Develop Reference

Generate a new set of points along a line

I have a Python project where I need to redraw a line many times with the points in random places but keeping the line's shape and point count roughly the same. The final output will be using polygonal points and not Bezier paths (though I wouldn't be opposed to using Bezier as an intermediary step).
This animation is demonstrating how the points could move along the line to different positions while maintaining the general shape.
I also have a working example below where I'm moving along the line and picking random new points between existing points (the red line, below). It works okay, but I'd love to hear some other approaches I might take if someone knows of a better one?
Though this code is using matplotlib to demonstrate the line, the final program will not.
import numpy as np
from matplotlib import pyplot as plt
import random
from random import (randint,uniform)
def move_along_line(p1, p2, scalar):
distX = p2[0] - p1[0]
distY = p2[1] - p1[1]
modX = (distX * scalar) + p1[0]
modY = (distY * scalar) + p1[1]
return [modX, modY]
x_coords = [213.5500031,234.3809357,255.211853,276.0427856,296.8737183,317.7046204,340.1997681,364.3751221,388.5505066,414.8896484,444.5192261,478.5549622,514.5779419,545.4779053,570.3830566,588.0241699,598.2469482,599.772583,596.758728,593.7449341,590.7310791,593.373291,610.0373535,642.1326294,677.4451904,710.0697021,737.6887817,764.4020386,791.1152954,817.8284912,844.541687,871.2550049,897.9682007,924.6813965,951.3945923,978.1078491,1009.909546,1042.689941,1068.179199,1089.543091]
y_coords = [487.3099976,456.8832703,426.4565125,396.0297852,365.6030273,335.1763,306.0349426,278.1913452,250.3477478,224.7166748,203.0908051,191.2358704,197.6810608,217.504303,244.4946136,276.7698364,312.0551453,348.6885986,385.4395447,422.1904297,458.9414063,495.5985413,527.0128479,537.1477661,527.6642456,510.959259,486.6988525,461.2799683,435.8611145,410.4422913,385.023468,359.6045532,334.18573,308.7669067,283.3480835,257.929184,239.4429474,253.6099091,280.1803284,310.158783]
plt.plot(x_coords,y_coords,color='b')
plt.scatter(x_coords,y_coords,s=2)
new_line_x = []
new_line_y = []
for tgt in range(len(x_coords)-1):
#tgt = randint(0, len(x_coords)-1)
next_pt = tgt+1
new_pt = move_along_line([x_coords[tgt],y_coords[tgt]], [x_coords[next_pt],y_coords[next_pt]], uniform(0, 1))
new_line_x.append(new_pt[0])
new_line_y.append(new_pt[1])
plt.plot(new_line_x,new_line_y,color='r')
plt.scatter(new_line_x,new_line_y,s=10)
ax = plt.gca()
ax.set_aspect('equal')
plt.show()
Thank you very much!

I'm not sure if this is the most optimal way to do this but essentially you want to follow these steps:
Calculate the distance of the entire path, and the distance between all the points. Then for each point, tally the distances to that point.
Generate a new set of random points along the path starting with 0, then for each pair of points calculate a random distance: random value between 0 and 1 * total length of the path.
Sort these distances from smallest to largest.
For each random distance loop over the distances find the index where the random distance is > than distance i, and less than distance i+1. Interpolate new x and y values from these points.
from matplotlib import pyplot as plt
from scipy.interpolate import interp1d
import numpy
import random
import math
x_coords = [195.21,212.53,237.39,270.91,314.21,368.43,434.69,514.1,607.8,692.69,746.98,773.8,776.25,757.45,720.52,668.55,604.68,545.37,505.79,487.05,490.27,516.58,567.09,642.93,745.2,851.5,939.53,1010.54,1065.8,1106.58,1134.15,1149.75,1154.68]
y_coords = [195.34,272.27,356.59,438.98,510.14,560.76,581.52,563.13,496.27,404.39,318.83,242.15,176.92,125.69,91.02,75.48,81.62,113.49,168.57,239.59,319.29,400.38,475.6,537.67,579.32,586.78,558.32,504.7,436.69,365.05,300.55,253.95,236.03]
n_points = 100
x_coords = numpy.array(x_coords)
x_min = x_coords.min()
x_max = x_coords.max()
x_range = x_max - x_min
distances = []
tallied_distances = [0]
tallied_distance = 0
for i in range(0, len(x_coords) -1):
xi = x_coords[i]
xf = x_coords[i + 1]
yi= y_coords[i]
yf = y_coords[i+1]
d = math.sqrt((xf-xi)**2 + (yf-yi)**2)
tallied_distance += d
tallied_distances.append(tallied_distance)
random_distances_along_line = [0]
for i in range(0, n_points-2):
random_distances_along_line.append(random.random()*tallied_distance)
random_distances_along_line.sort()
new_x_points = [x_coords[0]]
new_y_points = [y_coords[0]]
for i in range(0, len(random_distances_along_line)):
dt = random_distances_along_line[i]
for j in range(0, len(tallied_distances)-1):
di = tallied_distances[j]
df = tallied_distances[j+1]
if di < dt and dt < df:
difference = dt - di
xi = x_coords[j]
xf = x_coords[j+1]
yi = y_coords[j]
yf = y_coords[j+1]
xt = xi+(xf-xi)*difference/(df-di)
yt = yi+(yf-yi)*difference/(df-di)
new_x_points.append(xt)
new_y_points.append(yt)
new_x_points.append(x_coords[len(x_coords)-1])
new_y_points.append(y_coords[len(y_coords)-1])
plt.plot(new_x_points, new_y_points)
plt.scatter(new_x_points, new_y_points,s=2)
ax = plt.gca()
ax.set_aspect('equal')
plt.show()

Problem with 2D mapping graphs using matplotlib

I am plotting 2D images of energy and density distribution. There is always a slight misalignment in the mapping where the very first "columns" seem to go to the last columns during the plot.
I have attach link to for data test file.
Data files
Here is the plot :
Is there anything to prevent this ?
The partial code in plotting is as follows:
import numpy as np
import matplotlib.pyplot as plt
import pylab as pyl
import scipy.stats as ss
import matplotlib.ticker as ticker
import matplotlib.transforms as tr
#%matplotlib inline
pi = 3.1415
n = 5e24 # density plasma
m = 9.109e-31
eps = 8.85e-12
e = 1.6021725e-19
c = 3e8
wp=np.sqrt(n*e*e/(m*eps))
kp = np.sqrt(n*e*e/(m*eps))/c #plasma wavenumber
case=400
## decide on the target range of analysis for multiples
start= 20500
end = 21500
gap = 1000
## Multiples plots
def target_range (start, end, gap):
while start<= end:
yield start
start += gap
for step in target_range(start, end, gap):
fdata =np.genfromtxt('./beam_{}'.format(step)).reshape(-1,6)
## dimension, dt, and superpaticle
xBoxsize = 50e-6 #window size
yBoxsize = 80e-6 #window size
xbind = 10
ybind = 1
dx = 4e-8 #cell size
dy = 4e-7 #cell size
dz = 1e-6 #assume to be same as dy
dt = 1.3209965456e-16
sptcl = 1.6e10
xsub = 0e-6
xmax = dt*step*c
xmin = xmax - xBoxsize
ysub = 1e-7
ymin = ysub #to make our view window
ymax = yBoxsize - ysub
xbins = int((xmax - xmin)/(dx*xbind))
ybins = int((ymax - ymin)/(dy*ybind))
#zbins = int((zmax - zmin)/dz) #option for 3D
# To make or define "data_arr" as a matrix with 2D array size 'xbins x ybins'
data_arr = np.zeros((2,xbins,ybins), dtype=np.float)
for line in fdata:
x = int((line[0]-xmin)/(dx*xbind))
y = int((line[1]-ymin)/(dy*ybind))
#z = int((line[2]-zmin)/dz)
if x >= xbins: x = xbins - 1
if y >= ybins: y = ybins - 1
#if z >= zbins: z = zbins - 1
data_arr[0, x, y] = data_arr[0,x, y] + 1 #cummulative adding up the number of particles
energy_total = np.sqrt(1+ line[2]*line[2]/(c*c)+line[3]*line[3]/(c*c))/0.511
data_arr[1, x, y] += energy_total
#array 1 tells us the energy while array 0 tells us the particles
## make average energy , total energy/particle number
np.errstate(divide='ignore',invalid='ignore')
en_arr = np.true_divide(data_arr[1],data_arr[0]) # total energy/number of particles
en_arr[en_arr == np.inf] = 0
en_arr = np.nan_to_num(en_arr)
en_arr = en_arr.T
## This part is real density of the distribution
data_arr[0]= data_arr[0] * sptcl/dx/dy #in m-3
d = data_arr[0].T
## Plot and save density and energy distribution figures
den_dist=plt.figure(1)
plt.imshow(d,origin='lower', aspect = 'auto',cmap =plt.get_cmap('gnuplot'),extent =(xmin/1e-3,xmax/1e-3,ymin/1e-6,ymax/1e-6))
plt.title('Density_dist [m-3]_{}'.format(step))
plt.xlabel('distance[mm]')
plt.ylabel('y [um]')
plt.colorbar()
plt.show()
den_dist.savefig("./Qen_distribution_{}.png".format(step),format ='png')
#note:cmap: rainbow, hot,jet,gnuplot,plasma
energy_dist=plt.figure(2)
plt.imshow(en_arr, origin ='lower',aspect = 'auto', cmap =plt.get_cmap('jet'),extent =(xmin/1e-3,xmax/1e-3,ymin/1e-6,ymax/1e-6))
plt.title ('Energy_dist [MeV]_{} '.format(step))
plt.xlabel('distance[mm]')
plt.ylabel('y [um]')
plt.colorbar()
plt.show()
energy_dist.savefig("./Qenergy_distribution_{}.png".format(step),format ='png')

Numpy: Generate grid according to density function

linspace generates a linear space. How can I generate a grid using an arbitrary density function?
Say, I would like to have a grid from 0 to 1, with 100 grid points, and where the density of points is given by (x - 0.5)**2 - how would I create such a grid in Python?
That is, I want many grid-points where the function (x - 0.5)**2) is large, and few points where the function is small. I do not want a grid that has values according to this function.

For example like this:
x = (np.linspace(0.5,1.5,100)-0.5)**2
The start and end values have to be chosen so that f(start) = 0 and f(end)=1.

In that case the following solution should work. Be sure that func is positive throughout the range...
import numpy as np
from matplotlib import pyplot as plt
def func(x):
return (x-0.5)**2
start = 0
end = 1
npoints = 100
x = np.linspace(start,end,npoints)
fx = func(x)
# take density (or intervals) as inverse of fx
# g in [0,1] controls how much warping you want.
# g = 0: fully warped
# g = 1: linearly spaced
g = 0
density = (1+g*(fx-1))/fx
# sum the intervals to get new grid
x_density = np.cumsum(density)
# rescale to match old range
x_density -= x_density.min()
x_density/= x_density.max()
x_density *= (end-start)
x_density += start
fx_density = func(x_density)
plt.plot(x,fx,'ok',ms = 10,label = 'linear')
plt.plot(x_density,fx_density,'or',ms = 10,label = 'warped')
plt.legend(loc = 'upper center')
plt.show()

Best way to interpolate a numpy.ndarray along an axis

I have 4-dimensional data, say for the temperature, in an numpy.ndarray.
The shape of the array is (ntime, nheight_in, nlat, nlon).
I have corresponding 1D arrays for each of the dimensions that tell me which time, height, latitude, and longitude a certain value corresponds to, for this example I need height_in giving the height in metres.
Now I need to bring it onto a different height dimension, height_out, with a different length.
The following seems to do what I want:
ntime, nheight_in, nlat, nlon = t_in.shape
nheight_out = len(height_out)
t_out = np.empty((ntime, nheight_out, nlat, nlon))
for time in range(ntime):
for lat in range(nlat):
for lon in range(nlon):
t_out[time, :, lat, lon] = np.interp(
height_out, height_in, t[time, :, lat, lon]
)
But with 3 nested loops, and lots of switching between python and numpy, I don't think this is the best way to do it.
Any suggestions on how to improve this? Thanks

scipy's interp1d can help:
import numpy as np
from scipy.interpolate import interp1d
ntime, nheight_in, nlat, nlon = (10, 20, 30, 40)
heights = np.linspace(0, 1, nheight_in)
t_in = np.random.normal(size=(ntime, nheight_in, nlat, nlon))
f_out = interp1d(heights, t_in, axis=1)
nheight_out = 50
new_heights = np.linspace(0, 1, nheight_out)
t_out = f_out(new_heights)

I was looking for a similar function that works with irregularly spaced coordinates, and ended up writing my own function. As far as I see, the interpolation is handled nicely and the performance in terms of memory and speed is also quite good. I thought I'd share it here in case anyone else comes across this question looking for a similar function:
import numpy as np
import warnings
def interp_along_axis(y, x, newx, axis, inverse=False, method='linear'):
""" Interpolate vertical profiles, e.g. of atmospheric variables
using vectorized numpy operations
This function assumes that the x-xoordinate increases monotonically
ps:
* Updated to work with irregularly spaced x-coordinate.
* Updated to work with irregularly spaced newx-coordinate
* Updated to easily inverse the direction of the x-coordinate
* Updated to fill with nans outside extrapolation range
* Updated to include a linear interpolation method as well
(it was initially written for a cubic function)
Peter Kalverla
March 2018
--------------------
More info:
Algorithm from: http://www.paulinternet.nl/?page=bicubic
It approximates y = f(x) = ax^3 + bx^2 + cx + d
where y may be an ndarray input vector
Returns f(newx)
The algorithm uses the derivative f'(x) = 3ax^2 + 2bx + c
and uses the fact that:
f(0) = d
f(1) = a + b + c + d
f'(0) = c
f'(1) = 3a + 2b + c
Rewriting this yields expressions for a, b, c, d:
a = 2f(0) - 2f(1) + f'(0) + f'(1)
b = -3f(0) + 3f(1) - 2f'(0) - f'(1)
c = f'(0)
d = f(0)
These can be evaluated at two neighbouring points in x and
as such constitute the piecewise cubic interpolator.
"""
# View of x and y with axis as first dimension
if inverse:
_x = np.moveaxis(x, axis, 0)[::-1, ...]
_y = np.moveaxis(y, axis, 0)[::-1, ...]
_newx = np.moveaxis(newx, axis, 0)[::-1, ...]
else:
_y = np.moveaxis(y, axis, 0)
_x = np.moveaxis(x, axis, 0)
_newx = np.moveaxis(newx, axis, 0)
# Sanity checks
if np.any(_newx[0] < _x[0]) or np.any(_newx[-1] > _x[-1]):
# raise ValueError('This function cannot extrapolate')
warnings.warn("Some values are outside the interpolation range. "
"These will be filled with NaN")
if np.any(np.diff(_x, axis=0) < 0):
raise ValueError('x should increase monotonically')
if np.any(np.diff(_newx, axis=0) < 0):
raise ValueError('newx should increase monotonically')
# Cubic interpolation needs the gradient of y in addition to its values
if method == 'cubic':
# For now, simply use a numpy function to get the derivatives
# This produces the largest memory overhead of the function and
# could alternatively be done in passing.
ydx = np.gradient(_y, axis=0, edge_order=2)
# This will later be concatenated with a dynamic '0th' index
ind = [i for i in np.indices(_y.shape[1:])]
# Allocate the output array
original_dims = _y.shape
newdims = list(original_dims)
newdims[0] = len(_newx)
newy = np.zeros(newdims)
# set initial bounds
i_lower = np.zeros(_x.shape[1:], dtype=int)
i_upper = np.ones(_x.shape[1:], dtype=int)
x_lower = _x[0, ...]
x_upper = _x[1, ...]
for i, xi in enumerate(_newx):
# Start at the 'bottom' of the array and work upwards
# This only works if x and newx increase monotonically
# Update bounds where necessary and possible
needs_update = (xi > x_upper) & (i_upper+1<len(_x))
# print x_upper.max(), np.any(needs_update)
while np.any(needs_update):
i_lower = np.where(needs_update, i_lower+1, i_lower)
i_upper = i_lower + 1
x_lower = _x[[i_lower]+ind]
x_upper = _x[[i_upper]+ind]
# Check again
needs_update = (xi > x_upper) & (i_upper+1<len(_x))
# Express the position of xi relative to its neighbours
xj = (xi-x_lower)/(x_upper - x_lower)
# Determine where there is a valid interpolation range
within_bounds = (_x[0, ...] < xi) & (xi < _x[-1, ...])
if method == 'linear':
f0, f1 = _y[[i_lower]+ind], _y[[i_upper]+ind]
a = f1 - f0
b = f0
newy[i, ...] = np.where(within_bounds, a*xj+b, np.nan)
elif method=='cubic':
f0, f1 = _y[[i_lower]+ind], _y[[i_upper]+ind]
df0, df1 = ydx[[i_lower]+ind], ydx[[i_upper]+ind]
a = 2*f0 - 2*f1 + df0 + df1
b = -3*f0 + 3*f1 - 2*df0 - df1
c = df0
d = f0
newy[i, ...] = np.where(within_bounds, a*xj**3 + b*xj**2 + c*xj + d, np.nan)
else:
raise ValueError("invalid interpolation method"
"(choose 'linear' or 'cubic')")
if inverse:
newy = newy[::-1, ...]
return np.moveaxis(newy, 0, axis)
And this is a small example to test it:
import numpy as np
import matplotlib.pyplot as plt
from scipy.interpolate import interp1d as scipy1d
# toy coordinates and data
nx, ny, nz = 25, 30, 10
x = np.arange(nx)
y = np.arange(ny)
z = np.tile(np.arange(nz), (nx,ny,1)) + np.random.randn(nx, ny, nz)*.1
testdata = np.random.randn(nx,ny,nz) # x,y,z
# Desired z-coordinates (must be between bounds of z)
znew = np.tile(np.linspace(2,nz-2,50), (nx,ny,1)) + np.random.randn(nx, ny, 50)*0.01
# Inverse the coordinates for testing
z = z[..., ::-1]
znew = znew[..., ::-1]
# Now use own routine
ynew = interp_along_axis(testdata, z, znew, axis=2, inverse=True)
# Check some random profiles
for i in range(5):
randx = np.random.randint(nx)
randy = np.random.randint(ny)
checkfunc = scipy1d(z[randx, randy], testdata[randx,randy], kind='cubic')
checkdata = checkfunc(znew)
fig, ax = plt.subplots()
ax.plot(testdata[randx, randy], z[randx, randy], 'x', label='original data')
ax.plot(checkdata[randx, randy], znew[randx, randy], label='scipy')
ax.plot(ynew[randx, randy], znew[randx, randy], '--', label='Peter')
ax.legend()
plt.show()

Following the criteria of numpy.interp, one can assign the left/right bounds to the points outside the range adding this lines after within_bounds = ...
out_lbound = (xi <= _x[0,...])
out_rbound = (_x[-1,...] <= xi)
and
newy[i, out_lbound] = _y[0, out_lbound]
newy[i, out_rbound] = _y[-1, out_rbound]
after newy[i, ...] = ....
If I understood well the strategy used by #Peter9192, I think the changes are in the same line. I've checked a little bit, but maybe some strange case could not work properly.

Inverse Wavelet Transform [/xpost signalprocessing]

Main Problem: How can the scipy.signal.cwt() function be inversed.
I have seen where Matlab has an inverse continuous wavelet transform function which will return the original form of the data by inputting the wavelet transform, although you can filter out the slices you don't want.
MATALAB inverse cwt funciton
Since scipy doesn't appear to have the same function, I have been trying to figure out how to get the data back in the same form, while removing the noise and background.
How do I do this?
I tried squaring it to remove negative values, but this gives me values way to large and not quite right.
Here is what I have been trying:
# Compute the wavelet transform
widths = range(1,11)
cwtmatr = signal.cwt(xy['y'], signal.ricker, widths)
# Maybe we multiple by the original data? and square?
WT_to_original_data = (xy['y'] * cwtmatr)**2
And here is a fully compilable short script to show you the type of data I am trying to get and what I have etc.:
import numpy as np
from scipy import signal
import matplotlib.pyplot as plt
# Make some random data with peaks and noise
def make_peaks(x):
bkg_peaks = np.array(np.zeros(len(x)))
desired_peaks = np.array(np.zeros(len(x)))
# Make peaks which contain the data desired
# (Mid range/frequency peaks)
for i in range(0,10):
center = x[-1] * np.random.random() - x[0]
amp = 60 * np.random.random() + 10
width = 10 * np.random.random() + 5
desired_peaks += amp * np.e**(-(x-center)**2/(2*width**2))
# Also make background peaks (not desired)
for i in range(0,3):
center = x[-1] * np.random.random() - x[0]
amp = 40 * np.random.random() + 10
width = 100 * np.random.random() + 100
bkg_peaks += amp * np.e**(-(x-center)**2/(2*width**2))
return bkg_peaks, desired_peaks
x = np.array(range(0, 1000))
bkg_peaks, desired_peaks = make_peaks(x)
y_noise = np.random.normal(loc=30, scale=10, size=len(x))
y = bkg_peaks + desired_peaks + y_noise
xy = np.array( zip(x,y), dtype=[('x',float), ('y',float)])
# Compute the wavelet transform
# I can't figure out what the width is or does?
widths = range(1,11)
# Ricker is 2nd derivative of Gaussian
# (*close* to what *most* of the features are in my data)
# (They're actually Lorentzians and Breit-Wigner-Fano lines)
cwtmatr = signal.cwt(xy['y'], signal.ricker, widths)
# Maybe we multiple by the original data? and square?
WT = (xy['y'] * cwtmatr)**2
# plot the data and results
fig = plt.figure()
ax_raw_data = fig.add_subplot(4,3,1)
ax = {}
for i in range(0, 11):
ax[i] = fig.add_subplot(4,3, i+2)
ax_desired_transformed_data = fig.add_subplot(4,3,12)
ax_raw_data.plot(xy['x'], xy['y'], 'g-')
for i in range(0,10):
ax[i].plot(xy['x'], WT[i])
ax_desired_transformed_data.plot(xy['x'], desired_peaks, 'k-')
fig.tight_layout()
plt.show()
This script will output this image:
Where the first plot is the raw data, the middle plots are the wavelet transforms and the last plot is what I want to get out as the processed (background and noise removed) data.
Does anyone have any suggestions? Thank you so much for the help.

I ended up finding a package which provides an inverse wavelet transform function called mlpy. The function is mlpy.wavelet.uwt. This is the compilable script I ended up with which may interest people if they are trying to do noise or background removal:
import numpy as np
from scipy import signal
import matplotlib.pyplot as plt
import mlpy.wavelet as wave
# Make some random data with peaks and noise
############################################################
def gen_data():
def make_peaks(x):
bkg_peaks = np.array(np.zeros(len(x)))
desired_peaks = np.array(np.zeros(len(x)))
# Make peaks which contain the data desired
# (Mid range/frequency peaks)
for i in range(0,10):
center = x[-1] * np.random.random() - x[0]
amp = 100 * np.random.random() + 10
width = 10 * np.random.random() + 5
desired_peaks += amp * np.e**(-(x-center)**2/(2*width**2))
# Also make background peaks (not desired)
for i in range(0,3):
center = x[-1] * np.random.random() - x[0]
amp = 80 * np.random.random() + 10
width = 100 * np.random.random() + 100
bkg_peaks += amp * np.e**(-(x-center)**2/(2*width**2))
return bkg_peaks, desired_peaks
# make x axis
x = np.array(range(0, 1000))
bkg_peaks, desired_peaks = make_peaks(x)
avg_noise_level = 30
std_dev_noise = 10
size = len(x)
scattering_noise_amp = 100
scat_center = 100
scat_width = 15
scat_std_dev_noise = 100
y_scattering_noise = np.random.normal(scattering_noise_amp, scat_std_dev_noise, size) * np.e**(-(x-scat_center)**2/(2*scat_width**2))
y_noise = np.random.normal(avg_noise_level, std_dev_noise, size) + y_scattering_noise
y = bkg_peaks + desired_peaks + y_noise
xy = np.array( zip(x,y), dtype=[('x',float), ('y',float)])
return xy
# Random data Generated
#############################################################
xy = gen_data()
# Make 2**n amount of data
new_y, bool_y = wave.pad(xy['y'])
orig_mask = np.where(bool_y==True)
# wavelet transform parameters
levels = 8
wf = 'h'
k = 2
# Remove Noise first
# Wave transform
wt = wave.uwt(new_y, wf, k, levels)
# Matrix of the difference between each wavelet level and the original data
diff_array = np.array([(wave.iuwt(wt[i:i+1], wf, k)-new_y) for i in range(len(wt))])
# Index of the level which is most similar to original data (to obtain smoothed data)
indx = np.argmin(np.sum(diff_array**2, axis=1))
# Use the wavelet levels around this region
noise_wt = wt[indx:indx+1]
# smoothed data in 2^n length
new_y = wave.iuwt(noise_wt, wf, k)
# Background Removal
error = 10000
errdiff = 100
i = -1
iter_y_dict = {0:np.copy(new_y)}
bkg_approx_dict = {0:np.array([])}
while abs(errdiff)>=1*10**-24:
i += 1
# Wave transform
wt = wave.uwt(iter_y_dict[i], wf, k, levels)
# Assume last slice is lowest frequency (background approximation)
bkg_wt = wt[-3:-1]
bkg_approx_dict[i] = wave.iuwt(bkg_wt, wf, k)
# Get the error
errdiff = error - sum(iter_y_dict[i] - bkg_approx_dict[i])**2
error = sum(iter_y_dict[i] - bkg_approx_dict[i])**2
# Make every peak higher than bkg_wt
diff = (new_y - bkg_approx_dict[i])
peak_idxs_to_remove = np.where(diff>0.)[0]
iter_y_dict[i+1] = np.copy(new_y)
iter_y_dict[i+1][peak_idxs_to_remove] = np.copy(bkg_approx_dict[i])[peak_idxs_to_remove]
# new data without noise and background
new_y = new_y[orig_mask]
bkg_approx = bkg_approx_dict[len(bkg_approx_dict.keys())-1][orig_mask]
new_data = diff[orig_mask]
##############################################################
# plot the data and results
fig = plt.figure()
ax_raw_data = fig.add_subplot(121)
ax_WT = fig.add_subplot(122)
ax_raw_data.plot(xy['x'], xy['y'], 'g')
for bkg in bkg_approx_dict.values():
ax_raw_data.plot(xy['x'], bkg[orig_mask], 'k')
ax_WT.plot(xy['x'], new_data, 'y')
fig.tight_layout()
plt.show()
And here is the output I am getting now:
As you can see, there is still a problem with the background removal (it shifts to the right after each iteration), but it is a different question which I will address here.