def test_point_distance(self):
hotel = GeoPoint(*TEST_POINTS[0])
landmark = GeoPoint(*TEST_POINTS[1])
self.assertAlmostEqual(hotel.distance_to(landmark, 'mi'),
.7046874859635269)
self.assertAlmostEqual(hotel.distance_to(landmark, 'km'),
1.1340845774104864)
def test_point_distance(self):
hotel = GeoPoint(*TEST_POINTS[0])
landmark = GeoPoint(*TEST_POINTS[1])
self.assertAlmostEqual(
hotel.distance_to(landmark, 'mi'), .7046874859635269
)
self.assertAlmostEqual(
hotel.distance_to(landmark, 'km'), 1.1340845774104864
)
def __load_geo_index(self):
self.geo_index = GeoGridIndex()
for lodging in self.data:
# if self.debug: print 'loading geo for:' + lodging["name"]
lat = float(lodging["lat"])
lng = float(lodging["lng"])
self.geo_index.add_point(GeoPoint(lat, lng, ref=lodging))
def build_geo_index_from_coord_index(coord_index, precision=5):
geo_index = GeoGridIndex(precision=precision)
for (lat, lng) in coord_index:
geo_index.add_point(GeoPoint(lat, lng))
return geo_index
def get_interactive_candidates(amdh, geo_index, radius=6, nsim_threshold=0.5):
"""
Gets candidates for interactive matching for yet unmatched Amadeus hotels
"""
cands_by_hotel = defaultdict(list)
for i, h in amdh.iterrows():
center_point = GeoPoint(h['lat'], h['lng'], ref=h)
try:
cands = list(
geo_index.get_nearest_points(center_point, radius, 'km'))
except Exception:
continue
nsims = [
get_name_sim(hb.ref['name'], h['name'], swap_words=True)
for (hb, d) in cands
]
inds = [
ind for ind in range(len(nsims)) if nsims[ind] > nsim_threshold
]
inds = sorted(inds, key=lambda i: -nsims[i])
for ind in inds:
hb, d = cands[ind]
cands_by_hotel[h['amd_id']].append(
(hb.ref['bkg_id'], nsims[ind], d))
return cands_by_hotel
def test_bounds(self):
glen = lambda x: len(list(x))
# ezv block
point1 = GeoPoint(43.59375, -4.21875) # ezv
point2 = GeoPoint(43.59375, -4.218750001) # ezu
point3 = GeoPoint(43.59375, -2.812500001) # ezv
point4 = GeoPoint(43.59375, -2.8125) # ezy
point5 = GeoPoint(43.59375, (-4.21875 + -2.8125) / 2)
points = [point1, point2, point3, point4, point5]
index = GeoGridIndex(precision=3)
# import ipdb; ipdb.set_trace()
map(index.add_point, points)
self.assertEquals(glen(index.get_nearest_points(point1, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point2, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point3, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point4, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point5, 57)), 5)
def match_stops_to_nodes(gtfs, walk_network):
"""
Parameters
----------
gtfs : a GTFS object
walk_network : networkx.Graph
Returns
-------
stop_I_to_node: dict
maps stop_I to closest walk_network node
stop_I_to_dist: dict
maps stop_I to the distance to the closest walk_network node
"""
network_nodes = walk_network.nodes(data="true")
stop_Is = set(gtfs.get_straight_line_transfer_distances()['from_stop_I'])
stops_df = gtfs.stops()
geo_index = GeoGridIndex(precision=6)
for net_node, data in network_nodes:
geo_index.add_point(GeoPoint(data['lat'], data['lon'], ref=net_node))
stop_I_to_node = {}
stop_I_to_dist = {}
for stop_I in stop_Is:
stop_lat = float(stops_df[stops_df.stop_I == stop_I].lat)
stop_lon = float(stops_df[stops_df.stop_I == stop_I].lon)
geo_point = GeoPoint(stop_lat, stop_lon)
min_dist = float('inf')
min_dist_node = None
search_distances_m = [0.100, 0.500]
for search_distance_m in search_distances_m:
for point, distance in geo_index.get_nearest_points(
geo_point, search_distance_m, "km"):
if distance < min_dist:
min_dist = distance * 1000
min_dist_node = point.ref
if min_dist_node is not None:
break
if min_dist_node is None:
warn("No OSM node found for stop: " +
str(stops_df[stops_df.stop_I == stop_I]))
stop_I_to_node[stop_I] = min_dist_node
stop_I_to_dist[stop_I] = min_dist
return stop_I_to_node, stop_I_to_dist
def geo_search(self, lat, lng, range):
center_point = GeoPoint(lat, lng)
lodgings = []
for geo_point, distance in self.geo_index.get_nearest_points(
center_point, range, 'km'):
# if self.debug: print("We found {0} in {1} km".format(geo_point.ref["name"], distance))
lodgings.append(geo_point.ref)
return lodgings
def get_nearest_point(geo_index, lat, lng, r):
nearest_points_dists = list(
geo_index.get_nearest_points(GeoPoint(lat, lng), r / 1000))
if nearest_points_dists:
nearest_point, dist = min(nearest_points_dists, key=lambda x: x[1])
dist *= 1000
if dist <= r:
return nearest_point.ref, dist
return None, None
def build_geo_index_from_point_index(index, precision=5):
geo_index = GeoGridIndex(precision=precision)
for id_, point_info in index.iteritems():
lat, lon = point_info.get('latitude',
point_info.get('lat')), point_info.get(
'longitude', point_info.get('lon'))
geo_index.add_point(GeoPoint(lat, lon, point_info['id']))
return geo_index
def calculate_population_within_x_km(row, index, km):
center_point = GeoPoint(row['#lat_deg'], row['#lon_deg'])
total_population = 0
try:
for point, distance in index.get_nearest_points(
center_point, km, 'km'):
total_population += point.ref
except:
print("Invalid data - Record skipped")
#print("Total population within", km, "kilometers:", int(total_population))
return total_population
def generate_comparison_vectors(amdh, geo_index, radius=6, nsim_threshold=0.5):
"""
Creation of comparison vectors for training a matching classifier
amdh: data frame containing Amadeus Hotels
geo_index: index of Booking hotels, easy to query by geo radius
radius: distance to fetch candidates from
nsim_threshold: minimum name similarity to be considered a candidate
"""
cand_pair_ids = []
features = []
count = 0
for i, h in amdh.iterrows():
count += 1
if count % 500 == 0:
progress = count * 100.0 / len(amdh)
print("%.2f %%" % progress)
center_point = GeoPoint(h['lat'], h['lng'], ref=h)
try:
cands = list(
geo_index.get_nearest_points(center_point, radius, 'km'))
except Exception:
continue
nsims1 = [
get_name_sim(hb.ref['name'], h['name'], swap_words=False)
for (hb, d) in cands
]
nsims2 = [
get_name_sim(hb.ref['name'], h['name'], swap_words=True)
for (hb, d) in cands
]
inds = [
ind for ind in range(len(nsims2)) if nsims2[ind] > nsim_threshold
]
for ind in inds:
hb, d = cands[ind]
cand_pair_ids.append((h['amd_id'], hb.ref['bkg_id']))
features.append((nsims1[ind], nsims2[ind], d))
cand_pairs = pd.MultiIndex.from_tuples(cand_pair_ids,
names=['amd_id', 'bkg_id'])
cand_data = pd.DataFrame(features,
index=cand_pairs,
columns=['nsim1', 'nsim2', 'dist'])
return cand_data
def test_point(self):
point = GeoPoint(*TEST_POINTS[0])
self.assertEqual(point.latitude, TEST_POINTS[0][0])
self.assertEqual(point.longitude, TEST_POINTS[0][1])
self.assertIsNone(point._rad_latitude)
self.assertIsNone(point._rad_longitude)
self.assertEqual(point.rad_latitude, math.radians(TEST_POINTS[0][0]))
self.assertEqual(point.rad_longitude, math.radians(TEST_POINTS[0][1]))
self.assertIsNotNone(point._rad_latitude)
self.assertIsNotNone(point._rad_longitude)
self.assertEqual(point.rad_latitude, point._rad_latitude)
self.assertEqual(point.rad_longitude, point._rad_longitude)
same = GeoPoint(TEST_POINTS[0][0], TEST_POINTS[0][1])
self.assertEqual(point, same)
self.assertTrue(point == same)
other = GeoPoint(TEST_POINTS[1][0], TEST_POINTS[1][1])
self.assertNotEqual(point, other)
self.assertFalse(point == other)
self.assertNotEqual(point, TEST_POINTS[0])
self.assertFalse(point == TEST_POINTS[0])
def geocoder(lat, lon, rad=.5):
taxi_point = GeoPoint(lat, lon)
# iterate throug the nearest tracts to the point
for point, distance in index.get_nearest_points(taxi_point, rad,
unit='km'):
for feature in js['features']:
properties = feature.get('properties')
BoroCT2010 = properties.get('BoroCT2010')
# check if the point belongs to one of the nearest tracts to it
if point.ref == BoroCT2010:
geometry = feature.get('geometry')
polygon = shape(geometry)
if polygon.contains(Point(lon, lat)):
return BoroCT2010
# if no tract is found, return an invalid string
return "notfound"
def load_index(self, input=None):
"""
Load all of the geolocated cemetery towers into memory,
inside of our geo_index variable
"""
print 'Loading locations of interest into internal spatial index.'
input_counter = 0
sf = shapefile.Reader('/Users/chrisholloway/Downloads/virginia-latest-free.shp/gis.osm.pois_a_free_1.shp')
shaperec = sf.shapeRecords()
university_hash=[]
for rec in range(len(shaperec)):
if 'university' in shaperec[rec].record:
lat = shaperec[rec].shape.points[0][1]
lon = shaperec[rec].shape.points[0][0]
self.geo_index.add_point(GeoPoint(lat,lon))
input_counter +=1
print 'Done loading index of university (added %s values)' %(input_counter)
def load_index(self, input=None):
"""
Load all of the geolocated cemetery towers into memory,
inside of our geo_index variable
"""
print 'Loading locations of interest into internal spatial index.'
input_counter = 0
for line in open(input,'rU'):
line = line.strip()
parts = line.split('\t')
#print parts
#if len(parts) < 20 or len(parts)<2:
# continue
admin1, lat, lon, tag = parts[10], float(parts[4]), float(parts[5]), parts[7]
if admin1 == 'VA' and tag == 'CMTY':
print lat
self.geo_index.add_point(GeoPoint(lat,lon))
input_counter +=1
print 'Done loading index of cemetery (added %s values)' %(input_counter)
def calc_transfers(conn, threshold_meters=1000):
geohash_precision = _get_geo_hash_precision(threshold_meters / 1000.)
geo_index = GeoGridIndex(precision=geohash_precision)
g = GTFS(conn)
stops = g.get_table("stops")
stop_geopoints = []
cursor = conn.cursor()
for stop in stops.itertuples():
stop_geopoint = GeoPoint(stop.lat, stop.lon, ref=stop.stop_I)
geo_index.add_point(stop_geopoint)
stop_geopoints.append(stop_geopoint)
for stop_geopoint in stop_geopoints:
nearby_stop_geopoints = geo_index.get_nearest_points_dirty(
stop_geopoint, threshold_meters / 1000.0, "km")
from_stop_I = int(stop_geopoint.ref)
from_lat = stop_geopoint.latitude
from_lon = stop_geopoint.longitude
to_stop_Is = []
distances = []
for nearby_stop_geopoint in nearby_stop_geopoints:
to_stop_I = int(nearby_stop_geopoint.ref)
if to_stop_I == from_stop_I:
continue
to_lat = nearby_stop_geopoint.latitude
to_lon = nearby_stop_geopoint.longitude
distance = math.ceil(
wgs84_distance(from_lat, from_lon, to_lat, to_lon))
if distance <= threshold_meters:
to_stop_Is.append(to_stop_I)
distances.append(distance)
n_pairs = len(to_stop_Is)
from_stop_Is = [from_stop_I] * n_pairs
cursor.executemany(
'INSERT OR REPLACE INTO stop_distances VALUES (?, ?, ?, ?, ?, ?);',
zip(from_stop_Is, to_stop_Is, distances, [None] * n_pairs,
[None] * n_pairs, [None] * n_pairs))
cursor.execute(
'CREATE INDEX IF NOT EXISTS idx_sd_fsid ON stop_distances (from_stop_I);'
)
def enumerate_all_distances(self, admin1=None):
"""
Walk the geohash5 centroids,
calculate the distance to the nearest tower for each one,
and write the distance value to the database.
"""
#Walk the geohash5 centroids,
c = self.cursor
c.execute(
'SELECT geohash, centroid_lat, centroid_lon from boxes where admin1=?',
(admin1, ))
geohashes_plus_coords = []
for row in c.fetchall():
geo5_item, lat, lon = row
geohashes_plus_coords.append([geo5_item, lat, lon])
#print geo5_item
#print 'Those are the geohashes'
progress_counter = 0
for geo5, lat, lon in geohashes_plus_coords:
progress_counter += 1
if progress_counter % 50 == 0:
print 'Processed %s records.' % (progress_counter)
if self.debug == True:
print '--------'
print 'geohash of interest:', geo5, lat, lon
#calculate the distance to the nearest tower for each one,
temp_geo_point = GeoPoint(lat, lon)
values = self.geo_index.get_nearest_points(temp_geo_point, 50.0,
'km')
#print values
minimum_distance = MINIMUM_DISTANCE
for value in values:
the_point, the_distance = value
if the_distance < minimum_distance:
minimum_distance = the_distance
#and write the distance value to the database.
c.execute(
'UPDATE boxes set bus_station_distance=? where geohash=?',
(minimum_distance, geo5))
self.conn.commit()
print 'Finished updating distance from geo5 centroids to input data'
def test_geo_point_distance(self):
location_x = GeoPoint(*TEST_POINTS[0])
location_y = GeoPoint(*TEST_POINTS[1])
self.assertAlmostEqual(
location_x.distance_to(location_y, 'mi'), .7046874859635269
)
self.assertAlmostEqual(
location_x.distance_to(location_y, 'km'), 1.1340845774104864
)
self.assertAlmostEqual(
location_y.distance_to(location_x, 'mi'), .7046874859635269
)
self.assertAlmostEqual(
location_y.distance_to(location_x, 'km'), 1.1340845774104864
)
def initialize_matching(overwrite=False):
# 1. fetch all unmatched Amadeus hotels
print("Loading Amadeus hotels")
amdh = load_amadeus_from_db()
namdh = len(amdh)
print("Loaded %d hotels" % namdh)
# 2. fetch all unmatched Booking.com hotels
print("Loading Booking hotels")
bkgh = load_booking()
# bkgh = load_booking_from_mysql()
print("Loaded %d hotels" % len(bkgh))
# 3. load existing matches
if not overwrite:
print("Loading previous matches")
matches = load_matches()
else:
matches = {}
matched_amdids = matches.keys()
matched_bkgids = set(matches.values())
# 4. Exclude already matched
amdh = amdh[~amdh.amd_id.isin(matched_amdids)]
bkgh = bkgh[~bkgh.bkg_id.isin(matched_bkgids)]
print "%d Amadeus hotels left to match to %d Booking hotels" % (len(amdh),
len(bkgh))
# 5. Build geo index
print("Building Geo Index")
geo_index = GeoGridIndex()
for i, hb in bkgh.iterrows():
if hb['lat'] == 90:
hb['lat'] = -90.0
geo_index.add_point(GeoPoint(hb['lat'], hb['lng'], ref=hb))
return amdh, bkgh, matches, geo_index, namdh
if 'sid' in form:
c1, c2 = (-31.36023, -64.26264)
z = 13
banda = '025'
lat = 0
prop = int(form['sid'].value)
geo_index = GeoGridIndex()
cursor.execute(
"select origen, destino, frecuencia, calidad from link where propietario='%s'"
% (prop))
datapoint = cursor.fetchall()
for p in datapoint:
lat, lon = geohash.decode(p[0])
geo_index.add_point(GeoPoint(lat, lon))
lat, lon = geohash.decode(p[1])
geo_index.add_point(GeoPoint(lat, lon))
cursor.execute(
"select point, name, ip, numeroenlaces from nodo where propietario='%s'"
% (prop))
datanodo = cursor.fetchall()
numero = []
nodos = {}
for p in datanodo:
nodos[p[0]] = p[3]
numero.append(p[2])
if 'center' in form:
def get_nearest_points(geo_index, lat, lng, r):
for point, dist in geo_index.get_nearest_points(GeoPoint(lat, lng),
r / 1000):
dist *= 1000
if dist <= r:
yield point.ref, dist
def match_in_neighborhood(amdh,
geo_index,
radius,
nsim_threshold,
matches,
namdh,
save=True,
unique=False,
swap_words=False,
return_cands=True):
count = 0
amdh = amdh[~amdh.amd_id.isin(matches.keys())]
if return_cands:
cands_by_hotel = {}
for _, h in amdh.iterrows():
count += 1
if count % 1000 == 0:
progress = count * 100.0 / len(amdh)
print("%.2f %%" % progress)
center_point = GeoPoint(h['lat'], h['lng'], ref=h)
try:
cands = list(
geo_index.get_nearest_points(center_point, radius, 'km'))
except Exception:
continue
cands = [hb.ref for (hb, d) in cands]
cands = [hb for hb in cands if hb['bkg_id'] not in matches.values()]
if not cands:
continue
nsims = [
get_name_sim(hb['name'], h['name'], swap_words) for hb in cands
]
inds = [
i for i in reversed(np.argsort(nsims)) if nsims[i] > nsim_threshold
]
if inds and (not unique or len(inds) == 1):
best_ind = inds[0]
hb = cands[best_ind]
nsim = nsims[best_ind]
matches[h['amd_id']] = hb['bkg_id']
continue
if return_cands and len(inds) > 1:
candsh = []
for i in inds:
ns = nsims[i]
candsh.append({'candidate': cands[i], 'name_sim': ns})
cands_by_hotel[h['amd_id']] = candsh
perc_matched = len(matches) * 100.0 / namdh
print("%.1f%% matched" % perc_matched)
# Save Matches
if save:
with open('matches_excel.json', 'w') as f:
json.dump(matches, f)
if return_cands:
return cands_by_hotel
array([[0. , 1. ],
[0. , 1. ],
[0. , 1.41421356],
[0. , 1. ],
[0. , 1. ],
[0. , 1.41421356]])
from geoindex import GeoGridIndex, GeoPoint
import random
index = GeoGridIndex()
for _ in range(10000):
lat = random.random()*180 - 90
lng = random.random()*360 - 180
index.add_point(GeoPoint(lat, lng))
center_point = GeoPoint(37.7772448, -122.3955118)
for distance, point in index.get_nearest_points(center_point, 10, 'km'):
print("We found {0} in {1} km".format(point, distance))
#index = GeoGridIndex()
for airport in get_all_airports():
index.add_point(GeoPoint(lat, lng, ref=airport))
center_point = GeoPoint(37.7772448, -122.3955118)
def match_in_neighborhood(amdh,
geo_index,
radius,
nsim_threshold,
matches,
namdh,
save=True,
unique=False,
swap_words=False,
return_cands=True):
count = 0
amdh = amdh[~amdh.lvr_id.isin(matches.keys())]
if return_cands:
candidates = {}
for _, h in amdh.iterrows():
count += 1
if count % 1000 == 0:
progress = count * 100.0 / len(amdh)
print("%.2f %%" % progress)
center_point = GeoPoint(h['lat'], h['lng'], ref=h)
try:
cands = list(
geo_index.get_nearest_points(center_point, radius, 'km'))
except Exception:
continue
cands = [hb.ref for (hb, d) in cands]
cands = []
for (hb, d) in cands:
hb_ = hb.ref
hb_['dist'] = d
cands.append(hb)
cands = [hb for hb in cands if hb['bkg_id'] not in matches.values()]
if not cands:
continue
sw = extract_stopwords([hb['name'] for hb in cands])
nsims_plain = [
get_name_sim(hb['name'], h['name'], False, sw) for hb in cands
]
if swap_words:
nsims_swap = [
get_name_sim(hb['name'], h['name'], True, sw) for hb in cands
]
nsims = nsims_swap
else:
nsims = nsims_plain
inds = [
i for i in reversed(np.argsort(nsims)) if nsims[i] > nsim_threshold
]
if inds and (not unique or len(inds) == 1) and (not return_cands):
best_ind = inds[0]
hb = cands[best_ind]
nsim = nsims[best_ind]
matches[h['lvr_id']] = hb['bkg_id']
if return_cands:
candsh = []
for i in inds:
ns = nsims[i]
hb = cands[i]
cand = {
# 'candidate': cands[i],
# 'name_sim': ns
'lvr_id': h['lvr_id'],
'bkg_id': hb['bkg_id'],
'name': h['name'],
'chain': h['chain'],
'name_bkg': hb['name'],
'chain_bkg': hb['chain'],
'name_sim': nsims_plain[i],
'name_sim_sw': nsims_swap[i],
'dist': hb['d']
}
candsh.append(cand)
candidates[h['lvr_id']] = candsh
perc_matched = len(matches) * 100.0 / namdh
print("%.1f%% matched" % perc_matched)
# Save Matches
if save:
with open('matches.json', 'w') as f:
json.dump(matches, f)
if return_cands:
return candidates
skiprows=1)
amdh = convert_amd_df_to_matching_format(amdh_full)
namdh = len(amdh)
print("Loaded %d hotels" % namdh)
print("Loading Booking hotels")
bkgh = load_booking()
# bkgh = load_booking_from_mysql()
print("Loaded %d hotels" % len(bkgh))
print("Building Geo Index")
geo_index = GeoGridIndex()
for i, hb in bkgh.iterrows():
if hb['lat'] == 90:
hb['lat'] = -90.0
geo_index.add_point(GeoPoint(hb['lat'], hb['lng'], ref=hb))
matches = {}
print("1st pass")
match_in_neighborhood(amdh, geo_index, 1, 0.6, matches, namdh)
print("2nd pass")
match_in_neighborhood(amdh, geo_index, 2, 0.75, matches, namdh)
print("3rd pass")
match_in_neighborhood(amdh, geo_index, 4, 0.8, matches, namdh)
print("4th pass")
match_in_neighborhood(amdh, geo_index, 6, 0.86, matches, namdh)
def extract_candidates(amdh, geo_index, radius, nsim_threshold, namdh):
count = 0
candidates = {}
for _, h in amdh.iterrows():
count += 1
if count % 1000 == 0:
progress = count * 100.0 / len(amdh)
print("%.2f %%" % progress)
center_point = GeoPoint(h['lat'], h['lng'], ref=h)
try:
geo_cands = list(
geo_index.get_nearest_points(center_point, radius, 'km'))
except Exception:
continue
cands = []
for (hb, d) in geo_cands:
hbd = hb.ref
hbd['dist'] = d
cands.append(hbd)
if not cands:
continue
sw = extract_stopwords([hb['name'] for hb in cands])
nsims_plain = [
get_name_sim(hb['name'], h['name'], False, sw) for hb in cands
]
nsims_swap = [
get_name_sim(hb['name'], h['name'], True, sw) for hb in cands
]
nsims = nsims_swap
inds = [
i for i in reversed(np.argsort(nsims)) if nsims[i] > nsim_threshold
]
candsh = []
for i in inds:
ns = nsims[i]
hb = cands[i]
cand = {
# 'candidate': cands[i],
# 'name_sim': ns
'lvr_id': h['lvr_id'],
'bkg_id': hb['bkg_id'],
'name': h['name'],
'chain': h['chain'],
'name_bkg': hb['name'],
'chain_bkg': hb['chain'],
'name_sim': nsims_plain[i],
'name_sim_sw': nsims_swap[i],
'dist': hb['dist']
}
candsh.append(cand)
candidates[h['lvr_id']] = candsh
return candidates
def __init__(self, lat, lon, radius, unit='km'):
GeoGridIndex.__init__(self, precision=3)
self.center_point = GeoPoint(latitude=float(lat), longitude=float(lon))
self.radius = radius
self.unit = unit
self._config = None
myfile = opener.open(myurl)
js = json.load(myfile)
# build index of tract representative points
index = GeoGridIndex()
for feature in js['features']:
# get feature properties and unique tract identifier
properties = feature.get('properties')
BoroCT2010 = properties.get('BoroCT2010')
# geometry of tract
geometry = feature.get('geometry')
polygon = shape(geometry)
# get a representative point from each tract
lon, lat = polygon.representative_point().coords[0]
# add representative point to index
index.add_point(GeoPoint(lat, lon, ref=BoroCT2010))
# function returning the Census tract of a point
def geocoder(lat, lon, rad=.5):
taxi_point = GeoPoint(lat, lon)
# iterate throug the nearest tracts to the point
for point, distance in index.get_nearest_points(taxi_point, rad,
unit='km'):
for feature in js['features']:
properties = feature.get('properties')
BoroCT2010 = properties.get('BoroCT2010')
# check if the point belongs to one of the nearest tracts to it
if point.ref == BoroCT2010:
geometry = feature.get('geometry')
polygon = shape(geometry)
class TestIndexAccurate(TestCase):
point_1bluxome = GeoPoint(37.7772448, -122.3955118)
point_market_street = GeoPoint(37.785275, -122.4062836)
point_oakland = GeoPoint(37.7919585, -122.2287941)
point_walnut_creek = GeoPoint(37.8942235, -122.040223)
point_freemont = GeoPoint(37.5293865, -121.9992648)
point_la = GeoPoint(34.0204989, -118.4117325)
points = [
point_1bluxome, point_market_street, point_oakland, point_walnut_creek,
point_freemont, point_la
]
def test_bounds(self):
glen = lambda x: len(list(x))
# ezv block
point1 = GeoPoint(43.59375, -4.21875) # ezv
point2 = GeoPoint(43.59375, -4.218750001) # ezu
point3 = GeoPoint(43.59375, -2.812500001) # ezv
point4 = GeoPoint(43.59375, -2.8125) # ezy
point5 = GeoPoint(43.59375, (-4.21875 + -2.8125) / 2)
points = [point1, point2, point3, point4, point5]
index = GeoGridIndex(precision=3)
# import ipdb; ipdb.set_trace()
map(index.add_point, points)
self.assertEquals(glen(index.get_nearest_points(point1, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point2, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point3, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point4, 57)), 3)
self.assertEquals(glen(index.get_nearest_points(point5, 57)), 5)
def test_big_distance(self):
index = GeoGridIndex(precision=2)
map(index.add_point, self.points)
ls = list(index.get_nearest_points(self.point_la, 600))
self.assertEquals(len(ls), len(self.points))
def test_simple_accurate(self, precision=3):
glen = lambda x: len(list(x))
index = GeoGridIndex(precision=precision)
map(index.add_point, self.points)
ls = index.get_nearest_points(self.point_1bluxome, 10)
ls = list(ls)
eq_(glen(ls), 2)
points = map(itemgetter(0), ls)
self.assertIn(self.point_1bluxome, points)
self.assertIn(self.point_market_street, points)
eq_(glen(index.get_nearest_points(self.point_1bluxome, 15)), 3)
eq_(glen(index.get_nearest_points(self.point_1bluxome, 34)), 4)
def test_distance_km(self, precision=3):
index = GeoGridIndex(precision=precision)
map(index.add_point, self.points)
for pt, distance in index.get_nearest_points(self.point_1bluxome, 10):
if pt == self.point_1bluxome:
self.assertEquals(distance, 0)
if pt == self.point_market_street:
self.assertEquals(distance, 1.301272755220718)
def test_distance_mi(self, precision=3):
index = GeoGridIndex(precision=precision)
map(index.add_point, self.points)
for pt, distance in index.get_nearest_points(self.point_1bluxome, 10,
'mi'):
if pt == self.point_1bluxome:
self.assertEquals(distance, 0)
if pt == self.point_market_street:
self.assertEquals(distance, 0.808573403337458)
def test_different_precision(self):
for precision in [1, 2, 3]:
self.test_simple_accurate(precision)
def test_wrong_precision(self):
index = GeoGridIndex(precision=4)
self.assertRaisesRegexp(
Exception, 'precision=2', lambda: list(
index.get_nearest_points(self.point_market_street, 100)))
import dask.dataframe as dd
from dask.multiprocessing import get
#Load Swaziland Population File
swaz_pop = pd.read_csv("swaz_pop_data.csv")
#Load Water Data
water_data = pd.read_csv("Water_Point_Data_Exchange_Complete_Dataset.csv")
#Create df with only Swaziland water
swaz_water = water_data[water_data['#country_name'] == 'Swaziland']
#Create Geo Index of Swaziland Population Data
geo_index = GeoGridIndex()
for index, row in swaz_pop.iterrows():
geo_index.add_point(GeoPoint(row['y'], row['x'], ref=row['value']))
#Calculate population with x distance of random well
def calculate_population_within_x_km(row, index, km):
center_point = GeoPoint(row['#lat_deg'], row['#lon_deg'])
total_population = 0
try:
for point, distance in index.get_nearest_points(
center_point, km, 'km'):
total_population += point.ref
except:
print("Invalid data - Record skipped")
#print("Total population within", km, "kilometers:", int(total_population))
return total_population