We Keep Coding

Can one create a distribution characterizing the multiplication of two distributions in Python?

I have two distributions and I would like to know the properties of the multiplication of these distributions.
For example, if I had the distribution of properties velocity and time, I want the characteristics of the probability distribution of distance.
With reasonable estimates for the inegration bounds, I can calculate the probability density function from the product of two random variables:
from scipy import stats
import numpy as np
import matplotlib.pyplot as plt
T, dt = np.linspace(0,20,201, retstep = True)
T = T[1:] # avoid divide by zero below
V = np.linspace(0,20,201)
D = np.linspace(0,120,201)
P_t = stats.gamma(4,1) # probability distribution for time
P_v = stats.norm(8,2) # probability distribution for speed
# complete integration
P_d = [np.trapz(P_t.pdf(T) * P_v.pdf(d / T) / T, dx = dt) for d in D]
plt.plot(T, P_t.pdf(T), label = 'time')
plt.plot(V, P_v.pdf(V), label = 'velocity')
plt.plot(D, P_d, label = 'distance')
plt.legend()
plt.ylabel('Probability density')
I would like to be able to compute things like P_d.sf(d), P_d.cdf(d), etc., for arbitrary values of d. Can I create a new distribution (perhaps using scipy.stats.rv_continuous) to characterize distance?

The solution took a bit of time to understand the rv_continuous. Cobbling together knowledge from a bunch of examples (I should have documented them--sorry) I think I got a working solution.
The only issue is that the domain needs to be known in advance, but I can work with that. If someone has ideas for how to fix that, please let me know.
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import scipy as sp
interp1d = sp.interpolate.interp1d
trapz = sp.integrate.trapz
# Time domain vector - needed in class
dt = 0.01
t_max = 10
T = np.arange(dt, t_max + dt, dt)
# Distance domain vector - needed in class
dd = 0.01
d_max = 30
D = np.arange(0, d_max + dd, dd)
class MultiplicativeModel(stats.rv_continuous):
def __init__(self, Tmodel, Vmodel, *args, **kwargs):
super().__init__(*args, **kwargs)
self.Tmodel = Tmodel # The time-domain probability function
self.Vmodel = Vmodel # The velocity-domain probability function
# Create vectors for interpolation of distributions
self.pdf_vec = np.array([trapz(self.Tmodel.pdf(T) * \
self.Vmodel.pdf(_ / T) / T, dx = dt) \
for _ in D])
self.cdf_vec = np.cumsum(self.pdf_vec) * dd
self.sf_vec = 1 - self.cdf_vec
# define key functions for rv_continuous class
self._pdf = interp1d(D, self.pdf_vec, assume_sorted=True)
self._sf = interp1d(D, self.sf_vec, assume_sorted=True)
self._cdf = interp1d(D, self.cdf_vec, assume_sorted=True)
# Extraolation option below is necessary because sometimes rvs picks
# a number really really close to 1 or 0 and this spits out an error if it
# is outside of the interpolation range.
self._ppf = interp1d(self.cdf_vec, D, assume_sorted=True,
fill_value = 'extrapolate')
# Moments
self._munp = lambda n, *args: np.trapz(self.pdf_vec * D ** n, dx=dd)
With the above defined, we get results like:
dv = 0.01
v_max = 10
V = np.arange(0, v_max + dv, dv)
model = MultiplicativeModel(stats.norm(3, 1),
stats.uniform(loc=2, scale = 2))
# test moments and stats functions
print(f'median: {model.median()}')
# median: 8.700970199181763
print(f'moments: {model.stats(moments = "mvsk")}')
#moments: (array(9.00872026), array(12.2315612), array(0.44131568), array(0.16819043))
plt.figure(figsize=(6,4))
plt.plot(T, model.Tmodel.pdf(T), label = 'Time PDF')
plt.plot(V, model.Vmodel.pdf(V), label = 'Velocity PDF')
plt.plot(D, model.pdf(D), label = 'Distance PDF')
plt.plot(D, model.cdf(D), label = 'Distance CDF')
plt.plot(D, model.sf(D), label = 'Distance SF')
x = model.rvs(size=10**5)
plt.hist(x, bins = 50, density = True, alpha = 0.5, label = 'Sampled distribution')
plt.legend()
plt.xlim([0,30])

Progressively filter/smooth a signal in python (to straight line on the left to no filtering on the right)

A picture is worth a thousand words (sorry for the shoddy work):
If the solution is preserving the value and the slope at both ends it is better.
If, in addition, the position and sharpness of the transition can be adjusted it is perfect.
But I have not found any solution yet...
Thank you very much for your help
Here is a piece of code to get started:
import matplotlib.pyplot as plt
from scipy.signal import savgol_filter
import numpy as np
def round_up_to_odd(f):
return np.int(np.ceil(f / 2.) * 2 + 1)
def generateRandomSignal(n=1000, seed=None):
"""
Parameters
----------
n : integer, optional
Number of points in the signal. The default is 1000.
Returns
-------
sig : numpy array
"""
np.random.seed(seed)
print("Seed was:", seed)
steps = np.random.choice(a=[-1, 0, 1], size=(n-1))
roughSig = np.concatenate([np.array([0]), steps]).cumsum(0)
sig = savgol_filter(roughSig, round_up_to_odd(n/20), 6)
return sig
n = 1000
t = np.linspace(0,10,n)
seed = np.random.randint(0,high=100000)
#seed = 45136
sig = generateRandomSignal(seed=seed)
###############################
# ????
# sigFilt = adaptiveFilter(sig)
###############################
# Plot
plt.figure()
plt.plot(t, sig, label="Signal")
# plt.plot(t, sigFilt, label="Signal filtered")
plt.legend()

Simple convolution does smoothing. However, as mentioned below, here we need strong smoothing first and no smoothing towards the end. I used the moving average approach with the dynamic size of the window. In the example below, the window size changes linearly.
def dynamic_smoothing(x, start_window_length=(len(x)//2), end_window_length=1):
d_sum = np.cumsum(a, dtype=float)
smoothed = list()
for i in range(len(x)):
# compute window length
a = i / len(x)
w = int(np.round(a * start_window_length + (1.0-a) * end_window_length))
# get the window
w0 = max(0, i - w) # the window must stay inside the array
w1 = min(len(x), i + w)
smoothed.append(sum(x[w0:w1])/(w1+w0))
return np.array(smoothed)

Multiple gaussian auto-fitting in Python

The problem is to fitter on all my wavelength peaks a Gaussian in order to make a medium adjustment as accurate as possible
My question is how to make the Gaussian adjustment on all my peaks automatically without having to manually specify the coordinates of the peaks
For that, I realized the Gaussian adjustment of the brightest peaks, but I would like to generalize it to the following peaks. Subsequently, the Gaussian adjustment will allow me to obtain a polynomial adjustment fine enough to stagger pixels in wavelength
import numpy as np
from astropy.io import fits
import matplotlib.pyplot as plt
from scipy import interpolate
from tqdm import tqdm
from scipy import ndimage
import peakutils
from scipy.optimize import curve_fit
def gauss(x, x0, amp, wid):
return amp * np.exp( -((x - x0)/wid)**2)
def multi_gauss(x, *params):
y = np.zeros_like(x)
for i in range(0, len(params), 3):
x0, amp, wid = params[i:i+3]
y = y + gauss(x, x0, amp, wid)
return y
neon = fits.getdata(data_directory + wave_filename + '.fits')
neon_sp = np.mean(neon, axis= 0)
n_pix = len(neon_sp)
peaks_index = peakutils.peak.indexes(neon_sp, thres=0.05, min_dist=2)
### peals around the brightest peak
bright_index = peaks_index[np.argmax(neon_sp[peaks_index])]
delta_pix = 20
ind_min = bright_index - delta_pix
ind_max = bright_index + delta_pix
peak_select = peaks_index[np.where((peaks_index > ind_min) & (peaks_index < ind_max))]
peak_select_sort = peak_select[np.argsort(-neon_sp[peak_select])]
if peak_select_sort[1] > peak_select_sort[0] :
ind_max = bright_index + 40
else :
ind_min = bright_index - 40
peak_select = peaks_index[np.where((peaks_index > ind_min) & (peaks_index < ind_max))]
peak_select_sort = peak_select[np.argsort(-neon_sp[peak_select])]
plt.figure(num=0)
plt.clf()
plt.plot(neon_sp)
plt.plot(peaks_index,neon_sp[peaks_index], 'r+')
plt.plot(peak_select,neon_sp[peak_select], 'ro')
### Gaussian fit
x = np.arange(n_pix)
xx = np.arange(0, n_pix, .1)
n_peak = 4
bright_index_fit = np.zeros(n_peak)
for i in range(n_peak):
p = peak_select_sort[i]
guess = [p, neon_sp[p], .5]
popt, pcov = curve_fit(gauss, x, neon_sp, p0=guess)
fit = gauss(xx, *popt)
bright_index_fit[i] = popt[0]
plt.plot(xx,fit, '--')
bright_wave = [703.2, 724.5, 693.0, 743.9]

Separating gaussian components of a curve using python

I am trying to deblend the emission lines of low resolution spectrum in order to get the gaussian components. This plot represents the kind of data I am using:
After searching a bit, the only option I found was the application of the gauest function from the kmpfit package (http://www.astro.rug.nl/software/kapteyn/kmpfittutorial.html#gauest). I have copied their example but I cannot make it work.
I wonder if anyone could please offer me any alternative to do this or how to correct my code:
import numpy as np
import matplotlib.pyplot as plt
from scipy import optimize
def CurveData():
x = np.array([3963.67285156, 3964.49560547, 3965.31835938, 3966.14111328, 3966.96362305,
3967.78637695, 3968.60913086, 3969.43188477, 3970.25463867, 3971.07714844,
3971.89990234, 3972.72265625, 3973.54541016, 3974.36791992, 3975.19067383])
y = np.array([1.75001533e-16, 2.15520995e-16, 2.85030769e-16, 4.10072843e-16, 7.17558032e-16,
1.27759917e-15, 1.57074192e-15, 1.40802933e-15, 1.45038722e-15, 1.55195653e-15,
1.09280316e-15, 4.96611341e-16, 2.68777266e-16, 1.87075114e-16, 1.64335999e-16])
return x, y
def FindMaxima(xval, yval):
xval = np.asarray(xval)
yval = np.asarray(yval)
sort_idx = np.argsort(xval)
yval = yval[sort_idx]
gradient = np.diff(yval)
maxima = np.diff((gradient > 0).view(np.int8))
ListIndeces = np.concatenate((([0],) if gradient[0] < 0 else ()) + (np.where(maxima == -1)[0] + 1,) + (([len(yval)-1],) if gradient[-1] > 0 else ()))
X_Maxima, Y_Maxima = [], []
for index in ListIndeces:
X_Maxima.append(xval[index])
Y_Maxima.append(yval[index])
return X_Maxima, Y_Maxima
def GaussianMixture_Model(p, x, ZeroLevel):
y = 0.0
N_Comps = int(len(p) / 3)
for i in range(N_Comps):
A, mu, sigma = p[i*3:(i+1)*3]
y += A * np.exp(-(x-mu)*(x-mu)/(2.0*sigma*sigma))
Output = y + ZeroLevel
return Output
def Residuals_GaussianMixture(p, x, y, ZeroLevel):
return GaussianMixture_Model(p, x, ZeroLevel) - y
Wave, Flux = CurveData()
Wave_Maxima, Flux_Maxima = FindMaxima(Wave, Flux)
EmLines_Number = len(Wave_Maxima)
ContinuumLevel = 1.64191e-16
# Define initial values
p_0 = []
for i in range(EmLines_Number):
p_0.append(Flux_Maxima[i])
p_0.append(Wave_Maxima[i])
p_0.append(2.0)
p1, conv = optimize.leastsq(Residuals_GaussianMixture, p_0[:],args=(Wave, Flux, ContinuumLevel))
Fig = plt.figure(figsize = (16, 10))
Axis1 = Fig.add_subplot(111)
Axis1.plot(Wave, Flux, label='Emission line')
Axis1.plot(Wave, GaussianMixture_Model(p1, Wave, ContinuumLevel), 'r', label='Fit with optimize.leastsq')
print p1
Axis1.plot(Wave, GaussianMixture_Model([p1[0],p1[1],p1[2]], Wave, ContinuumLevel), 'g:', label='Gaussian components')
Axis1.plot(Wave, GaussianMixture_Model([p1[3],p1[4],p1[5]], Wave, ContinuumLevel), 'g:')
Axis1.set_xlabel( r'Wavelength $(\AA)$',)
Axis1.set_ylabel('Flux' + r'$(erg\,cm^{-2} s^{-1} \AA^{-1})$')
plt.legend()
plt.show()

A typical simplistic way to fit:
def model(p,x):
A,x1,sig1,B,x2,sig2 = p
return A*np.exp(-(x-x1)**2/sig1**2) + B*np.exp(-(x-x2)**2/sig2**2)
def res(p,x,y):
return model(p,x) - y
from scipy import optimize
p0 = [1e-15,3968,2,1e-15,3972,2]
p1,conv = optimize.leastsq(res,p0[:],args=(x,y))
plot(x,y,'+') # data
#fitted function
plot(arange(3962,3976,0.1),model(p1,arange(3962,3976,0.1)),'-')
Where p0 is your initial guess. By the looks of things, you might want to use Lorentzian functions...
If you use full_output=True, you get all kind of info about the fitting. Also check out curve_fit and the fmin* functions in scipy.optimize. There are plenty of wrappers around these around, but often, like here, it's easier to use them directly.

Python: fit data with gaussian rising and exponential decay

I am trying to fit some data that are distributed in the time following a rising gaussian curve, and then decaying exponentially.
I have found this example on the web, that is very similar to my case, but I just started to fit with python, and the example seems quite confusing to me.
Nonetheless, I have tryied to adapt the example to my script and data, and in the following is my progress:
#!/usr/bin/env python
import pyfits, os, re, glob, sys
from scipy.optimize import leastsq
from numpy import *
from pylab import *
from scipy import *
from scipy import optimize
import numpy as N
import pylab as P
data=pyfits.open('http://heasarc.gsfc.nasa.gov/docs/swift/results/transients/weak/GX304-1.orbit.lc.fits')
time = data[1].data.field(0)/86400. + data[1].header['MJDREFF'] + data[1].header['MJDREFI']
rate = data[1].data.field(1)
error = data[1].data.field(2)
data.close()
cond = ((time > 56200) & (time < 56220))
time=time[cond]
rate=rate[cond]
error=error[cond]
def expGauss(x, pos, wid, tConst, expMod = 0.5, amp = 1):
expMod *= 1.0
gNorm = amp * N.exp(-0.5*((x-pos)/(wid))**2)
g = expBroaden(gNorm, tConst, expMod)
return g, gNorm
def expBroaden(y, t, expMod):
fy = F.fft(y)
a = N.exp(-1*expMod*time/t)
fa = F.fft(a)
fy1 = fy*fa
yb = (F.ifft(fy1).real)/N.sum(a)
return yb
if __name__ == '__main__':
# Fit the first set
#p[0] -- amplitude, p[1] -- position, p[2] -- width
fitfuncG = lambda p, x: p[0]*N.exp(-0.5*(x-p[1])**2/p[2]**2) # Target function
errfuncG = lambda p, x, y: fitfuncG(p, x) - y # Distance to the target function
p0 = [0.20, 56210, 2.0] # Initial guess for the parameters
p1, success = optimize.leastsq(errfuncG, p0[:], args=(time, rate))
p1G = fitfuncG(p1, time)
# P.plot(rate, 'ro', alpha = 0.4, label = "Gaussian")
# P.plot(p1G, label = 'G-Fit')
def expGauss(x, pos, wid, tConst, expMod = 0.5, amp = 1):
#p[0] -- amplitude, p[1] -- position, p[2] -- width, p[3]--tConst, p[4] -- expMod
fitfuncExpG = lambda p, x: expGauss(x, p[1], p[2], p[3], p[4], p[0])[0]
errfuncExpG = lambda p, x, y: fitfuncExpG(p, x) - y # Distance to the target function
p0a = [0.20, 56210, 2.0] # Initial guess for the parameters
p1a, success = optimize.leastsq(errfuncExpG, p0a[:], args=(time, rate))
p1aG = fitfuncExpG(p1a, time)
print type(rate), type(time), len(rate), len(time)
P.plot(rate, 'go', alpha = 0.4, label = "ExpGaussian")
P.plot(p1aG, label = 'ExpG-Fit')
P.legend()
P.show()
I am sure to have confused the whole thing, so sorry in advance for that, but at this point I don't know how to go further...
The code take the data from the web, so it is directly executable.
At the moment the code runs without any error, but it doesn't produce any plot.
Again, my goal is to fit the data with those two functions, how can I improve my code to do that?
Any suggestion is really appreciated.

Similarly to your other question, here also I would use a trigonometric function to fit this peaK:
The following code works if pasted after your code:
import numpy as np
from scipy.optimize import curve_fit
x = time
den = x.max() - x.min()
x -= x.min()
y_points = rate
def func(x, a1, a2, a3):
return a1*sin(1*pi*x/den)+\
a2*sin(2*pi*x/den)+\
a3*sin(3*pi*x/den)
popt, pcov = curve_fit(func, x, y_points)
y = func(x, *popt)
plot(time,rate)
plot(x,y, color='r', linewidth=2.)
show()