def best_cluster(self):
"""Return the best cluster from this collection."""
if len(self) <= 1:
return self
results = sorted(self, key=operator.attrgetter("accuracy"))
clusters = {}
for i, result1 in enumerate(results):
clusters[i] = [result1]
# allow a 50% buffer zone around each result
radius1 = result1.accuracy * 1.5
for j, result2 in enumerate(results):
if j > i:
# only calculate the upper triangle
radius2 = result2.accuracy * 1.5
max_radius = max(radius1, radius2)
apart = distance(result1.lat, result1.lon, result2.lat,
result2.lon)
if apart <= max_radius:
clusters[i].append(result2)
def sum_score(values):
# Sort by highest cumulative score,
# break tie by highest individual score
return (sum([v.score
for v in values]), max([v.score for v in values]))
clusters = sorted(clusters.values(), key=sum_score, reverse=True)
return clusters[0]
def confirm_station_obs(self):
confirm = False
if self.has_position():
# station with position
confirm = True
for obs in self.observations:
obs_distance = distance(
obs.lat, obs.lon, self.station.lat, self.station.lon
)
if obs_distance > self.MAX_DIST_METERS:
confirm = False
break
return confirm
def aggregate_mac_position(networks, minimum_accuracy):
# Idea based on https://gis.stackexchange.com/questions/40660
def func(point, points):
return numpy.array([
distance(p["lat"], p["lon"], point[0], point[1]) *
min(math.sqrt(2000.0 / p["age"]), 1.0) /
math.pow(p["signalStrength"], 2) for p in points
])
# Guess initial position as the weighted mean over all networks.
points = numpy.array([(net["lat"], net["lon"]) for net in networks],
dtype=numpy.double)
weights = numpy.array(
[
net["score"] * min(math.sqrt(2000.0 / net["age"]), 1.0) /
math.pow(net["signalStrength"], 2) for net in networks
],
dtype=numpy.double,
)
initial = numpy.average(points, axis=0, weights=weights)
(lat, lon), cov_x, info, mesg, ier = leastsq(func,
initial,
args=networks,
full_output=True)
if ier not in (1, 2, 3, 4):
# No solution found, use initial estimate.
lat, lon = initial
# Guess the accuracy as the 95th percentile of the distances
# from the lat/lon to the positions of all networks.
distances = numpy.array(
[distance(lat, lon, net["lat"], net["lon"]) for net in networks],
dtype=numpy.double,
)
accuracy = max(numpy.percentile(distances, 95), minimum_accuracy)
return (float(lat), float(lon), float(accuracy))
def aggregate_obs(self):
positions = numpy.array(
[(obs.lat, obs.lon) for obs in self.observations], dtype=numpy.double
)
max_lat, max_lon = positions.max(axis=0)
min_lat, min_lon = positions.min(axis=0)
box_distance = distance(min_lat, min_lon, max_lat, max_lon)
if box_distance > self.MAX_DIST_METERS:
return None
weights = numpy.array(
[obs.weight for obs in self.observations], dtype=numpy.double
)
lat, lon = numpy.average(positions, axis=0, weights=weights)
lat = float(lat)
lon = float(lon)
radius = circle_radius(lat, lon, max_lat, max_lon, min_lat, min_lon)
region = GEOCODER.region(lat, lon)
samples, weight = self.bounded_samples_weight(
len(self.observations), float(weights.sum())
)
return {
"positions": positions,
"weights": weights,
"lat": lat,
"lon": lon,
"max_lat": float(max_lat),
"min_lat": float(min_lat),
"max_lon": float(max_lon),
"min_lon": float(min_lon),
"radius": radius,
"region": region,
"samples": samples,
"weight": weight,
}
def aggregate_cell_position(networks, min_accuracy, max_accuracy):
"""
Calculate the aggregate position of the user inside the given
cluster of networks.
Return the position, an accuracy estimate and a combined score.
The accuracy is bounded by the min_accuracy and max_accuracy.
"""
if len(networks) == 1:
lat = networks[0]["lat"]
lon = networks[0]["lon"]
radius = min(max(networks[0]["radius"], min_accuracy), max_accuracy)
score = networks[0]["score"]
return (float(lat), float(lon), float(radius), float(score))
points = numpy.array([(net["lat"], net["lon"]) for net in networks],
dtype=numpy.double)
weights = numpy.array(
[
net["score"] * min(math.sqrt(2000.0 / net["age"]), 1.0) /
math.pow(net["signalStrength"], 2) for net in networks
],
dtype=numpy.double,
)
lat, lon = numpy.average(points, axis=0, weights=weights)
score = networks["score"].sum()
# Guess the accuracy as the 95th percentile of the distances
# from the lat/lon to the positions of all networks.
distances = numpy.array(
[distance(lat, lon, net["lat"], net["lon"]) for net in networks],
dtype=numpy.double,
)
accuracy = min(max(numpy.percentile(distances, 95), min_accuracy),
max_accuracy)
return (float(lat), float(lon), float(accuracy), float(score))
def get(self, query):
"""
Get a cached result for the query.
:param query: The query for which to look for a cached value.
:type query: :class:`ichnaea.api.locate.query.Query`
:returns: The cache result or None.
:rtype: :class:`~ichnaea.api.locate.fallback.ExternalResult`
"""
fallback_name = query.api_key.fallback_name
if not self._should_cache(query):
self._capture_incr(fallback_name, "bypassed")
return None
cache_keys = self._cache_keys(query)
# dict of (lat, lon, fallback) tuples to ExternalResult list
# lat/lon clustered into ~100x100 meter grid cells
clustered_results = defaultdict(list)
not_found_cluster = (None, None, None)
try:
for value in self.redis_client.mget(cache_keys):
if not value:
continue
value = json.loads(value)
if value == LOCATION_NOT_FOUND:
value = ExternalResult(None, None, None, None)
clustered_results[not_found_cluster] = [value]
else:
value = ExternalResult(**value)
# ~100x100m clusters
clustered_results[
(round(value.lat, 3), round(value.lat, 3), value.fallback)
].append(value)
except (json.JSONDecodeError, RedisError):
self.raven_client.captureException()
self._capture_incr(fallback_name, "failure")
return None
if not clustered_results:
self._capture_incr(fallback_name, "miss")
return None
if list(clustered_results.keys()) == [not_found_cluster]:
# the only match was for not found results
self._capture_incr(fallback_name, "hit")
return clustered_results[not_found_cluster][0]
if len(clustered_results) == 1:
# all the cached values agree with each other
self._capture_incr(fallback_name, "hit")
results = list(clustered_results.values())[0]
circles = numpy.array(
[(res.lat, res.lon, res.accuracy) for res in results],
dtype=numpy.double,
)
points, accuracies = numpy.hsplit(circles, [2])
lat, lon = points.mean(axis=0)
lat = float(lat)
lon = float(lon)
radius = 0.0
for circle in circles:
p_dist = distance(lat, lon, circle[0], circle[1]) + circle[2]
radius = max(radius, p_dist)
return ExternalResult(
lat=lat, lon=lon, accuracy=float(radius), fallback=results[0].fallback
)
# inconsistent results
self._capture_incr(fallback_name, "inconsistent")
return None
def cluster_networks(models,
lookups,
min_age=0,
min_radius=None,
min_signal=None,
max_distance=None):
"""
Given a list of database models and lookups, return
a list of clusters of nearby networks.
"""
now = util.utcnow()
today = now.date()
# Create a dict of macs mapped to their age and signal strength.
obs_data = {}
for lookup in lookups:
obs_data[decode_mac(lookup.mac)] = (
max(abs(lookup.age or min_age), 1000),
lookup.signalStrength or min_signal,
)
networks = numpy.array(
[(
model.lat,
model.lon,
model.radius or min_radius,
obs_data[model.mac][0],
obs_data[model.mac][1],
station_score(model, now),
encode_mac(model.mac, codec="base64"),
bool(model.last_seen is not None and model.last_seen >= today),
) for model in models],
dtype=NETWORK_DTYPE,
)
# Only consider clusters that have at least 2 found networks
# inside them. Otherwise someone could use a combination of
# one real network and one fake and therefor not found network to
# get the position of the real network.
length = len(networks)
if length < 2:
# Not enough networks to form a valid cluster.
return []
positions = networks[["lat", "lon"]]
if length == 2:
one = positions[0]
two = positions[1]
if distance(one[0], one[1], two[0], two[1]) <= max_distance:
# Only two networks and they agree, so cluster them.
return [networks]
else:
# Or they disagree forming two clusters of size one,
# neither of which is large enough to be returned.
return []
# Calculate the condensed distance matrix based on distance in meters.
# This avoids calculating the square form, which would calculate
# each value twice and avoids calculating the diagonal of zeros.
# We avoid the special cases for length < 2 with the above checks.
# See scipy.spatial.distance.squareform and
# https://stackoverflow.com/questions/13079563
dist_matrix = numpy.zeros(length * (length - 1) // 2, dtype=numpy.double)
for i, (a, b) in enumerate(itertools.combinations(positions, 2)):
dist_matrix[i] = distance(a[0], a[1], b[0], b[1])
link_matrix = hierarchy.linkage(dist_matrix, method="complete")
assignments = hierarchy.fcluster(link_matrix,
max_distance,
criterion="distance",
depth=2)
indexed_clusters = defaultdict(list)
for i, net in zip(assignments, networks):
indexed_clusters[i].append(net)
clusters = []
for values in indexed_clusters.values():
if len(values) >= 2:
clusters.append(numpy.array(values, dtype=NETWORK_DTYPE))
return clusters
def func(point, points):
return numpy.array([
distance(p["lat"], p["lon"], point[0], point[1]) *
min(math.sqrt(2000.0 / p["age"]), 1.0) /
math.pow(p["signalStrength"], 2) for p in points
])
def region(self, lat, lon):
"""
Return a region code matching the provided position.
If the position is not found inside any region return None.
"""
# Look up point in RTree of buffered region envelopes.
# This is a coarse-grained but very fast match.
point = geometry.Point(lon, lat)
codes = set([
self._tree_ids[id_]
for id_ in self._tree.intersection(point.bounds)
])
if not codes:
return None
# match point against the buffered polygon shapes
buffered_codes = set([
code for code in codes
if self._buffered_shapes[code].contains(point)
])
if len(buffered_codes) < 2:
return tuple(buffered_codes)[0] if buffered_codes else None
# match point against the precise polygon shapes
precise_codes = set([
code for code in buffered_codes
if self._prepared_shapes[code].contains(point)
])
if len(precise_codes) == 1:
return tuple(precise_codes)[0]
# Use distance from the border of each region as the tie-breaker.
distances = {}
# point wasn't in any precise region, which one of the buffered
# regions is it closest to?
if not precise_codes:
for code in buffered_codes:
coords = []
if isinstance(self._shapes[code].boundary,
geometry.base.BaseMultipartGeometry):
for geom in self._shapes[code].boundary.geoms:
coords.extend([coord for coord in geom.coords])
else:
coords = self._shapes[code].boundary.coords
for coord in coords:
distances[geocalc.distance(coord[1], coord[0], lat,
lon)] = code
return distances[min(distances.keys())]
# point was in multiple overlapping regions, take the one where it
# is farthest away from the border / the most inside a region
for code in precise_codes:
coords = []
if isinstance(self._shapes[code].boundary,
geometry.base.BaseMultipartGeometry):
for geom in self._shapes[code].boundary.geoms:
coords.extend([coord for coord in geom.coords])
else:
coords = self._shapes[code].boundary.coords
for coord in coords:
distances[geocalc.distance(coord[1], coord[0], lat,
lon)] = code
return distances[max(distances.keys())]
