def compute_table_coordinates(self, xthresh=8., ythresh=8.):
"""
Sorts all clusters into spreadsheet-like x/y coordinates.
Set self.cell_table_coord of shape (0, n)
"""
center_x = self.cell_centers[:, 0]
center_y = self.cell_centers[:, 1]
# Compute adjacency list
hgroup_adjlist, vgroup_adjlist = {}, {}
for i in range(center_x.shape[0]):
hgroup_adjlist[i] = np.nonzero(
np.abs(center_x - center_x[i]) < xthresh)[0]
vgroup_adjlist[i] = np.nonzero(
np.abs(center_y - center_y[i]) < ythresh)[0]
# Compute transitive closures so we get ALL grouped cells for each group,
# not just the ones that are similar to the first node.
hgroups, hgroup_lut = transitive_closure(hgroup_adjlist)
vgroups, vgroup_lut = transitive_closure(vgroup_adjlist)
####
# Reorder groups by x/y
####
# Compute mean X/Y coords for each hgroup/vgroup
hgroup_mean_centers = np.zeros(len(hgroups))
vgroup_mean_centers = np.zeros(len(vgroups))
for i, st in enumerate(hgroups):
hgroup_mean_centers[i] = np.mean(self.cell_centers[list(st)][:, 0])
for i, st in enumerate(vgroups):
vgroup_mean_centers[i] = np.mean(self.cell_centers[list(st)][:, 1])
# Find the sorted ordering (like in a spreadsheet) for both x and y coords
hgroup_sort_order = np.argsort(hgroup_mean_centers)
vgroup_sort_order = np.argsort(vgroup_mean_centers)
# Output of argsort: Input => new index ; output => old index
# BUT WE NEED: Input oldplace, output newplace
hgroup_sort_order = invert_bijection(hgroup_sort_order)
vgroup_sort_order = invert_bijection(vgroup_sort_order)
# Reorder everything based on the new order
hgroups = multiselect(hgroups, hgroup_sort_order)
vgroups = multiselect(vgroups, vgroup_sort_order)
# Convert LUTs
hgroup_lut = hgroup_sort_order[hgroup_lut]
vgroup_lut = vgroup_sort_order[vgroup_lut]
# Build a (n, (tx,ty)) table coordinate LUT for all nodes
self.cell_table_coord = np.dstack([hgroup_lut, vgroup_lut])[0]
# Build index of table coordinates to node ID
self.table_coords_to_node = {}
for i, (x, y) in enumerate(self.cell_table_coord):
self.table_coords_to_node[(x, y)] = i
def compute_table_coordinates(self, xthresh=8., ythresh=8.):
"""
Sorts all clusters into spreadsheet-like x/y coordinates.
Set self.cell_table_coord of shape (0, n)
"""
center_x = self.cell_centers[:, 0]
center_y = self.cell_centers[:, 1]
# Compute adjacency list
hgroup_adjlist, vgroup_adjlist = {}, {}
for i in range(center_x.shape[0]):
hgroup_adjlist[i] = np.nonzero(np.abs(center_x - center_x[i]) < xthresh)[0]
vgroup_adjlist[i] = np.nonzero(np.abs(center_y - center_y[i]) < ythresh)[0]
# Compute transitive closures so we get ALL grouped cells for each group,
# not just the ones that are similar to the first node.
hgroups, hgroup_lut = transitive_closure(hgroup_adjlist)
vgroups, vgroup_lut = transitive_closure(vgroup_adjlist)
####
# Reorder groups by x/y
####
# Compute mean X/Y coords for each hgroup/vgroup
hgroup_mean_centers = np.zeros(len(hgroups))
vgroup_mean_centers = np.zeros(len(vgroups))
for i, st in enumerate(hgroups):
hgroup_mean_centers[i] = np.mean(self.cell_centers[list(st)][:, 0])
for i, st in enumerate(vgroups):
vgroup_mean_centers[i] = np.mean(self.cell_centers[list(st)][:, 1])
# Find the sorted ordering (like in a spreadsheet) for both x and y coords
hgroup_sort_order = np.argsort(hgroup_mean_centers)
vgroup_sort_order = np.argsort(vgroup_mean_centers)
# Output of argsort: Input => new index ; output => old index
# BUT WE NEED: Input oldplace, output newplace
hgroup_sort_order = invert_bijection(hgroup_sort_order)
vgroup_sort_order = invert_bijection(vgroup_sort_order)
# Reorder everything based on the new order
hgroups = multiselect(hgroups, hgroup_sort_order)
vgroups = multiselect(vgroups, vgroup_sort_order)
# Convert LUTs
hgroup_lut = hgroup_sort_order[hgroup_lut]
vgroup_lut = vgroup_sort_order[vgroup_lut]
# Build a (n, (tx,ty)) table coordinate LUT for all nodes
self.cell_table_coord = np.dstack([hgroup_lut, vgroup_lut])[0]
# Build index of table coordinates to node ID
self.table_coords_to_node = {}
for i, (x, y) in enumerate(self.cell_table_coord):
self.table_coords_to_node[(x, y)] = i
def compute_cell_polygons(self):
"""
Compute a list of cell polygons from the contours and the associated
corner clusters. Generates a list of cells, with a cell being a list of
cluster IDs. This list is stored in self.cell_polygons
"""
cell_polygons = []
for i in range(len(self.contours)):
# Skip invalidated contours
if self.contours[i] is None: continue
bbox = self.contours_bbox[i] # Guaranteed to have 4 nodes by design (it's a bounding box)!
# bbox == corner1, ..., corner4
bclust = multiselect(self.cluster_coords_to_node_id, bbox, convert=tuple)
cell_polygons.append(bclust)
self.cell_polygons = cell_polygons
def filter_shapes_by_total_area_threshold(points, pivots, threshold=.005):
"""
Split a given point list by a pivot list to obtain a list
of polygons.
then filter out polygons that have less than the given fraction of
the total area.
"""
parts = list(split_by_pivot(points, pivots))
partareas = np.zeros(len(parts))
# Compute all part areas
for i, part in enumerate(parts):
partareas[i] = polygon_area(part)
total_area = np.sum(partareas)
# Find areas below the threshold
idxs = np.where(partareas > threshold * total_area)[0]
# Select from parts list
return multiselect(parts, idxs)