class QuietPlacesData:
def __init__(self, datafile, debug):
self.debug = debug
fileObject = open(datafile, 'r')
self.data = pickle.load(fileObject)
# print 'loaded ' + str(len(self.data)) + 'records, initializing index'
self.__load_geo_index()
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 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 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 test_plot_grid(self):
grid = GeoGridIndex(precision=4)
for i in range(0,10):
lat = random.random()*180 - 90
lng = random.random()*360 - 180
grid.add_point(GeoPoint(lat, lng))
self.assertEqual(len(grid.data), 10)
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 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 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 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
class DistanceCalculator(object):
def __init__(self):
self.geo_index = GeoGridIndex(precision=3)
self.conn = sqlite3.connect('rockstar_02.db',
isolation_level="DEFERRED")
self.conn.text_factory = str
self.cursor = self.conn.cursor()
self.debug = False
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 == 'HSP':
#print lat
self.geo_index.add_point(GeoPoint(lat, lon))
input_counter += 1
print 'Done loading index of hospital (added %s values)' % (
input_counter)
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 hospital_distance=? where geohash=?',
(minimum_distance, geo5))
self.conn.commit()
print 'Finished updating distance from geo5 centroids to input data'
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)
class DistanceCalculator(object):
def __init__(self):
self.geo_index = GeoGridIndex(precision=3)
self.conn = sqlite3.connect('rockstar_02.db',
isolation_level="DEFERRED")
self.conn.text_factory = str
self.cursor = self.conn.cursor()
self.debug = False
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.roads_free_1.shp'
)
shaperec = sf.shapeRecords()
motorway_hash = []
for rec in range(len(shaperec)):
if 'secondary_link' in shaperec[rec].record[2]:
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 secondary_links (added %s values)' % (
input_counter)
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 secondary_link_distance=? where geohash=?',
(minimum_distance, geo5))
self.conn.commit()
print 'Finished updating distance from geo5 centroids to input data'
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
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)
if polygon.contains(Point(lon, lat)):
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:
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)
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)
"""
print(head)
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:
c1,c2 = (form['center'].value)[7:].rstrip(')').split(',')
z = form['zoom'].value