def predict_probability_area(self, upper_bound, lower_bound,
estimated_loc):
'''
Given a prediction and a bounding box this will return a confidence range
for that prediction
Args:
upper_bound (geoCoord): bounding box top right geoCoord
lower_bound (geoCoord): bounding box bottom left geoCoord
estimated_loc (LocEstimate): geoCoord of the estimated location
Returns:
Probability Tuple(Tuple(float,float)): A probability range tuple (min probability, max probability)
'''
geo = estimated_loc.geo_coord
top_dist = haversine(geo, GeoCoord(upper_bound.lat, geo.lon))
bottom_dist = haversine(geo, GeoCoord(lower_bound.lat, geo.lon))
r_dist = haversine(geo, GeoCoord(geo.lat, upper_bound.lon))
l_dist = haversine(geo, GeoCoord(geo.lat, lower_bound.lon))
min_dist = min([top_dist, bottom_dist, r_dist, l_dist])
max_dist = max([top_dist, bottom_dist, r_dist, l_dist])
#min_prob = self.lookup( (min_dist- med_error)/std_dev)
#max_prob = self.lookup( (max_dist - med_error)/ std_dev)
return (self.lookup((min_dist-estimated_loc.dispersion)/estimated_loc.dispersion_std_dev),\
self.lookup((max_dist-estimated_loc.dispersion)/estimated_loc.dispersion_std_dev))
def predict_probability_area(self, upper_bound, lower_bound, estimated_loc):
'''
Given a prediction and a bounding box this will return a confidence range
for that prediction
Args:
upper_bound (geoCoord): bounding box top right geoCoord
lower_bound (geoCoord): bounding box bottom left geoCoord
estimated_loc (LocEstimate): geoCoord of the estimated location
Returns:
Probability Tuple(Tuple(float,float)): A probability range tuple (min probability, max probability)
'''
geo = estimated_loc.geo_coord
top_dist = haversine(geo, GeoCoord(upper_bound.lat, geo.lon))
bottom_dist = haversine(geo, GeoCoord(lower_bound.lat, geo.lon))
r_dist = haversine(geo, GeoCoord(geo.lat, upper_bound.lon))
l_dist = haversine(geo, GeoCoord(geo.lat, lower_bound.lon))
min_dist = min([top_dist, bottom_dist, r_dist, l_dist])
max_dist = max([top_dist, bottom_dist, r_dist, l_dist])
#min_prob = self.lookup( (min_dist- med_error)/std_dev)
#max_prob = self.lookup( (max_dist - med_error)/ std_dev)
return (self.lookup((min_dist-estimated_loc.dispersion)/estimated_loc.dispersion_std_dev),\
self.lookup((max_dist-estimated_loc.dispersion)/estimated_loc.dispersion_std_dev))
def load_from_rdds(locs_known,
edges,
desired_samples=1000,
dispersion_threshold=150,
neighbor_threshold=3):
'''
Creates an EstimatorCurve
Args:
locs_known (rdd of LocEstimate): RDD of locations that are known
edges (rdd of (src_id (dest_id, weight)): RDD of edges in the network
desired_samples (int): Limit the curve to just a sample of data
Returns:
EstimatorCurve: A new EstimatorCurve representing the known input data
'''
# Filter edge list so we never attempt to estimate a "known" location
known_edges = edges.keyBy(lambda (src_id, (dst_id, weight)): dst_id)\
.leftOuterJoin(locs_known)\
.flatMap(lambda (dst_id, (edge, loc_known)): [edge] if loc_known is not None else [] )
medians = known_edges.join(locs_known)\
.map(lambda (src_id, ((dst_id, weight), src_loc)) : (dst_id, (src_loc, weight)))\
.groupByKey()\
.filter(lambda (src_id, neighbors) : len(neighbors) >= neighbor_threshold)\
.mapValues(lambda neighbors :\
median(haversine, [loc for loc,w in neighbors], [w for loc,w in neighbors]))\
.join(locs_known)\
.mapValues(lambda (found_loc, known_loc) :\
(found_loc, known_loc, haversine(known_loc.geo_coord, found_loc.geo_coord)))\
.filter(lambda (src_id, (found_loc, known_loc, dist)) : found_loc.dispersion < dispersion_threshold)
#some medians might have std_devs of zero
close_locs = medians.filter(lambda (src_id, (
found_loc, known_loc, dist)): found_loc.dispersion_std_dev == 0)
#remaining_locs = medians.filter(lambda (src_id, (found_loc, known_loc, dist)) : found_loc.dispersion_std_dev != 0)
values = medians.map(lambda (src_id, (found_loc, known_loc, dist)) :\
(src_id, ((dist-found_loc.dispersion)/found_loc.dispersion_std_dev if found_loc.dispersion_std_dev != 0 else 0)))\
.values()
values_wo_stdev = close_locs.map(lambda (src_id, (found_loc, known_loc, dist)): (src_id, dist))\
.values()
return EstimatorCurve(EstimatorCurve.build_curve(values, desired_samples),\
EstimatorCurve.build_curve(values_wo_stdev, desired_samples))
def load_from_rdds(locs_known, edges, desired_samples=1000, dispersion_threshold=150, neighbor_threshold=3):
'''
Creates an EstimatorCurve
Args:
locs_known (rdd of LocEstimate): RDD of locations that are known
edges (rdd of (src_id (dest_id, weight)): RDD of edges in the network
desired_samples (int): Limit the curve to just a sample of data
Returns:
EstimatorCurve: A new EstimatorCurve representing the known input data
'''
# Filter edge list so we never attempt to estimate a "known" location
known_edges = edges.keyBy(lambda (src_id, (dst_id, weight)): dst_id)\
.leftOuterJoin(locs_known)\
.flatMap(lambda (dst_id, (edge, loc_known)): [edge] if loc_known is not None else [] )
medians = known_edges.join(locs_known)\
.map(lambda (src_id, ((dst_id, weight), src_loc)) : (dst_id, (src_loc, weight)))\
.groupByKey()\
.filter(lambda (src_id, neighbors) : len(neighbors) >= neighbor_threshold)\
.mapValues(lambda neighbors :\
median(haversine, [loc for loc,w in neighbors], [w for loc,w in neighbors]))\
.join(locs_known)\
.mapValues(lambda (found_loc, known_loc) :\
(found_loc, known_loc, haversine(known_loc.geo_coord, found_loc.geo_coord)))\
.filter(lambda (src_id, (found_loc, known_loc, dist)) : found_loc.dispersion < dispersion_threshold)
#some medians might have std_devs of zero
close_locs = medians.filter(lambda (src_id, (found_loc, known_loc, dist)) : found_loc.dispersion_std_dev == 0)
#remaining_locs = medians.filter(lambda (src_id, (found_loc, known_loc, dist)) : found_loc.dispersion_std_dev != 0)
values = medians.map(lambda (src_id, (found_loc, known_loc, dist)) :\
(src_id, ((dist-found_loc.dispersion)/found_loc.dispersion_std_dev if found_loc.dispersion_std_dev != 0 else 0)))\
.values()
values_wo_stdev = close_locs.map(lambda (src_id, (found_loc, known_loc, dist)): (src_id, dist))\
.values()
return EstimatorCurve(EstimatorCurve.build_curve(values, desired_samples),\
EstimatorCurve.build_curve(values_wo_stdev, desired_samples))
