Detecting geographic clusters - python

I have a R data.frame containing longitude, latitude which spans over the entire USA map. When X number of entries are all within a small geographic region of say a few degrees longitude & a few degrees latitude, I want to be able to detect this and then have my program then return the coordinates for the geographic bounding box. Is there a Python or R CRAN package that already does this? If not, how would I go about ascertaining this information?

I was able to combine Joran's answer along with Dan H's comment. This is an example ouput:
The python code emits functions for R: map() and rect(). This USA example map was created with:
map('state', plot = TRUE, fill = FALSE, col = palette())
and then you can apply the rect()'s accordingly from with in the R GUI interpreter (see below).
import math
from collections import defaultdict
to_rad = math.pi / 180.0 # convert lat or lng to radians
fname = "site.tsv" # file format: LAT\tLONG
threshhold_dist=50 # adjust to your needs
threshhold_locations=15 # minimum # of locations needed in a cluster
def dist(lat1,lng1,lat2,lng2):
global to_rad
earth_radius_km = 6371
dLat = (lat2-lat1) * to_rad
dLon = (lng2-lng1) * to_rad
lat1_rad = lat1 * to_rad
lat2_rad = lat2 * to_rad
a = math.sin(dLat/2) * math.sin(dLat/2) + math.sin(dLon/2) * math.sin(dLon/2) * math.cos(lat1_rad) * math.cos(lat2_rad)
c = 2 * math.atan2(math.sqrt(a), math.sqrt(1-a));
dist = earth_radius_km * c
return dist
def bounding_box(src, neighbors):
neighbors.append(src)
# nw = NorthWest se=SouthEast
nw_lat = -360
nw_lng = 360
se_lat = 360
se_lng = -360
for (y,x) in neighbors:
if y > nw_lat: nw_lat = y
if x > se_lng: se_lng = x
if y < se_lat: se_lat = y
if x < nw_lng: nw_lng = x
# add some padding
pad = 0.5
nw_lat += pad
nw_lng -= pad
se_lat -= pad
se_lng += pad
# sutiable for r's map() function
return (se_lat,nw_lat,nw_lng,se_lng)
def sitesDist(site1,site2):
#just a helper to shorted list comprehension below
return dist(site1[0],site1[1], site2[0], site2[1])
def load_site_data():
global fname
sites = defaultdict(tuple)
data = open(fname,encoding="latin-1")
data.readline() # skip header
for line in data:
line = line[:-1]
slots = line.split("\t")
lat = float(slots[0])
lng = float(slots[1])
lat_rad = lat * math.pi / 180.0
lng_rad = lng * math.pi / 180.0
sites[(lat,lng)] = (lat,lng) #(lat_rad,lng_rad)
return sites
def main():
sites_dict = {}
sites = load_site_data()
for site in sites:
#for each site put it in a dictionary with its value being an array of neighbors
sites_dict[site] = [x for x in sites if x != site and sitesDist(site,x) < threshhold_dist]
results = {}
for site in sites:
j = len(sites_dict[site])
if j >= threshhold_locations:
coord = bounding_box( site, sites_dict[site] )
results[coord] = coord
for bbox in results:
yx="ylim=c(%s,%s), xlim=c(%s,%s)" % (results[bbox]) #(se_lat,nw_lat,nw_lng,se_lng)
print('map("county", plot=T, fill=T, col=palette(), %s)' % yx)
rect='rect(%s,%s, %s,%s, col=c("red"))' % (results[bbox][2], results[bbox][0], results[bbox][3], results[bbox][2])
print(rect)
print("")
main()
Here is an example TSV file (site.tsv)
LAT LONG
36.3312 -94.1334
36.6828 -121.791
37.2307 -121.96
37.3857 -122.026
37.3857 -122.026
37.3857 -122.026
37.3895 -97.644
37.3992 -122.139
37.3992 -122.139
37.402 -122.078
37.402 -122.078
37.402 -122.078
37.402 -122.078
37.402 -122.078
37.48 -122.144
37.48 -122.144
37.55 126.967
With my data set, the output of my python script, shown on the USA map. I changed the colors for clarity.
rect(-74.989,39.7667, -73.0419,41.5209, col=c("red"))
rect(-123.005,36.8144, -121.392,38.3672, col=c("green"))
rect(-78.2422,38.2474, -76.3,39.9282, col=c("blue"))
Addition on 2013-05-01 for Yacob
These 2 lines give you the over all goal...
map("county", plot=T )
rect(-122.644,36.7307, -121.46,37.98, col=c("red"))
If you want to narrow in on a portion of a map, you can use ylim and xlim
map("county", plot=T, ylim=c(36.7307,37.98), xlim=c(-122.644,-121.46))
# or for more coloring, but choose one or the other map("country") commands
map("county", plot=T, fill=T, col=palette(), ylim=c(36.7307,37.98), xlim=c(-122.644,-121.46))
rect(-122.644,36.7307, -121.46,37.98, col=c("red"))
You will want to use the 'world' map...
map("world", plot=T )
It has been a long time since I have used this python code I have posted below so I will try my best to help you.
threshhold_dist is the size of the bounding box, ie: the geographical area
theshhold_location is the number of lat/lng points needed with in
the bounding box in order for it to be considered a cluster.
Here is a complete example. The TSV file is located on pastebin.com. I have also included an image generated from R that contains the output of all of the rect() commands.
# pyclusters.py
# May-02-2013
# -John Taylor
# latlng.tsv is located at http://pastebin.com/cyvEdx3V
# use the "RAW Paste Data" to preserve the tab characters
import math
from collections import defaultdict
# See also: http://www.geomidpoint.com/example.html
# See also: http://www.movable-type.co.uk/scripts/latlong.html
to_rad = math.pi / 180.0 # convert lat or lng to radians
fname = "latlng.tsv" # file format: LAT\tLONG
threshhold_dist=20 # adjust to your needs
threshhold_locations=20 # minimum # of locations needed in a cluster
earth_radius_km = 6371
def coord2cart(lat,lng):
x = math.cos(lat) * math.cos(lng)
y = math.cos(lat) * math.sin(lng)
z = math.sin(lat)
return (x,y,z)
def cart2corrd(x,y,z):
lon = math.atan2(y,x)
hyp = math.sqrt(x*x + y*y)
lat = math.atan2(z,hyp)
return(lat,lng)
def dist(lat1,lng1,lat2,lng2):
global to_rad, earth_radius_km
dLat = (lat2-lat1) * to_rad
dLon = (lng2-lng1) * to_rad
lat1_rad = lat1 * to_rad
lat2_rad = lat2 * to_rad
a = math.sin(dLat/2) * math.sin(dLat/2) + math.sin(dLon/2) * math.sin(dLon/2) * math.cos(lat1_rad) * math.cos(lat2_rad)
c = 2 * math.atan2(math.sqrt(a), math.sqrt(1-a));
dist = earth_radius_km * c
return dist
def bounding_box(src, neighbors):
neighbors.append(src)
# nw = NorthWest se=SouthEast
nw_lat = -360
nw_lng = 360
se_lat = 360
se_lng = -360
for (y,x) in neighbors:
if y > nw_lat: nw_lat = y
if x > se_lng: se_lng = x
if y < se_lat: se_lat = y
if x < nw_lng: nw_lng = x
# add some padding
pad = 0.5
nw_lat += pad
nw_lng -= pad
se_lat -= pad
se_lng += pad
#print("answer:")
#print("nw lat,lng : %s %s" % (nw_lat,nw_lng))
#print("se lat,lng : %s %s" % (se_lat,se_lng))
# sutiable for r's map() function
return (se_lat,nw_lat,nw_lng,se_lng)
def sitesDist(site1,site2):
# just a helper to shorted list comprehensioin below
return dist(site1[0],site1[1], site2[0], site2[1])
def load_site_data():
global fname
sites = defaultdict(tuple)
data = open(fname,encoding="latin-1")
data.readline() # skip header
for line in data:
line = line[:-1]
slots = line.split("\t")
lat = float(slots[0])
lng = float(slots[1])
lat_rad = lat * math.pi / 180.0
lng_rad = lng * math.pi / 180.0
sites[(lat,lng)] = (lat,lng) #(lat_rad,lng_rad)
return sites
def main():
color_list = ( "red", "blue", "green", "yellow", "orange", "brown", "pink", "purple" )
color_idx = 0
sites_dict = {}
sites = load_site_data()
for site in sites:
#for each site put it in a dictionarry with its value being an array of neighbors
sites_dict[site] = [x for x in sites if x != site and sitesDist(site,x) < threshhold_dist]
print("")
print('map("state", plot=T)') # or use: county instead of state
print("")
results = {}
for site in sites:
j = len(sites_dict[site])
if j >= threshhold_locations:
coord = bounding_box( site, sites_dict[site] )
results[coord] = coord
for bbox in results:
yx="ylim=c(%s,%s), xlim=c(%s,%s)" % (results[bbox]) #(se_lat,nw_lat,nw_lng,se_lng)
# important!
# if you want an individual map for each cluster, uncomment this line
#print('map("county", plot=T, fill=T, col=palette(), %s)' % yx)
if len(color_list) == color_idx:
color_idx = 0
rect='rect(%s,%s, %s,%s, col=c("%s"))' % (results[bbox][2], results[bbox][0], results[bbox][3], results[bbox][1], color_list[color_idx])
color_idx += 1
print(rect)
print("")
main()

I'm doing this on a regular basis by first creating a distance matrix and then running clustering on it. Here is my code.
library(geosphere)
library(cluster)
clusteramounts <- 10
distance.matrix <- (distm(points.to.group[,c("lon","lat")]))
clustersx <- as.hclust(agnes(distance.matrix, diss = T))
points.to.group$group <- cutree(clustersx, k=clusteramounts)
I'm not sure if it completely solves your problem. You might want to test with different k, and also perhaps do a second run of clustering of some of the first clusters in case they are too big, like if you have one point in Minnesota and a thousand in California.
When you have the points.to.group$group, you can get the bounding boxes by finding max and min lat lon per group.
If you want X to be 20, and you have 18 points in New York and 22 in Dallas, you must decide if you want one small and one really big box (20 points each), if it is better to have have the Dallas box include 22 points, or if you want to split the 22 points in Dallas to two groups. Clustering based on distance can be good in some of these cases. But it of course depend on why you want to group the points.
/Chris

A few ideas:
Ad-hoc & approximate: The "2-D histogram". Create arbitrary "rectangular" bins, of the degree width of your choice, assign each bin an ID. Placing a point in a bin means "associate the point with the ID of the bin". Upon each add to a bin, ask the bin how many points it has. Downside: doesn't correctly "see" a cluster of points that stradle a bin boundary; and: bins of "constant longitudinal width" actually are (spatially) smaller as you move north.
Use the "Shapely" library for Python. Follow it's stock example for "buffering points", and do a cascaded union of the buffers. Look for globs over a certain area, or that "contain" a certain number of original points. Note that Shapely is not intrinsically "geo-savy", so you'll have to add corrections if you need them.
Use a true DB with spatial processing. MySQL, Oracle, Postgres (with PostGIS), MSSQL all (I think) have "Geometry" and "Geography" datatypes, and you can do spatial queries on them (from your Python scripts).
Each of these has different costs in dollars and time (in the learning curve)... and different degrees of geospatial accuracy. You have to pick what suits your budget and/or requirements.

if you use shapely, you could extend my cluster_points function
to return the bounding box of the cluster via the .bounds property of the shapely geometry , for example like this:
clusterlist.append(cluster, (poly.buffer(-b)).bounds)

maybe something like
def dist(lat1,lon1,lat2,lon2):
#just return normal x,y dist
return sqrt((lat1-lat2)**2+(lon1-lon2)**2)
def sitesDist(site1,site2):
#just a helper to shorted list comprehensioin below
return dist(site1.lat,site1.lon,site2.lat,site2.lon)
sites_dict = {}
threshhold_dist=5 #example dist
for site in sites:
#for each site put it in a dictionarry with its value being an array of neighbors
sites_dict[site] = [x for x in sites if x != site and sitesDist(site,x) < threshhold_dist]
print "\n".join(sites_dict)

Related

How to check if two polygons from geopositions touch or overlap on python?

I would like to check if two polygons built from coordinates touch or overlap. The following example should touch (they came from a simulation), however, the code doesn't detect they touch, hence, crash. Any clue?
import geopy
import geopy.distance
import math
from shapely import geometry
def bearing_calc(a_lat, a_lon, b_lat, b_lon): # a previous position b current position
# print(a)
# a.type
rlat1 = math.radians(a_lat)
# print(a_lat)
rlon1 = math.radians(a_lon)
rlat2 = math.radians(b_lat)
rlon2 = math.radians(b_lon)
dlon = math.radians(b_lon - a_lon)
b = math.atan2(math.sin(dlon) * math.cos(rlat2),
math.cos(rlat1) * math.sin(rlat2) - math.sin(rlat1) * math.cos(rlat2) * math.cos(
dlon)) # bearing calc
bd = math.degrees(b)
br, bn = divmod(bd + 360, 360) # the bearing remainder and final bearing
return bn
# To get a rotated rectangle at a bearing, you need to get the points of the the recatangle at that bearing
def get_rotated_points(coordinates, bearing, width, length):
start = geopy.Point(coordinates)
width = width / 1000
length = length / 1000
rectlength = geopy.distance.distance(kilometers=length)
rectwidth = geopy.distance.distance(kilometers=width)
halfwidth = geopy.distance.distance(kilometers=width / 2)
halflength = geopy.distance.distance(kilometers=length / 2)
pointAB = halflength.destination(point=start, bearing=bearing)
pointA = halfwidth.destination(point=pointAB, bearing=0 - bearing)
pointB = rectwidth.destination(point=pointA, bearing=180 - bearing)
pointC = rectlength.destination(point=pointB, bearing=bearing - 180)
pointD = rectwidth.destination(point=pointC, bearing=0 - bearing)
points = []
for point in [pointA, pointB, pointC, pointD]:
coords = (point.latitude, point.longitude)
points.append(coords)
return points
v1_id = 176
v1_coord_5 = [41.39129840757358, 2.1658667401858738]
v1_coord_4 = [41.391335226146495, 2.1658363842310404]
v1_length = 5 #meters
v1_width = 1.8 #meters
v1_bearing = bearing_calc(v1_coord_4[0], v1_coord_4[1],
v1_coord_5[0], v1_coord_5[1])
v1_points = get_rotated_points(tuple(v1_coord_5), v1_bearing,
v1_width, v1_length)
polygon1 = geometry.Polygon(v1_points)
v2_id = 210
v2_coord_5 = [41.39134056977012, 2.1658847515529804]
v2_coord_4 = [41.39127485461452, 2.165851515431892]
v2_length = 5 #meters
v2_width = 1.8 #meters
v2_bearing = bearing_calc(v2_coord_4[0], v2_coord_4[1],
v2_coord_5[0], v2_coord_5[1])
v2_points = get_rotated_points(tuple(v2_coord_5), v2_bearing,
v2_width, v2_length)
polygon2 = geometry.Polygon(v2_points)
if polygon1.intersection(polygon2).area > 0.0:
print("COLISION")
else:
print("NO COLISION")
I've also tried the function touches
polygon1.touches(polygon2)
Unfortunately, also, false. I don't know if there is a function to check if the two borders touch even in one points, minimally.
If I plot the two polygons, they do not collide, as shown above, however, they should. Is it because the code is not considering the earth surface curvature? How can I adapt the code to consider that factor.

Calculating distances in TSPLIB

Hello i have a problem with calculating distances between cities from tsp library: http://www.math.uwaterloo.ca/tsp/world/countries.html. I have this set of data (cities in djibouti): http://www.math.uwaterloo.ca/tsp/world/dj38.tsp. I used this function to calculate distaces in this QaA here: http://comopt.ifi.uni-heidelberg.de/software/TSPLIB95/TSPFAQ.html. i programed this in python and now it looks like this, here is my code:
cityCoords = {
1:(11003.611100,42102.500000),
2:(11108.611100,42373.888900),
3:(11133.333300,42885.833300),
4:(11155.833300,42712.500000),
5:(11183.333300,42933.333300),
6:(11297.500000,42853.333300),
7:(11310.277800,42929.444400),
8:(11416.666700,42983.333300),
9:(11423.888900,43000.277800),
10:(11438.333300,42057.222200),
11:(11461.111100,43252.777800),
12:(11485.555600,43187.222200),
13:(11503.055600,42855.277800),
14:(11511.388900,42106.388900),
15:(11522.222200,42841.944400),
16:(11569.444400,43136.666700),
17:(11583.333300,43150.000000),
18:(11595.000000,43148.055600),
19:(11600.000000,43150.000000),
20:(11690.555600,42686.666700),
21:(11715.833300,41836.111100),
22:(11751.111100,42814.444400),
23:(11770.277800,42651.944400),
24:(11785.277800,42884.444400),
25:(11822.777800,42673.611100),
26:(11846.944400,42660.555600),
27:(11963.055600,43290.555600),
28:(11973.055600,43026.111100),
29:(12058.333300,42195.555600),
30:(12149.444400,42477.500000),
31:(12286.944400,43355.555600),
32:(12300.000000,42433.333300),
33:(12355.833300,43156.388900),
34:(12363.333300,43189.166700),
35:(12372.777800,42711.388900),
36:(12386.666700,43334.722200),
37:(12421.666700,42895.555600),
38:(12645.000000,42973.333300)
}
def calcCityDistances(coordDict):
cities = list(coordDict.keys())
n = len(cities)
distances = {}
latitude = []
longitude = []
RRR = 6378.388;
PI = 3.141592;
for i in range(1,n+1):
cityA = cities[i-1]
latA, longA = coordDict[cityA]
deg = int(latA)
Min = latA - deg
latitude.append(PI * (deg + 5 * Min / 3) / 180)
deg = int(longA);
Min = longA - deg;
longitude.append(PI * (deg + 5 * Min / 3) / 180)
for i in range(1,n+1):
for j in range(i + 1, n + 1):
q1 = cos(longitude[i-1] - longitude[j-1]);
q2 = cos(latitude[i-1] - latitude[j-1]);
q3 = cos(latitude[i-1] + latitude[j-1]);
key = frozenset((i, j))
distances[key] = {}
dist = RRR * acos(0.5 * ((1.0 + q1) * q2 - (1.0 - q1) * q3)) + 1.0
distances[key]['dist'] = dist
distances[key]['pher'] = init_fer
distances[key]['vis'] = 0
return distances
distances = calcCityDistances(cityCoords)
My problem is that the distances calculated in this algorithm are off mark in huge scale. average lenght of one route between cities is 10 000 km and the problem is that the optimal TSP route is 6635. you can imagine that when i apply this to my Ant Colony System algorithm the result is around 110 000 km. this is really different from 6 thousand. Can someone explain what am i doing wrong please ?
I'm not familiar with the distance calculation listed in the TSP FAQ. Here's the resource I've used in the past: http://www.movable-type.co.uk/scripts/latlong.html
He gives two great circle distance calculation methods. Neither one looks like the one TSP provided. But, they both produced a distance that seemed to match reality (that Diksa and Dikhil are about 31k apart).
The input data is in 1000ths of a degree, and I'm not sure if the conversion to radians given takes that into account.
Here's an implementation that might give you better results: note I updated the input data to degrees:
import cmath
import math
cityCoords = {
1:(11.0036111,42.1025),
2:(11.1086111,42.3738889)
}
def spherical_cosines(coordDict):
R = 6371; # kilometers
cities = list(coordDict.keys())
n = len(cities)
for i in range(1,n+1):
for j in range(i + 1, n + 1):
cityA = cities[i-1]
lat1, lon1 = coordDict[cityA]
cityB = cities[j-1]
lat2, lon2 = coordDict[cityB]
lat1_radians = math.radians(lat1)
lat2_radians = math.radians(lat2)
lon1_radians = math.radians(lon1)
lon2_radians = math.radians(lon2)
print('A={},{} B={},{}'.format(lat1_radians, lon1_radians, lat2_radians, lon2_radians))
delta_lon_radians = math.radians(lon2-lon1)
distance = cmath.acos(cmath.sin(lat1_radians) * cmath.sin(lat2_radians) + cmath.cos(lat1_radians) *
math.cos(lat2_radians) * cmath.cos(delta_lon_radians)) * R;
print('spherical_cosines distance={}'.format(distance))
spherical_cosines(cityCoords)
update:
The code you posted is not producing the correct distance values. Here's the first two cities using calcCityDistances and sperical cosines:
input loc=11003.6111, 42102.5
input loc=11108.6111, 42373.8889
radians A = 192.05631381917777,734.8329132074075
B=193.88890915251113,739.5740671363777
calcCityDistances distance = 8078.816781077703
input degrees A=11.0036111,42.1025 B=11.1086111,42.3738889
radians A=0.19204924330399503,0.7348272483209126
B=0.19388183901858905,0.7395638781792782
spherical_cosines> distance=(31.835225475974934+0j)
Units is kilometers. Spherical cosines produces approximately the right value. Is the code you're using the same as what you posted? Notice the radians conversion doesn't seem to take into account that the input is thousandths of a degree

Trying to calculate multiple line intersections using lists of tuples python

EDIT: Git Repo for sample files https://github.com/tpubben/lineIntersect
I am trying to calculate the line intersection points in x,y coordinates based on a set of intersecting lines crossing one continuous line made up of multiple segments.
The continuous line is represented by a list of tuples as follows where each segment starts with the x/y coordinate of the endpoint of the previous segment:
lineA = [((x1, y1),(x2,y2)), ((x2,y2),(x3,y3))....]
The crossing lines are represented in the same manner, however each is a discrete line (no shared points):
lineB = [((x1, y1),(x2,y2))...]
I am trying to iterate through the continuous line (lineA) and check to see which crossing lines intersect with which segments of lineA.
An example image of what the line intersections would look like is here:
so far I have tried the following:
from __future__ import print_function
def newSurveys(nintyin, injectorin):
# pull data out of pre-prepared CSV files
fh = open(nintyin)
fho = open(injectorin)
rlines = fho.readlines()
rlines90 = fh.readlines()
segA = []
segB = []
segA90 = []
segB90 = []
for item in rlines:
if not item.startswith('M'):
item = item.split(',')
segA.append((float(item[4]),float(item[5])))#easting northing
segB.append((float(item[4]),float(item[5])))#easting northing
segB.pop(0)
z = len(segA)-1
segA.pop(z)
for item in rlines90:
if not item.startswith('N'):
item = item.split(',')
segA90.append((float(item[1]),float(item[0])))#easting northing
segB90.append((float(item[3]),float(item[2])))#easting northing
activeWellSegs = []
injector90Segs = []
for a, b in zip(segA, segB):
activeWellSegs.append((a,b))
for c, d in zip(segA90, segB90):
injector90Segs.append((c,d))
if len(activeWellSegs) >= len(injector90Segs):
lineA = activeWellSegs
lineB = injector90Segs
else:
lineA = injector90Segs
lineB = activeWellSegs
for l1 in lineA:
for l2 in lineB:
##### Use differential equation to calculate line intersections,
##### taken from another user's post
def line_intersection(line1, line2):
xdiff = (line1[0][0] - line1[1][0], line2[0][0] - line2[1][0])
ydiff = (line1[0][1] - line1[1][1], line2[0][1] - line2[1][1])
def det(a, b):
return a[0] * b[1] - a[1] * b[0]
div = det(xdiff, ydiff)
if div == 0:
raise Exception('lines do not intersect')
d = (det(*line1), det(*line2))
x = det(d, xdiff) / div
y = det(d, ydiff) / div
return x, y
print (line_intersection(l1, l2), file=lprint)
newSurveys('producer90.csv', 'injector.csv')
Your code looks like it's dealing with a specific set of data (i.e. I have no idea what the "startsWith('N')" and the like are referring to) so I can only answer this question in the abstract.
Try splitting the code into multiple functions that do one specific task, rather than one big function that tries to do everything. You will find it much easier to work with and troubleshoot.
def getScalar(lineSegment):
return (lineSegment[1][0] - lineSegment[0][0],
lineSegment[1][1] - lineSegment[0][1])
def doTheyIntersect(lineA, lineB):
scalarA = getScalar(lineA)
scalarB = getScalar(lineB)
s = (-1.0 * scalarA[1] * (lineA[0][0] - lineB[0][0]) + scalarA[0] * (lineA[0][1] - lineB[0][1])) / (-1.0 * scalarB[0] * scalarA[1] + scalarA[0] * scalarB[1])
t = (scalarB[0] * (lineA[0][1] - lineB[0][1]) - scalarB[1] * (lineA[0][0] - lineB[0][0])) / (-1.0 * scalarB[0] * scalarA[1] + scalarA[0] * scalarB[1])
if 0.0 <= s <= 1.0 and 0.0 <= t <= 1.0:
return True
else:
return False
lineA = [(x, y), (x1, y1), ...]
lineB = [(x, y), (x1, y1), ...]
for index, segment in enumerate(lineA):
if index + 1 < len(lineA):
for index2 in range(0, len(lineB), 2):
if doTheyIntersect((lineA[index], lineA[index + 1]), (lineB[index2], lineB[index2+1])):
print("lineB ({0}, {1}) intersects lineA at ({2}, {3})".format(str(lineB[index2]),str(lineB[index2+1]), str(lineA[index]), str(lineA[index + 1]))
This this is the general idea. I got the geometry formulas from:
How do you detect where two line segments intersect?

Satellite elevation angles negative

Until recently, the code I used to calculate the elevation and azimuth of a satellite from one particular site appeared to work. Then I used a different file from a site, not in the northern but in the southern hemisphere. The elevation angles calculated were sometimes negative i.e. the satellite was below the horizon. This is incorrect, so either the file parameters to be used for the satellite position are false (less likely), or my code below is incorrect (more likely).
rx_position = (self.X_rx, self.Y_rx, self.Z_rx)
diff_position = satellite_carteisan_coords - rx_position
diff_position_individual = diff_position[0]
rho = np.sqrt(diff_position_individual[0]**2 + diff_position_individual[1]**2 + diff_position_individual[2]**2)
dphi, dlambda, h = self.cartesian_to_geoid(rx_position)
slat = np.sin(np.radians(dphi))
slon = np.sin(np.radians(dlambda))
clat = np.cos(np.radians(dphi))
clon = np.cos(np.radians(dlambda))
F = np.array([[-slon, -slat*clon, clat*clon],
[clon, -slat*slon, clat*slon],
[0, clat, slat ]])
np.split(diff_position_individual, 3)
local_vector = np.dot(F.T, diff_position_individual)
E = local_vector[0]
N = local_vector[1]
U = local_vector[2]
hor_dis = np.sqrt(E**2 + N**2)
if hor_dis < 1e-20:
Azi = 0
Ele = 90
else:
Azi = np.rad2deg(math.atan2(E, N))
Ele = np.rad2deg(math.atan2(U, hor_dis))
if Azi < 0:
Azi = Azi + 360
return Azi, Ele
How can I ensure that the code above does not end up calculating elevation angles that are negative?

How to calculate the midpoint of several geolocations in python

Is there's a library or a way to calculate the center point for several geolocations points?
This is my list of geolocations based in New York and want to find the approximate midpoint geolocation
L = [
(-74.2813611,40.8752222),
(-73.4134167,40.7287778),
(-74.3145014,40.9475244),
(-74.2445833,40.6174444),
(-74.4148889,40.7993333),
(-73.7789256,40.6397511)
]
After the comments I received and comment from HERE
With coordinates that close to each other, you can treat the Earth as being locally flat and simply find the centroid as though they were planar coordinates. Then you would simply take the average of the latitudes and the average of the longitudes to find the latitude and longitude of the centroid.
lat = []
long = []
for l in L :
lat.append(l[0])
long.append(l[1])
sum(lat)/len(lat)
sum(long)/len(long)
-74.07461283333332, 40.76800886666667
Based on: https://gist.github.com/tlhunter/0ea604b77775b3e7d7d25ea0f70a23eb
Assume you have a pandas DataFrame with latitude and longitude columns, the next code will return a dictionary with the mean coordinates.
import math
x = 0.0
y = 0.0
z = 0.0
for i, coord in coords_df.iterrows():
latitude = math.radians(coord.latitude)
longitude = math.radians(coord.longitude)
x += math.cos(latitude) * math.cos(longitude)
y += math.cos(latitude) * math.sin(longitude)
z += math.sin(latitude)
total = len(coords_df)
x = x / total
y = y / total
z = z / total
central_longitude = math.atan2(y, x)
central_square_root = math.sqrt(x * x + y * y)
central_latitude = math.atan2(z, central_square_root)
mean_location = {
'latitude': math.degrees(central_latitude),
'longitude': math.degrees(central_longitude)
}
Considering that you are using signed degrees format (more), simple averaging of latitude and longitudes would create problems for even small regions near to antimeridian (i.e. + or - 180-degree longitude) due to discontinuity of longitude value at this line (sudden jump between -180 to 180).
Consider two locations whose longitudes are -179 and 179, their mean would be 0, which is wrong.
This link can be useful, first convert lat/lon into an n-vector, then find average. A first stab at converting the code into Python
is below
import numpy as np
import numpy.linalg as lin
E = np.array([[0, 0, 1],
[0, 1, 0],
[-1, 0, 0]])
def lat_long2n_E(latitude,longitude):
res = [np.sin(np.deg2rad(latitude)),
np.sin(np.deg2rad(longitude)) * np.cos(np.deg2rad(latitude)),
-np.cos(np.deg2rad(longitude)) * np.cos(np.deg2rad(latitude))]
return np.dot(E.T,np.array(res))
def n_E2lat_long(n_E):
n_E = np.dot(E, n_E)
longitude=np.arctan2(n_E[1],-n_E[2]);
equatorial_component = np.sqrt(n_E[1]**2 + n_E[2]**2 );
latitude=np.arctan2(n_E[0],equatorial_component);
return np.rad2deg(latitude), np.rad2deg(longitude)
def average(coords):
res = []
for lat,lon in coords:
res.append(lat_long2n_E(lat,lon))
res = np.array(res)
m = np.mean(res,axis=0)
m = m / lin.norm(m)
return n_E2lat_long(m)
n = lat_long2n_E(30,20)
print (n)
print (n_E2lat_long(np.array(n)))
# find middle of france and libya
coords = [[30,20],[47,3]]
m = average(coords)
print (m)
I would like to improve on the #BBSysDyn'S answer.
The average calculation can be biased if you are calculating the center of a polygon with extra vertices on one side. Therefore the average function can be replaced with centroid calculation explained here
def get_centroid(points):
x = points[:,0]
y = points[:,1]
# Solving for polygon signed area
A = 0
for i, value in enumerate(x):
if i + 1 == len(x):
A += (x[i]*y[0] - x[0]*y[i])
else:
A += (x[i]*y[i+1] - x[i+1]*y[i])
A = A/2
#solving x of centroid
Cx = 0
for i, value in enumerate(x):
if i + 1 == len(x):
Cx += (x[i]+x[0]) * ( (x[i]*y[0]) - (x[0]*y[i]) )
else:
Cx += (x[i]+x[i+1]) * ( (x[i]*y[i+1]) - (x[i+1]*y[i]) )
Cx = Cx/(6*A)
#solving y of centroid
Cy = 0
for i , value in enumerate(y):
if i+1 == len(x):
Cy += (y[i]+y[0]) * ( (x[i]*y[0]) - (x[0]*y[i]) )
else:
Cy += (y[i]+y[i+1]) * ( (x[i]*y[i+1]) - (x[i+1]*y[i]) )
Cy = Cy/(6*A)
return Cx, Cy
Note: If it is a polygon or more than 2 points, they must be listed in order that the polygon or shape would be drawn.

Categories

Resources