Fitting 2D sum of gaussians, scipy.optimise.leastsq (Ans: Use curve_fit!) - python

I want to fit an 2D sum of gaussians to this data:
After failing at fitting a sum to this initially I instead sampled each peak separately (image) and returned a fit by find it's moments (essentially using this code).
Unfortunately, this results in an incorrect peak position measurement, due to the overlapping signal of the neighbouring peaks. Below is a plot of the sum of the separate fits. Obviously their peak all lean toward the centre. I need to account for this in order to return the correct peak position.
I've got working code which plots a 2D gaussian envelope function (twoD_Gaussian()), and I parse this through optimize.leastsq as a 1D array using numpy.ravel and an appropriate error function, however this results in a nonsense output.
I tried fitting a single peak within the sum and get the following erroneous output:
I'd appreciate any advice on what i could try to make this work, or alternative approaches if this isn't appropriate. All input welcomed of course!
Code below:
from scipy.optimize import leastsq
import numpy as np
import matplotlib.pyplot as plt
def twoD_Gaussian(amp0, x0, y0, amp1=13721, x1=356, y1=247, amp2=14753, x2=291, y2=339, sigma=40):
x0 = float(x0)
y0 = float(y0)
x1 = float(x1)
y1 = float(y1)
x2 = float(x2)
y2 = float(y2)
return lambda x, y: (amp0*np.exp(-(((x0-x)/sigma)**2+((y0-y)/sigma)**2)/2))+(
amp1*np.exp(-(((x1-x)/sigma)**2+((y1-y)/sigma)**2)/2))+(
amp2*np.exp(-(((x2-x)/sigma)**2+((y2-y)/sigma)**2)/2))
def fitgaussian2D(x, y, data, params):
"""Returns (height, x, y, width_x, width_y)
the gaussian parameters of a 2D distribution found by a fit"""
errorfunction = lambda p: np.ravel(twoD_Gaussian(*p)(*np.indices(np.shape(data))) - data)
p, success = optimize.leastsq(errorfunction, params)
return p
# Create data indices
I = image # Red channel of a scanned image, equivalent to the 1st image displayed in this post.
p = np.asarray(I).astype('float')
w,h = np.shape(I)
x, y = np.mgrid[0:h, 0:w]
xy = (x,y)
# scanned at 150 dpi = 5.91 dots per mm
dpmm = 5.905511811
plot_width = 40*dpmm
# create function indices
fdims = np.round(plot_width/2)
xdims = (RC[0] - fdims, RC[0] + fdims)
ydims = (RC[1] - fdims, RC[1] + fdims)
fx = np.linspace(xdims[0], xdims[1], np.round(plot_width))
fy = np.linspace(ydims[0], ydims[1], np.round(plot_width))
fx,fy = np.meshgrid(fx,fy)
#Crop image for display
crp_data = image[xdims[0]:xdims[1], ydims[0]:ydims[1]]
z = crp_data
# Parameters obtained from separate fits
Amplitudes = (13245, 13721, 15374)
px = (410, 356, 290)
py = (350, 247, 339)
initial_guess_sum = (Amp[0], px[0], py[0], Amp[1], px[1], py[1], Amp[2], px[2], py[2])
initial_guess_peak3 = (Amp[0], px[0], py[0]) # Try fitting single peak within sum
fitted_pars = fitgaussian2D(x, y, z, initial_guess_sum)
#fitted_pars = fitgaussian2D(x, y, z, initial_guess_peak3)
data_fitted= twoD_Gaussian(*fitted_pars)(fx,fy)
#data_fitted= twoD_Gaussian(*initial_guess_sum)(fx,fy)
fig = plt.figure(figsize=(10, 30))
ax = fig.add_subplot(111, aspect="equal")
#fig, ax = plt.subplots(1)
cb = ax.imshow(p, cmap=plt.cm.jet, origin='bottom',
extent=(x.min(), x.max(), y.min(), y.max()))
ax.contour(fx, fy, data_fitted.reshape(fx.shape[0], fy.shape[1]), 4, colors='w')
ax.set_xlim(np.int(RC[0])-135, np.int(RC[0])+135)
ax.set_ylim(np.int(RC[1])+135, np.int(RC[1])-135)
#plt.colorbar(cb)
plt.show()

I tried any number of other things before giving up and trying curve_fit again, albeit with more knowledge of parsing lambda functions. It worked. Example output and code below (still with redundancies) for the sake of posterity.
def twoD_Gaussian(amp0, x0, y0, amp1=13721, x1=356, y1=247, amp2=14753, x2=291, y2=339, sigma=40):
x0 = float(x0)
y0 = float(y0)
x1 = float(x1)
y1 = float(y1)
x2 = float(x2)
y2 = float(y2)
return lambda x, y: (amp0*np.exp(-(((x0-x)/sigma)**2+((y0-y)/sigma)**2)/2))+(
amp1*np.exp(-(((x1-x)/sigma)**2+((y1-y)/sigma)**2)/2))+(
amp2*np.exp(-(((x2-x)/sigma)**2+((y2-y)/sigma)**2)/2))
def twoD_GaussianCF(xy, amp0, x0, y0, amp1=13721, amp2=14753, x1=356, y1=247, x2=291, y2=339, sigma_x=12, sigma_y=12):
x0 = float(x0)
y0 = float(y0)
x1 = float(x1)
y1 = float(y1)
x2 = float(x2)
y2 = float(y2)
g = (amp0*np.exp(-(((x0-x)/sigma_x)**2+((y0-y)/sigma_y)**2)/2))+(
amp1*np.exp(-(((x1-x)/sigma_x)**2+((y1-y)/sigma_y)**2)/2))+(
amp2*np.exp(-(((x2-x)/sigma_x)**2+((y2-y)/sigma_y)**2)/2))
return g.ravel()
# Create data indices
I = image # Red channel of a scanned image, equivalent to the 1st image displayed in this post.
p = np.asarray(I).astype('float')
w,h = np.shape(I)
x, y = np.mgrid[0:h, 0:w]
xy = (x,y)
N_points = 3
display_width = 80
initial_guess_sum = (Amp[0], px[0], py[0], Amp[1], px[1], py[1], Amp[2], px[2], py[2])
popt, pcov = opt.curve_fit(twoD_GaussianCF, xy, np.ravel(p), p0=initial_guess_sum)
data_fitted= twoD_Gaussian(*popt)(x,y)
peaks = [(popt[1],popt[2]), (popt[5],popt[6]), (popt[7],popt[8])]
fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(111, aspect="equal")
cb = ax.imshow(p, cmap=plt.cm.jet, origin='bottom',
extent=(x.min(), x.max(), y.min(), y.max()))
ax.contour(x, y, data_fitted.reshape(x.shape[0], y.shape[1]), 20, colors='w')
ax.set_xlim(np.int(RC[0])-135, np.int(RC[0])+135)
ax.set_ylim(np.int(RC[1])+135, np.int(RC[1])-135)
for k in range(0,N_points):
plt.plot(peaks[k][0],peaks[k][1],'bo',markersize=7)
plt.show()

If all you care about is the centroid of each gaussian, I would just go with scipy.optimize.minimize. Multiply your data by -1 and then do some coarse sampling to find minima. The height of each peak will be offset by the neighboring gaussians but the positions are unchanged, so if you find a local extreme value then that must be the centroid of a gaussian.
If you need the other parameters, it might make sense to find the centroids as I suggest and then use leastsq to find the amplitudes and widths. It might add a lot of overhead if you're running these fits many times, but it would significantly reduce the number of free parameters in the least squares fit.

Related

How to delete all points/coordinates within a (parametrically defined) ellipse

I have some data which looks like this:
I've drawn an ellipse around some of the data using from skimage.measure import EllipseModel
I was able to fit the ellipse by providing the package with B0_M data and the corresponding q^2 between 5200 and 5350, and then I was able to extract some parameters from the fit, to plot the ellipse myself, as follows:
X1Y1 = np.column_stack((X1,Y1))
ell = EllipseModel()
ell.estimate(X1Y1)
xc, yc, a, b, theta = ell.params
where X1 is the full B_0 data and X2 is the full q^2 dataset. It returned the following values for the ellipse parameters:
a = 0.399894
b = 37.826
xc = 5272
yc = 9.27
theta = 1.573
Unfortunately this fit was not perfect, so I scaled some of the parameters, or added some small numbers etc, essentially to tinker to get the fit shown in the figure. Here is how I plotted the ellipse fit:
xc, yc, a, b, theta = ell.params
t = np.linspace(0, 2*np.pi, 100)
dt = 0.01*theta
ell_x = xc + 2*a*np.cos(theta+dt)*np.cos(t) - 1.8*b*np.sin(theta+dt)*np.sin(t)
ell_y = yc + 0.47*a*np.sin(theta+dt)*np.cos(t) + 0.47*b*np.cos(theta+dt)*np.sin(t)+0.26
plt.scatter(X,Y, marker = '.', alpha = 0.05, color = 'navy', s =0.2)
plt.scatter(xc, yc+0.26, color='red', s=10)
plt.plot(ell_x, ell_y, color = 'red')
plt.xlim(5150,5400)
plt.ylim(7,12)
plt.xlabel('B0_M')
plt.ylabel('$q^2$')
plt.title('jpsi')
Now I'd like to remove all of the points, from X1 and Y1, that are inside the ellipse
How can I do this? I wanted to use a simple mathematical argument like basically using the equation of an ellipse, but it is more complicated since I have it in parametric form, and its also not the most tidiest thing since I have scaled different variables by different amounts as I said before.
Is there some way to simply say, "delete points in X, Y if they are inside the ellipse with coordinates ell_x and ell_y"?
Many thanks
I think you can use the equation for an ellipse to construct a mask that isolates the points outside your model.
The trick is to transform your X1 and Y1 into the ellipse's coordinate system by shifting and rotating them using xc, yc, and theta before applying the ellipse equation.
dx = X1 - xc
dy = Y1 - yc
x2 = dx * np.cos(theta) + dy * np.sin(theta)
y2 = -dx * np.sin(theta) + dy * np.cos(theta)
mask = np.square(x2 / a) + np.square(y2 / b) > 1
X1_outside = X1[mask]
Y1_outside = Y1[mask]
Note: I expected that skimage.measure.Ellipse would have some method that makes this easier, but I can't find it after a quick read through the docs. If anyone knows how to do this using Ellipse that would be much more readable.

Inverse of numpy.gradient function

I need to create a function which would be the inverse of the np.gradient function.
Where the Vx,Vy arrays (Velocity component vectors) are the input and the output would be an array of anti-derivatives (Arrival Time) at the datapoints x,y.
I have data on a (x,y) grid with scalar values (time) at each point.
I have used the numpy gradient function and linear interpolation to determine the gradient vector Velocity (Vx,Vy) at each point (See below).
I have achieved this by:
#LinearTriInterpolator applied to a delaunay triangular mesh
LTI= LinearTriInterpolator(masked_triang, time_array)
#Gradient requested at the mesh nodes:
(Vx, Vy) = LTI.gradient(triang.x, triang.y)
The first image below shows the velocity vectors at each point, and the point labels represent the time value which formed the derivatives (Vx,Vy)
The next image shows the resultant scalar value of the derivatives (Vx,Vy) plotted as a colored contour graph with associated node labels.
So my challenge is:
I need to reverse the process!
Using the gradient vectors (Vx,Vy) or the resultant scalar value to determine the original Time-Value at that point.
Is this possible?
Knowing that the numpy.gradient function is computed using second order accurate central differences in the interior points and either first or second order accurate one-sides (forward or backwards) differences at the boundaries, I am sure there is a function which would reverse this process.
I was thinking that taking a line derivative between the original point (t=0 at x1,y1) to any point (xi,yi) over the Vx,Vy plane would give me the sum of the velocity components. I could then divide this value by the distance between the two points to get the time taken..
Would this approach work? And if so, which numpy integrate function would be best applied?
An example of my data can be found here [http://www.filedropper.com/calculatearrivaltimefromgradientvalues060820]
Your help would be greatly appreciated
EDIT:
Maybe this simplified drawing might help understand where I'm trying to get to..
EDIT:
Thanks to #Aguy who has contibuted to this code.. I Have tried to get a more accurate representation using a meshgrid of spacing 0.5 x 0.5m and calculating the gradient at each meshpoint, however I am not able to integrate it properly. I also have some edge affects which are affecting the results that I don't know how to correct.
import numpy as np
from scipy import interpolate
from matplotlib import pyplot
from mpl_toolkits.mplot3d import Axes3D
#Createmesh grid with a spacing of 0.5 x 0.5
stepx = 0.5
stepy = 0.5
xx = np.arange(min(x), max(x), stepx)
yy = np.arange(min(y), max(y), stepy)
xgrid, ygrid = np.meshgrid(xx, yy)
grid_z1 = interpolate.griddata((x,y), Arrival_Time, (xgrid, ygrid), method='linear') #Interpolating the Time values
#Formatdata
X = np.ravel(xgrid)
Y= np.ravel(ygrid)
zs = np.ravel(grid_z1)
Z = zs.reshape(X.shape)
#Calculate Gradient
(dx,dy) = np.gradient(grid_z1) #Find gradient for points on meshgrid
Velocity_dx= dx/stepx #velocity ms/m
Velocity_dy= dy/stepx #velocity ms/m
Resultant = (Velocity_dx**2 + Velocity_dy**2)**0.5 #Resultant scalar value ms/m
Resultant = np.ravel(Resultant)
#Plot Original Data F(X,Y) on the meshgrid
fig = pyplot.figure()
ax = fig.add_subplot(projection='3d')
ax.scatter(x,y,Arrival_Time,color='r')
ax.plot_trisurf(X, Y, Z)
ax.set_xlabel('X-Coordinates')
ax.set_ylabel('Y-Coordinates')
ax.set_zlabel('Time (ms)')
pyplot.show()
#Plot the Derivative of f'(X,Y) on the meshgrid
fig = pyplot.figure()
ax = fig.add_subplot(projection='3d')
ax.scatter(X,Y,Resultant,color='r',s=0.2)
ax.plot_trisurf(X, Y, Resultant)
ax.set_xlabel('X-Coordinates')
ax.set_ylabel('Y-Coordinates')
ax.set_zlabel('Velocity (ms/m)')
pyplot.show()
#Integrate to compare the original data input
dxintegral = np.nancumsum(Velocity_dx, axis=1)*stepx
dyintegral = np.nancumsum(Velocity_dy, axis=0)*stepy
valintegral = np.ma.zeros(dxintegral.shape)
for i in range(len(yy)):
for j in range(len(xx)):
valintegral[i, j] = np.ma.sum([dxintegral[0, len(xx) // 2],
dyintegral[i, len(yy) // 2], dxintegral[i, j], - dxintegral[i, len(xx) // 2]])
valintegral = valintegral * np.isfinite(dxintegral)
Now the np.gradient is applied at every meshnode (dx,dy) = np.gradient(grid_z1)
Now in my process I would analyse the gradient values above and make some adjustments (There is some unsual edge effects that are being create which I need to rectify) and would then integrate the values to get back to a surface which would be very similar to f(x,y) shown above.
I need some help adjusting the integration function:
#Integrate to compare the original data input
dxintegral = np.nancumsum(Velocity_dx, axis=1)*stepx
dyintegral = np.nancumsum(Velocity_dy, axis=0)*stepy
valintegral = np.ma.zeros(dxintegral.shape)
for i in range(len(yy)):
for j in range(len(xx)):
valintegral[i, j] = np.ma.sum([dxintegral[0, len(xx) // 2],
dyintegral[i, len(yy) // 2], dxintegral[i, j], - dxintegral[i, len(xx) // 2]])
valintegral = valintegral * np.isfinite(dxintegral)
And now I need to calculate the new 'Time' values at the original (x,y) point locations.
UPDATE (08-09-20) : I am getting some promising results using the help from #Aguy. The results can be seen below (with the blue contours representing the original data, and the red contours representing the integrated values).
I am still working on an integration approach which can remove the inaccuarcies at the areas of min(y) and max(y)
from matplotlib.tri import (Triangulation, UniformTriRefiner,
CubicTriInterpolator,LinearTriInterpolator,TriInterpolator,TriAnalyzer)
import pandas as pd
from scipy.interpolate import griddata
import matplotlib.pyplot as plt
import numpy as np
from scipy import interpolate
#-------------------------------------------------------------------------
# STEP 1: Import data from Excel file, and set variables
#-------------------------------------------------------------------------
df_initial = pd.read_excel(
r'C:\Users\morga\PycharmProjects\venv\Development\Trial'
r'.xlsx')
Inputdata can be found here link
df_initial = df_initial .sort_values(by='Delay', ascending=True) #Update dataframe and sort by Delay
x = df_initial ['X'].to_numpy()
y = df_initial ['Y'].to_numpy()
Arrival_Time = df_initial ['Delay'].to_numpy()
# Createmesh grid with a spacing of 0.5 x 0.5
stepx = 0.5
stepy = 0.5
xx = np.arange(min(x), max(x), stepx)
yy = np.arange(min(y), max(y), stepy)
xgrid, ygrid = np.meshgrid(xx, yy)
grid_z1 = interpolate.griddata((x, y), Arrival_Time, (xgrid, ygrid), method='linear') # Interpolating the Time values
# Calculate Gradient (velocity ms/m)
(dy, dx) = np.gradient(grid_z1) # Find gradient for points on meshgrid
Velocity_dx = dx / stepx # x velocity component ms/m
Velocity_dy = dy / stepx # y velocity component ms/m
# Integrate to compare the original data input
dxintegral = np.nancumsum(Velocity_dx, axis=1) * stepx
dyintegral = np.nancumsum(Velocity_dy, axis=0) * stepy
valintegral = np.ma.zeros(dxintegral.shape) # Makes an array filled with 0's the same shape as dx integral
for i in range(len(yy)):
for j in range(len(xx)):
valintegral[i, j] = np.ma.sum(
[dxintegral[0, len(xx) // 2], dyintegral[i, len(xx) // 2], dxintegral[i, j], - dxintegral[i, len(xx) // 2]])
valintegral[np.isnan(dx)] = np.nan
min_value = np.nanmin(valintegral)
valintegral = valintegral + (min_value * -1)
##Plot Results
fig = plt.figure()
ax = fig.add_subplot()
ax.scatter(x, y, color='black', s=7, zorder=3)
ax.set_xlabel('X-Coordinates')
ax.set_ylabel('Y-Coordinates')
ax.contour(xgrid, ygrid, valintegral, levels=50, colors='red', zorder=2)
ax.contour(xgrid, ygrid, grid_z1, levels=50, colors='blue', zorder=1)
ax.set_aspect('equal')
plt.show()
TL;DR;
You have multiple challenges to address in this issue, mainly:
Potential reconstruction (scalar field) from its gradient (vector field)
But also:
Observation in a concave hull with non rectangular grid;
Numerical 2D line integration and numerical inaccuracy;
It seems it can be solved by choosing an adhoc interpolant and a smart way to integrate (as pointed out by #Aguy).
MCVE
In a first time, let's build a MCVE to highlight above mentioned key points.
Dataset
We recreate a scalar field and its gradient.
import numpy as np
from scipy import interpolate
import matplotlib.pyplot as plt
def f(x, y):
return x**2 + x*y + 2*y + 1
Nx, Ny = 21, 17
xl = np.linspace(-3, 3, Nx)
yl = np.linspace(-2, 2, Ny)
X, Y = np.meshgrid(xl, yl)
Z = f(X, Y)
zl = np.arange(np.floor(Z.min()), np.ceil(Z.max())+1, 2)
dZdy, dZdx = np.gradient(Z, yl, xl, edge_order=1)
V = np.hypot(dZdx, dZdy)
The scalar field looks like:
axe = plt.axes(projection='3d')
axe.plot_surface(X, Y, Z, cmap='jet', alpha=0.5)
axe.view_init(elev=25, azim=-45)
And, the vector field looks like:
axe = plt.contour(X, Y, Z, zl, cmap='jet')
axe.axes.quiver(X, Y, dZdx, dZdy, V, units='x', pivot='tip', cmap='jet')
axe.axes.set_aspect('equal')
axe.axes.grid()
Indeed gradient is normal to potential levels. We also plot the gradient magnitude:
axe = plt.contour(X, Y, V, 10, cmap='jet')
axe.axes.set_aspect('equal')
axe.axes.grid()
Raw field reconstruction
If we naively reconstruct the scalar field from the gradient:
SdZx = np.cumsum(dZdx, axis=1)*np.diff(xl)[0]
SdZy = np.cumsum(dZdy, axis=0)*np.diff(yl)[0]
Zhat = np.zeros(SdZx.shape)
for i in range(Zhat.shape[0]):
for j in range(Zhat.shape[1]):
Zhat[i,j] += np.sum([SdZy[i,0], -SdZy[0,0], SdZx[i,j], -SdZx[i,0]])
Zhat += Z[0,0] - Zhat[0,0]
We can see the global result is roughly correct, but levels are less accurate where the gradient magnitude is low:
Interpolated field reconstruction
If we increase the grid resolution and pick a specific interpolant (usual when dealing with mesh grid), we can get a finer field reconstruction:
r = np.stack([X.ravel(), Y.ravel()]).T
Sx = interpolate.CloughTocher2DInterpolator(r, dZdx.ravel())
Sy = interpolate.CloughTocher2DInterpolator(r, dZdy.ravel())
Nx, Ny = 200, 200
xli = np.linspace(xl.min(), xl.max(), Nx)
yli = np.linspace(yl.min(), yl.max(), Nx)
Xi, Yi = np.meshgrid(xli, yli)
ri = np.stack([Xi.ravel(), Yi.ravel()]).T
dZdxi = Sx(ri).reshape(Xi.shape)
dZdyi = Sy(ri).reshape(Xi.shape)
SdZxi = np.cumsum(dZdxi, axis=1)*np.diff(xli)[0]
SdZyi = np.cumsum(dZdyi, axis=0)*np.diff(yli)[0]
Zhati = np.zeros(SdZxi.shape)
for i in range(Zhati.shape[0]):
for j in range(Zhati.shape[1]):
Zhati[i,j] += np.sum([SdZyi[i,0], -SdZyi[0,0], SdZxi[i,j], -SdZxi[i,0]])
Zhati += Z[0,0] - Zhati[0,0]
Which definitely performs way better:
So basically, increasing the grid resolution with an adhoc interpolant may help you to get more accurate result. The interpolant also solve the need to get a regular rectangular grid from a triangular mesh to perform integration.
Concave and convex hull
You also have pointed out inaccuracy on the edges. Those are the result of the combination of the interpolant choice and the integration methodology. The integration methodology fails to properly compute the scalar field when it reach concave region with few interpolated points. The problem disappear when choosing a mesh-free interpolant able to extrapolate.
To illustrate it, let's remove some data from our MCVE:
q = np.full(dZdx.shape, False)
q[0:6,5:11] = True
q[-6:,-6:] = True
dZdx[q] = np.nan
dZdy[q] = np.nan
Then the interpolant can be constructed as follow:
q2 = ~np.isnan(dZdx.ravel())
r = np.stack([X.ravel(), Y.ravel()]).T[q2,:]
Sx = interpolate.CloughTocher2DInterpolator(r, dZdx.ravel()[q2])
Sy = interpolate.CloughTocher2DInterpolator(r, dZdy.ravel()[q2])
Performing the integration we see that in addition of classical edge effect we do have less accurate value in concave regions (swingy dot-dash lines where the hull is concave) and we have no data outside the convex hull as Clough Tocher is a mesh-based interpolant:
Vl = np.arange(0, 11, 1)
axe = plt.contour(X, Y, np.hypot(dZdx, dZdy), Vl, cmap='jet')
axe.axes.contour(Xi, Yi, np.hypot(dZdxi, dZdyi), Vl, cmap='jet', linestyles='-.')
axe.axes.set_aspect('equal')
axe.axes.grid()
So basically the error we are seeing on the corner are most likely due to integration issue combined with interpolation limited to the convex hull.
To overcome this we can choose a different interpolant such as RBF (Radial Basis Function Kernel) which is able to create data outside the convex hull:
Sx = interpolate.Rbf(r[:,0], r[:,1], dZdx.ravel()[q2], function='thin_plate')
Sy = interpolate.Rbf(r[:,0], r[:,1], dZdy.ravel()[q2], function='thin_plate')
dZdxi = Sx(ri[:,0], ri[:,1]).reshape(Xi.shape)
dZdyi = Sy(ri[:,0], ri[:,1]).reshape(Xi.shape)
Notice the slightly different interface of this interpolator (mind how parmaters are passed).
The result is the following:
We can see the region outside the convex hull can be extrapolated (RBF are mesh free). So choosing the adhoc interpolant is definitely a key point to solve your problem. But we still need to be aware that extrapolation may perform well but is somehow meaningless and dangerous.
Solving your problem
The answer provided by #Aguy is perfectly fine as it setups a clever way to integrate that is not disturbed by missing points outside the convex hull. But as you mentioned there is inaccuracy in concave region inside the convex hull.
If you wish to remove the edge effect you detected, you will have to resort to an interpolant able to extrapolate as well, or find another way to integrate.
Interpolant change
Using RBF interpolant seems to solve your problem. Here is the complete code:
df = pd.read_excel('./Trial-Wireup 2.xlsx')
x = df['X'].to_numpy()
y = df['Y'].to_numpy()
z = df['Delay'].to_numpy()
r = np.stack([x, y]).T
#S = interpolate.CloughTocher2DInterpolator(r, z)
#S = interpolate.LinearNDInterpolator(r, z)
S = interpolate.Rbf(x, y, z, epsilon=0.1, function='thin_plate')
N = 200
xl = np.linspace(x.min(), x.max(), N)
yl = np.linspace(y.min(), y.max(), N)
X, Y = np.meshgrid(xl, yl)
#Zp = S(np.stack([X.ravel(), Y.ravel()]).T)
Zp = S(X.ravel(), Y.ravel())
Z = Zp.reshape(X.shape)
dZdy, dZdx = np.gradient(Z, yl, xl, edge_order=1)
SdZx = np.nancumsum(dZdx, axis=1)*np.diff(xl)[0]
SdZy = np.nancumsum(dZdy, axis=0)*np.diff(yl)[0]
Zhat = np.zeros(SdZx.shape)
for i in range(Zhat.shape[0]):
for j in range(Zhat.shape[1]):
#Zhat[i,j] += np.nansum([SdZy[i,0], -SdZy[0,0], SdZx[i,j], -SdZx[i,0]])
Zhat[i,j] += np.nansum([SdZx[0,N//2], SdZy[i,N//2], SdZx[i,j], -SdZx[i,N//2]])
Zhat += Z[100,100] - Zhat[100,100]
lz = np.linspace(0, 5000, 20)
axe = plt.contour(X, Y, Z, lz, cmap='jet')
axe = plt.contour(X, Y, Zhat, lz, cmap='jet', linestyles=':')
axe.axes.plot(x, y, '.', markersize=1)
axe.axes.set_aspect('equal')
axe.axes.grid()
Which graphically renders as follow:
The edge effect is gone because of the RBF interpolant can extrapolate over the whole grid. You can confirm it by comparing the result of mesh-based interpolants.
Linear
Clough Tocher
Integration variable order change
We can also try to find a better way to integrate and mitigate the edge effect, eg. let's change the integration variable order:
Zhat[i,j] += np.nansum([SdZy[N//2,0], SdZx[N//2,j], SdZy[i,j], -SdZy[N//2,j]])
With a classic linear interpolant. The result is quite correct, but we still have an edge effect on the bottom left corner:
As you noticed the problem occurs at the middle of the axis in region where the integration starts and lacks a reference point.
Here is one approach:
First, in order to be able to do integration, it's good to be on a regular grid. Using here variable names x and y as short for your triang.x and triang.y we can first create a grid:
import numpy as np
n = 200 # Grid density
stepx = (max(x) - min(x)) / n
stepy = (max(y) - min(y)) / n
xspace = np.arange(min(x), max(x), stepx)
yspace = np.arange(min(y), max(y), stepy)
xgrid, ygrid = np.meshgrid(xspace, yspace)
Then we can interpolate dx and dy on the grid using the same LinearTriInterpolator function:
fdx = LinearTriInterpolator(masked_triang, dx)
fdy = LinearTriInterpolator(masked_triang, dy)
dxgrid = fdx(xgrid, ygrid)
dygrid = fdy(xgrid, ygrid)
Now comes the integration part. In principle, any path we choose should get us to the same value. In practice, since there are missing values and different densities, the choice of path is very important to get a reasonably accurate answer.
Below I choose to integrate over dxgrid in the x direction from 0 to the middle of the grid at n/2. Then integrate over dygrid in the y direction from 0 to the i point of interest. Then over dxgrid again from n/2 to the point j of interest. This is a simple way to make sure most of the path of integration is inside the bulk of available data by simply picking a path that goes mostly in the "middle" of the data range. Other alternative consideration would lead to different path selections.
So we do:
dxintegral = np.nancumsum(dxgrid, axis=1) * stepx
dyintegral = np.nancumsum(dygrid, axis=0) * stepy
and then (by somewhat brute force for clarity):
valintegral = np.ma.zeros(dxintegral.shape)
for i in range(n):
for j in range(n):
valintegral[i, j] = np.ma.sum([dxintegral[0, n // 2], dyintegral[i, n // 2], dxintegral[i, j], - dxintegral[i, n // 2]])
valintegral = valintegral * np.isfinite(dxintegral)
valintegral would be the result up to an arbitrary constant which can help put the "zero" where you want.
With your data shown here:
ax.tricontourf(masked_triang, time_array)
This is what I'm getting reconstructed when using this method:
ax.contourf(xgrid, ygrid, valintegral)
Hopefully this is somewhat helpful.
If you want to revisit the values at the original triangulation points, you can use interp2d on the valintegral regular grid data.
EDIT:
In reply to your edit, your adaptation above has a few errors:
Change the line (dx,dy) = np.gradient(grid_z1) to (dy,dx) = np.gradient(grid_z1)
In the integration loop change the dyintegral[i, len(yy) // 2] term to dyintegral[i, len(xx) // 2]
Better to replace the line valintegral = valintegral * np.isfinite(dxintegral) with valintegral[np.isnan(dx)] = np.nan

Generate profiles through a 2D array at an angle without altering pixels

I'd like to plot two profiles through the highest intensity point in a 2D numpy array, which is an image of a blob (i.e. a line through the semi-major axis, and another line through the semi-minor axis). The blob is rotated at an angle theta counterclockwise from the standard x-axis and is asymmetric.
It is a 600x600 array with a max intensity of 1 (at only one pixel) that is located right at the center at (300, 300). The angle rotation from the x-axis (which then gives the location of the semi-major axis when rotated by that angle) is theta = 89.54 degrees. I do not want to use scipy.ndimage.rotate because it uses spline interpolation, and I do not want to change any of my pixel values. But I suppose a nearest-neighbor interpolation method would be okay.
I tried generating lines corresponding to the major and minor axes across the image, but the result was not right at all (the peak was far less than 1), so maybe I did something wrong. The code for this is below:
import numpy as np
import matplotlib.pyplot as plt
from scipy import ndimage
def profiles_at_angle(image, axis, theta):
theta = np.deg2rad(theta)
if axis == 'major':
x_0, y_0 = 0, 300-300*np.tan(theta)
x_1, y_1 = 599, 300+300*np.tan(theta)
elif axis=='minor':
x_0, y_0 = 300-300*np.tan(theta), 599
x_1, y_1 = 300+300*np.tan(theta), -599
num = 600
x, y = np.linspace(x_0, x_1, num), np.linspace(y_0, y_1, num)
z = ndimage.map_coordinates(image, np.vstack((x,y)))
fig, axes = plt.subplots(nrows=2)
axes[0].imshow(image, cmap='gray')
axes[0].axis('image')
axes[1].plot(z)
plt.xlim(250,350)
plt.show()
profiles_at_angle(image, 'major', theta)
Did I do something obviously wrong in my code above? Or how else can I accomplish this? Thank you.
Edit: Here are some example images. Sorry for the bad quality; my browser crashed every time I tried uploading them anywhere so I had to take photos of the screen.
Figure 1: This is the result of my code above, which is clearly wrong since the peak should be at 1. I'm not sure what I did wrong though.
Figure 2: I made this plot below by just taking the profiles through the standard x and y axes, ignoring any rotation (this only looks good coincidentally because the real angle of rotation is so close to 90 degrees, so I was able to just switch the labels and get this). I want my result to look something like this, but taking the correction rotation angle into account.
Edit: It could be useful to run tests on this method using data very much like my own (it's a 2D Gaussian with nearly the same parameters):
image = np.random.random((600,600))
def generate(data_set):
xvec = np.arange(0, np.shape(data_set)[1], 1)
yvec = np.arange(0, np.shape(data_set)[0], 1)
X, Y = np.meshgrid(xvec, yvec)
return X, Y
def gaussian_func(xy, x0, y0, sigma_x, sigma_y, amp, theta, offset):
x, y = xy
a = (np.cos(theta))**2/(2*sigma_x**2) + (np.sin(theta))**2/(2*sigma_y**2)
b = -np.sin(2*theta)/(4*sigma_x**2) + np.sin(2*theta)/(4*sigma_y**2)
c = (np.sin(theta))**2/(2*sigma_x**2) + (np.cos(theta))**2/(2*sigma_y**2)
inner = a * (x-x0)**2
inner += 2*b*(x-x0)*(y-y0)
inner += c * (y-y0)**2
return (offset + amp * np.exp(-inner)).ravel()
xx, yy = generate(image)
image = gaussian_func((xx.ravel(), yy.ravel()), 300, 300, 5, 4, 1, 1.56, 0)
image = np.reshape(image, (600, 600))
This should do it for you. You just did not properly compute your lines.
theta = 65
peak = np.argwhere(image==1)[0]
x = np.linspace(peak[0]-100,peak[0]+100,1000)
y = lambda x: (x-peak[1])*np.tan(np.deg2rad(theta))+peak[0]
y_maj = np.linspace(y(peak[1]-100),y(peak[1]+100),1000)
y = lambda x: -(x-peak[1])/np.tan(np.deg2rad(theta))+peak[0]
y_min = np.linspace(y(peak[1]-100),y(peak[1]+100),1000)
del y
z_min = scipy.ndimage.map_coordinates(image, np.vstack((x,y_min)))
z_maj = scipy.ndimage.map_coordinates(image, np.vstack((x,y_maj)))
fig, axes = plt.subplots(nrows=2)
axes[0].imshow(image)
axes[0].plot(x,y_maj)
axes[0].plot(x,y_min)
axes[0].axis('image')
axes[1].plot(z_min)
axes[1].plot(z_maj)
plt.show()

How can I make my 2D Gaussian fit to my image

I am trying to fit a 2D Gaussian to an image to find the location of the brightest point in it. My code looks like this:
import numpy as np
import astropy.io.fits as fits
import os
from astropy.stats import mad_std
from scipy.optimize import curve_fit
import matplotlib.pyplot as plt
from matplotlib.patches import Circle
from lmfit.models import GaussianModel
from astropy.modeling import models, fitting
def gaussian(xycoor,x0, y0, sigma, amp):
'''This Function is the Gaussian Function'''
x, y = xycoor # x and y taken from fit function. Stars at 0, increases by 1, goes to length of axis
A = 1 / (2*sigma**2)
eq = amp*np.exp(-A*((x-x0)**2 + (y-y0)**2)) #Gaussian
return eq
def fit(image):
med = np.median(image)
image = image-med
image = image[0,0,:,:]
max_index = np.where(image >= np.max(image))
x0 = max_index[1] #Middle of X axis
y0 = max_index[0] #Middle of Y axis
x = np.arange(0, image.shape[1], 1) #Stars at 0, increases by 1, goes to length of axis
y = np.arange(0, image.shape[0], 1) #Stars at 0, increases by 1, goes to length of axis
xx, yy = np.meshgrid(x, y) #creates a grid to plot the function over
sigma = np.std(image) #The standard dev given in the Gaussian
amp = np.max(image) #amplitude
guess = [x0, y0, sigma, amp] #The initial guess for the gaussian fitting
low = [0,0,0,0] #start of data array
#Upper Bounds x0: length of x axis, y0: length of y axis, st dev: max value in image, amplitude: 2x the max value
upper = [image.shape[0], image.shape[1], np.max(image), np.max(image)*2]
bounds = [low, upper]
params, pcov = curve_fit(gaussian, (xx.ravel(), yy.ravel()), image.ravel(),p0 = guess, bounds = bounds) #optimal fit. Not sure what pcov is.
return params
def plotting(image, params):
fig, ax = plt.subplots()
ax.imshow(image)
ax.scatter(params[0], params[1],s = 10, c = 'red', marker = 'x')
circle = Circle((params[0], params[1]), params[2], facecolor = 'none', edgecolor = 'red', linewidth = 1)
ax.add_patch(circle)
plt.show()
data = fits.getdata('AzTECC100.fits') #read in file
med = np.median(data)
data = data - med
data = data[0,0,:,:]
parameters = fit(data)
#generates a gaussian based on the parameters given
plotting(data, parameters)
The image is plotting and the code is giving no errors but the fitting isn't working. It's just putting an x wherever the x0 and y0 are. The pixel values in my image are very small. The max value is 0.0007 and std dev is 0.0001 and the x and y are a few orders of magnitude larger. So I believe my problem is that because of this my eq is going to zero everywhere so the curve_fit is failing. I'm wondering if there's a better way to construct my gaussian so that it plots correctly?
I do not have access to your image. Instead I have generated some test "image" as follows:
y, x = np.indices((51,51))
x -= 25
y -= 25
data = 3 * np.exp(-0.7 * ((x+2)**2 + (y-1)**2))
Also, I have modified your code for plotting to increase the radius of the circle by 10:
circle = Circle((params[0], params[1]), 10 * params[2], ...)
and I commented out two more lines:
# image = image[0,0,:,:]
# data = data[0,0,:,:]
The result that I get is shown in the attached image and it looks reasonable to me:
Could it be that the issue is in how you access data from the FITS file? (e.g., image = image[0,0,:,:]) Are the data 4D array? Why do you have 4 indices?
I also saw that you have asked a similar question here: Astropy.model 2DGaussian issue in which you tried to use just astropy.modeling. I will look into that question.
NOTE: you can replace code such as
max_index = np.where(image >= np.max(image))
x0 = max_index[1] #Middle of X axis
y0 = max_index[0] #Middle of Y axis
with
y0, x0 = np.unravel_index(np.argmax(data), data.shape)

How do I fit my data to an Airy Function in python?

My code takes an image of a pinhole aperture and fits the data to a Gaussian. Using the Gaussian fit it calculates the Full-Width at Half Maximum. This tells me the resolution of my imaging system.
Here is the fit I get with my code right now:
According to the theory for pinhole diffraction images, the data should correspond to an Airy disk function. For completeness I want to fit the data to a Bessel function or Airy disk pattern. I cannot find any packages that will fit these functions.
Here is the picture I am using:
You can just make out the outer fringes around the central bright spot. Those are the fringes I want to account for in my fit.
import numpy as np
import scipy.optimize as opt
import PIL
from PIL import ImageFilter
from pylab import *
#defining the Gaussian
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))
im = PIL.Image.open('C:/Documents/User/3000.bmp').convert("L") #convert to array
imArr = np.array(im, dtype=float)
bg = np.average(imArr) #find the background, subtract it
imArr = imArr - bg
#get the approx coordinates of brightest spot by filtering
im2 = im.filter(ImageFilter.GaussianBlur(radius=2))
imArr2 = np.array(im2, dtype=float)
tuple = unravel_index(imArr2.argmax(), imArr2.shape)
#find and plot FWHM for the brightest spot
x = np.arange(tuple[1] - 100, tuple[1] + 100, dtype=np.float)
y = imArr[tuple[0], tuple[1] - 100:tuple[1] + 100]
y /= ((max(x) - min(x)) / len(x)) * np.sum(y) # renormalize to a proper Gaussian
p0 = [tuple[1], tuple[0]]
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
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.show()

Categories