def overlap_summary(groupbydata, valuedata, fieldmapping=[]):
# prep
data1,data2 = groupbydata,valuedata
if fieldmapping: aggfields,aggtypes = zip(*fieldmapping)
aggfunctions = dict([("count",len),
("sum",sum),
("max",max),
("min",min),
("average",lambda seq: sum(seq)/float(len(seq)) ) ])
# create spatial index
if not hasattr(data1, "spindex"): data1.create_spatial_index()
if not hasattr(data2, "spindex"): data2.create_spatial_index()
# create new
new = GeoTable()
new.fields = list(data1.fields)
if fieldmapping:
for aggfield,aggtype in fieldmapping:
new.fields.append(aggfield)
# for each groupby feature
for i,feat in enumerate(data1.quick_overlap(data2.bbox)):
geom = geoj2shapely(feat.geometry)
geom = supershapely(geom)
matches = []
# get all value features that intersect
for otherfeat in data2.quick_overlap(feat.bbox):
othergeom = geoj2shapely(otherfeat.geometry)
if geom.intersects(othergeom):
matches.append(otherfeat)
# make newrow from original row
newrow = list(feat.row)
# if any matches
if matches:
def make_number(value):
try: return float(value)
except: return None
# add summary values to newrow based on fieldmapping
for aggfield,aggtype in fieldmapping:
values = [otherfeat[aggfield] for otherfeat in matches]
if aggtype in ("sum","max","min","average"):
# only consider number values if numeric stats
values = [make_number(value) for value in values if make_number(value) != None]
aggregatefunc = aggfunctions[aggtype]
summaryvalue = aggregatefunc(values)
newrow.append(summaryvalue)
# otherwise, add empty values
else:
newrow.extend(("" for _ in fieldmapping))
# write feature to output
new.add_feature(newrow, feat.geometry)
return new
def vector_clean(data, tolerance=0):
"""Cleans the vector data of unnecessary clutter such as repeat
points or closely related points within the distance specified in the
'tolerance' parameter. Also tries to fix any broken geometries, dropping
any unfixable ones.
Adds the resulting cleaned data to the layers list.
"""
# create new file
outfile = GeoTable()
outfile.fields = list(data.fields)
# clean
for feat in data:
shapelyobj = geoj2shapely(feat.geometry)
# try fixing invalid geoms
if not shapelyobj.is_valid:
if "Polygon" in shapelyobj.type:
# fix bowtie polygons
shapelyobj = shapelyobj.buffer(0.0)
# remove repeat points (tolerance=0)
# (and optionally smooth out complex shapes, tolerance >= 1)
shapelyobj = shapelyobj.simplify(tolerance)
# if still invalid, do not add to output
if not shapelyobj.is_valid:
continue
# write to file
geoj = shapely2geoj(shapelyobj)
outfile.add_feature(feat.row, geoj)
return outfile
def vector_spatialjoin(data1, data2, joincondition, radius=None):
"""Possible joinconditions:
intersects, within, contains, crosses, touches, equals
Also:
distance
"""
# create spatial index
if not hasattr(data1, "spindex"): data1.create_spatial_index()
if not hasattr(data2, "spindex"): data2.create_spatial_index()
# create new
new = GeoTable()
new.fields = list(data1.fields)
new.fields.extend(data2.fields)
# intersect each feat in first with all others
if joincondition in ("distance", ):
new.fields.append("DISTANCE")
if joincondition == "distance" and radius is None:
raise Exception("radius arg must be set when using distance mode")
maxnum = 9223372036854775807
for feat in data1.quick_nearest(data2.bbox, n=maxnum):
geom = geoj2shapely(feat.geometry)
matchtest = getattr(geom, "distance")
for otherfeat in data2.quick_nearest(feat.bbox, n=maxnum):
othergeom = geoj2shapely(otherfeat.geometry)
match = matchtest(othergeom)
if match <= radius:
joined = list(feat.row)
joined.extend(otherfeat.row)
joined.append(match)
print "match", match
new.add_feature(joined, feat.geometry)
else:
for feat in data1.quick_overlap(data2.bbox):
geom = geoj2shapely(feat.geometry)
matchtest = getattr(geom, joincondition)
for otherfeat in data2.quick_overlap(feat.bbox):
othergeom = geoj2shapely(otherfeat.geometry)
match = matchtest(othergeom)
if match:
joined = list(feat.row)
joined.extend(otherfeat.row)
print "match", len(joined)
new.add_feature(joined, feat.geometry)
return new
def vector_spatialjoin(data1, data2, joincondition, radius=None):
"""Possible joinconditions:
intersects, within, contains, crosses, touches, equals
Also:
distance
"""
# create spatial index
if not hasattr(data1, "spindex"): data1.create_spatial_index()
if not hasattr(data2, "spindex"): data2.create_spatial_index()
# create new
new = GeoTable()
new.fields = list(data1.fields)
new.fields.extend(data2.fields)
# intersect each feat in first with all others
if joincondition in ("distance",):
new.fields.append("DISTANCE")
if joincondition == "distance" and radius is None: raise Exception("radius arg must be set when using distance mode")
maxnum = 9223372036854775807
for feat in data1.quick_nearest(data2.bbox, n=maxnum):
geom = geoj2shapely(feat.geometry)
matchtest = getattr(geom, "distance")
for otherfeat in data2.quick_nearest(feat.bbox, n=maxnum):
othergeom = geoj2shapely(otherfeat.geometry)
match = matchtest(othergeom)
if match <= radius:
joined = list(feat.row)
joined.extend(otherfeat.row)
joined.append(match)
print "match", match
new.add_feature(joined, feat.geometry)
else:
for feat in data1.quick_overlap(data2.bbox):
geom = geoj2shapely(feat.geometry)
matchtest = getattr(geom, joincondition)
for otherfeat in data2.quick_overlap(feat.bbox):
othergeom = geoj2shapely(otherfeat.geometry)
match = matchtest(othergeom)
if match:
joined = list(feat.row)
joined.extend(otherfeat.row)
print "match", len(joined)
new.add_feature(joined, feat.geometry)
return new
def _to_centroids(data):
"""create one centroid point for each multi geometry part"""
# create new file
outfile = GeoTable()
outfile.fields = list(data.fields)
# loop features
for feat in data:
if feat.geometry["type"] != "Point":
shapelypoint = geoj2shapely(feat.geometry).centroid
geoj = shapely2geoj(shapelypoint)
outfile.add_feature(feat.row, geoj)
return outfile
def vector_buffer(data, dist_expression):
# buffer and change each geojson dict in-place
new = GeoTable()
new.fields = list(data.fields)
for feat in data:
geom = geoj2shapely(feat.geometry)
dist = eval(dist_expression)
buffered = geom.buffer(dist)
if not buffered.is_empty:
geoj = shapely2geoj(buffered)
geoj["type"] = buffered.type
new.add_feature(feat.row, geoj)
# change data type to polygon
new.type = "Polygon"
return new
def vector_buffer(data, dist_expression):
# buffer and change each geojson dict in-place
new = GeoTable()
new.fields = list(data.fields)
for feat in data:
geom = geoj2shapely(feat.geometry)
dist = eval(dist_expression)
buffered = geom.buffer(dist)
if not buffered.is_empty:
geoj = shapely2geoj(buffered)
geoj["type"] = buffered.type
new.add_feature(feat.row, geoj)
# change data type to polygon
new.type = "Polygon"
return new
def _to_multicentroids(data):
"""create multiple centroid points for each multi geometry part"""
# create new file
outfile = GeoTable()
outfile.fields = list(data.fields)
# loop features
if "LineString" in data.type or "Polygon" in data.type:
for feat in data:
if "Multi" in feat.geometry["type"]:
multishape = geoj2shapely(feat.geometry)
for geom in multishape.geoms:
shapelypoint = geom.centroid
geoj = shapely2geoj(shapelypoint)
outfile.add_feature(feat.row, geoj)
else:
shapelypoint = geoj2shapely(feat.geometry).centroid
geoj = shapely2geoj(shapelypoint)
outfile.add_feature(feat.row, geoj)
return outfile
else:
return data.copy()
def overlap_summary(groupbydata, valuedata, fieldmapping=[]):
# prep
data1, data2 = groupbydata, valuedata
if fieldmapping: aggfields, aggtypes = zip(*fieldmapping)
aggfunctions = dict([("count", len), ("sum", sum), ("max", max),
("min", min),
("average", lambda seq: sum(seq) / float(len(seq)))])
# create spatial index
if not hasattr(data1, "spindex"): data1.create_spatial_index()
if not hasattr(data2, "spindex"): data2.create_spatial_index()
# create new
new = GeoTable()
new.fields = list(data1.fields)
if fieldmapping:
for aggfield, aggtype in fieldmapping:
new.fields.append(aggfield)
# for each groupby feature
for i, feat in enumerate(data1.quick_overlap(data2.bbox)):
geom = geoj2shapely(feat.geometry)
geom = supershapely(geom)
matches = []
# get all value features that intersect
for otherfeat in data2.quick_overlap(feat.bbox):
othergeom = geoj2shapely(otherfeat.geometry)
if geom.intersects(othergeom):
matches.append(otherfeat)
# make newrow from original row
newrow = list(feat.row)
# if any matches
if matches:
def make_number(value):
try:
return float(value)
except:
return None
# add summary values to newrow based on fieldmapping
for aggfield, aggtype in fieldmapping:
values = [otherfeat[aggfield] for otherfeat in matches]
if aggtype in ("sum", "max", "min", "average"):
# only consider number values if numeric stats
values = [
make_number(value) for value in values
if make_number(value) != None
]
aggregatefunc = aggfunctions[aggtype]
summaryvalue = aggregatefunc(values)
newrow.append(summaryvalue)
# otherwise, add empty values
else:
newrow.extend(("" for _ in fieldmapping))
# write feature to output
new.add_feature(newrow, feat.geometry)
return new
def vector_to_polygons(data, polytype="convex hull"):
# create new file
outfile = GeoTable()
outfile.fields = list(data.fields)
if polytype == "convex hull":
for feat in data:
shapelygeom = geoj2shapely(feat.geometry)
convex = shapelygeom.convex_hull
geoj = shapely2geoj(convex)
# sometimes the convex hull is only a line or point
# but we cannot mix shapetypes, so exclude those
if geoj["type"] == "Polygon":
outfile.add_feature(feat.row, geoj)
return outfile
elif polytype == "delauney triangles":
if "Point" in data.type:
def get_flattened_points():
for feat in data:
if "Multi" in feat.geometry["type"]:
for point in feat.geometry["coordinates"]:
yield point
else: yield feat.geometry["coordinates"]
triangles = pytess.triangulate(get_flattened_points())
# triangle polygons are between multiple existing points,
# so do not inherit any attributes
for tri in triangles:
geoj = {"type": "Polygon",
"coordinates": [tri] }
row = ["" for field in outfile.fields]
outfile.add_feature(row, geoj)
return outfile
else:
raise Exception("Delauney triangles can only be made from point data")
elif polytype == "voronoi polygons":
if "Point" in data.type:
def get_flattened_points():
for feat in data:
if "Multi" in feat.geometry["type"]:
for point in feat.geometry["coordinates"]:
yield point
else: yield feat.geometry["coordinates"]
results = pytess.voronoi(get_flattened_points())
# return new file with polygon geometries
for midpoint,polygon in results:
geoj = {"type": "Polygon",
"coordinates": [polygon] }
row = ["" for field in outfile.fields]
outfile.add_feature(row, geoj)
return outfile
else:
raise Exception("Voronoi polygons can only be made from point data")
elif polytype == "enclose lines":
if "LineString" in data.type:
shapelylines = (geoj2shapely(feat.geometry) for feat in data)
for polygon in shapely.ops.polygonize(shapelylines):
geoj = shapely2geoj(polygon)
row = ["" for field in outfile.fields]
outfile.add_feature(row, geoj)
return outfile
else:
raise Exception("Enclose lines can only be done on line data")
