We Keep Coding

Python Binning using triangular bins

I'm trying to find a simple python module/package that has implemented 2D triangular bins so that it can be use in a similar fashion to scipy binned_statistic_dd. Is anyone aware of such a tool? I've searched but not found anything: the closest I've found is matplotlib's hexbin.
If I have to create a home-made solution, generating the vertex points for the triangular grid is easy, but how would you efficiently (need to avoid slow loops if possible as datasets are about 100K points) search which triangle a point lies in?

import matplotlib.pyplot as plt
import matplotlib.tri as tri
import numpy as np
def plot_triangular_bin_freq(x,y,Vx,Vy):
X, Y = np.meshgrid(x, y)
Ny, Nx = X.shape
iy,ix = np.indices((Ny-1, Nx-1))
# max vertice is supposed to be
# max(iy)*Nx + max(ix) + (Nx+1)
# = (Ny-2)*Nx + (Nx-2) + (Nx+1)
# = Ny * Nx - 1
assert iy.max() == Ny-2
assert ix.max() == Nx-2
# build square grid and split it in a lower-left, upper-right triangles
# and construct the triangulation
vertices = (((iy * Nx) + ix)[:,:,None] + np.array([0,1,Nx,Nx,Nx+1,1])[None,None,:]).reshape(-1, 3)
triangles = tri.Triangulation(X.flatten(), Y.flatten(), vertices)
# Normalized point coordinates
Vx = (np.asarray(Vx).flatten() - x[0]) * ((Nx-1) / (x[-1] - x[0]))
Vy = (np.asarray(Vy).flatten() - y[0]) * ((Ny-1) / (y[-1] - y[0]))
m = (0 <= Vx) & (Vx < Nx-1) & (0 <= Vy) & (Vy < Ny-1)
# get indices on the x,y boxes
Ix, Rx = divmod(Vx[m], 1)
Iy, Ry = divmod(Vy[m], 1)
# (Rx+Ry)=1 is the boundary between the two triangles
# w indicates the index of the triangle where the point lies on
w = ((Rx+Ry)>=1) + 2*(Ix + (Nx-1)*Iy)
assert max(Ix) < Nx-1
assert max(Iy) < Ny-1
assert max(Ix + Iy*(Nx-1)) < (Nx-1)*(Ny-1)
# z[i] is the number of points that lies inside z[i]
z = np.bincount(w.astype(np.int64), minlength=2*(Nx-1)*(Ny-1))
plt.tripcolor(triangles, z, shading='flat')
x = np.arange(15)/2.
y = np.arange(10)/2.
Vx = np.random.randn(1000) + 3
Vy = np.random.randn(1000) + 1
plot_triangular_bin_freq(x,y,Vx,Vy)

Fastest way to get list of xyz coordinates between 2 points

I have 2 Points A and B and their xyz-coordinates. I need a list of all xyz points that are on the line between those 2 points. The Bresenham's line algorithm was too slow for my case.
Example xyz for A and B:
p = np.array([[ 275.5, 244.2, -27.3],
[ 153.2, 184.3, -0.3]])
Expected output:
x3 = p[0,0] + t*(p[1,0]-p[0,0])
y3 = p[0,1] + t*(p[1,1]-p[0,1])
z3 = p[0,2] + t*(p[1,2]-p[0,2])
p3 = [x3,y3,z3]
There was a very fast approach for 2D:
def connect(ends):
d0, d1 = np.diff(ends, axis=0)[0]
if np.abs(d0) > np.abs(d1):
return np.c_[np.arange(ends[0, 0], ends[1,0] + np.sign(d0), np.sign(d0), dtype=np.int32),
np.arange(ends[0, 1] * np.abs(d0) + np.abs(d0)//2,
ends[0, 1] * np.abs(d0) + np.abs(d0)//2 + (np.abs(d0)+1) * d1, d1, dtype=np.int32) // np.abs(d0)]
else:
return np.c_[np.arange(ends[0, 0] * np.abs(d1) + np.abs(d1)//2,
ends[0, 0] * np.abs(d1) + np.abs(d1)//2 + (np.abs(d1)+1) * d0, d0, dtype=np.int32) // np.abs(d1),
np.arange(ends[0, 1], ends[1,1] + np.sign(d1), np.sign(d1), dtype=np.int32)]

It is impossible to give "all" points on a line, as there are countless points. You could do that for a discrete data type like integers, though.
My answer assumes floating point numbers, as in your example.
Technically, floating point numbers are stored in a binary format with a fixed width, so they are discrete, but I will disregard that fact, as it is most likely not what you want.
As you already typed in your question, every point P on that line satisfies this equation:
P = P1 + t * (P2 - P1), 0 < t < 1
My version uses numpy broadcasting to circumvent explicit loops.
import numpy as np
p = np.array([[ 275.5, 244.2, -27.3],
[ 153.2, 184.3, -0.3]])
def connect(points, n_points):
p1, p2 = points
diff = p2 - p1
t = np.linspace(0, 1, n_points+2)[1:-1]
return p1[np.newaxis, :] + t[:, np.newaxis] * diff[np.newaxis, :]
print(connect(p, n_points=4))
# [[251.04 232.22 -21.9 ]
# [226.58 220.24 -16.5 ]
# [202.12 208.26 -11.1 ]
# [177.66 196.28 -5.7 ]]

Maybe I missunderstand something here, but couldn't you just create a function (like you already did just for one single point) and then create a list of points depending of how manny points you want?
I mean between 2 points are an infinite number of other points, so you have to either define a number or use the function directly, which describes where the points are at.
import numpy as np
p = np.array([[ 275.5, 244.2, -27.3],
[ 153.2, 184.3, -0.3]])
def gen_line(p, n):
points = []
stepsize = 1/n
for t in np.arange(0,1,stepsize):
x = (p[1,0]-p[0,0])
y = (p[1,1]-p[0,1])
z = (p[1,2]-p[0,2])
px = p[0,0]
py = p[0,1]
pz = p[0,2]
x3 = px + t*x
y3 = py + t*y
z3 = pz + t*z
points.append([x3,y3,z3])
return points
# generates list of 30k points
gen_line(p, 30000)

Python uniform random number generation to a triangle shape

I have three data points which I performed a linear fit and obtained the 1 sigma uncertainty lines. Now I would like to generate 100k data point uniformly distributed between the 1 sigma error bars (the big triangle on the left side) but I do not have any idea how am I able to do that. Here is my code
import matplotlib.pyplot as plt
import numpy as np
import math
from scipy.optimize import curve_fit
x = np.array([339.545772, 339.545781, 339.545803])
y = np.array([-0.430843, -0.43084 , -0.430842])
def line(x,m,c):
return m*x + c
popt, pcov = curve_fit(line,x,y)
slope = popt[0]
intercept = popt[1]
xx = np.array([326.0,343.0])
fit = line(xx,slope,intercept)
fit_plus1sigma = line(xx, slope + pcov[0,0]**0.5, intercept - pcov[1,1]**0.5)
fit_minus1sigma = line(xx, slope - pcov[0,0]**0.5, intercept + pcov[1,1]**0.5)
plt.plot(xx,fit,"C4",label="Linear fit")
plt.plot(xx,fit_plus1sigma,'g--',label=r'One sigma uncertainty')
plt.plot(xx,fit_minus1sigma,'g--')
plt.fill_between(xx, fit_plus1sigma, fit_minus1sigma, facecolor="gray", alpha=0.15)
In NumPy there is a Numpy random triangle function, however, I was not able to implement that in my case and I am not even sure if that is the right approach. I appreciate any help.

You can use this answer by Severin Pappadeux to sample uniformly in a triangle shape. You need the corner points of your triangle for that.
To find where your lines intersect you can follow this answer by Norbu Tsering. Then you just need the top-left corner and bottom-left corner coordinates of your triangle shape.
Putting all of this together, you can solve your problem like this.
Find the intersection:
# Source: https://stackoverflow.com/a/42727584/5320601
def get_intersect(a1, a2, b1, b2):
"""
Returns the point of intersection of the lines passing through a2,a1 and b2,b1.
a1: [x, y] a point on the first line
a2: [x, y] another point on the first line
b1: [x, y] a point on the second line
b2: [x, y] another point on the second line
"""
s = np.vstack([a1, a2, b1, b2]) # s for stacked
h = np.hstack((s, np.ones((4, 1)))) # h for homogeneous
l1 = np.cross(h[0], h[1]) # get first line
l2 = np.cross(h[2], h[3]) # get second line
x, y, z = np.cross(l1, l2) # point of intersection
if z == 0: # lines are parallel
return (float('inf'), float('inf'))
return (x / z, y / z)
p1 = ((xx[0], fit_plus1sigma[0]), (xx[1], fit_plus1sigma[1]))
p2 = ((xx[0], fit_minus1sigma[0]), (xx[1], fit_minus1sigma[1]))
cross = get_intersect(p1[0], p1[1], p2[0], p2[1])
This way you get your two points per line that are on it, and the intersection point, which you need to sample from within this triangle shape.
Then you can sample the points you need:
# Source: https://stackoverflow.com/a/47425047/5320601
def trisample(A, B, C):
"""
Given three vertices A, B, C,
sample point uniformly in the triangle
"""
r1 = random.random()
r2 = random.random()
s1 = math.sqrt(r1)
x = A[0] * (1.0 - s1) + B[0] * (1.0 - r2) * s1 + C[0] * r2 * s1
y = A[1] * (1.0 - s1) + B[1] * (1.0 - r2) * s1 + C[1] * r2 * s1
return (x, y)
points = []
for _ in range(100000):
points.append(trisample(p1[0], p2[0], cross))
Example picture for 1000 points:

Solve a nonlinear ODE system for the Frenet frame

I have checked python non linear ODE with 2 variables , which is not my case. Maybe my case is not called as nonlinear ODE, correct me please.
The question isFrenet Frame actually, in which there are 3 vectors T(s), N(s) and B(s); the parameter s>=0. And there are 2 scalar with known math formula expression t(s) and k(s). I have the initial value T(0), N(0) and B(0).
diff(T(s), s) = k(s)*N(s)
diff(N(s), s) = -k(s)*T(s) + t(s)*B(s)
diff(B(s), s) = -t(s)*N(s)
Then how can I get T(s), N(s) and B(s) numerically or symbolically?
I have checked scipy.integrate.ode but I don't know how to pass k(s)*N(s) into its first parameter at all
def model (z, tspan):
T = z[0]
N = z[1]
B = z[2]
dTds = k(s) * N # how to express function k(s)?
dNds = -k(s) * T + t(s) * B
dBds = -t(s)* N
return [dTds, dNds, dBds]
z = scipy.integrate.ode(model, [T0, N0, B0]

Here is a code using solve_ivp interface from Scipy (instead of odeint) to obtain a numerical solution:
import numpy as np
from scipy.integrate import solve_ivp
from scipy.integrate import cumtrapz
import matplotlib.pylab as plt
# Define the parameters as regular Python function:
def k(s):
return 1
def t(s):
return 0
# The equations: dz/dt = model(s, z):
def model(s, z):
T = z[:3] # z is a (9, ) shaped array, the concatenation of T, N and B
N = z[3:6]
B = z[6:]
dTds = k(s) * N
dNds = -k(s) * T + t(s) * B
dBds = -t(s)* N
return np.hstack([dTds, dNds, dBds])
T0, N0, B0 = [1, 0, 0], [0, 1, 0], [0, 0, 1]
z0 = np.hstack([T0, N0, B0])
s_span = (0, 6) # start and final "time"
t_eval = np.linspace(*s_span, 100) # define the number of point wanted in-between,
# It is not necessary as the solver automatically
# define the number of points.
# It is used here to obtain a relatively correct
# integration of the coordinates, see the graph
# Solve:
sol = solve_ivp(model, s_span, z0, t_eval=t_eval, method='RK45')
print(sol.message)
# >> The solver successfully reached the end of the integration interval.
# Unpack the solution:
T, N, B = np.split(sol.y, 3) # another way to unpack the z array
s = sol.t
# Bonus: integration of the normal vector in order to get the coordinates
# to plot the curve (there is certainly better way to do this)
coords = cumtrapz(T, x=s)
plt.plot(coords[0, :], coords[1, :]);
plt.axis('equal'); plt.xlabel('x'); plt.xlabel('y');
T, N and B are vectors. Therefore, there are 9 equations to solve: z is a (9,) array.
For constant curvature and no torsion, the result is a circle:

thanks for your example. And I thought it again, found that since there is formula for dZ where Z is matrix(T, N, B), we can calculate Z[i] = Z[i-1] + dZ[i-1]*deltaS according to the concept of derivative. Then I code and find this idea can solve the circle example. So
is Z[i] = Z[i-1] + dZ[i-1]*deltaS suitable for other ODE? will it fail in some situation, or does scipy.integrate.solve_ivp/scipy.integrate.ode supply advantage over the direct usage of Z[i] = Z[i-1] + dZ[i-1]*deltaS?
in my code, I have to normalize Z[i] because ||Z[i]|| is not always 1. Why does it happen? A float numerical calculation error?
my answer to my question, at least it works for the circle
import numpy as np
from scipy.integrate import cumtrapz
import matplotlib.pylab as plt
# Define the parameters as regular Python function:
def k(s):
return 1
def t(s):
return 0
def dZ(s, Z):
return np.array(
[k(s) * Z[1], -k(s) * Z[0] + t(s) * Z[2], -t(s)* Z[1]]
)
T0, N0, B0 = np.array([1, 0, 0]), np.array([0, 1, 0]), np.array([0, 0, 1])
deltaS = 0.1 # step to calculate dZ/ds
num = int(2*np.pi*1/deltaS) + 1 # how many points on the curve we have to calculate
T = np.zeros([num, ], dtype=object)
N = np.zeros([num, ], dtype=object)
B = np.zeros([num, ], dtype=object)
T[0] = T0
N[0] = N0
B[0] = B0
for i in range(num-1):
temp_dZ = dZ(i*deltaS, np.array([T[i], N[i], B[i]]))
T[i+1] = T[i] + temp_dZ[0]*deltaS
T[i+1] = T[i+1]/np.linalg.norm(T[i+1]) # have to do this
N[i+1] = N[i] + temp_dZ[1]*deltaS
N[i+1] = N[i+1]/np.linalg.norm(N[i+1])
B[i+1] = B[i] + temp_dZ[2]*deltaS
B[i+1] = B[i+1]/np.linalg.norm(B[i+1])
coords = cumtrapz(
[
[i[0] for i in T], [i[1] for i in T], [i[2] for i in T]
]
, x=np.arange(num)*deltaS
)
plt.figure()
plt.plot(coords[0, :], coords[1, :]);
plt.axis('equal'); plt.xlabel('x'); plt.xlabel('y');
plt.show()

I found that the equation I listed in the first post does not work for my curve. So I read Gray A., Abbena E., Salamon S-Modern Differential Geometry of Curves and Surfaces with Mathematica. 2006 and found that for arbitrary curve, Frenet equation should be written as
diff(T(s), s) = ||r'||* k(s)*N(s)
diff(N(s), s) = ||r'||*(-k(s)*T(s) + t(s)*B(s))
diff(B(s), s) = ||r'||* -t(s)*N(s)
where ||r'||(or ||r'(s)||) is diff([x(s), y(s), z(s)], s).norm()
now the problem has changed to be some different from that in the first post, because there is no r'(s) function or discrete data array. So I think this is suitable for a new reply other than comment.
I met 2 questions while trying to solve the new equation:
how can we program with r'(s) if scipy's solve_ivp is used?
I try to modify my gaussian solution, but the result is totally wrong.
thanks again
import numpy as np
from scipy.integrate import cumtrapz
import matplotlib.pylab as plt
# Define the parameters as regular Python function:
def k(s):
return 1
def t(s):
return 0
def dZ(s, Z, r_norm):
return np.array([
r_norm * k(s) * Z[1],
r_norm*(-k(s) * Z[0] + t(s) * Z[2]),
r_norm*(-t(s)* Z[1])
])
T0, N0, B0 = np.array([1, 0, 0]), np.array([0, 1, 0]), np.array([0, 0, 1])
deltaS = 0.1 # step to calculate dZ/ds
num = int(2*np.pi*1/deltaS) + 1 # how many points on the curve we have to calculate
T = np.zeros([num, ], dtype=object)
N = np.zeros([num, ], dtype=object)
B = np.zeros([num, ], dtype=object)
R0 = N0
T[0] = T0
N[0] = N0
B[0] = B0
for i in range(num-1):
r_norm = np.linalg.norm(R0)
temp_dZ = dZ(i*deltaS, np.array([T[i], N[i], B[i]]), r_norm)
T[i+1] = T[i] + temp_dZ[0]*deltaS
T[i+1] = T[i+1]/np.linalg.norm(T[i+1])
N[i+1] = N[i] + temp_dZ[1]*deltaS
N[i+1] = N[i+1]/np.linalg.norm(N[i+1])
B[i+1] = B[i] + temp_dZ[2]*deltaS
B[i+1] = B[i+1]/np.linalg.norm(B[i+1])
R0 = R0 + T[i]*deltaS
coords = cumtrapz(
[
[i[0] for i in T], [i[1] for i in T], [i[2] for i in T]
]
, x=np.arange(num)*deltaS
)
plt.figure()
plt.plot(coords[0, :], coords[1, :]);
plt.axis('equal'); plt.xlabel('x'); plt.xlabel('y');
plt.show()

How to get the x,y coordinates of a offset spline from a x,y list of points and offset distance

I need to make an offset parallel enclosure of an airfoil profile curve, but I cant figure out how to make all the points be equidistant to the points on the primary profile curve at desired distance.
this is my example airfoil profile
this is my best and not good approach
EDIT #Patrick Solution for distance 0.2

You'll have to special-case slopes of infinity/zero, but the basic approach is to use interpolation to calculate the slope at a point, and then find the perpendicular slope, and then calculate the point at that distance.
I have modified the example from here to add a second graph. It works with the data file you provided, but you might need to change the sign calculation for a different envelope.
EDIT As per your comments about wanting the envelope to be continuous, I have added a cheesy semicircle at the end that gets really close to doing this for you. Essentially, when creating the envelope, the rounder and more convex you can make it, the better it will work. Also, you need to overlap the beginning and the end, or you'll have a gap.
Also, it could almost certainly be made more efficient -- I am not a numpy expert by any means, so this is just pure Python.
def offset(coordinates, distance):
coordinates = iter(coordinates)
x1, y1 = coordinates.next()
z = distance
points = []
for x2, y2 in coordinates:
# tangential slope approximation
try:
slope = (y2 - y1) / (x2 - x1)
# perpendicular slope
pslope = -1/slope # (might be 1/slope depending on direction of travel)
except ZeroDivisionError:
continue
mid_x = (x1 + x2) / 2
mid_y = (y1 + y2) / 2
sign = ((pslope > 0) == (x1 > x2)) * 2 - 1
# if z is the distance to your parallel curve,
# then your delta-x and delta-y calculations are:
# z**2 = x**2 + y**2
# y = pslope * x
# z**2 = x**2 + (pslope * x)**2
# z**2 = x**2 + pslope**2 * x**2
# z**2 = (1 + pslope**2) * x**2
# z**2 / (1 + pslope**2) = x**2
# z / (1 + pslope**2)**0.5 = x
delta_x = sign * z / ((1 + pslope**2)**0.5)
delta_y = pslope * delta_x
points.append((mid_x + delta_x, mid_y + delta_y))
x1, y1 = x2, y2
return points
def add_semicircle(x_origin, y_origin, radius, num_x = 50):
points = []
for index in range(num_x):
x = radius * index / num_x
y = (radius ** 2 - x ** 2) ** 0.5
points.append((x, -y))
points += [(x, -y) for x, y in reversed(points)]
return [(x + x_origin, y + y_origin) for x, y in points]
def round_data(data):
# Add infinitesimal rounding of the envelope
assert data[-1] == data[0]
x0, y0 = data[0]
x1, y1 = data[1]
xe, ye = data[-2]
x = x0 - (x0 - x1) * .01
y = y0 - (y0 - y1) * .01
yn = (x - xe) / (x0 - xe) * (y0 - ye) + ye
data[0] = x, y
data[-1] = x, yn
data.extend(add_semicircle(x, (y + yn) / 2, abs((y - yn) / 2)))
del data[-18:]
from pylab import *
with open('ah79100c.dat', 'rb') as f:
f.next()
data = [[float(x) for x in line.split()] for line in f if line.strip()]
t = [x[0] for x in data]
s = [x[1] for x in data]
round_data(data)
parallel = offset(data, 0.1)
t2 = [x[0] for x in parallel]
s2 = [x[1] for x in parallel]
plot(t, s, 'g', t2, s2, 'b', lw=1)
title('Wing with envelope')
grid(True)
axes().set_aspect('equal', 'datalim')
savefig("test.png")
show()

If you are willing (and able) to install a third-party tool, I'd highly recommend the Shapely module. Here's a small sample that offsets both inward and outward:
from StringIO import StringIO
import matplotlib.pyplot as plt
import numpy as np
import requests
import shapely.geometry as shp
# Read the points
AFURL = 'http://m-selig.ae.illinois.edu/ads/coord_seligFmt/ah79100c.dat'
afpts = np.loadtxt(StringIO(requests.get(AFURL).content), skiprows=1)
# Create a Polygon from the nx2 array in `afpts`
afpoly = shp.Polygon(afpts)
# Create offset airfoils, both inward and outward
poffafpoly = afpoly.buffer(0.03) # Outward offset
noffafpoly = afpoly.buffer(-0.03) # Inward offset
# Turn polygon points into numpy arrays for plotting
afpolypts = np.array(afpoly.exterior)
poffafpolypts = np.array(poffafpoly.exterior)
noffafpolypts = np.array(noffafpoly.exterior)
# Plot points
plt.plot(*afpolypts.T, color='black')
plt.plot(*poffafpolypts.T, color='red')
plt.plot(*noffafpolypts.T, color='green')
plt.axis('equal')
plt.show()
And here's the output; notice how the 'bowties' (self-intersections) on the inward offset are automatically removed: