class StreetIndex(object):
def __init__(self, streets_file):
self.idx = Index()
with open(streets_file) as f:
for line in f.readlines():
street = json.loads(line)
street_id = street['properties']['id']
street_shape = asShape(street['geometry'])
for i in range(len(street_shape.geoms)):
seg_id = self.encode_seg_id(i, street_id)
self.idx.insert(seg_id, street_shape.geoms[i].coords[0])
self.idx.insert(-seg_id, street_shape.geoms[i].coords[-1])
self.bb_idx = Index()
with open(streets_file) as f:
for line in f.readlines():
street = json.loads(line)
street_id = int(street['properties']['id'])
street_shape = asShape(street['geometry'])
self.bb_idx.insert(street_id, list(street_shape.bounds))
def encode_seg_id(self, i, street_id):
return i * 1000000 + int(street_id)
def decode_seg_id(self, seg_id):
i = abs(seg_id) / 1000000
return abs(seg_id) - i
def find_nearest_street(self, shape):
shape = asShape(shape['geometry'])
shape_type = shape.geom_type
if shape_type == 'Polygon' or shape_type == 'MultiPolygon':
ref_point = (
float(shape.centroid.coords.xy[0][0]),
float(shape.centroid.coords.xy[1][0])
)
else:
ref_point = (
float(shape.coords.xy[0][0]),
float(shape.coords.xy[1][0])
)
street_id = list(self.bb_idx.nearest(ref_point))[0]
return str(street_id)
def find_connected_street(self, street):
street_id = int(street['properties']['id'])
street_shape = asShape(street['geometry'])
street_start = street_shape.geoms[0].coords[0]
street_end = street_shape.geoms[-1].coords[-1]
seg_ids = list(self.idx.intersection(street_start))
seg_ids += list(self.idx.intersection(street_end))
street_ids = set(map(self.decode_seg_id, seg_ids))
if street_id in street_ids:
street_ids.remove(street_id)
return street_ids
def snap_to_edge_position(gdf, points, k=3, rtree=None):
"""
Snap given points in the plane to edges in GeoDataFrame of edges.
Parameters
----------
gdf : GeoDataframe
The edges of spatial network as a Geodataframe.
points : array of floats, shape (M, 2)
The cartesian coordinates of the points to be snapped.
k : integer, optional
Number of nearest edges to consider.
Returns
-------
nearest_edges : list of integers, length M
Indices of nearest edges in the GeoDataframe.
refdistances : list of floats, length M
Linear referencing distances of points along nearest edge.
"""
X, Y = points.T
geom = gdf["geometry"]
# If not passed, build the r-tree spatial index by position for subsequent iloc
if rtree == None:
rtree = RTreeIndex()
for pos, bounds in enumerate(geom.bounds.values):
rtree.insert(pos, bounds)
# use r-tree to find possible nearest neighbors, one point at a time,
# then minimize euclidean distance from point to the possible matches
nearest_edges = list()
refdistances = list()
for xy in zip(X, Y):
p = Point(xy)
dists = geom.iloc[list(rtree.nearest(xy, num_results=k))].distance(p)
ne = geom[dists.idxmin()]
nearest_edges.append(dists.idxmin())
refdistances.append(ne.project(p))
return nearest_edges, refdistances
def nearest_edges(G, X, Y, interpolate=None, return_dist=False):
"""
Find the nearest edge to a point or to each of several points.
If `X` and `Y` are single coordinate values, this will return the nearest
edge to that point. If `X` and `Y` are lists of coordinate values, this
will return the nearest edge to each point.
If `interpolate` is None, search for the nearest edge to each point, one
at a time, using an r-tree and minimizing the euclidean distances from the
point to the possible matches. For accuracy, use a projected graph and
points. This method is precise and also fastest if searching for few
points relative to the graph's size.
For a faster method if searching for many points relative to the graph's
size, use the `interpolate` argument to interpolate points along the edges
and index them. If the graph is projected, this uses a k-d tree for
euclidean nearest neighbor search, which requires that scipy is installed
as an optional dependency. If graph is unprojected, this uses a ball tree
for haversine nearest neighbor search, which requires that scikit-learn is
installed as an optional dependency.
Parameters
----------
G : networkx.MultiDiGraph
graph in which to find nearest edges
X : float or list
points' x (longitude) coordinates, in same CRS/units as graph and
containing no nulls
Y : float or list
points' y (latitude) coordinates, in same CRS/units as graph and
containing no nulls
interpolate : float
spacing distance between interpolated points, in same units as graph.
smaller values generate more points.
return_dist : bool
optionally also return distance between points and nearest edges
Returns
-------
ne or (ne, dist) : tuple or list
nearest edges as (u, v, key) or optionally a tuple where `dist`
contains distances between the points and their nearest edges
"""
is_scalar = False
if not (hasattr(X, "__iter__") and hasattr(Y, "__iter__")):
# make coordinates arrays if user passed non-iterable values
is_scalar = True
X = np.array([X])
Y = np.array([Y])
if np.isnan(X).any() or np.isnan(Y).any(): # pragma: no cover
raise ValueError("`X` and `Y` cannot contain nulls")
geoms = utils_graph.graph_to_gdfs(G, nodes=False)["geometry"]
# if no interpolation distance was provided
if interpolate is None:
# build the r-tree spatial index by position for subsequent iloc
rtree = RTreeIndex()
for pos, bounds in enumerate(geoms.bounds.values):
rtree.insert(pos, bounds)
# use r-tree to find possible nearest neighbors, one point at a time,
# then minimize euclidean distance from point to the possible matches
ne_dist = list()
for xy in zip(X, Y):
dists = geoms.iloc[list(rtree.nearest(xy))].distance(Point(xy))
ne_dist.append((dists.idxmin(), dists.min()))
ne, dist = zip(*ne_dist)
# otherwise, if interpolation distance was provided
else:
# interpolate points along edges to index with k-d tree or ball tree
uvk_xy = list()
for uvk, geom in zip(geoms.index, geoms.values):
uvk_xy.extend(
(uvk, xy)
for xy in utils_geo.interpolate_points(geom, interpolate))
labels, xy = zip(*uvk_xy)
vertices = pd.DataFrame(xy, index=labels, columns=["x", "y"])
if projection.is_projected(G.graph["crs"]):
# if projected, use k-d tree for euclidean nearest-neighbor search
if cKDTree is None: # pragma: no cover
raise ImportError(
"scipy must be installed to search a projected graph")
dist, pos = cKDTree(vertices).query(np.array([X, Y]).T, k=1)
ne = vertices.index[pos]
else:
# if unprojected, use ball tree for haversine nearest-neighbor search
if BallTree is None: # pragma: no cover
raise ImportError(
"scikit-learn must be installed to search an unprojected graph"
)
# haversine requires lat, lng coords in radians
vertices_rad = np.deg2rad(vertices[["y", "x"]])
points_rad = np.deg2rad(np.array([Y, X]).T)
dist, pos = BallTree(vertices_rad,
metric="haversine").query(points_rad, k=1)
dist = dist[:, 0] * EARTH_RADIUS_M # convert radians -> meters
ne = vertices.index[pos[:, 0]]
# convert results to correct types for return
ne = list(ne)
dist = list(dist)
if is_scalar:
ne = ne[0]
dist = dist[0]
if return_dist:
return ne, dist
else:
return ne
def parse_temperatures(database: SqliteUtil, tmin_files: List[str],
tmax_files: List[str], steps: int, day: int,
src_epsg: int, prj_epsg: int):
log.info('Allocating tables for air temperatures.')
create_tables(database)
files = zip(tmax_files, tmin_files)
profile_count = 0
point_count = 0
temperatures = []
points = []
profiles = {}
n = 1
transformer = Transformer.from_crs(f'epsg:{src_epsg}',
f'epsg:{prj_epsg}',
always_xy=True,
skip_equivalent=True)
project = transformer.transform
def apply(id: int, temp: Callable):
for step in range(steps):
prop = step / steps
row = (id, step, int(86400 * prop), temp(24 * prop))
yield row
log.info('Loading temperatures from netCDF4 files.')
for tmax_file, tmin_file in files:
tmaxnc = Dataset(tmax_file, 'r')
tminnc = Dataset(tmin_file, 'r')
lons = tmaxnc.variables['lon']
lats = tmaxnc.variables['lat']
shape = tmaxnc.variables['tmax'].shape
tmaxs = tmaxnc.variables['tmax'][day]
tmins = tminnc.variables['tmin'][day]
for i in range(shape[1]):
for j in range(shape[2]):
tmax = tmaxs[i][j]
tmin = tmins[i][j]
if tmax != -9999.0:
x, y = project(lons[i][j], lats[i][j])
idx = f'{tmax}-{tmin}'
if idx not in profiles:
temp = iterpolation(tmin, tmax, 5, 15)
temperatures.extend(apply(profile_count, temp))
profiles[idx] = profile_count
profile_count += 1
profile = profiles[idx]
point = Point(point_count, x, y, profile)
points.append(point)
point_count += 1
if point_count == n:
log.info(
f'Loading air temperature reading {point_count}.')
n <<= 1
tmaxnc.close()
tminnc.close()
if point_count != n >> 1:
log.info(f'Loading air temperature reading {point_count}.')
def load():
for point in points:
x, y = point.x, point.y
yield (point.id, (x, y, x, y), point.profile)
log.info('Starting network update for air temperatures.')
log.info('Building spatial index from temperature profile locations.')
index = Index(load())
used = set()
log.info('Loading network links.')
links = load_links(database)
log.info('Applying temperature profiles to links.')
iter_links = counter(links, 'Applying profile to link %s.')
for link in iter_links:
result = index.nearest((link.x, link.y, link.x, link.y), objects=True)
profile = next(result).object
link.air_temperature = profile
used.add(profile)
def dump_links():
for link in links:
yield (link.id, link.air_temperature)
log.info('Writing updated links to database.')
database.insert_values('temp_links', dump_links(), 2)
database.connection.commit()
del links
log.info('Loading network parcels.')
parcels = load_parcels(database)
residential = profile_count
temperatures.extend(apply(profile_count, lambda x: 26.6667))
profile_count += 1
commercial = profile_count
temperatures.extend(apply(profile_count, lambda x: 26.6667))
profile_count += 1
other = profile_count
temperatures.extend(apply(profile_count, lambda x: 26.6667))
profile_count += 1
used.add(residential)
used.add(commercial)
used.add(other)
log.info('Applying temperature profiles to parcels.')
iter_parcels = counter(parcels, 'Applying profile to parcel %s.')
for parcel in iter_parcels:
if not parcel.cooling:
x, y = xy(parcel.center)
result = index.nearest((x, y, x, y), objects=True)
profile = next(result).object
parcel.air_temperature = profile
used.add(profile)
elif parcel.kind == 'residential':
parcel.air_temperature = residential
elif parcel.kind == 'commercial':
parcel.air_temperature = commercial
else:
parcel.air_temperature = other
def dump_parcels():
for parcel in parcels:
yield (parcel.apn, parcel.air_temperature)
log.info('Writing updated parcels to database.')
database.insert_values('temp_parcels', dump_parcels(), 2)
database.connection.commit()
del parcels
def dump_temperatures():
for temp in temperatures:
if temp[0] in used:
yield temp
log.info('Writing parsed air temperatures to database.')
database.insert_values('air_temperatures', dump_temperatures(), 4)
database.connection.commit()
del temperatures
log.info('Merging, dropping and renaming old tables.')
query = '''
CREATE INDEX temp_links_link
ON temp_links(link_id);
'''
database.cursor.execute(query)
query = '''
CREATE TABLE temp_links_merged
AS SELECT
links.link_id,
links.source_node,
links.terminal_node,
links.length,
links.freespeed,
links.capacity,
links.permlanes,
links.oneway,
links.modes,
temp_links.air_temperature,
links.mrt_temperature
FROM links
INNER JOIN temp_links
USING(link_id);
'''
database.cursor.execute(query)
query = '''
CREATE INDEX temp_parcels_parcel
ON temp_parcels(apn);
'''
database.cursor.execute(query)
query = '''
CREATE TABLE temp_parcels_merged
AS SELECT
parcels.apn,
parcels.maz,
parcels.type,
parcels.cooling,
temp_parcels.air_temperature,
parcels.mrt_temperature,
parcels.center,
parcels.region
FROM parcels
INNER JOIN temp_parcels
USING(apn);
'''
database.cursor.execute(query)
original = database.count_rows('links')
merged = database.count_rows('temp_links_merged')
if original != merged:
log.error('Original links and updated links tables '
'do not align; quiting to prevent data loss.')
raise RuntimeError
else:
database.drop_table('links', 'temp_links')
query = '''
ALTER TABLE temp_links_merged
RENAME TO links;
'''
database.cursor.execute(query)
original = database.count_rows('parcels')
merged = database.count_rows('temp_parcels_merged')
if original != merged:
log.error('Original parcels and updated parcels tables '
'do not align; quiting to prevent data loss.')
raise RuntimeError
else:
database.drop_table('parcels', 'temp_parcels')
query = '''
ALTER TABLE temp_parcels_merged
RENAME TO parcels;
'''
database.cursor.execute(query)
database.connection.commit()
log.info('Creating indexes on new tables.')
create_indexes(database)
log.info('Writing process metadata.')
def isolation(
X,
coordinates,
metric="euclidean",
middle="mean",
return_all=False,
progressbar=False,
):
"""
Compute the isolation of each value of X by constructing the distance
to the nearest higher value in the data.
Parameters
----------
X : numpy.ndarray
(N, p) array of data to use as input. If p > 1, the "elevation" is computed
using the topo.to_elevation function.
coordinates : numpy.ndarray
(N,k) array of locations for X to compute distances. If metric='precomputed', this
should contain the distances from each point to every other point, and k == N.
metric : string or callable (default: 'euclidean')
name of distance metric in scipy.spatial.distance, or function, that can be
used to compute distances between locations. If 'precomputed', ad-hoc function
will be defined to look up distances between points instead.
middle : string or callable (default: 'mean')
method to define the elevation of points. See to_elevation for more details.
return_all : bool (default: False)
if False, only return the isolation (distance to nearest higher value).
progressbar: bool (default: False)
if True, show a progressbar for the computation.
Returns
-------
either (N,) array of isolation values, or a pandas dataframe containing the full
tree of precedence for the isolation tree.
"""
X = check_array(X, ensure_2d=False)
X = to_elevation(X, middle=middle).squeeze()
try:
from rtree.index import Index as SpatialIndex
except ImportError:
raise ImportError(
"rtree library must be installed to use the prominence measure"
)
distance_func = _resolve_metric(X, coordinates, metric)
sort_order = numpy.argsort(-X)
tree = SpatialIndex()
ix = sort_order[0]
tree.insert(0, tuple(coordinates[ix]), obj=X[ix])
precedence_tree = [[ix, numpy.nan, 0, numpy.nan, numpy.nan, numpy.nan]]
if progressbar and HAS_TQDM:
pbar = tqdm
elif progressbar and (not HAS_TQDM):
try:
import tqdm
except ImportError as e:
raise ImportError("the tqdm module is required for progressbars")
else:
pbar = _passthrough
for iter_ix, ix in pbar(enumerate(sort_order[1:])):
rank = iter_ix + 1
value = X[ix]
location = coordinates[
ix,
]
(match,) = tree.nearest(tuple(location), objects=True)
higher_rank = match.id
higher_value = match.object
higher_location = match.bbox[:2]
higher_ix = sort_order[higher_rank]
distance = distance_func(location, higher_location)
gap = higher_value - value
precedence_tree.append([ix, higher_ix, rank, higher_rank, distance, gap])
tree.insert(rank, tuple(location), obj=value)
# return precedence_tree
precedence_tree = numpy.asarray(precedence_tree)
# print(precedence_tree.shape)
out = numpy.empty_like(precedence_tree)
out[sort_order] = precedence_tree
result = pandas.DataFrame(
out,
columns=["index", "parent_index", "rank", "parent_rank", "isolation", "gap"],
).sort_values(["index", "parent_index"])
if return_all:
return result
else:
return result.isolation.values
