Generate 2D Gaussian with Python - python

How would i generate 1000 2D samples for a Gaussian with mu = (2,0), and sigma = [[1,0],[0,1]]? This is my code below so far:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D
# Our 2-dimensional distribution will be over variables X and Y
N = 40
X = np.linspace(-2, 2, N)
Y = np.linspace(-2, 2, N)
X, Y = np.meshgrid(X, Y)
# Mean vector and covariance matrix
mu = np.array([2, 0])
Sigma = np.array([[ 1 , 0], [0, 1]])
# Pack X and Y into a single 3-dimensional array
pos = np.empty(X.shape + (2,))
pos[:, :, 0] = X
pos[:, :, 1] = Y
def multivariate_gaussian(pos, mu, Sigma):
"""Return the multivariate Gaussian distribution on array pos."""
n = mu.shape[0]
Sigma_det = np.linalg.det(Sigma)
Sigma_inv = np.linalg.inv(Sigma)
N = np.sqrt((2*np.pi)**n * Sigma_det)
# This einsum call calculates (x-mu)T.Sigma-1.(x-mu) in a vectorized
# way across all the input variables.
fac = np.einsum('...k,kl,...l->...', pos-mu, Sigma_inv, pos-mu)
return np.exp(-fac / 2) / N
# The distribution on the variables X, Y packed into pos.
Z = multivariate_gaussian(pos, mu, Sigma)
Does this look correct? How can I better this code?

Related

newton interpolation in pyton

I have to do a second degree interpolation using an already existing code and changing the values for mine, but for some reason when i go ahead and gragth the interpolation, the fuction suddently stops (it is not continuous). Can someone help me figuring out whats wrong? I believe it has something to do with line 43 (evaluation on new data points), but I am not sure.
Source code:
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('seaborn-poster')
%matplotlib inline
def divided_diff(x, y):
'''
function to calculate the divided
differences table
'''
n = len(y)
coef = np.zeros([n, n])
# the first column is y
coef[:,0] = y
for j in range(1,n):
for i in range(n-j):
coef[i][j] = \
(coef[i+1][j-1] - coef[i][j-1]) / (x[i+j]-x[i])
return coef
def newton_poly(coef, x_data, x):
'''
evaluate the newton polynomial
at x
'''
n = len(x_data) - 1
p = coef[n]
for k in range(1,n+1):
p = coef[n-k] + (x -x_data[n-k])*p
return p
x = np.array([-5, -1, 0, 2])
y = np.array([-2, 6, 1, 3])
# get the divided difference coef
a_s = divided_diff(x, y)[0, :]
# evaluate on new data points
x_new = np.arange(-5, 2.1, .1)
y_new = newton_poly(a_s, x, x_new)
plt.figure(figsize = (12, 8))
plt.plot(x, y, 'bo')
plt.plot(x_new, y_new)
My code (adjusted for data points (0,0);(6.4,1.9);(10.6,4.3)):
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('seaborn-poster')
%matplotlib inline
def divided_diff(x, y):
'''
function to calculate the divided
differences table
'''
n = len(y)
coef = np.zeros([n, n])
# the first column is y
coef[:,0] = y
for j in range(1,n):
for i in range(n-j):
coef[i][j] = \
(coef[i+1][j-1] - coef[i][j-1]) / (x[i+j]-x[i])
return coef
def newton_poly(coef, x_data, x):
'''
evaluate the newton polynomial
at x
'''
n = len(x_data) - 1
p = coef[n]
for k in range(1,n+1):
p = coef[n-k] + (x -x_data[n-k])*p
return p
x = np.array([0, 6.4, 10.6])
y = np.array([0, 1.9, 4.3])
# get the divided difference coef
a_s = divided_diff(x, y)[0, :]
# evaluate on new data points
x_new = np.arange(-5, 2.1, .1)
y_new = newton_poly(a_s, x, x_new)
plt.figure(figsize = (12, 8))
plt.plot(x, y, 'bo')
plt.plot(x_new, y_new)

Cubic spline for non-monotonic data (not a 1d function)

I have a curve as shown below:
The x coordinates and the y coordinates for this plot are:
path_x= (4.0, 5.638304088577984, 6.785456961280076, 5.638304088577984, 4.0)
path_y =(0.0, 1.147152872702092, 2.7854569612800755, 4.423761049858059, 3.2766081771559668)
And I obtained the above picture by:
x_min =min(path_x)-1
x_max =max(path_x)+1
y_min =min(path_y)-1
y_max =max(path_y)+1
num_pts = len(path_x)
fig = plt.figure(figsize=(8,8))
#fig = plt.figure()
plt.suptitle("Curve and the boundary")
ax = fig.add_subplot(1,1,1)
ax.set_xlim([min(x_min,y_min),max(x_max,y_max)])
ax.set_ylim([min(x_min,y_min),max(x_max,y_max)])
ax.plot(path_x,path_y)
Now my intention is to draw a smooth curve using cubic splines. But looks like for cubic splines you need the x coordinates to be on ascending order. whereas in this case, neither x values nor y values are in the ascending order.
Also this is not a function. That is an x value is mapped with more than one element in the range.
I also went over this post. But I couldn't figure out a proper method to solve my problem.
I really appreciate your help in this regard
As suggested in the comments, you can always parameterize any curve/surface with an arbitrary (and linear!) parameter.
For example, define t as a parameter such that you get x=x(t) and y=y(t). Since t is arbitrary, you can define it such that at t=0, you get your first path_x[0],path_y[0], and at t=1, you get your last pair of coordinates, path_x[-1],path_y[-1].
Here is a code using scipy.interpolate
import numpy
import scipy.interpolate
import matplotlib.pyplot as plt
path_x = numpy.asarray((4.0, 5.638304088577984, 6.785456961280076, 5.638304088577984, 4.0),dtype=float)
path_y = numpy.asarray((0.0, 1.147152872702092, 2.7854569612800755, 4.423761049858059, 3.2766081771559668),dtype=float)
# defining arbitrary parameter to parameterize the curve
path_t = numpy.linspace(0,1,path_x.size)
# this is the position vector with
# x coord (1st row) given by path_x, and
# y coord (2nd row) given by path_y
r = numpy.vstack((path_x.reshape((1,path_x.size)),path_y.reshape((1,path_y.size))))
# creating the spline object
spline = scipy.interpolate.interp1d(path_t,r,kind='cubic')
# defining values of the arbitrary parameter over which
# you want to interpolate x and y
# it MUST be within 0 and 1, since you defined
# the spline between path_t=0 and path_t=1
t = numpy.linspace(numpy.min(path_t),numpy.max(path_t),100)
# interpolating along t
# r[0,:] -> interpolated x coordinates
# r[1,:] -> interpolated y coordinates
r = spline(t)
plt.plot(path_x,path_y,'or')
plt.plot(r[0,:],r[1,:],'-k')
plt.xlabel('x')
plt.ylabel('y')
plt.show()
With output
For non-ascending x splines can be easily computed if you make both x and y functions of another parameter t: x(t), y(t).
In your case you have 5 points so t should be just enumeration of these points, i.e. t = 0, 1, 2, 3, 4 for 5 points.
So if x = [5, 2, 7, 3, 6] then x(t) = x(0) = 5, x(1) = 2, x(2) = 7, x(3) = 3, x(4) = 6. Same for y.
Then compute spline function for both x(t) and y(t). Afterwards compute values of splines in all many intermediate t points. Lastly just use all calculated values x(t) and y(t) as a function y(x).
Once before I implemented cubic spline computation from scratch using Numpy, so I use this code in my example below if you don't mind (it could be useful for you to learn about spline math), replace with your library functions. Also in my code you can see numba lines commented out, if you want you can use these Numba annotations to speed up computation.
You have to look at main() function at the bottom of code, it shows how to compute and use x(t) and y(t).
Try it online!
import numpy as np, matplotlib.pyplot as plt
# Solves linear system given by Tridiagonal Matrix
# Helper for calculating cubic splines
##numba.njit(cache = True, fastmath = True, inline = 'always')
def tri_diag_solve(A, B, C, F):
n = B.size
assert A.ndim == B.ndim == C.ndim == F.ndim == 1 and (
A.size == B.size == C.size == F.size == n
) #, (A.shape, B.shape, C.shape, F.shape)
Bs, Fs = np.zeros_like(B), np.zeros_like(F)
Bs[0], Fs[0] = B[0], F[0]
for i in range(1, n):
Bs[i] = B[i] - A[i] / Bs[i - 1] * C[i - 1]
Fs[i] = F[i] - A[i] / Bs[i - 1] * Fs[i - 1]
x = np.zeros_like(B)
x[-1] = Fs[-1] / Bs[-1]
for i in range(n - 2, -1, -1):
x[i] = (Fs[i] - C[i] * x[i + 1]) / Bs[i]
return x
# Calculate cubic spline params
##numba.njit(cache = True, fastmath = True, inline = 'always')
def calc_spline_params(x, y):
a = y
h = np.diff(x)
c = np.concatenate((np.zeros((1,), dtype = y.dtype),
np.append(tri_diag_solve(h[:-1], (h[:-1] + h[1:]) * 2, h[1:],
((a[2:] - a[1:-1]) / h[1:] - (a[1:-1] - a[:-2]) / h[:-1]) * 3), 0)))
d = np.diff(c) / (3 * h)
b = (a[1:] - a[:-1]) / h + (2 * c[1:] + c[:-1]) / 3 * h
return a[1:], b, c[1:], d
# Spline value calculating function, given params and "x"
##numba.njit(cache = True, fastmath = True, inline = 'always')
def func_spline(x, ix, x0, a, b, c, d):
dx = x - x0[1:][ix]
return a[ix] + (b[ix] + (c[ix] + d[ix] * dx) * dx) * dx
# Compute piece-wise spline function for "x" out of sorted "x0" points
##numba.njit([f'f{ii}[:](f{ii}[:], f{ii}[:], f{ii}[:], f{ii}[:], f{ii}[:], f{ii}[:])' for ii in (4, 8)],
# cache = True, fastmath = True, inline = 'always')
def piece_wise_spline(x, x0, a, b, c, d):
xsh = x.shape
x = x.ravel()
ix = np.searchsorted(x0[1 : -1], x)
y = func_spline(x, ix, x0, a, b, c, d)
y = y.reshape(xsh)
return y
def main():
x0 = np.array([4.0, 5.638304088577984, 6.785456961280076, 5.638304088577984, 4.0])
y0 = np.array([0.0, 1.147152872702092, 2.7854569612800755, 4.423761049858059, 3.2766081771559668])
t0 = np.arange(len(x0)).astype(np.float64)
plt.plot(x0, y0)
vs = []
for e in (x0, y0):
a, b, c, d = calc_spline_params(t0, e)
x = np.linspace(0, t0[-1], 100)
vs.append(piece_wise_spline(x, t0, a, b, c, d))
plt.plot(vs[0], vs[1])
plt.show()
if __name__ == '__main__':
main()
Output:

Producing 2D perlin noise with numpy

I'm trying to produce 2D perlin noise using numpy, but instead of something smooth I get this :
my broken perlin noise, with ugly squares everywhere
For sure, I'm mixing up my dimensions somewhere, probably when I combine the four gradients ... But I can't find it and my brain is melting right now. Anyone can help me pinpoint the problem ?
Anyway, here is the code:
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
def perlin(x,y,seed=0):
# permutation table
np.random.seed(seed)
p = np.arange(256,dtype=int)
np.random.shuffle(p)
p = np.stack([p,p]).flatten()
# coordinates of the first corner
xi = x.astype(int)
yi = y.astype(int)
# internal coordinates
xf = x - xi
yf = y - yi
# fade factors
u = fade(xf)
v = fade(yf)
# noise components
n00 = gradient(p[p[xi]+yi],xf,yf)
n01 = gradient(p[p[xi]+yi+1],xf,yf-1)
n11 = gradient(p[p[xi+1]+yi+1],xf-1,yf-1)
n10 = gradient(p[p[xi+1]+yi],xf-1,yf)
# combine noises
x1 = lerp(n00,n10,u)
x2 = lerp(n10,n11,u)
return lerp(x2,x1,v)
def lerp(a,b,x):
"linear interpolation"
return a + x * (b-a)
def fade(t):
"6t^5 - 15t^4 + 10t^3"
return 6 * t**5 - 15 * t**4 + 10 * t**3
def gradient(h,x,y):
"grad converts h to the right gradient vector and return the dot product with (x,y)"
vectors = np.array([[0,1],[0,-1],[1,0],[-1,0]])
g = vectors[h%4]
return g[:,:,0] * x + g[:,:,1] * y
lin = np.linspace(0,5,100,endpoint=False)
y,x = np.meshgrid(lin,lin)
plt.imshow(perlin(x,y,seed=0))
Thanks to Paul Panzer and a good night of sleep it works now ...
import numpy as np
import matplotlib.pyplot as plt
def perlin(x, y, seed=0):
# permutation table
np.random.seed(seed)
p = np.arange(256, dtype=int)
np.random.shuffle(p)
p = np.stack([p, p]).flatten()
# coordinates of the top-left
xi, yi = x.astype(int), y.astype(int)
# internal coordinates
xf, yf = x - xi, y - yi
# fade factors
u, v = fade(xf), fade(yf)
# noise components
n00 = gradient(p[p[xi] + yi], xf, yf)
n01 = gradient(p[p[xi] + yi + 1], xf, yf - 1)
n11 = gradient(p[p[xi + 1] + yi + 1], xf - 1, yf - 1)
n10 = gradient(p[p[xi + 1] + yi], xf - 1, yf)
# combine noises
x1 = lerp(n00, n10, u)
x2 = lerp(n01, n11, u) # FIX1: I was using n10 instead of n01
return lerp(x1, x2, v) # FIX2: I also had to reverse x1 and x2 here
def lerp(a, b, x):
"linear interpolation"
return a + x * (b - a)
def fade(t):
"6t^5 - 15t^4 + 10t^3"
return 6 * t**5 - 15 * t**4 + 10 * t**3
def gradient(h, x, y):
"grad converts h to the right gradient vector and return the dot product with (x,y)"
vectors = np.array([[0, 1], [0, -1], [1, 0], [-1, 0]])
g = vectors[h % 4]
return g[:, :, 0] * x + g[:, :, 1] * y
lin = np.linspace(0, 5, 100, endpoint=False)
x, y = np.meshgrid(lin, lin) # FIX3: I thought I had to invert x and y here but it was a mistake
plt.imshow(perlin(x, y, seed=2), origin='upper')

Equivalent of `polyfit` for a 2D polynomial in Python

I'd like to find a least-squares solution for the a coefficients in
z = (a0 + a1*x + a2*y + a3*x**2 + a4*x**2*y + a5*x**2*y**2 + a6*y**2 +
a7*x*y**2 + a8*x*y)
given arrays x, y, and z of length 20. Basically I'm looking for the equivalent of numpy.polyfit but for a 2D polynomial.
This question is similar, but the solution is provided via MATLAB.
Here is an example showing how you can use numpy.linalg.lstsq for this task:
import numpy as np
x = np.linspace(0, 1, 20)
y = np.linspace(0, 1, 20)
X, Y = np.meshgrid(x, y, copy=False)
Z = X**2 + Y**2 + np.random.rand(*X.shape)*0.01
X = X.flatten()
Y = Y.flatten()
A = np.array([X*0+1, X, Y, X**2, X**2*Y, X**2*Y**2, Y**2, X*Y**2, X*Y]).T
B = Z.flatten()
coeff, r, rank, s = np.linalg.lstsq(A, B)
the adjusting coefficients coeff are:
array([ 0.00423365, 0.00224748, 0.00193344, 0.9982576 , -0.00594063,
0.00834339, 0.99803901, -0.00536561, 0.00286598])
Note that coeff[3] and coeff[6] respectively correspond to X**2 and Y**2, and they are close to 1. because the example data was created with Z = X**2 + Y**2 + small_random_component.
Based on the answers from #Saullo and #Francisco I have made a function which I have found helpful:
def polyfit2d(x, y, z, kx=3, ky=3, order=None):
'''
Two dimensional polynomial fitting by least squares.
Fits the functional form f(x,y) = z.
Notes
-----
Resultant fit can be plotted with:
np.polynomial.polynomial.polygrid2d(x, y, soln.reshape((kx+1, ky+1)))
Parameters
----------
x, y: array-like, 1d
x and y coordinates.
z: np.ndarray, 2d
Surface to fit.
kx, ky: int, default is 3
Polynomial order in x and y, respectively.
order: int or None, default is None
If None, all coefficients up to maxiumum kx, ky, ie. up to and including x^kx*y^ky, are considered.
If int, coefficients up to a maximum of kx+ky <= order are considered.
Returns
-------
Return paramters from np.linalg.lstsq.
soln: np.ndarray
Array of polynomial coefficients.
residuals: np.ndarray
rank: int
s: np.ndarray
'''
# grid coords
x, y = np.meshgrid(x, y)
# coefficient array, up to x^kx, y^ky
coeffs = np.ones((kx+1, ky+1))
# solve array
a = np.zeros((coeffs.size, x.size))
# for each coefficient produce array x^i, y^j
for index, (j, i) in enumerate(np.ndindex(coeffs.shape)):
# do not include powers greater than order
if order is not None and i + j > order:
arr = np.zeros_like(x)
else:
arr = coeffs[i, j] * x**i * y**j
a[index] = arr.ravel()
# do leastsq fitting and return leastsq result
return np.linalg.lstsq(a.T, np.ravel(z), rcond=None)
And the resultant fit can be visualised with:
fitted_surf = np.polynomial.polynomial.polyval2d(x, y, soln.reshape((kx+1,ky+1)))
plt.matshow(fitted_surf)
Excellent answer by Saullo Castro. Just to add the code to reconstruct the function using the least-squares solution for the a coefficients,
def poly2Dreco(X, Y, c):
return (c[0] + X*c[1] + Y*c[2] + X**2*c[3] + X**2*Y*c[4] + X**2*Y**2*c[5] +
Y**2*c[6] + X*Y**2*c[7] + X*Y*c[8])
You can also use scikit-learn for this.
import numpy as np
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
x = np.linspace(0, 1, 20)
y = np.linspace(0, 1, 20)
X, Y = np.meshgrid(x, y, copy=False)
X = X.flatten()
Y = Y.flatten()
# Generate noisy data
np.random.seed(0)
Z = X**2 + Y**2 + np.random.randn(*X.shape)*0.01
# Process 2D inputs
poly = PolynomialFeatures(degree=2)
input_pts = np.stack([X, Y]).T
assert(input_pts.shape == (400, 2))
in_features = poly.fit_transform(input_pts)
# Linear regression
model = LinearRegression()
model.fit(in_features, Z)
# Display coefficients
print(dict(zip(poly.get_feature_names_out(), model.coef_.round(4))))
# Check fit
print(f"R-squared: {model.score(poly.transform(input_pts), Z):.3f}")
# Make predictions
Z_predicted = model.predict(poly.transform(input_pts))
Out:
{'1': 0.0, 'x0': 0.003, 'x1': -0.0074, 'x0^2': 0.9974, 'x0 x1': 0.0047, 'x1^2': 1.0014}
R-squared: 1.000
Note that if kx != ky the code will fail because the j and i indices are inverted in the loop.
You get (j,i) from enumerate(np.ndindex(coeffs.shape)), but then you address elements in coeffs as coeffs[i,j]. Since the shape of the coefficient matrix is given by the maximum polynomial order that you are asking to use, the matrix will be rectangular if kx != ky and you will exceed one of its dimensions.

Python: heat density plot in a disk

My goal is to make a density heat map plot of sphere in 2D. The plotting code below the line works when I use rectangular domains. However, I am trying to use the code for a circular domain. The radius of sphere is 1. The code I have so far is:
from pylab import *
import numpy as np
from matplotlib.colors import LightSource
from numpy.polynomial.legendre import leggauss, legval
xi = 0.0
xf = 1.0
numx = 500
yi = 0.0
yf = 1.0
numy = 500
def f(x):
if 0 <= x <= 1:
return 100
if -1 <= x <= 0:
return 0
deg = 1000
xx, w = leggauss(deg)
L = np.polynomial.legendre.legval(xx, np.identity(deg))
integral = (L * (f(x) * w)[None,:]).sum(axis = 1)
c = (np.arange(1, 500) + 0.5) * integral[1:500]
def r(x, y):
return np.sqrt(x ** 2 + y ** 2)
theta = np.arctan2(y, x)
x, y = np.linspace(0, 1, 500000)
def T(x, y):
return (sum(r(x, y) ** l * c[:,None] *
np.polynomial.legendre.legval(xx, identity(deg)) for l in range(1, 500)))
T(x, y) should equal the sum of c the coefficients times the radius as a function of x and y to the l power times the legendre polynomial where the argument is of the legendre polynomial is cos(theta).
In python: integrating a piecewise function, I learned how to use the Legendre polynomials in a summation but that method is slightly different, and for the plotting, I need a function T(x, y).
This is the plotting code.
densityinterpolation = 'bilinear'
densitycolormap = cm.jet
densityshadedflag = False
densitybarflag = True
gridflag = True
plotfilename = 'laplacesphere.eps'
x = arange(xi, xf, (xf - xi) / (numx - 1))
y = arange(yi, yf, (yf - yi) / (numy - 1))
X, Y = meshgrid(x, y)
z = T(X, Y)
if densityshadedflag:
ls = LightSource(azdeg = 120, altdeg = 65)
rgb = ls.shade(z, densitycolormap)
im = imshow(rgb, extent = [xi, xf, yi, yf], cmap = densitycolormap)
else:
im = imshow(z, extent = [xi, xf, yi, yf], cmap = densitycolormap)
im.set_interpolation(densityinterpolation)
if densitybarflag:
colorbar(im)
grid(gridflag)
show()
I made the plot in Mathematica for reference of what my end goal is
If you set the values outside of the disk domain (or whichever domain you want) to float('nan'), those points will be ignored when plotting (leaving them in white color).

Categories

Resources