def findClusters(mlist_name, clist_name, eps, mc, ignore_z = True, ignore_category = True):
# Load the data.
pix_to_nm = 160.0
i3_data_in = readinsight3.loadI3GoodOnly(mlist_name)
c = i3_data_in['c']
x = i3_data_in['xc']*pix_to_nm
y = i3_data_in['yc']*pix_to_nm
if ignore_z:
print("Warning! Clustering without using localization z value!")
z = numpy.zeros(x.size)
else:
z = i3_data_in['zc']
# Perform analysis without regard to category.
if ignore_category:
print("Warning! Clustering without regard to category!")
c = numpy.zeros(c.size)
# Cluster the data.
labels = dbscanC.dbscan(x, y, z, c, eps, mc, z_factor=1.0)
# Save the data.
i3_data_out = writeinsight3.I3Writer(clist_name)
i3dtype.setI3Field(i3_data_in, 'lk', labels)
i3_data_out.addMolecules(i3_data_in)
i3_data_out.close()
def findClusters(mlist_name, clist_name, eps, mc, ignore_z = True, ignore_category = True):
# Load the data.
pix_to_nm = 160.0
i3_data_in = readinsight3.loadI3GoodOnly(mlist_name)
c = i3_data_in['c']
x = i3_data_in['xc']*pix_to_nm
y = i3_data_in['yc']*pix_to_nm
if ignore_z:
print("Warning! Clustering without using localization z value!")
z = numpy.zeros(x.size)
else:
z = i3_data_in['zc']
# Perform analysis without regard to category.
if ignore_category:
print("Warning! Clustering without regard to category!")
c = numpy.zeros(c.size)
# Cluster the data.
labels = dbscanC.dbscan(x, y, z, c, eps, mc, z_factor=1.0)
# Save the data.
i3_data_out = writeinsight3.I3Writer(clist_name)
i3dtype.setI3Field(i3_data_in, 'lk', labels)
i3_data_out.addMolecules(i3_data_in)
i3_data_out.close()
def findClusters(h5_name, eps, mc, ignore_z = True, ignore_category = True, z_factor = 1.0):
"""
Perform DBSCAN clustering on an HDF5 localization file.
h5_name - The name of the HDF5 file.
eps - DBSCAN epsilon parameter (in nanometers).
mc - DBSCAN mc parameter.
ignore_z - Ignore localization z position when clustering.
ignore_category - Ignore localization category when clustering.
z_factor - Weighting of Z versus X/Y position. A value of 0.5 for
example will make the clustering 1/2 as sensitive to
Z position.
Note: Because all the x/y/z location information must be loaded
into memory for the DBSCAN algorithm there is a limit to
the size of localization file that can be clustered.
"""
with clSAH5Py.SAH5Clusters(h5_name) as cl_h5:
[x, y, z, c, cl_dict] = cl_h5.getDataForClustering()
if ignore_z:
print("Warning! Clustering without using localization z value!")
# Perform analysis without regard to category.
if ignore_category:
print("Warning! Clustering without regard to category!")
c = numpy.zeros(c.size)
# Convert data to nanometers
pix_to_nm = cl_h5.getPixelSize()
x_nm = x * pix_to_nm
y_nm = y * pix_to_nm
if ignore_z:
z_nm = numpy.zeros(z.size)
else:
z_nm = 1000.0 * z
# Cluster the data.
labels = dbscanC.dbscan(x_nm, y_nm, z_nm, c, eps, mc, z_factor = z_factor)
# Save the data. As an optimization we also save the x,y,z and
# category values for each cluster with the cluster. Note that
# these are the original units x/y in pixels and z in microns,
# not the nanometer values used for clustering.
#
cl_dict["x"] = x
cl_dict["y"] = y
cl_dict["z"] = z
cl_dict["category"] = c
cl_h5.addClusters(labels, cl_dict)
# Save clustering info.
info = "dbscan,eps,{0:0.3f},mc,{1:d}".format(eps,mc)
info += ",iz," + str(ignore_z)
info += ",ic," + str(ignore_category)
info += ",zf,{0:3f}".format(z_factor)
cl_h5.setClusteringInfo(info)
def test_dbscan1():
from storm_analysis.dbscan.dbscan_c import dbscan
x = numpy.random.random(20)
y = numpy.random.random(20)
z = numpy.zeros(20)
c = numpy.zeros(20)
clusters = dbscan(x, y, z, c, 1.0, 10)
for elt in clusters:
assert (elt == 2)
if False:
z = i3_data_in['zc']
else:
print "Warning! Clustering without using localization z value!"
z = numpy.zeros(x.size)
# Perform analysis without regard to category.
if True:
print "Warning! Clustering without regard to category!"
c = numpy.zeros(c.size)
# Cluster the data.
if (len(sys.argv) == 4):
print "Using eps =", sys.argv[2], "mc =", sys.argv[3]
labels = dbscanC.dbscan(x,
y,
z,
c,
float(sys.argv[2]),
int(sys.argv[3]),
z_factor=1.0)
else:
print "Using eps = 80, mc = 5"
labels = dbscanC.dbscan(x, y, z, c, 80.0, 5, z_factor=1.0)
# Save the data.
i3_data_out = writeinsight3.I3Writer(sys.argv[1][:-8] + "clusters_list.bin")
i3dtype.setI3Field(i3_data_in, 'lk', labels)
i3_data_out.addMolecules(i3_data_in)
i3_data_out.close()