I have a set of points which approximate a 2D curve. I would like to use Python with numpy and scipy to find a cubic Bézier path which approximately fits the points, where I specify the exact coordinates of two endpoints, and it returns the coordinates of the other two control points.
I initially thought scipy.interpolate.splprep() might do what I want, but it seems to force the curve to pass through each one of the data points (as I suppose you would want for interpolation). I'll assume that I was on the wrong track with that.
My question is similar to this one: How can I fit a Bézier curve to a set of data?, except that they said they didn't want to use numpy. My preference would be to find what I need already implemented somewhere in scipy or numpy. Otherwise, I plan to implement the algorithm linked from one of the answers to that question, using numpy: An algorithm for automatically fitting digitized curves (pdf.page 622).
Thank you for any suggestions!
Edit: I understand that a cubic Bézier curve is not guaranteed to pass through all the points; I want one which passes through two given endpoints, and which is as close as possible to the specified interior points.
Here's a way to do Bezier curves with numpy:
import numpy as np
from scipy.special import comb
def bernstein_poly(i, n, t):
"""
The Bernstein polynomial of n, i as a function of t
"""
return comb(n, i) * ( t**(n-i) ) * (1 - t)**i
def bezier_curve(points, nTimes=1000):
"""
Given a set of control points, return the
bezier curve defined by the control points.
points should be a list of lists, or list of tuples
such as [ [1,1],
[2,3],
[4,5], ..[Xn, Yn] ]
nTimes is the number of time steps, defaults to 1000
See http://processingjs.nihongoresources.com/bezierinfo/
"""
nPoints = len(points)
xPoints = np.array([p[0] for p in points])
yPoints = np.array([p[1] for p in points])
t = np.linspace(0.0, 1.0, nTimes)
polynomial_array = np.array([ bernstein_poly(i, nPoints-1, t) for i in range(0, nPoints) ])
xvals = np.dot(xPoints, polynomial_array)
yvals = np.dot(yPoints, polynomial_array)
return xvals, yvals
if __name__ == "__main__":
from matplotlib import pyplot as plt
nPoints = 4
points = np.random.rand(nPoints,2)*200
xpoints = [p[0] for p in points]
ypoints = [p[1] for p in points]
xvals, yvals = bezier_curve(points, nTimes=1000)
plt.plot(xvals, yvals)
plt.plot(xpoints, ypoints, "ro")
for nr in range(len(points)):
plt.text(points[nr][0], points[nr][1], nr)
plt.show()
Here is a piece of python code for fitting points:
'''least square qbezier fit using penrose pseudoinverse
>>> V=array
>>> E, W, N, S = V((1,0)), V((-1,0)), V((0,1)), V((0,-1))
>>> cw = 100
>>> ch = 300
>>> cpb = V((0, 0))
>>> cpe = V((cw, 0))
>>> xys=[cpb,cpb+ch*N+E*cw/8,cpe+ch*N+E*cw/8, cpe]
>>>
>>> ts = V(range(11), dtype='float')/10
>>> M = bezierM (ts)
>>> points = M*xys #produces the points on the bezier curve at t in ts
>>>
>>> control_points=lsqfit(points, M)
>>> linalg.norm(control_points-xys)<10e-5
True
>>> control_points.tolist()[1]
[12.500000000000037, 300.00000000000017]
'''
from numpy import array, linalg, matrix
from scipy.misc import comb as nOk
Mtk = lambda n, t, k: t**(k)*(1-t)**(n-k)*nOk(n,k)
bezierM = lambda ts: matrix([[Mtk(3,t,k) for k in range(4)] for t in ts])
def lsqfit(points,M):
M_ = linalg.pinv(M)
return M_ * points
Generally on bezier curves check out
Animated bezier and
bezierinfo
Resulting Plot
Building upon the answers from #reptilicus and #Guillaume P., here is the complete code to:
Get the Bezier Parameters i.e. the control points from a list of points.
Create the Bezier Curve from the Bezier Parameters i.e. the control points.
Plot the original points, the control points and the resulting Bezier Curve.
Getting the Bezier Parameters i.e. the control points from a set of X,Y points or coordinates. The other parameter needed is the degree for the approximation and the resulting control points will be (degree + 1)
import numpy as np
from scipy.special import comb
def get_bezier_parameters(X, Y, degree=3):
""" Least square qbezier fit using penrose pseudoinverse.
Parameters:
X: array of x data.
Y: array of y data. Y[0] is the y point for X[0].
degree: degree of the Bézier curve. 2 for quadratic, 3 for cubic.
Based on https://stackoverflow.com/questions/12643079/b%C3%A9zier-curve-fitting-with-scipy
and probably on the 1998 thesis by Tim Andrew Pastva, "Bézier Curve Fitting".
"""
if degree < 1:
raise ValueError('degree must be 1 or greater.')
if len(X) != len(Y):
raise ValueError('X and Y must be of the same length.')
if len(X) < degree + 1:
raise ValueError(f'There must be at least {degree + 1} points to '
f'determine the parameters of a degree {degree} curve. '
f'Got only {len(X)} points.')
def bpoly(n, t, k):
""" Bernstein polynomial when a = 0 and b = 1. """
return t ** k * (1 - t) ** (n - k) * comb(n, k)
#return comb(n, i) * ( t**(n-i) ) * (1 - t)**i
def bmatrix(T):
""" Bernstein matrix for Bézier curves. """
return np.matrix([[bpoly(degree, t, k) for k in range(degree + 1)] for t in T])
def least_square_fit(points, M):
M_ = np.linalg.pinv(M)
return M_ * points
T = np.linspace(0, 1, len(X))
M = bmatrix(T)
points = np.array(list(zip(X, Y)))
final = least_square_fit(points, M).tolist()
final[0] = [X[0], Y[0]]
final[len(final)-1] = [X[len(X)-1], Y[len(Y)-1]]
return final
Create the Bezier curve given the Bezier Parameters i.e. control points.
def bernstein_poly(i, n, t):
"""
The Bernstein polynomial of n, i as a function of t
"""
return comb(n, i) * ( t**(n-i) ) * (1 - t)**i
def bezier_curve(points, nTimes=50):
"""
Given a set of control points, return the
bezier curve defined by the control points.
points should be a list of lists, or list of tuples
such as [ [1,1],
[2,3],
[4,5], ..[Xn, Yn] ]
nTimes is the number of time steps, defaults to 1000
See http://processingjs.nihongoresources.com/bezierinfo/
"""
nPoints = len(points)
xPoints = np.array([p[0] for p in points])
yPoints = np.array([p[1] for p in points])
t = np.linspace(0.0, 1.0, nTimes)
polynomial_array = np.array([ bernstein_poly(i, nPoints-1, t) for i in range(0, nPoints) ])
xvals = np.dot(xPoints, polynomial_array)
yvals = np.dot(yPoints, polynomial_array)
return xvals, yvals
Sample data used (can be replaced with any data, this is GPS data).
points = []
xpoints = [19.21270, 19.21269, 19.21268, 19.21266, 19.21264, 19.21263, 19.21261, 19.21261, 19.21264, 19.21268,19.21274, 19.21282, 19.21290, 19.21299, 19.21307, 19.21316, 19.21324, 19.21333, 19.21342]
ypoints = [-100.14895, -100.14885, -100.14875, -100.14865, -100.14855, -100.14847, -100.14840, -100.14832, -100.14827, -100.14823, -100.14818, -100.14818, -100.14818, -100.14818, -100.14819, -100.14819, -100.14819, -100.14820, -100.14820]
for i in range(len(xpoints)):
points.append([xpoints[i],ypoints[i]])
Plot the original points, the control points and the resulting Bezier Curve.
import matplotlib.pyplot as plt
# Plot the original points
plt.plot(xpoints, ypoints, "ro",label='Original Points')
# Get the Bezier parameters based on a degree.
data = get_bezier_parameters(xpoints, ypoints, degree=4)
x_val = [x[0] for x in data]
y_val = [x[1] for x in data]
print(data)
# Plot the control points
plt.plot(x_val,y_val,'k--o', label='Control Points')
# Plot the resulting Bezier curve
xvals, yvals = bezier_curve(data, nTimes=1000)
plt.plot(xvals, yvals, 'b-', label='B Curve')
plt.legend()
plt.show()
#keynesiancross asked for "comments in [Roland's] code as to what the variables are" and others completely missed the stated problem. Roland started with a Bézier curve as input (to get a perfect match), which made it harder to understand both the problem and (at least for me) the solution. The difference from interpolation is easier to see for input that leaves residuals. Here is both paraphrased code and non-Bézier input -- and an unexpected outcome.
import matplotlib.pyplot as plt
import numpy as np
from scipy.special import comb as n_over_k
Mtk = lambda n, t, k: t**k * (1-t)**(n-k) * n_over_k(n,k)
BézierCoeff = lambda ts: [[Mtk(3,t,k) for k in range(4)] for t in ts]
fcn = np.log
tPlot = np.linspace(0. ,1. , 81)
xPlot = np.linspace(0.1,2.5, 81)
tData = tPlot[0:81:10]
xData = xPlot[0:81:10]
data = np.column_stack((xData, fcn(xData))) # shapes (9,2)
Pseudoinverse = np.linalg.pinv(BézierCoeff(tData)) # (9,4) -> (4,9)
control_points = Pseudoinverse.dot(data) # (4,9)*(9,2) -> (4,2)
Bézier = np.array(BézierCoeff(tPlot)).dot(control_points)
residuum = fcn(Bézier[:,0]) - Bézier[:,1]
fig, ax = plt.subplots()
ax.plot(xPlot, fcn(xPlot), 'r-')
ax.plot(xData, data[:,1], 'ro', label='input')
ax.plot(Bézier[:,0],
Bézier[:,1], 'k-', label='fit')
ax.plot(xPlot, 10.*residuum, 'b-', label='10*residuum')
ax.plot(control_points[:,0],
control_points[:,1], 'ko:', fillstyle='none')
ax.legend()
fig.show()
This works well for fcn = np.cos but not for log. I kind of expected that the fit would use the t-component of the control points as additional degrees of freedom, as we would do by dragging the control points:
manual_points = np.array([[0.1,np.log(.1)],[.27,-.6],[.82,.23],[2.5,np.log(2.5)]])
Bézier = np.array(BézierCoeff(tPlot)).dot(manual_points)
residuum = fcn(Bézier[:,0]) - Bézier[:,1]
fig, ax = plt.subplots()
ax.plot(xPlot, fcn(xPlot), 'r-')
ax.plot(xData, data[:,1], 'ro', label='input')
ax.plot(Bézier[:,0],
Bézier[:,1], 'k-', label='fit')
ax.plot(xPlot, 10.*residuum, 'b-', label='10*residuum')
ax.plot(manual_points[:,0],
manual_points[:,1], 'ko:', fillstyle='none')
ax.legend()
fig.show()
The cause of failure, I guess, is that the norm measures the distance between points on the curves instead of the distance between a point on one curve to the nearest point on the other curve.
Short answer: you don't, because that's not how Bezier curves work. Longer answer: have a look at Catmull-Rom splines instead. They're pretty easy to form (the tangent vector at any point P, barring start and end, is parallel to the lines {P-1,P+1}, so they're easy to program, too) and always pass through the points that define them, unlike Bezier curves, which interpolates "somewhere" inside the convex hull set up by all the control points.
A Bezier curve isn't guaranteed to pass through every point you supply it with; control points are arbitrary (in the sense that there is no specific algorithm for finding them, you simply choose them yourself) and only pull the curve in a direction.
If you want a curve which will pass through every point you supply it with, you need something like a natural cubic spline, and due to the limitations of those (you must supply them with increasing x co-ordinates, or it tends to infinity), you'll probably want a parametric natural cubic spline.
There are nice tutorials here:
Cubic Splines
Parametric Cubic Splines
I had the same problem as detailed in the question. I took the code provided Roland Puntaier and was able to make it work. Here:
def get_bezier_parameters(X, Y, degree=2):
""" Least square qbezier fit using penrose pseudoinverse.
Parameters:
X: array of x data.
Y: array of y data. Y[0] is the y point for X[0].
degree: degree of the Bézier curve. 2 for quadratic, 3 for cubic.
Based on https://stackoverflow.com/questions/12643079/b%C3%A9zier-curve-fitting-with-scipy
and probably on the 1998 thesis by Tim Andrew Pastva, "Bézier Curve Fitting".
"""
if degree < 1:
raise ValueError('degree must be 1 or greater.')
if len(X) != len(Y):
raise ValueError('X and Y must be of the same length.')
if len(X) < degree + 1:
raise ValueError(f'There must be at least {degree + 1} points to '
f'determine the parameters of a degree {degree} curve. '
f'Got only {len(X)} points.')
def bpoly(n, t, k):
""" Bernstein polynomial when a = 0 and b = 1. """
return t ** k * (1 - t) ** (n - k) * comb(n, k)
def bmatrix(T):
""" Bernstein matrix for Bézier curves. """
return np.matrix([[bpoly(degree, t, k) for k in range(degree + 1)] for t in T])
def least_square_fit(points, M):
M_ = np.linalg.pinv(M)
return M_ * points
T = np.linspace(0, 1, len(X))
M = bmatrix(T)
points = np.array(list(zip(X, Y)))
return least_square_fit(points, M).tolist()
To fix the end points of the curve, ignore the first and last parameter returned by the function and use your own points.
What Mike Kamermans said is true, but I also wanted to point out that, as far as I know, catmull-rom splines can be defined in terms of cubic beziers. So, if you only have a library that works with cubics, you should still be able to do catmull-rom splines:
http://schepers.cc/getting-to-the-point
https://github.com/DmitryBaranovskiy/raphael/blob/d8fbe4be81d362837f95e33886b80fb41de443b4/dev/raphael.core.js#L1021
Related
I have several points on the unit sphere that are distributed according to the algorithm described in https://www.cmu.edu/biolphys/deserno/pdf/sphere_equi.pdf (and implemented in the code below). On each of these points, I have a value that in my particular case represents 1 minus a small error. The errors are in [0, 0.1] if this is important, so my values are in [0.9, 1].
Sadly, computing the errors is a costly process and I cannot do this for as many points as I want. Still, I want my plots to look like I am plotting something "continuous".
So I want to fit an interpolation function to my data, to be able to sample as many points as I want.
After a little bit of research I found scipy.interpolate.SmoothSphereBivariateSpline which seems to do exactly what I want. But I cannot make it work properly.
Question: what can I use to interpolate (spline, linear interpolation, anything would be fine for the moment) my data on the unit sphere? An answer can be either "you misused scipy.interpolation, here is the correct way to do this" or "this other function is better suited to your problem".
Sample code that should be executable with numpy and scipy installed:
import typing as ty
import numpy
import scipy.interpolate
def get_equidistant_points(N: int) -> ty.List[numpy.ndarray]:
"""Generate approximately n points evenly distributed accros the 3-d sphere.
This function tries to find approximately n points (might be a little less
or more) that are evenly distributed accros the 3-dimensional unit sphere.
The algorithm used is described in
https://www.cmu.edu/biolphys/deserno/pdf/sphere_equi.pdf.
"""
# Unit sphere
r = 1
points: ty.List[numpy.ndarray] = list()
a = 4 * numpy.pi * r ** 2 / N
d = numpy.sqrt(a)
m_v = int(numpy.round(numpy.pi / d))
d_v = numpy.pi / m_v
d_phi = a / d_v
for m in range(m_v):
v = numpy.pi * (m + 0.5) / m_v
m_phi = int(numpy.round(2 * numpy.pi * numpy.sin(v) / d_phi))
for n in range(m_phi):
phi = 2 * numpy.pi * n / m_phi
points.append(
numpy.array(
[
numpy.sin(v) * numpy.cos(phi),
numpy.sin(v) * numpy.sin(phi),
numpy.cos(v),
]
)
)
return points
def cartesian2spherical(x: float, y: float, z: float) -> numpy.ndarray:
r = numpy.linalg.norm([x, y, z])
theta = numpy.arccos(z / r)
phi = numpy.arctan2(y, x)
return numpy.array([r, theta, phi])
n = 100
points = get_equidistant_points(n)
# Random here, but costly in real life.
errors = numpy.random.rand(len(points)) / 10
# Change everything to spherical to use the interpolator from scipy.
ideal_spherical_points = numpy.array([cartesian2spherical(*point) for point in points])
r_interp = 1 - errors
theta_interp = ideal_spherical_points[:, 1]
phi_interp = ideal_spherical_points[:, 2]
# Change phi coordinate from [-pi, pi] to [0, 2pi] to please scipy.
phi_interp[phi_interp < 0] += 2 * numpy.pi
# Create the interpolator.
interpolator = scipy.interpolate.SmoothSphereBivariateSpline(
theta_interp, phi_interp, r_interp
)
# Creating the finer theta and phi values for the final plot
theta = numpy.linspace(0, numpy.pi, 100, endpoint=True)
phi = numpy.linspace(0, numpy.pi * 2, 100, endpoint=True)
# Creating the coordinate grid for the unit sphere.
X = numpy.outer(numpy.sin(theta), numpy.cos(phi))
Y = numpy.outer(numpy.sin(theta), numpy.sin(phi))
Z = numpy.outer(numpy.cos(theta), numpy.ones(100))
thetas, phis = numpy.meshgrid(theta, phi)
heatmap = interpolator(thetas, phis)
Issue with the code above:
With the code as-is, I have a
ValueError: The required storage space exceeds the available storage space: nxest or nyest too small, or s too small. The weighted least-squares spline corresponds to the current set of knots.
that is raised when initialising the interpolator instance.
The issue above seems to say that I should change the value of s that is one on the parameters of scipy.interpolate.SmoothSphereBivariateSpline. I tested different values of s ranging from 0.0001 to 100000, the code above always raise, either the exception described above or:
ValueError: Error code returned by bispev: 10
Edit: I am including my findings here. They can't really be considered as a solution, that is why I am editing and not posting as an answer.
With more research I found this question Using Radial Basis Functions to Interpolate a Function on a Sphere. The author has exactly the same problem as me and use a different interpolator: scipy.interpolate.Rbf. I changed the above code by replacing the interpolator and plotting:
# Create the interpolator.
interpolator = scipy.interpolate.Rbf(theta_interp, phi_interp, r_interp)
# Creating the finer theta and phi values for the final plot
plot_points = 100
theta = numpy.linspace(0, numpy.pi, plot_points, endpoint=True)
phi = numpy.linspace(0, numpy.pi * 2, plot_points, endpoint=True)
# Creating the coordinate grid for the unit sphere.
X = numpy.outer(numpy.sin(theta), numpy.cos(phi))
Y = numpy.outer(numpy.sin(theta), numpy.sin(phi))
Z = numpy.outer(numpy.cos(theta), numpy.ones(plot_points))
thetas, phis = numpy.meshgrid(theta, phi)
heatmap = interpolator(thetas, phis)
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib import cm
colormap = cm.inferno
normaliser = mpl.colors.Normalize(vmin=numpy.min(heatmap), vmax=1)
scalar_mappable = cm.ScalarMappable(cmap=colormap, norm=normaliser)
scalar_mappable.set_array([])
fig = plt.figure()
ax = fig.add_subplot(111, projection="3d")
ax.plot_surface(
X,
Y,
Z,
facecolors=colormap(normaliser(heatmap)),
alpha=0.7,
cmap=colormap,
)
plt.colorbar(scalar_mappable)
plt.show()
This code runs smoothly and gives the following result:
The interpolation seems OK except on one line that is discontinuous, just like in the question that led me to this class. One of the answer give the idea of using a different distance, more adapted the the spherical coordinates: the Haversine distance.
def haversine(x1, x2):
theta1, phi1 = x1
theta2, phi2 = x2
return 2 * numpy.arcsin(
numpy.sqrt(
numpy.sin((theta2 - theta1) / 2) ** 2
+ numpy.cos(theta1) * numpy.cos(theta2) * numpy.sin((phi2 - phi1) / 2) ** 2
)
)
# Create the interpolator.
interpolator = scipy.interpolate.Rbf(theta_interp, phi_interp, r_interp, norm=haversine)
which, when executed, gives a warning:
LinAlgWarning: Ill-conditioned matrix (rcond=1.33262e-19): result may not be accurate.
self.nodes = linalg.solve(self.A, self.di)
and a result that is not at all the one expected: the interpolated function have values that may go up to -1 which is clearly wrong.
You can use Cartesian coordinate instead of Spherical coordinate.
The default norm parameter ('euclidean') used by Rbf is sufficient
# interpolation
x, y, z = numpy.array(points).T
interpolator = scipy.interpolate.Rbf(x, y, z, r_interp)
# predict
heatmap = interpolator(X, Y, Z)
Here the result:
ax.plot_surface(
X, Y, Z,
rstride=1, cstride=1,
# or rcount=50, ccount=50,
facecolors=colormap(normaliser(heatmap)),
cmap=colormap,
alpha=0.7, shade=False
)
ax.set_xlabel('x axis')
ax.set_ylabel('y axis')
ax.set_zlabel('z axis')
You can also use a cosine distance if you want (norm parameter):
def cosine(XA, XB):
if XA.ndim == 1:
XA = numpy.expand_dims(XA, axis=0)
if XB.ndim == 1:
XB = numpy.expand_dims(XB, axis=0)
return scipy.spatial.distance.cosine(XA, XB)
In order to better see the differences,
I stacked the two images, substracted them and inverted the layer.
I'm trying to work out how best to locate the centroid of an arbitrary shape draped over a unit sphere, with the input being ordered (clockwise or anti-cw) vertices for the shape boundary. The density of vertices is irregular along the boundary, so the arc-lengths between them are not generally equal. Because the shapes may be very large (half a hemisphere) it is generally not possible to simply project the vertices to a plane and use planar methods, as detailed on Wikipedia (sorry I'm not allowed more than 2 hyperlinks as a newcomer). A slightly better approach involves the use of planar geometry manipulated in spherical coordinates, but again, with large polygons this method fails, as nicely illustrated here. On that same page, 'Cffk' highlighted this paper which describes a method for calculating the centroid of spherical triangles. I've tried to implement this method, but without success, and I'm hoping someone can spot the problem?
I have kept the variable definitions similar to those in the paper to make it easier to compare. The input (data) is a list of longitude/latitude coordinates, converted to [x,y,z] coordinates by the code. For each of the triangles I have arbitrarily fixed one point to be the +z-pole, the other two vertices being composed of a pair of neighboring points along the polygon boundary. The code steps along the boundary (starting at an arbitrary point), using each boundary segment of the polygon as a triangle side in turn. A sub-centroid is determined for each of these individual spherical triangles and they are weighted according to triangle area and added to calculate the total polygon centroid. I don't get any errors when running the code, but the total centroids returned are clearly wrong (I have run some very basic shapes where the centroid location is unambiguous). I haven't found any sensible pattern in the location of the centroids returned...so at the moment I'm not sure what is going wrong, either in the math or code (although, the suspicion is the math).
The code below should work copy-paste as is if you would like to try it. If you have matplotlib and numpy installed, it will plot the results (it will ignore plotting if you don't). You just have to put the longitude/latitude data below the code into a text file called example.txt.
from math import *
try:
import matplotlib as mpl
import matplotlib.pyplot
from mpl_toolkits.mplot3d import Axes3D
import numpy
plotting_enabled = True
except ImportError:
plotting_enabled = False
def sph_car(point):
if len(point) == 2:
point.append(1.0)
rlon = radians(float(point[0]))
rlat = radians(float(point[1]))
x = cos(rlat) * cos(rlon) * point[2]
y = cos(rlat) * sin(rlon) * point[2]
z = sin(rlat) * point[2]
return [x, y, z]
def xprod(v1, v2):
x = v1[1] * v2[2] - v1[2] * v2[1]
y = v1[2] * v2[0] - v1[0] * v2[2]
z = v1[0] * v2[1] - v1[1] * v2[0]
return [x, y, z]
def dprod(v1, v2):
dot = 0
for i in range(3):
dot += v1[i] * v2[i]
return dot
def plot(poly_xyz, g_xyz):
fig = mpl.pyplot.figure()
ax = fig.add_subplot(111, projection='3d')
# plot the unit sphere
u = numpy.linspace(0, 2 * numpy.pi, 100)
v = numpy.linspace(-1 * numpy.pi / 2, numpy.pi / 2, 100)
x = numpy.outer(numpy.cos(u), numpy.sin(v))
y = numpy.outer(numpy.sin(u), numpy.sin(v))
z = numpy.outer(numpy.ones(numpy.size(u)), numpy.cos(v))
ax.plot_surface(x, y, z, rstride=4, cstride=4, color='w', linewidth=0,
alpha=0.3)
# plot 3d and flattened polygon
x, y, z = zip(*poly_xyz)
ax.plot(x, y, z)
ax.plot(x, y, zs=0)
# plot the alleged 3d and flattened centroid
x, y, z = g_xyz
ax.scatter(x, y, z, c='r')
ax.scatter(x, y, 0, c='r')
# display
ax.set_xlim3d(-1, 1)
ax.set_ylim3d(-1, 1)
ax.set_zlim3d(0, 1)
mpl.pyplot.show()
lons, lats, v = list(), list(), list()
# put the two-column data at the bottom of the question into a file called
# example.txt in the same directory as this script
with open('example.txt') as f:
for line in f.readlines():
sep = line.split()
lons.append(float(sep[0]))
lats.append(float(sep[1]))
# convert spherical coordinates to cartesian
for lon, lat in zip(lons, lats):
v.append(sph_car([lon, lat, 1.0]))
# z unit vector/pole ('north pole'). This is an arbitrary point selected to act as one
#(fixed) vertex of the summed spherical triangles. The other two vertices of any
#triangle are composed of neighboring vertices from the polygon boundary.
np = [0.0, 0.0, 1.0]
# Gx,Gy,Gz are the cartesian coordinates of the calculated centroid
Gx, Gy, Gz = 0.0, 0.0, 0.0
for i in range(-1, len(v) - 1):
# cycle through the boundary vertices of the polygon, from 0 to n
if all((v[i][0] != v[i+1][0],
v[i][1] != v[i+1][1],
v[i][2] != v[i+1][2])):
# this just ignores redundant points which are common in my larger input files
# A,B,C are the internal angles in the triangle: 'np-v[i]-v[i+1]-np'
A = asin(sqrt((dprod(np, xprod(v[i], v[i+1])))**2
/ ((1 - (dprod(v[i+1], np))**2) * (1 - (dprod(np, v[i]))**2))))
B = asin(sqrt((dprod(v[i], xprod(v[i+1], np)))**2
/ ((1 - (dprod(np , v[i]))**2) * (1 - (dprod(v[i], v[i+1]))**2))))
C = asin(sqrt((dprod(v[i + 1], xprod(np, v[i])))**2
/ ((1 - (dprod(v[i], v[i+1]))**2) * (1 - (dprod(v[i+1], np))**2))))
# A/B/Cbar are the vertex angles, such that if 'O' is the sphere center, Abar
# is the angle (v[i]-O-v[i+1])
Abar = acos(dprod(v[i], v[i+1]))
Bbar = acos(dprod(v[i+1], np))
Cbar = acos(dprod(np, v[i]))
# e is the 'spherical excess', as defined on wikipedia
e = A + B + C - pi
# mag1/2/3 are the magnitudes of vectors np,v[i] and v[i+1].
mag1 = 1.0
mag2 = float(sqrt(v[i][0]**2 + v[i][1]**2 + v[i][2]**2))
mag3 = float(sqrt(v[i+1][0]**2 + v[i+1][1]**2 + v[i+1][2]**2))
# vec1/2/3 are cross products, defined here to simplify the equation below.
vec1 = xprod(np, v[i])
vec2 = xprod(v[i], v[i+1])
vec3 = xprod(v[i+1], np)
# multiplying vec1/2/3 by e and respective internal angles, according to the
#posted paper
for x in range(3):
vec1[x] *= Cbar / (2 * e * mag1 * mag2
* sqrt(1 - (dprod(np, v[i])**2)))
vec2[x] *= Abar / (2 * e * mag2 * mag3
* sqrt(1 - (dprod(v[i], v[i+1])**2)))
vec3[x] *= Bbar / (2 * e * mag3 * mag1
* sqrt(1 - (dprod(v[i+1], np)**2)))
Gx += vec1[0] + vec2[0] + vec3[0]
Gy += vec1[1] + vec2[1] + vec3[1]
Gz += vec1[2] + vec2[2] + vec3[2]
approx_expected_Gxyz = (0.78, -0.56, 0.27)
print('Approximate Expected Gxyz: {0}\n'
' Actual Gxyz: {1}'
''.format(approx_expected_Gxyz, (Gx, Gy, Gz)))
if plotting_enabled:
plot(v, (Gx, Gy, Gz))
Thanks in advance for any suggestions or insight.
EDIT: Here is a figure that shows a projection of the unit sphere with a polygon and the resulting centroid I calculate from the code. Clearly, the centroid is wrong as the polygon is rather small and convex but yet the centroid falls outside its perimeter.
EDIT: Here is a highly-similar set of coordinates to those above, but in the original [lon,lat] format I normally use (which is now converted to [x,y,z] by the updated code).
-39.366295 -1.633460
-47.282630 -0.740433
-53.912136 0.741380
-59.004217 2.759183
-63.489005 5.426812
-68.566001 8.712068
-71.394853 11.659135
-66.629580 15.362600
-67.632276 16.827507
-66.459524 19.069327
-63.819523 21.446736
-61.672712 23.532143
-57.538431 25.947815
-52.519889 28.691766
-48.606227 30.646295
-45.000447 31.089437
-41.549866 32.139873
-36.605156 32.956277
-32.010080 34.156692
-29.730629 33.756566
-26.158767 33.714080
-25.821513 34.179648
-23.614658 36.173719
-20.896869 36.977645
-17.991994 35.600074
-13.375742 32.581447
-9.554027 28.675497
-7.825604 26.535234
-7.825604 26.535234
-9.094304 23.363132
-9.564002 22.527385
-9.713885 22.217165
-9.948596 20.367878
-10.496531 16.486580
-11.151919 12.666850
-12.350144 8.800367
-15.446347 4.993373
-20.366139 1.132118
-24.784805 -0.927448
-31.532135 -1.910227
-39.366295 -1.633460
EDIT: A couple more examples...with 4 vertices defining a perfect square centered at [1,0,0] I get the expected result:
However, from a non-symmetric triangle I get a centroid that is nowhere close...the centroid actually falls on the far side of the sphere (here projected onto the front side as the antipode):
Interestingly, the centroid estimation appears 'stable' in the sense that if I invert the list (go from clockwise to counterclockwise order or vice-versa) the centroid correspondingly inverts exactly.
Anybody finding this, make sure to check Don Hatch's answer which is probably better.
I think this will do it. You should be able to reproduce this result by just copy-pasting the code below.
You will need to have the latitude and longitude data in a file called longitude and latitude.txt. You can copy-paste the original sample data which is included below the code.
If you have mplotlib it will additionally produce the plot below
For non-obvious calculations, I included a link that explains what is going on
In the graph below, the reference vector is very short (r = 1/10) so that the 3d-centroids are easier to see. You can easily remove the scaling to maximize accuracy.
Note to op: I rewrote almost everything so I'm not sure exactly where the original code was not working. However, at least I think it was not taking into consideration the need to handle clockwise / counterclockwise triangle vertices.
Legend:
(black line) reference vector
(small red dots) spherical triangle 3d-centroids
(large red / blue / green dot) 3d-centroid / projected to the surface / projected to the xy plane
(blue / green lines) the spherical polygon and the projection onto the xy plane
from math import *
try:
import matplotlib as mpl
import matplotlib.pyplot
from mpl_toolkits.mplot3d import Axes3D
import numpy
plotting_enabled = True
except ImportError:
plotting_enabled = False
def main():
# get base polygon data based on unit sphere
r = 1.0
polygon = get_cartesian_polygon_data(r)
point_count = len(polygon)
reference = ok_reference_for_polygon(polygon)
# decompose the polygon into triangles and record each area and 3d centroid
areas, subcentroids = list(), list()
for ia, a in enumerate(polygon):
# build an a-b-c point set
ib = (ia + 1) % point_count
b, c = polygon[ib], reference
if points_are_equivalent(a, b, 0.001):
continue # skip nearly identical points
# store the area and 3d centroid
areas.append(area_of_spherical_triangle(r, a, b, c))
tx, ty, tz = zip(a, b, c)
subcentroids.append((sum(tx)/3.0,
sum(ty)/3.0,
sum(tz)/3.0))
# combine all the centroids, weighted by their areas
total_area = sum(areas)
subxs, subys, subzs = zip(*subcentroids)
_3d_centroid = (sum(a*subx for a, subx in zip(areas, subxs))/total_area,
sum(a*suby for a, suby in zip(areas, subys))/total_area,
sum(a*subz for a, subz in zip(areas, subzs))/total_area)
# shift the final centroid to the surface
surface_centroid = scale_v(1.0 / mag(_3d_centroid), _3d_centroid)
plot(polygon, reference, _3d_centroid, surface_centroid, subcentroids)
def get_cartesian_polygon_data(fixed_radius):
cartesians = list()
with open('longitude and latitude.txt') as f:
for line in f.readlines():
spherical_point = [float(v) for v in line.split()]
if len(spherical_point) == 2:
spherical_point.append(fixed_radius)
cartesians.append(degree_spherical_to_cartesian(spherical_point))
return cartesians
def ok_reference_for_polygon(polygon):
point_count = len(polygon)
# fix the average of all vectors to minimize float skew
polyx, polyy, polyz = zip(*polygon)
# /10 is for visualization. Remove it to maximize accuracy
return (sum(polyx)/(point_count*10.0),
sum(polyy)/(point_count*10.0),
sum(polyz)/(point_count*10.0))
def points_are_equivalent(a, b, vague_tolerance):
# vague tolerance is something like a percentage tolerance (1% = 0.01)
(ax, ay, az), (bx, by, bz) = a, b
return all(((ax-bx)/ax < vague_tolerance,
(ay-by)/ay < vague_tolerance,
(az-bz)/az < vague_tolerance))
def degree_spherical_to_cartesian(point):
rad_lon, rad_lat, r = radians(point[0]), radians(point[1]), point[2]
x = r * cos(rad_lat) * cos(rad_lon)
y = r * cos(rad_lat) * sin(rad_lon)
z = r * sin(rad_lat)
return x, y, z
def area_of_spherical_triangle(r, a, b, c):
# points abc
# build an angle set: A(CAB), B(ABC), C(BCA)
# http://math.stackexchange.com/a/66731/25581
A, B, C = surface_points_to_surface_radians(a, b, c)
E = A + B + C - pi # E is called the spherical excess
area = r**2 * E
# add or subtract area based on clockwise-ness of a-b-c
# http://stackoverflow.com/a/10032657/377366
if clockwise_or_counter(a, b, c) == 'counter':
area *= -1.0
return area
def surface_points_to_surface_radians(a, b, c):
"""build an angle set: A(cab), B(abc), C(bca)"""
points = a, b, c
angles = list()
for i, mid in enumerate(points):
start, end = points[(i - 1) % 3], points[(i + 1) % 3]
x_startmid, x_endmid = xprod(start, mid), xprod(end, mid)
ratio = (dprod(x_startmid, x_endmid)
/ ((mag(x_startmid) * mag(x_endmid))))
angles.append(acos(ratio))
return angles
def clockwise_or_counter(a, b, c):
ab = diff_cartesians(b, a)
bc = diff_cartesians(c, b)
x = xprod(ab, bc)
if x < 0:
return 'clockwise'
elif x > 0:
return 'counter'
else:
raise RuntimeError('The reference point is in the polygon.')
def diff_cartesians(positive, negative):
return tuple(p - n for p, n in zip(positive, negative))
def xprod(v1, v2):
x = v1[1] * v2[2] - v1[2] * v2[1]
y = v1[2] * v2[0] - v1[0] * v2[2]
z = v1[0] * v2[1] - v1[1] * v2[0]
return [x, y, z]
def dprod(v1, v2):
dot = 0
for i in range(3):
dot += v1[i] * v2[i]
return dot
def mag(v1):
return sqrt(v1[0]**2 + v1[1]**2 + v1[2]**2)
def scale_v(scalar, v):
return tuple(scalar * vi for vi in v)
def plot(polygon, reference, _3d_centroid, surface_centroid, subcentroids):
fig = mpl.pyplot.figure()
ax = fig.add_subplot(111, projection='3d')
# plot the unit sphere
u = numpy.linspace(0, 2 * numpy.pi, 100)
v = numpy.linspace(-1 * numpy.pi / 2, numpy.pi / 2, 100)
x = numpy.outer(numpy.cos(u), numpy.sin(v))
y = numpy.outer(numpy.sin(u), numpy.sin(v))
z = numpy.outer(numpy.ones(numpy.size(u)), numpy.cos(v))
ax.plot_surface(x, y, z, rstride=4, cstride=4, color='w', linewidth=0,
alpha=0.3)
# plot 3d and flattened polygon
x, y, z = zip(*polygon)
ax.plot(x, y, z, c='b')
ax.plot(x, y, zs=0, c='g')
# plot the 3d centroid
x, y, z = _3d_centroid
ax.scatter(x, y, z, c='r', s=20)
# plot the spherical surface centroid and flattened centroid
x, y, z = surface_centroid
ax.scatter(x, y, z, c='b', s=20)
ax.scatter(x, y, 0, c='g', s=20)
# plot the full set of triangular centroids
x, y, z = zip(*subcentroids)
ax.scatter(x, y, z, c='r', s=4)
# plot the reference vector used to findsub centroids
x, y, z = reference
ax.plot((0, x), (0, y), (0, z), c='k')
ax.scatter(x, y, z, c='k', marker='^')
# display
ax.set_xlim3d(-1, 1)
ax.set_ylim3d(-1, 1)
ax.set_zlim3d(0, 1)
mpl.pyplot.show()
# run it in a function so the main code can appear at the top
main()
Here is the longitude and latitude data you can paste into longitude and latitude.txt
-39.366295 -1.633460
-47.282630 -0.740433
-53.912136 0.741380
-59.004217 2.759183
-63.489005 5.426812
-68.566001 8.712068
-71.394853 11.659135
-66.629580 15.362600
-67.632276 16.827507
-66.459524 19.069327
-63.819523 21.446736
-61.672712 23.532143
-57.538431 25.947815
-52.519889 28.691766
-48.606227 30.646295
-45.000447 31.089437
-41.549866 32.139873
-36.605156 32.956277
-32.010080 34.156692
-29.730629 33.756566
-26.158767 33.714080
-25.821513 34.179648
-23.614658 36.173719
-20.896869 36.977645
-17.991994 35.600074
-13.375742 32.581447
-9.554027 28.675497
-7.825604 26.535234
-7.825604 26.535234
-9.094304 23.363132
-9.564002 22.527385
-9.713885 22.217165
-9.948596 20.367878
-10.496531 16.486580
-11.151919 12.666850
-12.350144 8.800367
-15.446347 4.993373
-20.366139 1.132118
-24.784805 -0.927448
-31.532135 -1.910227
-39.366295 -1.633460
To clarify: the quantity of interest is the projection of the true 3d centroid
(i.e. 3d center-of-mass, i.e. 3d center-of-area) onto the unit sphere.
Since all you care about is the direction from the origin to the 3d centroid,
you don't need to bother with areas at all;
it's easier to just compute the moment (i.e. 3d centroid times area).
The moment of the region to the left of a closed path on the unit sphere
is half the integral of the leftward unit vector as you walk around the path.
This follows from a non-obvious application of Stokes' theorem; see Frank Jones's vector calculus book, chapter 13 Problem 13-12.
In particular, for a spherical polygon, the moment is half the sum of
(a x b) / ||a x b|| * (angle between a and b) for each pair of consecutive vertices a,b.
(That's for the region to the left of the path;
negate it for the region to the right of the path.)
(And if you really did want the 3d centroid, just compute the area and divide the moment by it. Comparing areas might also be useful in choosing which of the two regions to call "the polygon".)
Here's some code; it's really simple:
#!/usr/bin/python
import math
def plus(a,b): return [x+y for x,y in zip(a,b)]
def minus(a,b): return [x-y for x,y in zip(a,b)]
def cross(a,b): return [a[1]*b[2]-a[2]*b[1], a[2]*b[0]-a[0]*b[2], a[0]*b[1]-a[1]*b[0]]
def dot(a,b): return sum([x*y for x,y in zip(a,b)])
def length(v): return math.sqrt(dot(v,v))
def normalized(v): l = length(v); return [1,0,0] if l==0 else [x/l for x in v]
def addVectorTimesScalar(accumulator, vector, scalar):
for i in xrange(len(accumulator)): accumulator[i] += vector[i] * scalar
def angleBetweenUnitVectors(a,b):
# https://www.plunk.org/~hatch/rightway.html
if dot(a,b) < 0:
return math.pi - 2*math.asin(length(plus(a,b))/2.)
else:
return 2*math.asin(length(minus(a,b))/2.)
def sphericalPolygonMoment(verts):
moment = [0.,0.,0.]
for i in xrange(len(verts)):
a = verts[i]
b = verts[(i+1)%len(verts)]
addVectorTimesScalar(moment, normalized(cross(a,b)),
angleBetweenUnitVectors(a,b) / 2.)
return moment
if __name__ == '__main__':
import sys
def lonlat_degrees_to_xyz(lon_degrees,lat_degrees):
lon = lon_degrees*(math.pi/180)
lat = lat_degrees*(math.pi/180)
coslat = math.cos(lat)
return [coslat*math.cos(lon), coslat*math.sin(lon), math.sin(lat)]
verts = [lonlat_degrees_to_xyz(*[float(v) for v in line.split()])
for line in sys.stdin.readlines()]
#print "verts = "+`verts`
moment = sphericalPolygonMoment(verts)
print "moment = "+`moment`
print "centroid unit direction = "+`normalized(moment)`
For the example polygon, this gives the answer (unit vector):
[-0.7644875430808217, 0.579935445918147, -0.2814847687566214]
This is roughly the same as, but more accurate than, the answer computed by #KobeJohn's code, which uses rough tolerances and planar approximations to the sub-centroids:
[0.7628095787179151, -0.5977153368303585, 0.24669398601094406]
The directions of the two answers are roughly opposite (so I guess KobeJohn's code
decided to take the region to the right of the path in this case).
I think a good approximation would be to compute the center of mass using weighted cartesian coordinates and projecting the result onto the sphere (supposing the origin of coordinates is (0, 0, 0)^T).
Let be (p[0], p[1], ... p[n-1]) the n points of the polygon. The approximative (cartesian) centroid can be computed by:
c = 1 / w * (sum of w[i] * p[i])
whereas w is the sum of all weights and whereas p[i] is a polygon point and w[i] is a weight for that point, e.g.
w[i] = |p[i] - p[(i - 1 + n) % n]| / 2 + |p[i] - p[(i + 1) % n]| / 2
whereas |x| is the length of a vector x.
I.e. a point is weighted with half the length to the previous and half the length to the next polygon point.
This centroid c can now projected onto the sphere by:
c' = r * c / |c|
whereas r is the radius of the sphere.
To consider orientation of polygon (ccw, cw) the result may be
c' = - r * c / |c|.
Sorry I (as a newly registered user) had to write a new post instead of just voting/commenting on the above answer by Don Hatch. Don's answer, I think, is the best and most elegant. It is mathematically rigorous in computing the center of mass (first moment of mass) in a simple way when applying to the spherical polygon.
Kobe John's answer is a good approximation but only satisfactory for smaller areas. I also noticed a few glitches in the code. Firstly, the reference point should be projected to the spherical surface to compute the actual spherical area. Secondly, function points_are_equivalent() might need to be refined to avoid divided-by-zero.
The approximation error in Kobe's method lies in the calculation of the centroid of spherical triangles. The sub-centroid is NOT the center of mass of the spherical triangle but the planar one. This is not an issue if one is to determine that single triangle (sign may flip, see below). It is also not an issue if triangles are small (e.g. a dense triangulation of the polygon).
A few simple tests could illustrate the approximation error. For example if we use just four points:
10 -20
10 20
-10 20
-10 -20
The exact answer is (1,0,0) and both methods are good. But if you throw in a few more points along one edge (e.g. add {10,-15},{10,-10}... to the first edge), you'll see the results from Kobe's method start to shift. Further more, if you increase the longitude from [10,-10] to [100,-100], you'll see Kobe's result flips the direction. A possible improvement might be to add another level(s) for sub-centroid calculation (basically refine/reduce sizes of triangles).
For our application, the spherical area boundary is composed of multiple arcs and thus not polygon (i.e. the arc is not part of great circle). But this will just be a little more work to find the n-vector in the curve integration.
EDIT: Replacing the subcentroid calculation with the one given in Brock's paper should fix Kobe's method. But I did not try though.
I'm trying to plot the streamlines of a magnetic field around a sphere using matplotlib, and it does work quite nicely. However, the resulting image is not symmetric, but it should be (I think).
This is the code used to generate the image. Excuse the length, but I thought it would be better than just posting a non-working snippet. Also, it's not very pythonic; that's because I converted it from Matlab, which was easier than I expected.
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.patches import Circle
def cart2spherical(x, y, z):
r = np.sqrt(x**2 + y**2 + z**2)
phi = np.arctan2(y, x)
theta = np.arccos(z/r)
if r == 0:
theta = 0
return (r, theta, phi)
def S(theta, phi):
S = np.array([[np.sin(theta)*np.cos(phi), np.cos(theta)*np.cos(phi), -np.sin(phi)],
[np.sin(theta)*np.sin(phi), np.cos(theta)*np.sin(phi), np.cos(phi)],
[np.cos(theta), -np.sin(theta), 0]])
return S
def computeB(r, theta, phi, a=1, muR=100, B0=1):
delta = (muR - 1)/(muR + 2)
if r > a:
Bspherical = B0*np.array([np.cos(theta) * (1 + 2*delta*a**3 / r**3),
np.sin(theta) * (delta*a**3 / r**3 - 1),
0])
B = np.dot(S(theta, phi), Bspherical)
else:
B = 3*B0*(muR / (muR + 2)) * np.array([0, 0, 1])
return B
Z, X = np.mgrid[-2.5:2.5:1000j, -2.5:2.5:1000j]
Bx = np.zeros(np.shape(X))
Bz = np.zeros(np.shape(X))
Babs = np.zeros(np.shape(X))
for i in range(len(X)):
for j in range(len(Z)):
r, theta, phi = cart2spherical(X[0, i], 0, Z[j, 0])
B = computeB(r, theta, phi)
Bx[i, j], Bz[i, j] = B[0], B[2]
Babs[i, j] = np.sqrt(B[0]**2 + B[1]**2 + B[2]**2)
fig=plt.figure()
ax=fig.add_subplot(111)
plt.streamplot(X, Z, Bx, Bz, color='k', linewidth=0.8*Babs, density=1.3,
minlength=0.9, arrowstyle='-')
ax.add_patch(Circle((0, 0), radius=1, facecolor='none', linewidth=2))
plt.axis('equal')
plt.axis('off')
fig.savefig('streamlines.pdf', transparent=True, bbox_inches='tight', pad_inches=0)
First of all, for curiosity, why would you want to plot symmetric data? Why plotting half of isn't fine?
Said that, this is a possible hack. You can use mask arrays as Hooked suggested to plot half of it:
mask = X>0
BX_OUT = Bx.copy()
BZ_OUT = Bz.copy()
BX_OUT[mask] = None
BZ_OUT[mask] = None
res = plt.streamplot(X, Z, BX_OUT, BZ_OUT, color='k',
arrowstyle='-',linewidth=1,density=2)
then you save in res the result from streamplot, extract the lines and plot them with the opposite X coordinate.
lines = res.lines.get_paths()
for l in lines:
plot(-l.vertices.T[0],l.vertices.T[1],'k')
I used this hack to extract streamlines and arrows from a 2D plot, then apply a 3D transformation and plot it with mplot3d. A picture is in one of my questions here.
Quoting from the documentation:
density : float or 2-tuple
Controls the closeness of streamlines. When density = 1,
the domain is divided into
a 25x25 grid—density linearly scales this grid.
Each cell in the grid can have, at most, one traversing streamline.
For different densities in each direction, use [density_x, density_y].
so you are getting aliasing effects between the cells it uses to decide where the stream lines are, and the symmetries of your problem. You need to carefully choose your grid size (of the data) and the density.
It is also sensitive to where the box boundaries are relative to the top of the sphere. Is the center of your sphere on a data grid point or between the data grid points? If it is on a grid point then the box that contains the center point will be different than the boxes adjacent to it.
I am not familiar with exactly how it decides which stream lines to draw, but I could imagine that it is some sort of greedy algorithm and hence will give different results walking towards the high density region and away density region.
To be clear, you issue is not that the stream lines are wrong, they are valid stream lines, it is that you find the result not aesthetically pleasing.
Use a mask to separate the two regions of interest:
mask = np.sqrt(X**2+Z**2)<1
BX_OUT = Bx.copy()
BZ_OUT = Bz.copy()
BX_OUT[mask] = None
BZ_OUT[mask] = None
plt.streamplot(X, Z, BX_OUT, BZ_OUT, color='k',
arrowstyle='-', density=2)
BX_IN = Bx.copy()
BZ_IN = Bz.copy()
BX_IN[~mask] = None
BZ_IN[~mask] = None
plt.streamplot(X, Z, BX_IN, BZ_IN, color='r',
arrowstyle='-', density=2)
The resulting plot isn't exactly symmetric, but by giving the algorithm a hint, it's far closer than what you had before. Play with the density of the grid via meshgrid and the density parameter to achieve the effect you are looking for.
Use physics, instead... The magnetic field is symmetrical with respect to the z (vertical) axis! So you just need two streamplot's:
plt.streamplot(X, Z, Bx, Bz, color='k', linewidth=0.8*Babs, density=1.3, minlength=0.9, arrowstyle='-')
plt.streamplot(-X, Z, -Bx, Bz, color='k', linewidth=0.8*Babs, density=1.3, minlength=0.9, arrowstyle='-')
I am trying to use circle fitting code for 3D data set. I have modified it for 3D points just adding z-coordinate where necessary. My modification works fine for one set of points and works bad for another. Please look at the code, if it has some errors.
import trig_items
import numpy as np
from trig_items import *
from numpy import *
from matplotlib import pyplot as p
from scipy import optimize
# Coordinates of the 3D points
##x = r_[36, 36, 19, 18, 33, 26]
##y = r_[14, 10, 28, 31, 18, 26]
##z = r_[0, 1, 2, 3, 4, 5]
x = r_[ 2144.18908574, 2144.26880854, 2144.05552972, 2143.90303742, 2143.62520676,
2143.43628579, 2143.14005775, 2142.79919654, 2142.51436023, 2142.11240866,
2141.68564346, 2141.29333828, 2140.92596405, 2140.3475612, 2139.90848046,
2139.24661021, 2138.67384709, 2138.03313547, 2137.40301734, 2137.40908256,
2137.06611224, 2136.50943781, 2136.0553113, 2135.50313189, 2135.07049922,
2134.62098139, 2134.10459535, 2133.50838433, 2130.6600465, 2130.03537342,
2130.04047644, 2128.83522468, 2127.79827542, 2126.43513385, 2125.36700593,
2124.00350543, 2122.68564431, 2121.20709478, 2119.79047011, 2118.38417647,
2116.90063343, 2115.52685778, 2113.82246629, 2112.21159431, 2110.63180117,
2109.00713198, 2108.94434529, 2106.82777156, 2100.62343757, 2098.5090226,
2096.28787738, 2093.91550703, 2091.66075061, 2089.15316429, 2086.69753869,
2084.3002414, 2081.87590579, 2079.19141866, 2076.5394574, 2073.89128676,
2071.18786213]
y = r_[ 725.74913818, 724.43874065, 723.15226506, 720.45950581, 717.77827954,
715.07048092, 712.39633862, 709.73267688, 707.06039438, 704.43405908,
701.80074596, 699.15371526, 696.5309022, 693.96109921, 691.35585501,
688.83496327, 686.32148661, 683.80286662, 681.30705568, 681.30530975,
679.66483676, 678.01922321, 676.32721779, 674.6667554, 672.9658024,
671.23686095, 669.52021535, 667.84999077, 659.19757984, 657.46179949,
657.45700508, 654.46901086, 651.38177517, 648.41739432, 645.32356976,
642.39034578, 639.42628453, 636.51107198, 633.57732055, 630.63825133,
627.75308356, 624.80162215, 622.01980232, 619.18814892, 616.37688894,
613.57400131, 613.61535723, 610.4724493, 600.98277781, 597.84782844,
594.75983001, 591.77946964, 588.74874068, 585.84525834, 582.92311166,
579.99564481, 577.06666417, 574.30782762, 571.54115037, 568.79760614,
566.08551098]
z = r_[ 339.77146775, 339.60021095, 339.47645894, 339.47130963, 339.37216218,
339.4126132, 339.67942046, 339.40917728, 339.39500353, 339.15041461,
339.38959195, 339.3358209, 339.47764895, 339.17854867, 339.14624071,
339.16403926, 339.02308811, 339.27011082, 338.97684183, 338.95087698,
338.97321177, 339.02175448, 339.02543922, 338.88725411, 339.06942374,
339.0557553, 339.04414618, 338.89234303, 338.95572249, 339.00880416,
339.00413073, 338.91080374, 338.98214758, 339.01135789, 338.96393537,
338.73446188, 338.62784913, 338.72443217, 338.74880562, 338.69090173,
338.50765186, 338.49056867, 338.57353355, 338.6196255, 338.43754399,
338.27218569, 338.10587265, 338.43880881, 338.28962141, 338.14338705,
338.25784154, 338.49792568, 338.15572139, 338.52967693, 338.4594245,
338.1511823, 338.03711207, 338.19144663, 338.22022045, 338.29032321,
337.8623197 ]
# coordinates of the barycenter
xm = mean(x)
ym = mean(y)
zm = mean(z)
### Basic usage of optimize.leastsq
def calc_R(xc, yc, zc):
""" calculate the distance of each 3D points from the center (xc, yc, zc) """
return sqrt((x - xc) ** 2 + (y - yc) ** 2 + (z - zc) ** 2)
def func(c):
""" calculate the algebraic distance between the 3D points and the mean circle centered at c=(xc, yc, zc) """
Ri = calc_R(*c)
return Ri - Ri.mean()
center_estimate = xm, ym, zm
center, ier = optimize.leastsq(func, center_estimate)
##print center
xc, yc, zc = center
Ri = calc_R(xc, yc, zc)
R = Ri.mean()
residu = sum((Ri - R)**2)
print 'R =', R
So, for the first set of x, y, z (commented in the code) it works well: the output is R = 39.0097846735. If I run the code with the second set of points (uncommented) the resulting radius is R = 108576.859834, which is almost straight line. I plotted the last one.
The blue points is a given data set, the red ones is the arc of the resulting radius R = 108576.859834. It is obvious that the given data set has much smaller radius than the result.
Here is another set of points.
It is clear that the least squares does not work correctly.
Please help me solving this issue.
UPDATE
Here is my solution:
### fit 3D arc into a set of 3D points ###
### output is the centre and the radius of the arc ###
def fitArc3d(arr, eps = 0.0001):
# Coordinates of the 3D points
x = numpy.array([arr[k][0] for k in range(len(arr))])
y = numpy.array([arr[k][4] for k in range(len(arr))])
z = numpy.array([arr[k][5] for k in range(len(arr))])
# coordinates of the barycenter
xm = mean(x)
ym = mean(y)
zm = mean(z)
### gradient descent minimisation method ###
pnts = [[x[k], y[k], z[k]] for k in range(len(x))]
meanP = Point(xm, ym, zm) # mean point
Ri = [Point(*meanP).distance(Point(*pnts[k])) for k in range(len(pnts))] # radii to the points
Rm = math.fsum(Ri) / len(Ri) # mean radius
dR = Rm + 10 # difference between mean radii
alpha = 0.1
c = meanP
cArr = []
while dR > eps:
cArr.append(c)
Jx = math.fsum([2 * (x[k] - c[0]) * (Ri[k] - Rm) / Ri[k] for k in range(len(Ri))])
Jy = math.fsum([2 * (y[k] - c[1]) * (Ri[k] - Rm) / Ri[k] for k in range(len(Ri))])
Jz = math.fsum([2 * (z[k] - c[2]) * (Ri[k] - Rm) / Ri[k] for k in range(len(Ri))])
gradJ = [Jx, Jy, Jz] # find gradient
c = [c[k] + alpha * gradJ[k] for k in range(len(c)) if len(c) == len(gradJ)] # find new centre point
Ri = [Point(*c).distance(Point(*pnts[k])) for k in range(len(pnts))] # calculate new radii
RmOld = Rm
Rm = math.fsum(Ri) / len(Ri) # calculate new mean radius
dR = abs(Rm - RmOld) # new difference between mean radii
return Point(*c), Rm
It is not very optimal code (I do not have time to fine tune it) but it works.
I guess the problem is the data and the corresponding algorithm. The least square method works fine if it produces a local parabolic minimum, such that a simple gradient method goes approximately direction minimum. Unfortunately, this is not necessarily the case for your data. You can check this by keeping some rough estimates for xc and yc fixed and plotting the sum of the squared residuals as a function of zc and R. I get a boomerang shaped minimum. Depending on your starting parameters you might end in one of the branches going away from the real minimum. Once in the valley this can be very flat such that you exceed the number of max iterations or get something that is accepted within the tolerance of the algorithm. As always, thinks are better the better your starting parameters. Unfortunately you have only a small arc of the circle, so that it is difficult to get better. I am not a specialist in Python, but I think that leastsq allows you to play with the Jacobian and Gradient Methods. Try to play with the tolerance as well.
In short: the code looks basically fine to me, but your data is pathological and you have to adapt the code to that kind of data.
There is a non-iterative solution in 2D from Karimäki, maybe you can adapt
this method to 3D. You can also look at this. Sure you will find more literature.
I just checked the data using a Simplex-Algorithm. The minimum is, as I said, not well behaved. See here some cuts of the residual function. Only in the xy-plane you get some reasonable behavior. The properties of the zr- and xr- plane make the finding process very difficult.
So in the beginning the simplex algorithm finds several almost stable solutions. You can see them as flat steps in the graph below (blue x, purple y, yellow z, green R). At the end the algorithm has to walk down the almost flat but very stretched out valley, resulting in the final conversion of z and R. Nevertheless, I expect many regions that look like a solution if the tolerance is insufficient. With the standard tolerance of 10^-5 the algoritm stopped after approx 350 iterations. I had to set it to 10^-10 to get this solution, i.e. [1899.32, 741.874, 298.696, 248.956], which seems quite ok.
Update
As mentioned earlier, the solution depends on the working precision and requested accuracy. So your hand made gradient method works probably better as these values are different compared to the build-in least square fit. Nevertheless, this is my version making a two step fit. First I fit a plane to the data. In a next step I fit a circle within this plane. Both steps use the least square method. This time it works, as each step avoids critically shaped minima. (Naturally, the plane fit runs into problems if the arc segment becomes small and the data lies virtually on a straight line. But this will happen for all algorithms)
from math import *
from matplotlib import pyplot as plt
from scipy import optimize
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
import pprint as pp
dataTupel=zip(xs,ys,zs) #your data from above
# Fitting a plane first
# let the affine plane be defined by two vectors,
# the zero point P0 and the plane normal n0
# a point p is member of the plane if (p-p0).n0 = 0
def distanceToPlane(p0,n0,p):
return np.dot(np.array(n0),np.array(p)-np.array(p0))
def residualsPlane(parameters,dataPoint):
px,py,pz,theta,phi = parameters
nx,ny,nz =sin(theta)*cos(phi),sin(theta)*sin(phi),cos(theta)
distances = [distanceToPlane([px,py,pz],[nx,ny,nz],[x,y,z]) for x,y,z in dataPoint]
return distances
estimate = [1900, 700, 335,0,0] # px,py,pz and zeta, phi
#you may automize this by using the center of mass data
# note that the normal vector is given in polar coordinates
bestFitValues, ier = optimize.leastsq(residualsPlane, estimate, args=(dataTupel))
xF,yF,zF,tF,pF = bestFitValues
point = [xF,yF,zF]
normal = [sin(tF)*cos(pF),sin(tF)*sin(pF),cos(tF)]
# Fitting a circle inside the plane
#creating two inplane vectors
sArr=np.cross(np.array([1,0,0]),np.array(normal))#assuming that normal not parallel x!
sArr=sArr/np.linalg.norm(sArr)
rArr=np.cross(sArr,np.array(normal))
rArr=rArr/np.linalg.norm(rArr)#should be normalized already, but anyhow
def residualsCircle(parameters,dataPoint):
r,s,Ri = parameters
planePointArr = s*sArr + r*rArr + np.array(point)
distance = [ np.linalg.norm( planePointArr-np.array([x,y,z])) for x,y,z in dataPoint]
res = [(Ri-dist) for dist in distance]
return res
estimateCircle = [0, 0, 335] # px,py,pz and zeta, phi
bestCircleFitValues, ier = optimize.leastsq(residualsCircle, estimateCircle,args=(dataTupel))
rF,sF,RiF = bestCircleFitValues
print bestCircleFitValues
# Synthetic Data
centerPointArr=sF*sArr + rF*rArr + np.array(point)
synthetic=[list(centerPointArr+ RiF*cos(phi)*rArr+RiF*sin(phi)*sArr) for phi in np.linspace(0, 2*pi,50)]
[cxTupel,cyTupel,czTupel]=[ x for x in zip(*synthetic)]
### Plotting
d = -np.dot(np.array(point),np.array(normal))# dot product
# create x,y mesh
xx, yy = np.meshgrid(np.linspace(2000,2200,10), np.linspace(540,740,10))
# calculate corresponding z
# Note: does not work if normal vector is without z-component
z = (-normal[0]*xx - normal[1]*yy - d)/normal[2]
# plot the surface, data, and synthetic circle
fig = plt.figure()
ax = fig.add_subplot(211, projection='3d')
ax.scatter(xs, ys, zs, c='b', marker='o')
ax.plot_wireframe(xx,yy,z)
ax.set_xlabel('X Label')
ax.set_ylabel('Y Label')
ax.set_zlabel('Z Label')
bx = fig.add_subplot(212, projection='3d')
bx.scatter(xs, ys, zs, c='b', marker='o')
bx.scatter(cxTupel,cyTupel,czTupel, c='r', marker='o')
bx.set_xlabel('X Label')
bx.set_ylabel('Y Label')
bx.set_zlabel('Z Label')
plt.show()
which give a radius of 245. This is close to what the other approach gave (249). So within error margins I get the same.
The plotted result looks reasonable.
Hope this helps.
Feel like you missed some constraints in your 1st version code. The implementation could be explained as fitting a sphere to 3d points. So that's why the 2nd radius for 2nd data list is almost straight line. It's thinking like you are giving it a small circle on a large sphere.
I have been trying to figure out the full width half maximum (FWHM) of the the blue peak (see image). The green peak and the magenta peak combined make up the blue peak. I have been using the following equation to find the FWHM of the green and magenta peaks: fwhm = 2*np.sqrt(2*(math.log(2)))*sd where sd = standard deviation. I created the green and magenta peaks and I know the standard deviation which is why I can use that equation.
I created the green and magenta peaks using the following code:
def make_norm_dist(self, x, mean, sd):
import numpy as np
norm = []
for i in range(x.size):
norm += [1.0/(sd*np.sqrt(2*np.pi))*np.exp(-(x[i] - mean)**2/(2*sd**2))]
return np.array(norm)
If I did not know the blue peak was made up of two peaks and I only had the blue peak in my data, how would I find the FWHM?
I have been using this code to find the peak top:
peak_top = 0.0e-1000
for i in x_axis:
if i > peak_top:
peak_top = i
I could divide the peak_top by 2 to find the half height and then try and find y-values corresponding to the half height, but then I would run into trouble if there are no x-values exactly matching the half height.
I am pretty sure there is a more elegant solution to the one I am trying.
You can use spline to fit the [blue curve - peak/2], and then find it's roots:
import numpy as np
from scipy.interpolate import UnivariateSpline
def make_norm_dist(x, mean, sd):
return 1.0/(sd*np.sqrt(2*np.pi))*np.exp(-(x - mean)**2/(2*sd**2))
x = np.linspace(10, 110, 1000)
green = make_norm_dist(x, 50, 10)
pink = make_norm_dist(x, 60, 10)
blue = green + pink
# create a spline of x and blue-np.max(blue)/2
spline = UnivariateSpline(x, blue-np.max(blue)/2, s=0)
r1, r2 = spline.roots() # find the roots
import pylab as pl
pl.plot(x, blue)
pl.axvspan(r1, r2, facecolor='g', alpha=0.5)
pl.show()
Here is the result:
This worked for me in iPython (quick and dirty, can be reduced to 3 lines):
def FWHM(X,Y):
half_max = max(Y) / 2.
#find when function crosses line half_max (when sign of diff flips)
#take the 'derivative' of signum(half_max - Y[])
d = sign(half_max - array(Y[0:-1])) - sign(half_max - array(Y[1:]))
#plot(X[0:len(d)],d) #if you are interested
#find the left and right most indexes
left_idx = find(d > 0)[0]
right_idx = find(d < 0)[-1]
return X[right_idx] - X[left_idx] #return the difference (full width)
Some additions can be made to make the resolution more accurate, but in the limit that there are many samples along the X axis and the data is not too noisy, this works great.
Even when the data are not Gaussian and a little noisy, it worked for me (I just take the first and last time half max crosses the data).
If your data has noise (and it always does in the real world), a more robust solution would be to fit a Gaussian to the data and extract FWHM from that:
import numpy as np
import scipy.optimize as opt
def gauss(x, p): # p[0]==mean, p[1]==stdev
return 1.0/(p[1]*np.sqrt(2*np.pi))*np.exp(-(x-p[0])**2/(2*p[1]**2))
# Create some sample data
known_param = np.array([2.0, .7])
xmin,xmax = -1.0, 5.0
N = 1000
X = np.linspace(xmin,xmax,N)
Y = gauss(X, known_param)
# Add some noise
Y += .10*np.random.random(N)
# Renormalize to a proper PDF
Y /= ((xmax-xmin)/N)*Y.sum()
# Fit a guassian
p0 = [0,1] # Inital guess is a normal distribution
errfunc = lambda p, x, y: gauss(x, p) - y # Distance to the target function
p1, success = opt.leastsq(errfunc, p0[:], args=(X, Y))
fit_mu, fit_stdev = p1
FWHM = 2*np.sqrt(2*np.log(2))*fit_stdev
print "FWHM", FWHM
The plotted image can be generated by:
from pylab import *
plot(X,Y)
plot(X, gauss(X,p1),lw=3,alpha=.5, color='r')
axvspan(fit_mu-FWHM/2, fit_mu+FWHM/2, facecolor='g', alpha=0.5)
show()
An even better approximation would filter out the noisy data below a given threshold before the fit.
Here is a nice little function using the spline approach.
from scipy.interpolate import splrep, sproot, splev
class MultiplePeaks(Exception): pass
class NoPeaksFound(Exception): pass
def fwhm(x, y, k=10):
"""
Determine full-with-half-maximum of a peaked set of points, x and y.
Assumes that there is only one peak present in the datasset. The function
uses a spline interpolation of order k.
"""
half_max = amax(y)/2.0
s = splrep(x, y - half_max, k=k)
roots = sproot(s)
if len(roots) > 2:
raise MultiplePeaks("The dataset appears to have multiple peaks, and "
"thus the FWHM can't be determined.")
elif len(roots) < 2:
raise NoPeaksFound("No proper peaks were found in the data set; likely "
"the dataset is flat (e.g. all zeros).")
else:
return abs(roots[1] - roots[0])
You should use scipy to solve it: first find_peaks and then peak_widths.
With default value in rel_height(0.5) you're measuring the width at half maximum of the peak.
If you prefer interpolation over fitting:
import numpy as np
def get_full_width(x: np.ndarray, y: np.ndarray, height: float = 0.5) -> float:
height_half_max = np.max(y) * height
index_max = np.argmax(y)
x_low = np.interp(height_half_max, y[:index_max+1], x[:index_max+1])
x_high = np.interp(height_half_max, np.flip(y[index_max:]), np.flip(x[index_max:]))
return x_high - x_low
For monotonic functions with many data points and if there's no need for perfect accuracy, I would use:
def FWHM(X, Y):
deltax = x[1] - x[0]
half_max = max(Y) / 2.
l = np.where(y > half_max, 1, 0)
return np.sum(l) * deltax
I implemented an empirical solution which works for noisy and not-quite-Gaussian data fairly well in haggis.math.full_width_half_max. The usage is extremely straightforward:
fwhm = full_width_half_max(x, y)
The function is robust: it simply finds the maximum of the data and the nearest points crossing the "halfway down" threshold using the requested interpolation scheme.
Here are a couple of examples using data from the other answers.
#HYRY's smooth data
def make_norm_dist(x, mean, sd):
return 1.0/(sd*np.sqrt(2*np.pi))*np.exp(-(x - mean)**2/(2*sd**2))
x = np.linspace(10, 110, 1000)
green = make_norm_dist(x, 50, 10)
pink = make_norm_dist(x, 60, 10)
blue = green + pink
# create a spline of x and blue-np.max(blue)/2
spline = UnivariateSpline(x, blue-np.max(blue)/2, s=0)
r1, r2 = spline.roots() # find the roots
# Compute using my function
fwhm, (x1, y1), (x2, y2) = full_width_half_max(x, blue, return_points=True)
# Print comparison
print('HYRY:', r2 - r1, 'MP:', fwhm)
plt.plot(x, blue)
plt.axvspan(r1, r2, facecolor='g', alpha=0.5)
plt.plot(x1, y1, 'r.')
plt.plot(x2, y2, 'r.')
For smooth data, the results are pretty exact:
HYRY: 26.891157007233254 MP: 26.891193606203814
#Hooked's Noisy Data
def gauss(x, p): # p[0]==mean, p[1]==stdev
return 1.0/(p[1]*np.sqrt(2*np.pi))*np.exp(-(x-p[0])**2/(2*p[1]**2))
# Create some sample data
known_param = np.array([2.0, .7])
xmin,xmax = -1.0, 5.0
N = 1000
X = np.linspace(xmin,xmax,N)
Y = gauss(X, known_param)
# Add some noise
Y += .10*np.random.random(N)
# Renormalize to a proper PDF
Y /= ((xmax-xmin)/N)*Y.sum()
# Fit a guassian
p0 = [0,1] # Inital guess is a normal distribution
errfunc = lambda p, x, y: gauss(x, p) - y # Distance to the target function
p1, success = opt.leastsq(errfunc, p0[:], args=(X, Y))
fit_mu, fit_stdev = p1
FWHM = 2*np.sqrt(2*np.log(2))*fit_stdev
# Compute using my function
fwhm, (x1, y1), (x2, y2) = full_width_half_max(X, Y, return_points=True)
# Print comparison
print('Hooked:', FWHM, 'MP:', fwhm)
plt.plot(X, Y)
plt.plot(X, gauss(X, p1), lw=3, alpha=.5, color='r')
plt.axvspan(fit_mu - FWHM / 2, fit_mu + FWHM / 2, facecolor='g', alpha=0.5)
plt.plot(x1, y1, 'r.')
plt.plot(x2, y2, 'r.')
For noisy data (with a biased baseline), the results are not as consistent.
Hooked: 1.9903193212254346 MP: 1.5039676990530118
On the one hand the Gaussian fit is not very optimal for the data, but on the other hand, the strategy of picking the nearest point that intersects the half-max threshold is likely not optimal either.