I'm trying to generalise some code to be able to fit multiple (n from 1 to >10) gaussian curves/peaks within a single dataset.
Using Scipy Optimise Curve_fit I can get pretty good fits when I hard code functions for 1-3 gaussians, and I've managed to produce functions which run without error for a generalise, arbitrary number of gaussians. However, the output fit is very poor. This is despite giving the input parameters which are identical to those used to generate the 'raw' data - i.e. a best case scenario.
Also, there is a non-zero chance the specific function may need to be modified from a simple gaussian at some point, but for now it should be OK.
Below is my code example, and the output figure is shown below.
import numpy as np
import pandas as pd
import scipy
import scipy.optimize
import matplotlib.pyplot as plt
from matplotlib import gridspec
amp1 = 1
cen1 = 1
sigma1 = 0.05
df=pd.DataFrame(index=np.linspace(0,10,num=1000),columns=['int'])
def _ngaussian(x, amps,cens,sigmas):
fn = 0
if len(amps)== len(cens)== len(sigmas):
for i in range(len(amps)):
fn = fn+amps[i]*(1/(sigmas[i]*(np.sqrt(2*np.pi))))*\
(np.exp((-1.0/2.0)*(((x-cens[i])/sigmas[i])**2)))
else:
print('Your inputs have unequal lengths')
return fn
amps = [1,1.1,0.9]
cens = [1,2,1.7]
sigmas=[0.05]*3
popt_peaks = [amps,cens,sigmas]
df['peaks'] = _ngaussian(df.index, *popt_peaks)
# Optionally adding noise to the raw data
#noise = np.random.normal(0,0.1,len(df['peaks']))
#df['peaks'] = df['peaks']+noise
def wrapper_fit_func(x, *args):
N = len(args)
a, b, c = list(args[0][:N]),list(args[0][N:N*2]),list(args[0][2*N:3*N])
return _ngaussian(x, a, b, c)
def unwrapper_fit_func(x, *args):
N = int(len(args)/3)
a, b, c = list(args[:N]),list(args[N:N*2]),list(args[2*N:3*N])
return _ngaussian(x, a, b, c)
popt_fitpeaks, pcov_fitpeaks = scipy.optimize.curve_fit(lambda x, *popt_peaks: wrapper_fit_func(x, popt_peaks),
df.index, df['peaks'], p0=popt_peaks,
method='lm')
df['peaks_fit'] = unwrapper_fit_func(df.index, *popt_fitpeaks)
fig = plt.figure(figsize=(8,8))
gs = gridspec.GridSpec(1,1)
ax1 = fig.add_subplot(gs[0])
ax1.set_xlim(0,3)
ax1.plot(df.index, df['peaks'], "b",label='ideal data')
ax1.plot(df.index, df['peaks_fit'], "g",label='fit data')
ax1.legend(loc='upper right')
If you're interested, the context is in analytical chemistry, nuclear magnetic resonance (NMR) and Fourier transform ion cyclotron resonance mass spectrometry (FTICR MS) signal processing.
You might find lmfit (https://lmfit.github.io/lmfit-py/, disclosure: I am a lead author) useful for this. It provides an easy-to-use Model class for modeling data, including builtin Models for Gaussian, Voigt, and similar lineshapes making it easy to compare model functions.
Lmfit models can be added (or mulitplied) to make a Composite Model, making it easy to support 1, 2, 3, etc Gaussians and include different baseline functions as well. There are docs and several examples at the link above. A small rewrite of your example (including adding a bit of noise) might look like this:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from lmfit.models import GaussianModel
amp1 = 1
cen1 = 1
sigma1 = 0.05
df=pd.DataFrame(index=np.linspace(0,10,num=1000),columns=['int'])
def _ngaussian(x, amps,cens,sigmas):
fn = 0
if len(amps)== len(cens)== len(sigmas):
for i in range(len(amps)):
fn = fn+amps[i]*(1/(sigmas[i]*(np.sqrt(2*np.pi))))*\
(np.exp((-1.0/2.0)*(((x-cens[i])/sigmas[i])**2)))
fn = fn+np.random.normal(size=len(x), scale=0.05)
else:
print('Your inputs have unequal lengths')
return fn
amps = [1.30, 0.92, 2.11]
cens = [1.10, 1.73, 2.06]
sigmas=[0.05, 0.09, 0.07]
popt_peaks = [amps,cens,sigmas]
df['peaks'] = _ngaussian(df.index, *popt_peaks)
# create a model with 3 Gaussians: pretty easy to generalize
# to a loop to make N peaks
model = (GaussianModel(prefix='p1_') +
GaussianModel(prefix='p2_') +
GaussianModel(prefix='p3_') )
# create Parameters (named from function arguments). For
# Gaussian, Lorentzian, Voigt, etc these are "center", "amplitude", "sigma"
params = model.make_params(p1_center=1.0, p1_amplitude=2, p1_sigma=0.1,
p2_center=1.5, p2_amplitude=2, p2_sigma=0.1,
p3_center=2.0, p3_amplitude=2, p3_sigma=0.1)
# Parameters can have min/max bounds, be fixed (`.vary = False`)
# or constrained to a mathematical expression of other Parameter values
params['p1_center'].min = 0.8
params['p1_center'].max = 1.5
params['p2_center'].min = 1.1
params['p2_center'].max = 1.9
params['p3_center'].min = 1.88
params['p3_center'].max = 3.00
# run the fit
result = model.fit(df['peaks'], params, x=df.index)
# print out the fit results
print(result.fit_report())
# plot results
plt.plot(df.index, df['peaks'], 'o', label='data')
plt.plot(df.index, result.best_fit, '-', label='fit')
plt.legend()
plt.gca().set_xlim(0, 3)
plt.show()
This will produce a fit plot like this:
and print out a report of
[[Model]]
((Model(gaussian, prefix='p1_') + Model(gaussian, prefix='p2_')) + Model(gaussian, prefix='p3_'))
[[Fit Statistics]]
# fitting method = leastsq
# function evals = 102
# data points = 1000
# variables = 9
chi-square = 6.88439024
reduced chi-square = 0.00694691
Akaike info crit = -4960.49871
Bayesian info crit = -4916.32892
[[Variables]]
p1_amplitude: 1.29432022 +/- 0.00428720 (0.33%) (init = 2)
p1_center: 1.09993745 +/- 1.9012e-04 (0.02%) (init = 1)
p1_sigma: 0.04970776 +/- 1.9012e-04 (0.38%) (init = 0.1)
p2_amplitude: 0.91875183 +/- 0.00604913 (0.66%) (init = 2)
p2_center: 1.73039597 +/- 6.7594e-04 (0.04%) (init = 1.5)
p2_sigma: 0.09054027 +/- 7.0994e-04 (0.78%) (init = 0.1)
p3_amplitude: 2.10077395 +/- 0.00533617 (0.25%) (init = 2)
p3_center: 2.06019332 +/- 2.0105e-04 (0.01%) (init = 2)
p3_sigma: 0.06970239 +/- 2.0752e-04 (0.30%) (init = 0.1)
p1_fwhm: 0.11705282 +/- 4.4770e-04 (0.38%) == '2.3548200*p1_sigma'
p1_height: 10.3878975 +/- 0.03440799 (0.33%) == '0.3989423*p1_amplitude/max(2.220446049250313e-16, p1_sigma)'
p2_fwhm: 0.21320604 +/- 0.00167179 (0.78%) == '2.3548200*p2_sigma'
p2_height: 4.04824243 +/- 0.02582408 (0.64%) == '0.3989423*p2_amplitude/max(2.220446049250313e-16, p2_sigma)'
p3_fwhm: 0.16413657 +/- 4.8866e-04 (0.30%) == '2.3548200*p3_sigma'
p3_height: 12.0238006 +/- 0.02922330 (0.24%) == '0.3989423*p3_amplitude/max(2.220446049250313e-16, p3_sigma)'
[[Correlations]] (unreported correlations are < 0.100)
C(p3_amplitude, p3_sigma) = 0.622
C(p2_amplitude, p2_sigma) = 0.621
C(p1_amplitude, p1_sigma) = 0.577
C(p2_sigma, p3_sigma) = -0.299
C(p2_sigma, p3_amplitude) = -0.271
C(p2_amplitude, p3_sigma) = -0.239
C(p2_sigma, p3_center) = 0.226
C(p2_amplitude, p3_amplitude) = -0.210
C(p2_center, p3_sigma) = -0.192
C(p2_amplitude, p3_center) = 0.171
C(p2_center, p3_amplitude) = -0.160
C(p2_center, p3_center) = 0.126
I have an array of lists of numbers, e.g.:
[0] (0.01, 0.01, 0.02, 0.04, 0.03)
[1] (0.00, 0.02, 0.02, 0.03, 0.02)
[2] (0.01, 0.02, 0.02, 0.03, 0.02)
...
[n] (0.01, 0.00, 0.01, 0.05, 0.03)
I would like to efficiently calculate the mean and standard deviation at each index of a list, across all array elements.
To do the mean, I have been looping through the array and summing the value at a given index of a list. At the end, I divide each value in my "averages list" by n (I am working with a population, not a sample from the population).
To do the standard deviation, I loop through again, now that I have the mean calculated.
I would like to avoid going through the array twice, once for the mean and then once for the standard deviation (after I have a mean).
Is there an efficient method for calculating both values, only going through the array once? Any code in an interpreted language (e.g., Perl or Python) or pseudocode is fine.
The answer is to use Welford's algorithm, which is very clearly defined after the "naive methods" in:
Wikipedia: Algorithms for calculating variance
It's more numerically stable than either the two-pass or online simple sum of squares collectors suggested in other responses. The stability only really matters when you have lots of values that are close to each other as they lead to what is known as "catastrophic cancellation" in the floating point literature.
You might also want to brush up on the difference between dividing by the number of samples (N) and N-1 in the variance calculation (squared deviation). Dividing by N-1 leads to an unbiased estimate of variance from the sample, whereas dividing by N on average underestimates variance (because it doesn't take into account the variance between the sample mean and the true mean).
I wrote two blog entries on the topic which go into more details, including how to delete previous values online:
Computing Sample Mean and Variance Online in One Pass
Deleting Values in Welford’s Algorithm for Online Mean and Variance
You can also take a look at my Java implement; the javadoc, source, and unit tests are all online:
Javadoc: stats.OnlineNormalEstimator
Source: stats.OnlineNormalEstimator.java
JUnit Source: test.unit.stats.OnlineNormalEstimatorTest.java
LingPipe Home Page
The basic answer is to accumulate the sum of both x (call it 'sum_x1') and x2 (call it 'sum_x2') as you go. The value of the standard deviation is then:
stdev = sqrt((sum_x2 / n) - (mean * mean))
where
mean = sum_x / n
This is the sample standard deviation; you get the population standard deviation using 'n' instead of 'n - 1' as the divisor.
You may need to worry about the numerical stability of taking the difference between two large numbers if you are dealing with large samples. Go to the external references in other answers (Wikipedia, etc) for more information.
Here is a literal pure Python translation of the Welford's algorithm implementation from John D. Cook’s excellent Accurately computing running variance article:
File running_stats.py
import math
class RunningStats:
def __init__(self):
self.n = 0
self.old_m = 0
self.new_m = 0
self.old_s = 0
self.new_s = 0
def clear(self):
self.n = 0
def push(self, x):
self.n += 1
if self.n == 1:
self.old_m = self.new_m = x
self.old_s = 0
else:
self.new_m = self.old_m + (x - self.old_m) / self.n
self.new_s = self.old_s + (x - self.old_m) * (x - self.new_m)
self.old_m = self.new_m
self.old_s = self.new_s
def mean(self):
return self.new_m if self.n else 0.0
def variance(self):
return self.new_s / (self.n - 1) if self.n > 1 else 0.0
def standard_deviation(self):
return math.sqrt(self.variance())
Usage:
rs = RunningStats()
rs.push(17.0)
rs.push(19.0)
rs.push(24.0)
mean = rs.mean()
variance = rs.variance()
stdev = rs.standard_deviation()
print(f'Mean: {mean}, Variance: {variance}, Std. Dev.: {stdev}')
Perhaps not what you were asking, but ... If you use a NumPy array, it will do the work for you, efficiently:
from numpy import array
nums = array(((0.01, 0.01, 0.02, 0.04, 0.03),
(0.00, 0.02, 0.02, 0.03, 0.02),
(0.01, 0.02, 0.02, 0.03, 0.02),
(0.01, 0.00, 0.01, 0.05, 0.03)))
print nums.std(axis=1)
# [ 0.0116619 0.00979796 0.00632456 0.01788854]
print nums.mean(axis=1)
# [ 0.022 0.018 0.02 0.02 ]
By the way, there's some interesting discussion in this blog post and comments on one-pass methods for computing means and variances:
Computing sample mean and variance online in one pass
The Python runstats Module is for just this sort of thing. Install runstats from PyPI:
pip install runstats
Runstats summaries can produce the mean, variance, standard deviation, skewness, and kurtosis in a single pass of data. We can use this to create your "running" version.
from runstats import Statistics
stats = [Statistics() for num in range(len(data[0]))]
for row in data:
for index, val in enumerate(row):
stats[index].push(val)
for index, stat in enumerate(stats):
print 'Index', index, 'mean:', stat.mean()
print 'Index', index, 'standard deviation:', stat.stddev()
Statistics summaries are based on the Knuth and Welford method for computing standard deviation in one pass as described in the Art of Computer Programming, Vol 2, p. 232, 3rd edition. The benefit of this is numerically stable and accurate results.
Disclaimer: I am the author the Python runstats module.
Statistics::Descriptive is a very decent Perl module for these types of calculations:
#!/usr/bin/perl
use strict; use warnings;
use Statistics::Descriptive qw( :all );
my $data = [
[ 0.01, 0.01, 0.02, 0.04, 0.03 ],
[ 0.00, 0.02, 0.02, 0.03, 0.02 ],
[ 0.01, 0.02, 0.02, 0.03, 0.02 ],
[ 0.01, 0.00, 0.01, 0.05, 0.03 ],
];
my $stat = Statistics::Descriptive::Full->new;
# You also have the option of using sparse data structures
for my $ref ( #$data ) {
$stat->add_data( #$ref );
printf "Running mean: %f\n", $stat->mean;
printf "Running stdev: %f\n", $stat->standard_deviation;
}
__END__
Output:
Running mean: 0.022000
Running stdev: 0.013038
Running mean: 0.020000
Running stdev: 0.011547
Running mean: 0.020000
Running stdev: 0.010000
Running mean: 0.020000
Running stdev: 0.012566
Have a look at PDL (pronounced "piddle!").
This is the Perl Data Language which is designed for high precision mathematics and scientific computing.
Here is an example using your figures....
use strict;
use warnings;
use PDL;
my $figs = pdl [
[0.01, 0.01, 0.02, 0.04, 0.03],
[0.00, 0.02, 0.02, 0.03, 0.02],
[0.01, 0.02, 0.02, 0.03, 0.02],
[0.01, 0.00, 0.01, 0.05, 0.03],
];
my ( $mean, $prms, $median, $min, $max, $adev, $rms ) = statsover( $figs );
say "Mean scores: ", $mean;
say "Std dev? (adev): ", $adev;
say "Std dev? (prms): ", $prms;
say "Std dev? (rms): ", $rms;
Which produces:
Mean scores: [0.022 0.018 0.02 0.02]
Std dev? (adev): [0.0104 0.0072 0.004 0.016]
Std dev? (prms): [0.013038405 0.010954451 0.0070710678 0.02]
Std dev? (rms): [0.011661904 0.009797959 0.0063245553 0.017888544]
Have a look at PDL::Primitive for more information on the statsover function. This seems to suggest that ADEV is the "standard deviation".
However, it maybe PRMS (which Sinan's Statistics::Descriptive example show) or RMS (which ars's NumPy example shows). I guess one of these three must be right ;-)
For more PDL information, have a look at:
pdl.perl.org (official PDL page).
PDL quick reference guide on PerlMonks
Dr. Dobb's article on PDL
PDL Wiki
Wikipedia entry for PDL
SourceForge project page for PDL
Unless your array is zillions of elements long, don't worry about looping through it twice. The code is simple and easily tested.
My preference would be to use the NumPy array maths extension to convert your array of arrays into a NumPy 2D array and get the standard deviation directly:
>>> x = [ [ 1, 2, 4, 3, 4, 5 ], [ 3, 4, 5, 6, 7, 8 ] ] * 10
>>> import numpy
>>> a = numpy.array(x)
>>> a.std(axis=0)
array([ 1. , 1. , 0.5, 1.5, 1.5, 1.5])
>>> a.mean(axis=0)
array([ 2. , 3. , 4.5, 4.5, 5.5, 6.5])
If that's not an option and you need a pure Python solution, keep reading...
If your array is
x = [
[ 1, 2, 4, 3, 4, 5 ],
[ 3, 4, 5, 6, 7, 8 ],
....
]
Then the standard deviation is:
d = len(x[0])
n = len(x)
sum_x = [ sum(v[i] for v in x) for i in range(d) ]
sum_x2 = [ sum(v[i]**2 for v in x) for i in range(d) ]
std_dev = [ sqrt((sx2 - sx**2)/N) for sx, sx2 in zip(sum_x, sum_x2) ]
If you are determined to loop through your array only once, the running sums can be combined.
sum_x = [ 0 ] * d
sum_x2 = [ 0 ] * d
for v in x:
for i, t in enumerate(v):
sum_x[i] += t
sum_x2[i] += t**2
This isn't nearly as elegant as the list comprehension solution above.
I like to express the update this way:
def running_update(x, N, mu, var):
'''
#arg x: the current data sample
#arg N : the number of previous samples
#arg mu: the mean of the previous samples
#arg var : the variance over the previous samples
#retval (N+1, mu', var') -- updated mean, variance and count
'''
N = N + 1
rho = 1.0/N
d = x - mu
mu += rho*d
var += rho*((1-rho)*d**2 - var)
return (N, mu, var)
so that a one-pass function would look like this:
def one_pass(data):
N = 0
mu = 0.0
var = 0.0
for x in data:
N = N + 1
rho = 1.0/N
d = x - mu
mu += rho*d
var += rho*((1-rho)*d**2 - var)
# could yield here if you want partial results
return (N, mu, var)
note that this is calculating the sample variance (1/N), not the unbiased estimate of the population variance (which uses a 1/(N-1) normalzation factor). Unlike the other answers, the variable, var, that is tracking the running variance does not grow in proportion to the number of samples. At all times it is just the variance of the set of samples seen so far (there is no final "dividing by n" in getting the variance).
In a class it would look like this:
class RunningMeanVar(object):
def __init__(self):
self.N = 0
self.mu = 0.0
self.var = 0.0
def push(self, x):
self.N = self.N + 1
rho = 1.0/N
d = x-self.mu
self.mu += rho*d
self.var += + rho*((1-rho)*d**2-self.var)
# reset, accessors etc. can be setup as you see fit
This also works for weighted samples:
def running_update(w, x, N, mu, var):
'''
#arg w: the weight of the current sample
#arg x: the current data sample
#arg mu: the mean of the previous N sample
#arg var : the variance over the previous N samples
#arg N : the number of previous samples
#retval (N+w, mu', var') -- updated mean, variance and count
'''
N = N + w
rho = w/N
d = x - mu
mu += rho*d
var += rho*((1-rho)*d**2 - var)
return (N, mu, var)
Here's a "one-liner", spread over multiple lines, in functional programming style:
def variance(data, opt=0):
return (lambda (m2, i, _): m2 / (opt + i - 1))(
reduce(
lambda (m2, i, avg), x:
(
m2 + (x - avg) ** 2 * i / (i + 1),
i + 1,
avg + (x - avg) / (i + 1)
),
data,
(0, 0, 0)))
As the following answer describes:
Does Pandas, SciPy, or NumPy provide a cumulative standard deviation function?
The Python Pandas module contains a method to calculate the running or cumulative standard deviation. For that, you'll have to convert your data into a Pandas dataframe (or a series if it is one-dimensional), but there are functions for that.
Here is a practical example of how you could implement a running standard deviation with Python and NumPy:
a = np.arange(1, 10)
s = 0
s2 = 0
for i in range(0, len(a)):
s += a[i]
s2 += a[i] ** 2
n = (i + 1)
m = s / n
std = np.sqrt((s2 / n) - (m * m))
print(std, np.std(a[:i + 1]))
This will print out the calculated standard deviation and a check standard deviation calculated with NumPy:
0.0 0.0
0.5 0.5
0.8164965809277263 0.816496580927726
1.118033988749895 1.118033988749895
1.4142135623730951 1.4142135623730951
1.707825127659933 1.707825127659933
2.0 2.0
2.29128784747792 2.29128784747792
2.5819888974716116 2.581988897471611
I am just using the formula described in this thread:
stdev = sqrt((sum_x2 / n) - (mean * mean))
Responding to Charlie Parker's 2021 question:
I'd like an answer that I can just copy paste to my code in numpy. My input is a matrix of size [N, 1] where N is the number of data points and I already have computed the running mean and I assuming we have computed the running std/variance, how to update we the new batch of data.
Here we have two implementations of a function that takes the original mean, original variance and original size and the new sample and returns the total mean and total variance of the combined original and new sample (to get the standard deviation, just take variance's square root by using **(1/2)). The first uses NumPy, and the second one uses Welford. You may choose the one that best applies to your case.
def mean_and_variance_update_numpy(previous_mean, previous_var, previous_size, sample_to_append):
if type(sample_to_append) is np.matrix:
sample_to_append = sample_to_append.A1
else:
sample_to_append = sample_to_append.flatten()
sample_to_append_mean = np.mean(sample_to_append)
sample_to_append_size = len(sample_to_append)
total_size = previous_size+sample_to_append_size
total_mean = (previous_mean*previous_size+sample_to_append_mean*sample_to_append_size)/total_size
total_var = (((previous_var+(total_mean-previous_mean)**2)*previous_size)+((np.var(sample_to_append)+(sample_to_append_mean-tm)**2)*sample_to_append_size))/total_size
return (total_mean, total_var)
def mean_and_variance_update_welford(previous_mean, previous_var, previous_size, sample_to_append):
if type(sample_to_append) is np.matrix:
sample_to_append = sample_to_append.A1
else:
sample_to_append = sample_to_append.flatten()
pos = previous_size
mean = previous_mean
v = previous_var*previous_size
for value in sample_to_append:
pos += 1
mean_next = mean + (value - mean) / pos
v = v + (value - mean)*(value - mean_next)
mean = mean_next
return (mean, v/pos)
Let's check if it works:
import numpy as np
def mean_and_variance_udpate_numpy:
...
def mean_and_variance_udpate_welford:
...
# Making the samples and results deterministic
np.random.seed(0)
# Our initial sample has 100 samples, we want to append 10
n0, n1 = 100, 10
# Using np.matrix only, because it was in the question. 'np.array' is more common
s0 = np.matrix(1e3+np.random.random_sample(n0)*1e-3).T
s1 = np.matrix(1e3+np.random.random_sample(n1)*1e-3).T
# Precalculating our mean and var for initial sample:
s0mean, s0var = np.mean(s0), np.var(s0)
# Calculating mean and variance for s0+s1 using our NumPy updater
mean_and_variance_update_numpy(s0mean, s0var, len(s0), s1)
# (1000.0004826329636, 8.24577589696613e-08)
# Calculating mean and variance for s0+s1 using our Welford updater
mean_and_variance_update_welford(s0mean, s0var, len(s0), s1)
# (1000.0004826329634, 8.245775896913623e-08)
# Similar results, now checking with NumPy's calculation over the concatenation of s0 and s1
s0s1 = np.concatenate([s0,s1])
(np.mean(s0s1), np.var(s0s1))
# (1000.0004826329638, 8.245775896917313e-08)
Here the three results are closer:
# np(s0s1) (1000.0004826329638, 8.245775896917313e-08)
# np(s0)updnp(s1) (1000.0004826329636, 8.245775896966130e-08)
# np(s0)updwf(s1) (1000.0004826329634, 8.245775896913623e-08)
It is possible to see that the results are very similar.
n=int(raw_input("Enter no. of terms:"))
L=[]
for i in range (1,n+1):
x=float(raw_input("Enter term:"))
L.append(x)
sum=0
for i in range(n):
sum=sum+L[i]
avg=sum/n
sumdev=0
for j in range(n):
sumdev=sumdev+(L[j]-avg)**2
dev=(sumdev/n)**0.5
print "Standard deviation is", dev
Figure I could jump on the old bandwagon. This should work with rbg values
Adapted from
https://math.stackexchange.com/a/2148949
import numpy as np
class IterativeNormStats():
def __init__(self):
"""uint64 max is 18446744073709551615
256**2 = 65536
so we can store 18446744073709551615 / 65536 = 281,474,976,710,656
images before running into overflow issues. I think we'll be ok
"""
self.n = 0
self.rgb_sum = np.zeros(3, dtype=np.uint64)
self.rgb_sq_sum = np.zeros(3, dtype=np.uint64)
def update(self, img_arr):
rgbs = np.reshape(img_arr, (-1, 3)).astype(np.uint64)
self.n += rgbs.shape[0]
self.rgb_sum += np.sum(rgbs, axis=0)
self.rgb_sq_sum += np.sum(np.square(rgbs), axis=0)
def mean(self):
return self.rgb_sum / self.n
def std(self):
return np.sqrt((self.rgb_sq_sum / self.n) - np.square(self.rgb_sum / self.n))
def test_IterativeNormStats():
img_a = np.ones((10, 10, 3), dtype=np.uint8) * (1, 2, 3)
img_b = np.ones((10, 10, 3), dtype=np.uint8) * (2, 4, 6)
img_c = np.ones((10, 10, 3), dtype=np.uint8) * (3, 6, 9)
ins = IterativeNormStats()
for i in range(1000):
for img in [img_a, img_b, img_c]:
ins.update(img)
x = np.vstack([
np.reshape(img_a, (-1, 3)),
np.reshape(img_b, (-1, 3)),
np.reshape(img_c, (-1, 3)),
]*1000)
expected_mean = np.mean(x, axis=0)
expected_std = np.std(x, axis=0)
print(expected_mean)
print(ins.mean())
print(expected_std)
print(ins.std())
assert np.allclose(ins.mean(), expected_mean)
if __name__ == "__main__":
test_IterativeNormStats()
I came across thee welford package that's pretty simple to use:
pip install welford
Then
import numpy as np
from welford import Welford
# Initialize Welford object
w = Welford()
# Input data samples sequentialy
w.add(np.array([0, 100]))
w.add(np.array([1, 110]))
w.add(np.array([2, 120]))
# output
print(w.mean) # mean --> [ 1. 110.]
print(w.var_s) # sample variance --> [1, 100]
print(w.var_p) # population variance --> [ 0.6666 66.66]
# You can add other samples after calculating variances.
w.add(np.array([3, 130]))
w.add(np.array([4, 140]))
# output with added samples
print(w.mean) # mean --> [ 2. 120.]
print(w.var_s) # sample variance --> [ 2.5 250. ]
print(w.var_p) # population variance --> [ 2. 200.]
Notes:
Unlike most othere answers you can feed a Welford object a Numpy array directly
You can even add multiple with Welford.add_all(...)
You can merge independent computations with w1.merge(w2)
You should choose var_p or var_s depending on which one you want to use (Population and Sample variance)
As said, those are variances so you should use np.sqrt to get the associated standard deviation
Here is a simple implementation in python:
class RunningStats:
def __init__(self):
self.mean_x_square = 0
self.mean_x = 0
self.n = 0
def update(self, x):
self.mean_x_square = (self.mean_x_square * self.n + x ** 2) / (self.n + 1)
self.mean_x = (self.mean_x * self.n + x) / (self.n + 1)
self.n += 1
def mean(self):
return self.mean_x
def std(self):
return self.variance() ** 0.5
def variance(self):
return self.mean_x_square - self.mean_x ** 2
Test:
import numpy as np
running_stats = RunningStats()
v = [1.1, 3.5, 5, -8.1, 91]
[running_stats.update(x) for x in v]
print(running_stats.mean() - np.mean(v))
print(running_stats.std() - np.std(v))
print(running_stats.variance() - np.var(v))