dot(node_weights, chi_matrix) --"
	print np.dot(corr_node_weights, chi_matrix)
	print "-- chi matrix column max values --"
	print np.max(chi_matrix, axis=0)
	print "-- chi matrix row sums --"
	print np.sum(chi_matrix, axis=1)

	# store final results
	np.savez(pool.chi_mat_fn, matrix=chi_matrix, n_clusters=n_clusters, node_names=[n.name for n in active_nodes])
	np.savez(pool.qc_mat_fn,  matrix=qc_matrix,  n_clusters=n_clusters, node_names=[n.name for n in active_nodes], weights=cluster_weights)

	if options.export_matlab:		
		savemat(pool.analysis_dir+"chi_mat.mat", {"chi_matrix":chi_matrix})
		savemat(pool.analysis_dir+"qc_mat.mat", {"qc_matrix":qc_matrix, "weights":cluster_weights})

	register_file_dependency(pool.chi_mat_fn, pool.s_corr_mat_fn)
	register_file_dependency(pool.qc_mat_fn, pool.s_corr_mat_fn)

	for fn in (pool.s_mat_fn, pool.s_corr_mat_fn):
		register_file_dependency(pool.chi_mat_fn, fn)
		register_file_dependency(pool.qc_mat_fn, fn)

	# touch analysis directory (triggering update in zgf_browser)
	atime = mtime = time.time()
	os.utime(pool.analysis_dir, (atime, mtime))

	# show summary
	if(options.summary):
		print "\n### Preparing cluster summary ..."
		chi_threshold = 1E-3
		from pprint import pformat
	
		for i in range(n_clusters):
			involved_nodes = [active_nodes[ni] for ni in np.argwhere(chi_matrix[:,i] > chi_threshold)]
			max_chi_node = active_nodes[ np.argmax(chi_matrix[:,i]) ]
			c_max = []

			for c in  pool.converter:
				coord_range = pool.coord_range(c)
				scale = c.plot_scale
				edges = scale(np.linspace(np.min(coord_range), np.max(coord_range), num=50))
				hist_cluster = np.zeros(edges.size-1)

				for (n, chi) in zip([n for n in active_nodes], chi_matrix[:,i]):
					samples = scale( n.trajectory.getcoord(c) )
					hist_node = np.histogram(samples, bins=edges, weights=n.frameweights, normed=True)[0]
					hist_cluster += n.obs.weight_corrected * hist_node * chi

				c_max.append( scale(np.linspace(np.min(coord_range), np.max(coord_range), num=50))[np.argmax(hist_cluster)] )

			msg = "### Cluster %d (weight=%.4f, #involved nodes=%d, representative='%s'):"%(i+1, cluster_weights[i], len(involved_nodes), max_chi_node.name)
			print "\n"+msg
			print "-- internal coordinates --"
			print "%s"%pformat(["%.2f"%cm for cm in c_max])
			print "-- involved nodes --"
			print "%s"%pformat([n.name for n in involved_nodes])			
			print "-"*len(msg)