def add_clusters(df_cells, neighbor_dist=50):
"""Assigns -1 to clusters with only one cell.
"""
from scipy.spatial.kdtree import KDTree
import networkx as nx
x = df_cells[GLOBAL_X] + df_cells[POSITION_J]
y = df_cells[GLOBAL_Y] + df_cells[POSITION_I]
barcodes = df_cells[BARCODE_0]
barcodes = np.array(barcodes)
kdt = KDTree(np.array([x, y]).T)
num_cells = len(df_cells)
print('searching for clusters among %d cells' % num_cells)
pairs = kdt.query_pairs(neighbor_dist)
pairs = np.array(list(pairs))
x = barcodes[pairs]
y = x[:, 0] == x[:, 1]
G = nx.Graph()
G.add_edges_from(pairs[y])
clusters = list(nx.connected_components(G))
cluster_index = np.zeros(num_cells, dtype=int) - 1
for i, c in enumerate(clusters):
cluster_index[list(c)] = i
df_cells[CLUSTER] = cluster_index
return df_cells
def _merge(self, roi):
points = [ e[2] for e in roi ]
tree = KDTree(points)
pp = tree.query_pairs(4)
#pp = sorted( pp , key=lambda e: max(roi[e[0]] , roi[e[1]]), reverse=True)
skips = set()
for i,j in pp:
if self.Debug:
print '%s(%.2f),%s(%.2f)'%(roi[i][0],roi[i][1], roi[j][0], roi[j][1] )
if i in skips or j in skips: continue
skip = i if roi[i][1]<roi[j][1] else j
skips.add(skip)
rs = ( e for i, e in enumerate(roi) if not i in skips )
rs = sorted( rs , key=lambda e: e[1] )[-4:]
return sorted( rs, key=lambda e: e[2][1] )
def _merge(self, roi):
points = [e[2] for e in roi]
tree = KDTree(points)
pp = tree.query_pairs(4)
#pp = sorted( pp , key=lambda e: max(roi[e[0]] , roi[e[1]]), reverse=True)
skips = set()
for i, j in pp:
if self.Debug:
print '%s(%.2f),%s(%.2f)' % (roi[i][0], roi[i][1], roi[j][0],
roi[j][1])
if i in skips or j in skips: continue
skip = i if roi[i][1] < roi[j][1] else j
skips.add(skip)
rs = (e for i, e in enumerate(roi) if not i in skips)
rs = sorted(rs, key=lambda e: e[1])[-4:]
return sorted(rs, key=lambda e: e[2][1])
def add_clusters(df_cells,
barcode_col=BARCODE_0,
radius=50,
verbose=True,
ij=(POSITION_I, POSITION_J)):
"""Assigns -1 to clusters with only one cell.
"""
from scipy.spatial.kdtree import KDTree
import networkx as nx
I, J = ij
x = df_cells[GLOBAL_X] + df_cells[J]
y = df_cells[GLOBAL_Y] + df_cells[I]
barcodes = df_cells[barcode_col]
barcodes = np.array(barcodes)
kdt = KDTree(np.array([x, y]).T)
num_cells = len(df_cells)
if verbose:
message = 'searching for clusters among {} {} objects'
print(message.format(num_cells, barcode_col))
pairs = kdt.query_pairs(radius)
pairs = np.array(list(pairs))
x = barcodes[pairs]
y = x[:, 0] == x[:, 1]
G = nx.Graph()
G.add_edges_from(pairs[y])
clusters = list(nx.connected_components(G))
cluster_index = np.zeros(num_cells, dtype=int) - 1
for i, c in enumerate(clusters):
cluster_index[list(c)] = i
df_cells = df_cells.copy()
df_cells[CLUSTER] = cluster_index
df_cells[CLUSTER_SIZE] = (
df_cells.groupby(CLUSTER)[barcode_col].transform('size'))
df_cells.loc[df_cells[CLUSTER] == -1, CLUSTER_SIZE] = 1
return df_cells
