lattice/pyerrors
1
0
Fork 0
mirror of https://github.com/fjosw/pyerrors.git synced 2025-03-15 06:40:24 +01:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #104 from fjosw/feat/prefit

Browse source 
Prefit correlated fits
This commit is contained in:
Fabian Joswig 2022-05-26 09:58:37 +01:00 • committed by GitHub
commit e6aa679170
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 23 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
pyerrors/fits.py
View file

@ -482,15 +482,15 @@ def _standard_fit(x, y, func, silent=False, **kwargs):
chol_inv = np.linalg.inv(chol)
chol_inv = np.dot(chol_inv, covdiag)
def chisqfunc(p):
def chisqfunc_corr(p):
model = func(p, x)
chisq = anp.sum(anp.dot(chol_inv, (y_f - model)) ** 2)
return chisq
else:
def chisqfunc(p):
model = func(p, x)
chisq = anp.sum(((y_f - model) / dy_f) ** 2)
return chisq
def chisqfunc(p):
model = func(p, x)
chisq = anp.sum(((y_f - model) / dy_f) ** 2)
return chisq
output.method = kwargs.get('method', 'Levenberg-Marquardt')
if not silent:
@ -499,27 +499,32 @@ def _standard_fit(x, y, func, silent=False, **kwargs):
if output.method != 'Levenberg-Marquardt':
if output.method == 'migrad':
fit_result = iminuit.minimize(chisqfunc, x0, tol=1e-4) # Stopping criterion 0.002 * tol * errordef
if kwargs.get('correlated_fit') is True:
fit_result = iminuit.minimize(chisqfunc_corr, fit_result.x, tol=1e-4) # Stopping criterion 0.002 * tol * errordef
output.iterations = fit_result.nfev
else:
fit_result = scipy.optimize.minimize(chisqfunc, x0, method=kwargs.get('method'), tol=1e-12)
if kwargs.get('correlated_fit') is True:
fit_result = scipy.optimize.minimize(chisqfunc_corr, fit_result.x, method=kwargs.get('method'), tol=1e-12)
output.iterations = fit_result.nit
chisquare = fit_result.fun
else:
if kwargs.get('correlated_fit') is True:
def chisqfunc_residuals(p):
def chisqfunc_residuals_corr(p):
model = func(p, x)
chisq = anp.dot(chol_inv, (y_f - model))
return chisq
else:
def chisqfunc_residuals(p):
model = func(p, x)
chisq = ((y_f - model) / dy_f)
return chisq
def chisqfunc_residuals(p):
model = func(p, x)
chisq = ((y_f - model) / dy_f)
return chisq
fit_result = scipy.optimize.least_squares(chisqfunc_residuals, x0, method='lm', ftol=1e-15, gtol=1e-15, xtol=1e-15)
if kwargs.get('correlated_fit') is True:
fit_result = scipy.optimize.least_squares(chisqfunc_residuals_corr, fit_result.x, method='lm', ftol=1e-15, gtol=1e-15, xtol=1e-15)
chisquare = np.sum(fit_result.fun ** 2)

11
tests/fits_test.py
View file

@ -171,12 +171,13 @@ def test_fit_corr_independent():
y = a[0] * anp.exp(-a[1] * x)
return y
out = pe.least_squares(x, oy, func)
out_corr = pe.least_squares(x, oy, func, correlated_fit=True)
for method in ["Levenberg-Marquardt", "migrad", "Nelder-Mead"]:
out = pe.least_squares(x, oy, func, method=method)
out_corr = pe.least_squares(x, oy, func, correlated_fit=True, method=method)
assert np.isclose(out.chisquare, out_corr.chisquare)
assert (out[0] - out_corr[0]).is_zero(atol=1e-5)
assert (out[1] - out_corr[1]).is_zero(atol=1e-5)
assert np.isclose(out.chisquare, out_corr.chisquare)
assert (out[0] - out_corr[0]).is_zero(atol=1e-5)
assert (out[1] - out_corr[1]).is_zero(atol=1e-5)
def test_total_least_squares():