def fit_gauss(x, y):
"""
fitting a normal distribution on a given data
Input: x --- a list of the bin
y --- a list of the count
Output: amp --- amp of the a normal distribution
cent--- center of the normal distribution
width--- width of the normal distribution
"""
nx = numpy.array(x)
ny = numpy.array(y)
ne = numpy.ones(len(ny))
#
#--- we need to give an initial guess
#
ymax = numpy.max(ny)
cest = find_center(x, y)
p0 = [ymax, cest, 10, 0]
fitobj = kmpfit.Fitter(residuals=residualsG, data=(nx,ny,ne))
fitobj.fit(params0=p0)
[amp, cent, width, floor] = fitobj.params
return [cent, width, amp]
def setUp(self):
# Pearson's data retrieved from http://www.astro.rug.nl/software/kapteyn/kmpfittutorial.html#fitting-data-when-both-variables-have-uncertainties
x = np.array([0.0, 0.9, 1.8, 2.6, 3.3, 4.4, 5.2, 6.1, 6.5, 7.4])
y = np.array([5.9, 5.4, 4.4, 4.6, 3.5, 3.7, 2.8, 2.8, 2.4, 1.5])
wy = np.array([1, 1.8, 4, 8, 20, 20, 70, 70, 100, 500])
erry = 1 / np.sqrt(wy)
N = len(x)
# weights in x are ignored in linearfit
# wx = np.array([1000.0,1000,500,800,200,80,60,20,1.8,1.0])
# errx = 1/np.sqrt(wx)
# dependent variables
M = np.mat(y)
# diagonal covariance matrix of dependent variables
S = np.mat(np.diag(wy))
# matrix of independent variables, here only ones
C = np.mat(np.vstack((np.ones(len(x)), x)))
# initialise object
res = linearfit.LinearFit(M, S, C)
# do the fit
res.fit()
print("\n\n======== Results linearfit =========")
res.display_results(precision=10)
res.display_correlations()
self.result = res
# optional comparison with kapteyn (nonlinear fitting) package
if 0:
from kapteyn import kmpfit
def model(p, x):
a, b = p
return a + b * x
def residuals2(p, data):
# Residuals function for data with errors in y only
a, b = p
x, y, ey = data
wi = np.where(ey == 0.0, 0.0, 1.0 / ey)
d = wi * (y - model(p, x))
return d
# Prepare fit routine
beta0 = [5.0, 1.0] # Initial estimates
# Prepare fit routine
fitobj2 = kmpfit.Fitter(residuals=residuals2, data=(x, y, erry))
fitobj2.fit(params0=beta0)
print("\n\n======== Results kmpfit =========")
print("Fitted parameters: ", fitobj2.params)
print("Covariance errors: ", fitobj2.xerror)
print("Standard errors ", fitobj2.stderr)
print("Reduced Chi^2: ", fitobj2.rchi2_min)
def fit_pmodel(hist, ymax, xpos, hwidth):
"""
for a given histgram data, fit a gaussian distribution
input: hist --- hist data
ymax --- initial guess height of the profile
xpos --- initial guess center postion
hwidth --- initial guess sigma
Output: amp --- estimated height of the profile
cent --- estimated center postion
width --- estimated sigma
floor --- estimated floor level
"""
start = int(xpos) - hwidth
stop = int(xpos) + hwidth
ybin = hist[start:stop]
xbin = [x for x in range(start, stop)]
err = numpy.ones(2 * hwidth)
p0 = [ymax, xpos, 10, 0]
fitobj = kmpfit.Fitter(residuals=residualsG, data=(xbin, ybin, err))
fitobj.fit(params0=p0)
[amp, cent, width, floor] = fitobj.params
return [amp, cent, width, floor]
def fit_poly(x, y, nterms):
"""
estimate polynomial fitting coefficients
Input: x --- independent variable (array)
y --- dependent variable (array)
nterms --- degree of polynomial fit
Output: fitobj.params --- array of polynomial fit coefficient
Note: for the detail on kmpfit, read:
http://www.astro.rug.nl/software/kapteyn/kmpfittutorial.html#a-basic-example
"""
#
#--- make sure that the arrays are numpyed
#
d = numpy.array(x)
v = numpy.array(y)
#
#--- set the initial estimate of the coefficients, all "0" is fine
#
paraminitial = [0.0 for i in range(0, nterms)]
#
#--- call kmfit
#
fitobj = kmpfit.Fitter(residuals=residuals, data=(d, v))
try:
fitobj.fit(params0=paraminitial)
except:
print "Something wrong with kmpfit fit"
raise SystemExit
return fitobj.params
def getHistory(sDay,nAhead,x0,hWeek):
nLin = sDay.shape[0] + nAhead
nFit = sDay.shape[0] if int(x0['obs_time']) <= 14 else int(x0['obs_time'])
sDay['hist'] = sp.interpolate.interp1d(hWeek.t,hWeek.y,kind="cubic")(sDay['t'])
histNorm = sDay['hist'].mean()
sDay['hist'] = ( (sDay['hist']-sDay['hist'].min())/(sDay['hist'].max()-sDay['hist'].min()) + .5)*x0['hist_adj']
fitD = np.array([sDay.t.tail(nFit),sDay.y.tail(nFit)])
fitobj = kmpfit.Fitter(residuals=ser_residuals,data=fitD)
fitobj.fit(params0=x0['poly'])
x0['poly'] = fitobj.params
sDay['stat'] = (sDay['y']-ser_poly(x0['poly'],sDay.t))
sDay['stat'].ix[0:(sDay.shape[0]-nFit)] = sDay['stat'][sDay.shape[0]-nFit]
t_test = np.linspace(sDay['t'][0],sDay['t'][sDay.shape[0]-1]+sDay.t[nAhead]-sDay.t[0],nLin)
predS = pd.DataFrame({'t':t_test},index=[sDay.index[0]+datetime.timedelta(days=x) for x in range(nLin)])
predS['y'] = sDay.y
predS['hist'] = sp.interpolate.interp1d(hWeek.t,hWeek.y,kind="cubic")(predS['t'])
predS['hist'] = ( (predS['hist']-predS['hist'].min())/(predS['hist'].max()-predS['hist'].min())*x0['hist_adj'] + .5)
predS['trend'] = ser_poly(x0['poly'],predS['t'])
predS['trend'].ix[0:(sDay.shape[0]-nFit)] = predS['trend'][sDay.shape[0]-nFit]
predS['pred'] = 0
predS['lsq'] = 0
# plt.plot(sDay.t,sDay.y,'-',label='series')
# plt.plot(sDay.t,sDay['hist'],'-',label='hist')
# plt.plot(hWeek.t,hWeek.y,label='week')
# plt.plot(sDay.t,sDay['stat'],'-',label='stat')
# plt.plot(predS.t,predS['trend'],'-',label='fit')
# plt.legend()
# plt.show()
return predS, x0
def FocusRunResults():
data = np.loadtxt(directory_prefix + 'bahtinov_results/Focusrun/' +
today_utc_date + '/Results/FocusResults.txt')
image = data[:, 0]
defocus = data[:, 1]
focus = data[:, 2]
focuserr = data[:, 3]
xp = np.linspace(min(defocus), max(defocus), 100)
z = np.polyfit(defocus, focus, 1)
fitobj = kmpfit.Fitter(residuals=functions.linfitresiduals,
data=(defocus, focus, focuserr),
xtol=1e-12,
gtol=1e-12)
fitobj.fit(params0=z)
print "\n=================== Results linear fit best defocus M2 ==================="
print "Fitted parameters: ", fitobj.params
print "Covariance errors: ", fitobj.xerror
print "Standard errors: ", fitobj.stderr
print "Chi^2 min: ", round(fitobj.chi2_min, 2)
print "Reduced Chi^2: ", round(fitobj.rchi2_min, 2)
print "Iterations: ", fitobj.niter
print "Number of free pars.: ", fitobj.nfree
print "Degrees of freedom ", fitobj.dof
print "Status Message: ", fitobj.message
dfdp = [1, xp]
confprob = 95.0
ydummy, upperband, lowerband = functions.confidence_band(
xp, dfdp, confprob, fitobj, functions.linfit)
verts = zip(xp, lowerband) + zip(xp[::-1], upperband[::-1])
bestfocus = -fitobj.params[0] / fitobj.params[1]
bestfocusvar = bestfocus**2 * (
(fitobj.stderr[0] / fitobj.params[0])**2 +
(fitobj.stderr[1] / fitobj.params[1])**2 - 2 *
(fitobj.covar[0, 1] / (fitobj.params[0] * fitobj.params[1])))
fig, axis = plt.subplots()
axis.xaxis.set_minor_locator(AutoMinorLocator())
axis.yaxis.set_minor_locator(AutoMinorLocator())
axis.errorbar(defocus, focus, yerr=focuserr, fmt='ko')
axis.annotate('Best offset M2 = %.2f $\pm$ %.3f $\\mu m$' %
(bestfocus, bestfocusvar**.5),
xy=(0, 1),
xycoords='axes fraction',
fontsize=12,
horizontalalignment='left',
verticalalignment='top')
axis.plot(xp,
functions.linfit(fitobj.params, xp),
color='r',
ls='--',
lw=2)
axis.set_title('Focus run M2 vs calculated axial defocus', fontsize=14)
axis.set_xlabel('Piston M2 [$\mu m$]')
axis.set_ylabel('Calculated axial defocus [$\mu m$]')
axis.set_xlim(-5, 205)
axis.grid(True)
#axis.legend(loc=4,fancybox=True, shadow=True, ncol=4, borderpad=1.01)
fig.tight_layout()
fig.savefig(directory_prefix + 'bahtinov_results/Focusrun/' +
today_utc_date + '/Results/Focusrun_defocus.png')
def fit_model(x, y, err, p0, detail='no'):
"""
fitting a model to a given data
Input: data --- input data list of lists [xdata, ydata, error]
p0 --- initial guess of the parameters in a list
detail --- if you want to print out a detail fitting profile, set "yes'. Default: 'no'
Output: fitting parameter [noarmalization, center, sigma, zero level]
"""
#
#--- convert the data to numpy array
#
d = numpy.array(x)
v = numpy.array(y)
err = numpy.array(err)
#
#--- fitting routine starts
#
fitobj = kmpfit.Fitter(residuals=my_residuals,
deriv=my_derivs,
data=(d, v, err))
try:
fitobj.fit(params0=p0)
except Exception, mes:
print "Something wrong with fit:", mes
raise SystemExit
def gamma_fit(x, y, a0, b0, m0):
"""
fitting gammaf profile to the data
Input: x --- independent var
y --- dependent var
Output: [a, b]
"""
N = len(y)
x = numpy.array(x)
y = numpy.array(y)
err = numpy.ones(N)
#
#--- initial guess
#
p0 = [a0, b0, m0]
#
#--- fit the model
#
try:
fitter = kmpfit.Fitter(residuals=residualsG, data=(x, y, err))
#fitter.parinfo = [{}, {}, {'fixed':True}] # Take zero level fixed in fit
fitter.fit(params0=p0)
a, b, h = fitter.params
except:
a, b, h = p0
return [a, b, h]
def voigt_fit(x, y):
"""
fitting voigt profile to the data
Input: x --- independent var
y --- dependent var
Output: [nu_0, hwhm, amp, alphaD, alphaL, nu_0, I, a_back, b_back]
nu_0 --- central postion
hwhm --- HWHM
amp --- amp
alphaD --- doppler alpha
alphaL --- lorntz alpha
I --- area under profile
a_back --- base line intercept
b_back --- base line slope
"""
N = len(y)
x = numpy.array(x)
y = numpy.array(y)
err = numpy.ones(N)
#
#--- initial guess
#
A = max(y)
alphaD = 0.5
alphaL = 0.5
a = 0
b = 0
nu_0 = find_center(x, y)
p0 = [alphaD, alphaL, nu_0, A, a, b]
#
#--- fit the model
#
fitter = kmpfit.Fitter(residuals=residualsV, data=(x, y, err))
fitter.parinfo = [{}, {}, {}, {}, {}, {
'fixed': True
}] # Take zero level fixed in fit
fitter.fit(params0=p0)
alphaD, alphaL, nu_0, I, a_back, b_back = fitter.params
#
#--- compute width: HWHM
#
c1 = 1.0692
c2 = 0.86639
hwhm = 0.5 * (c1 * alphaL + numpy.sqrt(c2 * alphaL**2 + 4 * alphaD**2))
hwhm = 2.0 * hwhm
#
#--- compute amp
#
f = numpy.sqrt(ln2)
Y = alphaL / alphaD * f
amp = I / alphaD * numpy.sqrt(ln2 / numpy.pi) * voigt(0, Y)
return [nu_0, hwhm, amp, alphaD, alphaL, I, a_back, b_back]
def fit_line(paramsinit, x, y, err, type):
"""
kmpfit calling function to fit the lines on data
input: paramsinit --- initial guess for the parameters
x --- a list of x data
y --- a list of y data
err --- a list of y error
type --- linear or exp:
output: two parameters (a, b) are returned
"""
sx = []
sy = []
se = []
avg = mean(y)
stdp = std(y)
bot = avg - 3.0 * stdp
top = avg + 3.0 * stdp
i = 0
for val in y:
if (val >= bot) and (val <= top):
sx.append(x[i])
sy.append(y[i])
se.append(err[i])
i += 1
#
#--- make sure that the arrays are numpyed
#
d = numpy.array(sx)
v = numpy.array(sy)
e = numpy.array(se)
if type == 'linear':
#
#--- linear fit
#
fitobj = kmpfit.Fitter(residuals=linear_res, data=(d, v, e))
fitobj.fit(params0 = paramsinit)
else:
#
#--- exp fit
#
fitobj = kmpfit.Fitter(residuals=exp_res, data=(d, v, e))
fitobj.fit(params0 = paramsinit)
return fitobj.params
def fit_polinom_to_center(fdata, start, stop, action, grating, catg):
"""
fitting a 5th degree polinomial to the data and find differences
input: fdata --- a list of arrays of time and data
start --- starting time in seconds from 1998.1.1
stop --- stopping time in seconds from 1998.1.1
action --- movement
grating --- grating
cag --- catogry (roll/pitch/yaw)
output: estimates --- a list of model fitted data
diff_data --- a list of difference between themodel and the data
f_time --- a list of time for the selected data period
sec1,sec2,sec3 --- list of [avg, std] of three sections
"""
#
#--- set fitting range
#
tdiff = stop - start
dstart = -1.5 * tdiff
dstop = 1.5 * tdiff
#
#--- limit data to the fitting range
#
t_array = fdata[0]
v_array = fdata[1]
index = [(t_array > dstart) & (t_array < dstop)]
f_time = t_array[index]
f_data = v_array[index]
#
#--- fit the data
#
paraminitial = [0.0 for i in range(0, 5)]
fitobj = kmpfit.Fitter(residuals=residuals, data=(f_time, f_data))
try:
fitobj.fit(params0=paraminitial)
except:
print "Something wrong with kmpfit fit"
return False
#
#--- create lists of data of estimated fitting and deviations
#
[estimates, diff_data] = compute_difference(f_time, f_data, fitobj)
#
#--- find avg and std of three sections
#
[sec1, sec2, sec3] = compute_avg_of_three_sections(f_time, diff_data,
start, stop)
#
#--- write out the polinomial fitting result
#
write_poli_fitting_result(fitobj, start, stop, action, grating, catg)
return [estimates, diff_data, f_time, sec1, sec2, sec3]
def fit_model(x, y, err, p0, detail='no'):
"""
fitting a model to a given data
Input: data --- input data list of lists [xdata, ydata, error]
p0 --- initial guess of the parameters in a list
detail --- if you want to print out a detail fitting profile, set "yes'. Default: 'no'
Output: fitting parameter [noarmalization, center, sigma, zero level]
"""
#
#--- convert the data to numpy array
#
d = numpy.array(x)
v = numpy.array(y)
err = numpy.array(err)
#
#--- fitting routine starts
#
fitobj = kmpfit.Fitter(residuals=my_residuals,
deriv=my_derivs,
data=(d, v, err))
try:
fitobj.fit(params0=p0)
except Exception as mes:
print("Something wrong with fit:", mes)
raise SystemExit
#
#--- if detail fitting profile is asked, print it out
#
if detail == 'yes':
line = "\n\n======== Results kmpfit with explicit partial derivatives =========" + "\n"
line = line + "Params: " + str(fitobj.params) + "\n"
line = line + "Errors from covariance matrix : " + str(
fitobj.xerror) + "\n"
line = line + "Uncertainties assuming reduced Chi^2=1: " + str(
fitobj.stderr) + "\n"
line = line + "Chi^2 min: " + str(fitobj.chi2_min) + "\n"
line = line + "Reduced Chi^2: " + str(fitobj.rchi2_min) + "\n"
line = line + "Iterations: " + str(fitobj.niter) + "\n"
line = line + "Function ev: " + str(fitobj.nfev) + "\n"
line = line + "Status: " + str(fitobj.status) + "\n"
line = line + "Status Message:" + str(fitobj.message) + "\n"
line = line + "Covariance:\n" + str(fitobj.covar) + "\n"
f = open('./kmpfit_info', 'w')
f.write(line)
f.close()
return fitobj.params
def kmp_wrap(center, max_cnt, drange, xdata, ydata, dcnt):
"""
a wrapper function to use kmpfit
input: center --- gaussian center position
max_cnt --- gaussinan peak count
drange --- width of the data collecting area center +/- drange
xdata --- a list of the full sim position data
ydata --- a list of the full sim count data
dcnt --- a number of data points
output: [center position, count rate, width of the peak]
"""
freturn = [-999, -999, -999, -999, -999, -999]
xval = []
yval = []
chk = 0
rmin = int(center - drange)
rmax = int(center + drange)
for i in range(0, dcnt):
if xdata[i] >= rmin and xdata[i] <= rmax:
xval.append(xdata[i])
yval.append(ydata[i])
chk += 1
#
#--- kmpfit, least squares fitting from kapteyn package
#
if chk > 0 and max_cnt > 0:
try:
paramsinitial = (center, max_cnt, 10)
fitobj = kmpfit.Fitter(residuals=residuals, data=(xval, yval))
fitobj.fit(params0=paramsinitial)
[pos, count, width] = fitobj.params
[perr, cerr, werr] = fitobj.xerror
return [pos, count, width, perr, cerr, werr]
except:
return freturn
else:
return freturn
def kmp_wrap(center, max_cnt, drange, xdata, ydata, dcnt):
'''
a wrapper function to use kmpfit
input: center: gaussian center position
max_cnt: gaussinan peak count
drange: width of the data collecting area center +/- drange
xdata: full sim position data
ydata: full sim count data
dcnt: number of data points
output: [center position, count rate, width of the peak]
'''
xval = []
yval = []
chk = 0
rmin = int(center - drange)
rmax = int(center + drange)
for i in range(0, dcnt):
if xdata[i] >= rmin and xdata[i] <= rmax:
xval.append(xdata[i])
yval.append(ydata[i])
chk += 1
#
#--- kmpfit, least squares fitting from kapteyn package
#
if chk > 0 and max_cnt > 0:
paramsinitial = (center, max_cnt, 10)
fitobj = kmpfit.Fitter(residuals=residuals, data=(xval, yval))
fitobj.fit(params0=paramsinitial)
[pos, count, width] = fitobj.params
else:
pos = -999
count = -999
width = -999
return [pos, count, width]
def fitZshape(x,y,err) :
A = 0.5
alphaD = 1.4
alphaL = 2.5/2
a = 0.001
b = 0
nu_0 = 91.2
p0 = [alphaD, alphaL, nu_0, A, a, b]
# Do the fit
fitter = kmpfit.Fitter(residuals=residualsV, data=(x,y,err))
# fitter.parinfo = [{}, {}, {}, {}, {}, {'fixed':True}] # Take zero level fixed in fit
fitter.parinfo = [{}, {'fixed':True}, {}, {}, {}, {}]
fitter.fit(params0=p0)
print "\n========= Fit results Voigt profile =========="
print "Initial params:", fitter.params0
print "Params: ", fitter.params
print "Iterations: ", fitter.niter
print "Function ev: ", fitter.nfev
print "Uncertainties: ", fitter.xerror
print "dof: ", fitter.dof
print "chi^2, rchi2: ", fitter.chi2_min, fitter.rchi2_min
print "stderr: ", fitter.stderr
print "Status: ", fitter.status
alphaD, alphaL, nu_0, I, a_back, b_back = fitter.params
c1 = 1.0692
c2 = 0.86639
hwhm = 0.5*(c1*alphaL+np.sqrt(c2*alphaL**2+4*alphaD**2))
print "\nFWHM Voigt profile: ", 2*hwhm
f = np.sqrt(ln2)
Y = alphaL/alphaD * f
amp = I/alphaD*np.sqrt(ln2/np.pi)*voigt(0,Y)
print "Amplitude Voigt profile:", amp
print "Area under profile: ", I
return fitter.params
# Here one can experiment with errors on the measured values
err0 = numpy.zeros(N0) + normal(190.0, 1.0, N0) # Mean 200, sigma 1
# Hubble space telescope 2009: H0 = 74.2 +- 3.6 (km/s)/Mpc.
H0_last = 74.2
# Filter possible outliers based on Chauvenet's criterion
# Use the current literature value of the Hubble constant
# to create a line which is used as a base to calculate
# deviations. These offsets are distributed normally and we can
# apply Chauvenet's criterion to filter outliers.
print("\nPre filtering:")
print("=================")
paramsinitial = [70.0]
fitobj = kmpfit.Fitter(residuals=residuals, data=(d0, v0, err0))
fitobj.fit(params0=paramsinitial)
H0_fit0 = fitobj.params[0]
H0_fit0_delta = fitobj.stderr
print("H0 with unfiltered data: ", H0_fit0)
# If you want to know which data would have been excluded if
# you had a perfect fit with H0 = Ho_last, then use: mean = H0_last*d
mean = H0_fit0 * d0
# Use expression below for unit weighting. Otherwise use
# the errors in the data as standard deviations.
# stdv = numpy.sqrt(((v0-mean)**2).sum()/(N0))
stdv = err0
filter = chauvenet(d0, v0, mean=mean, stdv=stdv)
print("Excluded data based on Chauvenet's criterion:",
list(zip(d0[~filter], v0[~filter])))
def vertprofile(datafnme=(u'', ),
work_dir=(u'', ),
header=(1, ),
struct=([1, 2, 3, 4], ),
labelx=u'to be completed',
labely=u'to be completed',
labeldata=(u'Data', ),
rangex=None,
rangey=None,
statstypes=[0, 1, 2, 3],
confprob=95.0,
fontsz=10,
fontleg=9,
output='graph'):
"""
This code is to compute regressions for points with their error
using different regression methods
USAGE
>>>from vertprof import vertprofile
>>>vertprofile(datafnme = u'', work_dir = u'', header = 1, struct = [1,2,3,4],
labelx = 'to be completed', labely = 'to be completed', rangex = None, rangey = None,
statstypes = [0,1,2,3], confprob = 95.0,
fontsz = 10, fontleg = 9,
output = 'graph')
INPUTS
To use options or inputs, you need to set them as
vertprof(option_name = option_value, [...])
1. work_dir: tuple (i.e. (u'data1 workdir',u'data2 workdir',...) of the Working directory(-ies) (local path)
for each dataset
ex: work_dir = (u'Purgatorio3/',) (note the (,) structure if there is only one dataset to plot
Default None
2. datafnme: tuple (i.e. (u'data1 name ',u'data2 name',...) of the name(s) of text data file
should be in the form : Alt - Age - Age_Error
ex: datafnme = 'Purgatorio3.txt'
3. header: tuple of the number of lines of the header in the data for each dataset
ex: header = (1,) (Default)
4. struct: tuple of the structure of the data for each dataset
Struct = ([Xdata, Xerr, Ydata, Yerr],)
where Xdata, Xerr, Ydata, Yerr give their respective columns in the data file
If one of the data type do not exist, set the corresponding column to NONE
ex : struct = ([1,2,3,4],) (Default)
5. output: name of output
ex: output = 'graph' (Default)
6. labelx/labely: label x-axis/y-axis
ex: labelx = 'Exposure age (ka)'
labely ='Distance to the top of the scarp (m)'
7. labeldata: tuple (i.e. (u'data1 label',u'data2 label',...) with the name of the type of data
for each dataset plotted
default = (u'Data',)
8. rangex/rangey: Set the x- and y-range
Depends on type of data
ex: rangex = [0,8]
rangey = [10,4] (in that case, the axis is inverted)
9. statstypes: Type(s) of the stats to plot
0 = kmpfit effective variance
1 = kmpfit unweighted
2 = Williamson
3 = Cl relative weighting in X &/or Y
ex: statstype = [0,1,2,3] (Default)
statstype = [1,3]
10. fontsz: labels fontsize
ex: fontsz = 10 (Default)
11. fontleg: legend fontsize
ex: fontleg = 9 (Default)
12. confprob: the confidence interval probabilty (in %)
ex: confprob = 95.0 (Default)
OUTPUTS
For each dataset, the module outputs a pdf graph, and a text file with the stats outputs for each method asked
CONTACT
If needed, do not hesitate to contact the author.
Please, use https://isterre.fr/spip.php?page=contact&id_auteur=303
LICENCE
This package is licenced with `CCby-nc-sa` (https://creativecommons.org/licenses/by-nc-sa/2.0/)
"""
# set colors
# For the moment, only for 6 datasets, it should be enough
colors = ['b', 'darkorange', 'peru', 'black', 'darkviolet', 'green']
# initiate variables
erry = errx = a_will = b_will = verts = fitobj = fitobj2 = fitobj3 = None
# Tuples to lists
datafnme = list(datafnme)
work_dir = list(work_dir)
header = list(header)
struct = list(struct)
labeldata = list(labeldata)
# Initiate the plotting
plt.rc(u'font', size=fontsz)
#plt.rc(u'title', size = fontsz)
plt.rc(u'legend', fontsize=fontleg)
# Open figure
plt.figure(1).clear
#plt.add_subplot(1,1,1, aspect=1, adjustable=u'datalim')
# If the minima input data are not given print the help file
if not datafnme:
help(vertprofile)
raise TypeError(color.RED + u'ERROR : ' + color.END +
u'Name of Input file not given...')
# check if the length of work_dir, struct and labeldata are equal to the length of datafnme
# If not, copy the first record to the others, with a warning
for item in [work_dir, header, struct, labeldata]:
if len(datafnme) != len(item):
warnings.warn(
color.YELLOW + u"\nWARNING : " + color.END +
u"work_dir, header, struct and/or labeldata may be the same for all dataset"
)
#item = (item[0])
for i_data in range(1, len(datafnme)):
item = item.append(item[0])
#item[i_data] = item[0]
# do a loop on the number of dataset to plot
for i_data in range(0, len(datafnme)):
# check if the working directory exists, if not, create it
if work_dir[i_data].strip():
if work_dir[i_data][-1:] != u'/':
work_dir[i_data] = work_dir[i_data] + u'/'
if path.exists(work_dir[i_data]) == False:
os.mkdir(work_dir[i_data])
else:
warnings.warn(
color.YELLOW + u"\nWARNING : " + color.END +
u"Working directory already exists and will be erased\n")
# Check if the file exists in the main folder
# if not, ckeck in the working folder
# if only in the working folder, copy it to the main folder
if not path.isfile(datafnme[i_data]):
if not path.isfile(work_dir[i_data] + datafnme[i_data]):
#sys.exit(color.RED + u"ERROR : " + color.END + u"Input file %s does not exist..." % datafnme)
raise NameError(color.RED + u"ERROR : " + color.END +
u"Input file %s does not exist..." %
datafnme[i_data])
else:
copyfile(work_dir[i_data] + datafnme[i_data],
datafnme[i_data])
if not path.isfile(work_dir[i_data] + datafnme[i_data]):
copyfile(datafnme[i_data], work_dir[i_data] + datafnme[i_data])
datapath = work_dir[i_data] + datafnme[i_data]
else:
if not path.isfile(work_dir[i_data] + datafnme[i_data]):
#sys.exit(color.RED + u"ERROR : " + color.END + u"Input file %s does not exist..." % datafnme)
raise NameError(color.RED + u"ERROR : " + color.END +
u"Input file %s does not exist..." %
datafnme[i_data])
else:
datapath = datafnme[i_data]
work_dir[i_data] = u''
# read data
data = np.loadtxt(datapath, skiprows=header[i_data])
y = data[:, struct[i_data][0] - 1]
if struct[i_data][1] != 0 and struct[i_data][1] != None:
erry = data[:, struct[i_data][1] - 1]
else:
erry = 0
x = data[:, struct[i_data][2] - 1]
if struct[i_data][3] != 0 and struct[i_data][3] != None:
errx = data[:, struct[i_data][3] - 1]
else:
errx = 0
N = len(x)
# Open new file to print the results
f1w = open(work_dir[i_data] + u'results_' + datafnme[i_data], 'w')
string = ' '
print(string)
f1w.write(string + u"\n")
string = ' '
print(string)
f1w.write(string + u"\n")
string = ' '
print(string)
f1w.write(string + u"\n")
string = u' Dataset ' + labeldata[i_data]
print(color.RED + color.BOLD + string + color.END)
f1w.write(string + u"\n")
string = u"Results of weigthed least square from file " + datafnme[
i_data] + u"\n"
print(color.RED + color.BOLD + string + color.END)
f1w.write(string + u"\n")
string = u"xmax/min = " + str(x.max()) + u", " + str(x.min())
print(string)
f1w.write(string + u"\n")
string = u"ymax/min = " + str(y.max()) + u", " + str(y.min())
print(string)
f1w.write(string + u"\n")
string = u"x/y mean = " + str(x.mean()) + u", " + str(y.mean())
print(string)
f1w.write(string + u"\n")
string = (
u"\nMethods used are: \n" +
u" - kmpfit: kapteyn method, from " +
u"https://www.astro.rug.nl/software/kapteyn/kmpfittutorial.html \n"
+ u" with error on X and Y or Y only or none \n" +
u" - ODR: Orthogonal Distance Regression \n" +
u" - Williamson: least square fitting with errors in X and Y " +
u"according to \n" +
u" Williamson (Canadian Journal of Physics, 46, 1845-1847, 1968) \n"
)
print(color.CYAN + string + color.END)
f1w.write(string)
beta0 = [5.0, 1.0] # Initial estimates
if struct[i_data][3] != 0 and struct[i_data][3] != None:
if struct[i_data][1] != 0 or struct[i_data][1] != None:
# Prepare fit routine
fitobj = kmpfit.Fitter(residuals=residuals,
data=(x, y, errx, erry))
fitobj.fit(params0=beta0)
string = (
u"\n\n======== Results kmpfit: weights for both coordinates ========="
)
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(string + "\n")
string = (
u"Fitted parameters: " + str(fitobj.params) + u"\n"
u"Covariance errors: " + str(fitobj.xerror) + u"\n"
u"Standard errors " + str(fitobj.stderr) + u"\n"
u"Chi^2 min: " + str(fitobj.chi2_min) + u"\n"
u"Reduced Chi^2: " + str(fitobj.rchi2_min) + u"\n"
u"Iterations: " + str(fitobj.niter))
print(string)
f1w.write(string + u"\n")
else:
# Prepare fit routine
fitobj2 = kmpfit.Fitter(residuals=residuals2,
data=(x, y, erry))
fitobj2.fit(params0=beta0)
string = (
u"\n\n======== Results kmpfit errors in Y only =========")
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(string + u"\n")
string = (
u"Fitted parameters: " + str(fitobj2.params) + u"\n"
u"Covariance errors: " + str(fitobj2.xerror) + u"\n"
u"Standard errors " + str(fitobj2.stderr) + u"\n"
u"Chi^2 min: " + str(fitobj2.chi2_min) + u"\n"
u"Reduced Chi^2: " + str(fitobj2.rchi2_min))
print(string)
f1w.write(string)
# Unweighted (unit weighting)
fitobj3 = kmpfit.Fitter(residuals=residuals2, data=(x, y, np.ones(N)))
fitobj3.fit(params0=beta0)
string = (u"\n\n======== Results kmpfit unit weighting =========")
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(string + "\n")
string = (u"Fitted parameters: " + str(fitobj3.params) + u"\n"
u"Covariance errors: " + str(fitobj3.xerror) + u"\n"
u"Standard errors " + str(fitobj3.stderr) + u"\n"
u"Chi^2 min: " + str(fitobj3.chi2_min) + u"\n"
u"Reduced Chi^2: " + str(fitobj3.rchi2_min))
print(string)
f1w.write(string)
# Compare result with ODR
# Create the linear model from statsfuncs
linear = Model(model)
if struct[i_data][3] != 0 and struct[i_data][3] != None:
if struct[i_data][1] != 0 and struct[i_data][1] != None:
mydata = RealData(x, y, sx=errx, sy=erry)
else:
mydata = RealData(x, y, sy=erry)
else:
mydata = RealData(x, y)
myodr = ODR(mydata, linear, beta0=beta0, maxit=5000, sstol=1e-14)
myoutput = myodr.run()
string = (u"\n\n======== Results ODR =========")
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(string + u"\n")
string = (u"Fitted parameters: " + str(myoutput.beta) + u"\n"
u"Covariance errors: " +
str(np.sqrt(myoutput.cov_beta.diagonal())) + u"\n"
u"Standard errors: " + str(myoutput.sd_beta) + u"\n"
u"Minimum chi^2: " + str(myoutput.sum_square) +
u"\n"
u"Minimum (reduced)chi^2: " + str(myoutput.res_var))
print(string)
f1w.write(string)
# Compute Williamson regression
a_will, b_will, siga, sigb, beta, x_av, x__mean = williamson(
x, y, errx, erry, struct[i_data], myoutput)
if struct[i_data][3] != 0 and struct[i_data][3] != None:
if struct[i_data][1] != 0 and struct[i_data][1] != None:
chi2 = (residuals(fitobj.params, (x, y, errx, erry))**2).sum()
else:
chi2 = (residuals2(fitobj2.params, (x, y, erry))**2).sum()
else:
chi2 = (residuals2(fitobj3.params, (x, y, np.ones(N)))**2).sum()
string = (u"\n\n======== Results Williamson =========")
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(string + u"\n")
string = (u"Average x weighted: " + str(x_av) + u"\n"
u"Average x unweighted: " + str(x__mean) + u"\n"
u"Fitted parameters: " + u"[" + str(a_will) + u"," +
str(b_will) + u"]\n"
u"Covariance errors: " + u"[" + str(siga) + u"," +
str(sigb) + u"]\n"
u"Minimum chi^2: " + str(chi2))
print(string)
f1w.write(string)
string = (
u"\n====================================="
u"\nPractical results: a + b * x"
)
print(color.BLUE + color.BOLD + string + color.END)
f1w.write(u"\n" + string + u"\n")
string = (u"kmpfit unweighted: %13.4f %13.4f" %
(fitobj3.params[0], fitobj3.params[1]))
print(string)
f1w.write(string + u"\n")
string = (u" Exhumation Rate: %13.4f" % (1 / fitobj3.params[1]))
print(string)
f1w.write(string + u"\n")
string = (u" Min. Exh. Rate: %13.4f" %
(1 / (fitobj3.params[1] - np.sqrt(fitobj3.stderr[1]))))
print(string)
f1w.write(string + u"\n")
string = (u" Max. Exh. Rate: %13.4f" %
(1 / (fitobj3.params[1] + np.sqrt(fitobj3.stderr[1]))))
print(string)
f1w.write(string + "\n")
if struct[i_data][3] != 0 and struct[i_data][3] != None:
if struct[i_data][1] != 0 and struct[i_data][1] != None:
string = u"kmpfit effective variance: %13.4f %13.4f" % (
fitobj.params[0], fitobj.params[1])
print(string)
f1w.write(string + u"\n")
string = (u" Exhumation Rate: %13.4f" %
(1 / fitobj.params[1]))
print(string)
f1w.write(string + u"\n")
string = (u" Min. Exh. Rate: %13.4f" %
(1 / (fitobj.params[1] - np.sqrt(fitobj.stderr[1]))))
print(string)
f1w.write(string + u"\n")
string = (u" Max. Exh. Rate: %13.4f" %
(1 / (fitobj.params[1] + np.sqrt(fitobj.stderr[1]))))
print(string)
f1w.write(string + u"\n")
else:
string = u"kmpfit weights in Y only: %13.4f %13.4f" % (
fitobj2.params[0], fitobj2.params[1])
print(string)
f1w.write(string + u"\n")
string = (u" Exhumation Rate: %13.4f" %
(1 / fitobj2.params[1]))
print(string)
f1w.write(string + u"\n")
string = (u" Min. Exh. Rate: %13.4f" %
(1 /
(fitobj2.params[1] - np.sqrt(fitobj2.stderr[1]))))
print(string)
f1w.write(string + u"\n")
string = (u" Max. Exh. Rate: %13.4f" %
(1 /
(fitobj2.params[1] + np.sqrt(fitobj2.stderr[1]))))
print(string)
f1w.write(string + u"\n")
string = u"ODR: %13.4f %13.4f" % (beta[0],
beta[1])
print(string)
f1w.write(string + u"\n")
string = (u" Exhumation Rate: %13.4f" % (1 / beta[1]))
print(string)
f1w.write(string + u"\n")
string = (u" Min. Exh. Rate: %13.4f" %
(1 / (beta[1] - np.sqrt(myoutput.sd_beta[1]))))
print(string)
f1w.write(string + u"\n")
string = (u" Max. Exh. Rate: %13.4f" %
(1 / (beta[1] + np.sqrt(myoutput.sd_beta[1]))))
print(string)
f1w.write(string + u"\n")
string = u"Williamson: %13.4f %13.4f" % (a_will,
b_will)
print(string)
f1w.write(string + u"\n")
string = (u" Exhumation Rate: %13.4f" % (1 / b_will))
print(string)
f1w.write(string + u"\n")
# For the next lines, not sure that we have to use the chi2 as error...
string = (u" Min. Exh. Rate: %13.4f" % (1 / (b_will - chi2)))
print(string)
f1w.write(string + u"\n")
string = (u" Max. Exh. Rate: %13.4f" % (1 / (b_will + chi2)))
print(string)
f1w.write(string + u"\n")
print(u"\n")
# calcul of confidence intervals
dfdp = [1, x, x**2]
if struct[i_data][3] != 0 and struct[i_data][3] != None:
if struct[i_data][1] != 0 and struct[i_data][1] != None:
ydummy, upperband, lowerband = confidence_band(
x, dfdp, confprob, fitobj, model)
labelconf = u"CI (" + str(
confprob) + u"%) relative weighting in X & Y"
if i_data == 0:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
#stringl = (u"y_" + labeldata[i_data] + u" = a + b * x with a = %.2f +/- %.2f and b = %.2f +/- %.2f "
#stringl = (u" y_" + labeldata[i_data] + u" = a + b * x with a = %.2f +/- %.2f and b = %.2f +/- %.2f "
# %(fitobj.params[0], np.sqrt(fitobj.stderr[0]),
# fitobj.params[1], np.sqrt(fitobj.stderr[1])))
stringl = (
r" $\mathbf{Y_{%s}} = \mathbf{a} + \mathbf{b} \times \mathbf{X}$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj.params[0],
np.sqrt(fitobj.stderr[0]), fitobj.params[1],
np.sqrt(fitobj.stderr[1])))
else:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
stringl = stringl + "\n" + (
r"$\mathbf{Y_{%s}} = \mathbf{a} + \mathbf{b} \times \mathbf{X}$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj.params[0],
np.sqrt(fitobj.stderr[0]), fitobj.params[1],
np.sqrt(fitobj.stderr[1])))
else:
ydummy, upperband, lowerband = confidence_band(
x, dfdp, confprob, fitobj2, model)
labelconf = u"CI (" + str(
confprob) + u"%) relative weighting in Y"
if i_data == 0:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
stringl = (
r"$\mathbf{Y_{%s}} = \mathbf{a} + \mathbf{b} \times \mathbf{X}$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj2.params[0],
np.sqrt(fitobj2.stderr[0]), fitobj2.params[1],
np.sqrt(fitobj2.stderr[1])))
else:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
stringl = stringl + "\n" + (
r"$\mathbf{Y_{%s}} = \mathbf{a} + \mathbf{b} \times \mathbf{X}$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj2.params[0],
np.sqrt(fitobj2.stderr[0]), fitobj2.params[1],
np.sqrt(fitobj2.stderr[1])))
else:
ydummy, upperband, lowerband = confidence_band(
x, dfdp, confprob, fitobj3, model)
labelconf = u"CI (" + str(confprob) + u"%) with no weighting"
if i_data == 0:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
stringl = (
r"$\mathbf{y_{%s}} = \mathbf{a} + \mathbf{b} \times x$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj3.params[0],
np.sqrt(fitobj3.stderr[0]), fitobj3.params[1],
np.sqrt(fitobj3.stderr[1])))
else:
#string = (u"y = a + b * x with a = %6.4f +/- %6.4f and b = %6.4f +/- %6.4f "
stringl = stringl + "\n" + (
r"$\mathbf{Y_{%s}} = \mathbf{a} + \mathbf{b} \times \mathbf{X}$ with $\mathbf{a} = %.2f \pm %.2f$ and $\mathbf{b} = %.2f \pm %.2f$ "
% (labeldata[i_data], fitobj3.params[0],
np.sqrt(fitobj3.stderr[0]), fitobj3.params[1],
np.sqrt(fitobj3.stderr[1])))
#verts = zip(x, lowerband) + zip(x[::-1], upperband[::-1])
# Because we need to invert X and Y for the graph
verts = list(zip(lowerband, x)) + list(zip(upperband[::-1], x[::-1]))
# Close output file
f1w.close()
#if rangex:
# X = np.linspace(rangex[0], rangex[1], 50)
#else:
# d = (x.max() - x.min())/10
# X = np.linspace(x.min()-d, x.max()+d, 50)
#if rangey:
# Y = np.linspace(rangey[0], rangey[1], 50)
#else:
# d = (y.max() - y.min())/10
# Y = np.linspace(y.min()-d, y.max()+d, 50)
# Call the plotting function
#axes = plotgraphreg(struct[i_data], x, y, errx, erry, X, Y,
axes = plotgraphreg(struct[i_data], x, y, errx, erry, colors[i_data],
labeldata[i_data], statstypes, a_will, b_will,
verts, confprob, fitobj, fitobj2, fitobj3)
# Set graph characteristics/attributes
plt.xlabel(labelx)
plt.ylabel(labely)
plt.grid(True)
plt.title(stringl, size=fontsz)
# clean the legend from duplicates
handles, labels = plt.gca().get_legend_handles_labels()
by_label = OrderedDict(zip(labels, handles))
plt.legend(by_label.values(), by_label.keys(), loc="best")
# set the X and Y limits
if rangex:
axes.set_xlim([rangex[0], rangex[1]])
if rangey:
axes.set_ylim(bottom=rangey[0], top=rangey[1])
plt.savefig(work_dir[0] + output + u'.pdf')
plt.close()
fr = len(dat2[dat2 <= yy]) / float(n)
cdfnew.append(fr)
return numpy.asarray(cdfnew)
# Create data
N = 30
x = numpy.linspace(-5, 10, N)
# Parameters: A, mu, sigma, zerolev
truepars = [10.0, 4.0, 2.5, 0.0]
p0 = [10, 4.5, 0.8, 0]
y = func(truepars, x) + numpy.random.normal(0, 0.8, N)
err = numpy.random.normal(0.0, 0.6, N)
# Do the fit
fitter = kmpfit.Fitter(residuals=residuals, data=(x, y, err))
#fitter.parinfo = [{}, {}, {}, {'fixed':True}] # Take zero level fixed in fit
fitter.fit(params0=p0)
if (fitter.status <= 0):
print("Status: ", fitter.status)
print('error message = ', fitter.errmsg)
raise SystemExit
print("\n========= Fit results ==========")
print("Initial params:", fitter.params0)
print("Params: ", fitter.params)
print("Iterations: ", fitter.niter)
print("Function ev: ", fitter.nfev)
print("Uncertainties: ", fitter.xerror)
print("dof: ", fitter.dof)
def gauss_hermite_fit(data,
p0,
plot_op='no',
xname='X',
yname='Cnts',
tname='Voigt Fit',
xmin='na',
xmax='na',
ymin='na',
ymax='na',
detail='no'):
"""
control function of Gauss-Hermite fitting
Input:
data --- data list of lists [x, y, err]
p0 = --- parameter list: [A1, X1, S1, h31, h41, z01]
A1: area covered
X1: center position
S1:
h31:
h41:
zo1:
plot_op --- if yes, the script will plot. default: no
xname --- the name of x axis
yname --- the name of y axis
tname --- title of the plot
xmin --- lower boundary in x of the plot
xmax --- upper boundray in x of the plot
ymin --- lower boundary in y of the plot
ymax --- upper boundray in y of the plot
detail --- if yes, it will print fitting profiles. default: no
Output: param: [A1, X1, S1, h31, h41, z01, height, center, width, floor]
if plot is asked: out.png
if proflie is asked: gh_fitting_profile
"""
x, y, err = data
#
#--- convert the list ot numpy array
#
x = numpy.array(x)
y = numpy.array(y)
err = numpy.array(err)
#
#---- Fit the Gaussian model
#
[A1, X1, S1, h31, h41, z01] = p0
pg = [A1, X1, S1,
z01] #--- approximate the initial values using GH initial estimates
fitterG = kmpfit.Fitter(residuals=residualsG, data=(x, y, err))
fitterG.fit(params0=pg)
if detail == 'yes':
line = "\n========= Fit results Gaussian profile ==========\n\n"
line = line + "Initial params:" + str(fitterG.params0) + "\n"
line = line + "Params: " + str(fitterG.params) + "\n"
line = line + "Iterations: " + str(fitterG.niter) + "\n"
line = line + "Function ev: " + str(fitterG.nfev) + "\n"
line = line + "Uncertainties: " + str(fitterG.xerror) + "\n"
line = line + "dof: " + str(fitterG.dof) + "\n"
line = line + "chi^2, rchi2: " + str(fitterG.chi2_min) + ' ' + str(
fitterG.rchi2_min) + "\n"
line = line + "stderr: " + str(fitterG.stderr) + "\n"
line = line + "Status: " + str(fitterG.status) + "\n"
fwhmG = 2 * numpy.sqrt(2 * numpy.log(2)) * fitterG.params[2]
line = line + "FWHM Gaussian: " + str(fwhmG) + "\n"
z0G = fitterG.params0[-1] # Store background
#
#--- Fit the Gauss-Hermite model
#
#--- Initial estimates for A, xo, s, h3, h4, z0
#
fitterGH = kmpfit.Fitter(residuals=residualsGH, data=(x, y, err))
# fitterGH.parinfo = [{}, {}, {}, {}, {}] # Take zero level fixed in fit
fitterGH.fit(params0=p0)
if detail == 'yes':
line = line + "\n\n========= Fit results Gaussian-Hermite profile ==========\n\n"
line = line + "Initial params:" + str(fitterGH.params0) + "\n"
line = line + "Params: " + str(fitterGH.params) + "\n"
line = line + "Iterations: " + str(fitterGH.niter) + "\n"
line = line + "Function ev: " + str(fitterGH.nfev) + "\n"
line = line + "Uncertainties: " + str(fitterGH.xerror) + "\n"
line = line + "dof: " + str(fitterGH.dof) + "\n"
line = line + "chi^2, rchi2: " + str(fitterGH.chi2_min) + ' ' + str(
fitterGH.rchi2_min) + "\n"
line = line + "stderr: " + str(fitterGH.stderr) + "\n"
line = line + "Status: " + str(fitterGH.status) + "\n"
A, x0, s, h3, h4, z0GH = fitterGH.params
#
#--- xm, ampmax, area, mean, dispersion, skewness, kurtosis
#
res = hermite2gauss(fitterGH.params[:-1], fitterGH.stderr[:-1])
line = line + "Gauss-Hermite max=%g at x=%g\n" % (res['amplitude'],
res['xmax'])
line = line + "Area :" + str(
res['area']) + ' ' + str('+-') + ' ' + str(res['d_area']) + "\n"
line = line + "Mean (X0) :" + str(
res['mean']) + ' ' + str('+-') + ' ' + str(res['d_mean']) + "\n"
line = line + "Dispersion:" + str(
res['dispersion']) + ' ' + str('+-') + ' ' + str(
res['d_dispersion']) + "\n"
line = line + "Skewness :" + str(
res['skewness']) + ' ' + str('+-') + ' ' + str(
res['d_skewness']) + "\n"
line = line + "Kurtosis :" + str(
res['kurtosis']) + ' ' + str('+-') + ' ' + str(
res['d_kurtosis']) + "\n"
f = open('gh_fitting_profile', 'w')
f.write(line)
f.close()
#
#--- Plot the result
#
if plot_op == 'yes':
rc('legend', fontsize=6)
fig = figure()
frame1 = fig.add_subplot(1, 1, 1)
if xmax != 'na':
frame1.set_xlim(xmin=xmin, xmax=xmax, auto=False)
frame1.set_ylim(ymin=ymin, ymax=ymax, auto=False)
xd = numpy.linspace(x.min(), x.max(), 500)
frame1.plot(x, y, 'bo', label="data")
label = "Model with Gaussian function"
frame1.plot(xd, funcG(fitterG.params, xd), 'm', ls='--', label=label)
label = "Model with Gauss-Hermite function"
frame1.plot(xd, funcGH(fitterGH.params, xd), 'b', label=label)
frame1.plot(xd, [z0G] * len(xd), "y", ls="-.", label='Background G')
frame1.plot(xd, [z0GH] * len(xd), "y", ls="--", label='Background G-H')
frame1.set_xlabel(xname)
frame1.set_ylabel(yname)
t = (res['area'], res['mean'], res['dispersion'], res['skewness'],
res['kurtosis'])
title = tname + " GH: $\gamma_{gh}$=%.1f $\mu_{gh}$=%.1f $\sigma_{gh}$ = %.2f $\\xi_1$=%.2f $\\xi_f$=%.2f" % t
frame1.set_title(title, fontsize=9)
frame1.grid(True)
leg = frame1.legend(loc=1)
#
#--- set the size of the plotting area in inch (width: 10.0in, height 5.0in)
#
fig = mpl.pyplot.gcf()
fig.set_size_inches(10.0, 5.0)
#
#--- save the plot in png format
#
fig.savefig('out.png', format='png', dpi=100)
#
#--- returning parameters
#
[A1, X1, S1, h31, h41, z01] = fitterGH.params
[height, center, width, floor] = fitterG.params
return [A1, X1, S1, h31, h41, z01, height, center, width, floor]
Before fitting we will sample the chisquare plane to make a first guess of 'p0'. This will be the sample for which χ2 is minimal.
"""
Ns = 200
def chi2(p, *data):
return np.sum(residuals(p, data)**2)
prange = ((-np.pi, np.pi), (0, np.pi))
p0, fval, ϕθ, χ2 = brute(chi2,
ranges=prange,
args=data,
Ns=200,
full_output=True,
workers=-1)
fitobj = kmpfit.Fitter(residuals)
fitobj.data = data
fitobj.params0 = p0
#we don't impose any limits on the parameter space as that would cause branch cuts
fitobj.fit()
#Below we phase shift the results such that -π < ϕ < π and 0 < θ < π.
#phase shift ϕ
if fitobj.params[0] < 0:
N = fitobj.params[0] // -np.pi
fitobj.params = np.array(
[fitobj.params[0] + 2 * np.pi * N, fitobj.params[1]])
elif fitobj.params[0] > 0:
N = fitobj.params[0] // np.pi
fitobj.params = np.array(
[fitobj.params[0] - 2 * np.pi * N, fitobj.params[1]])
a_pearson = y_av - b_pearson*x_av
print("Best fit parameters: a=%.10f b=%.10f"%(a_pearson,b_pearson))
rxy = Sxy/numpy.sqrt(Sxx*Syy)
print("Pearson's Corr. coef: ", rxy)
tan2theta = 2*rxy*numpy.sqrt(Sxx*Syy)/(Sxx-Syy)
twotheta = numpy.arctan(tan2theta)
print("Pearson's best tan2theta, theta, slope: ", \
tan2theta, 0.5*twotheta, numpy.tan(0.5*twotheta))
b1 = rxy*numpy.sqrt(Syy)/numpy.sqrt(Sxx)
print("b1 (Y on X), slope: ", b1, b1)
b2 = rxy*numpy.sqrt(Sxx)/numpy.sqrt(Syy)
print("b2 (X on Y), slope", b2, 1/b2)
# Prepare fit routine
fitobj = kmpfit.Fitter(residuals=residuals, data=(x, y))
fitobj.fit(params0=beta0)
print("\n======== Results kmpfit: effective variance =========")
print("Params: ", fitobj.params[0], numpy.tan(fitobj.params[1]))
print("Covariance errors: ", fitobj.xerror)
print("Standard errors ", fitobj.stderr)
print("Chi^2 min: ", fitobj.chi2_min)
print("Reduced Chi^2: ", fitobj.rchi2_min)
# Prepare fit routine
fitobj2 = kmpfit.Fitter(residuals=residuals2, data=(x, y))
fitobj2.fit(params0=beta0)
print("\n======== Results kmpfit Y on X =========")
print("Params: ", fitobj2.params)
print("Covariance errors: ", fitobj2.xerror)
print("Standard errors ", fitobj2.stderr)
print("\nODR:")
print("==========")
from scipy.odr import Data, Model, ODR, RealData, odr_stop
linear = Model(model)
mydata = RealData(x, y, sx=errx, sy=erry)
myodr = ODR(mydata, linear, beta0=beta0, maxit=5000)
myoutput = myodr.run()
print("Fitted parameters: ", myoutput.beta)
print("Covariance errors: ", numpy.sqrt(myoutput.cov_beta.diagonal()))
print("Standard errors: ", myoutput.sd_beta)
print("Minimum chi^2: ", myoutput.sum_square)
print("Minimum (reduced)chi^2: ", myoutput.res_var)
beta = myoutput.beta
# Prepare fit routine
fitobj = kmpfit.Fitter(residuals=residuals, data=(x, y, errx, erry))
fitobj.fit(params0=beta0)
print("\n\n======== Results kmpfit with effective variance =========")
print("Fitted parameters: ", fitobj.params)
print("Covariance errors: ", fitobj.xerror)
print("Standard errors: ", fitobj.stderr)
print("Chi^2 min: ", fitobj.chi2_min)
print("Reduced Chi^2: ", fitobj.rchi2_min)
print("Status Message:", fitobj.message)
# Compare to a fit with weights for y only
fitobj2 = kmpfit.Fitter(residuals=residuals2, data=(x, y, erry))
fitobj2.fit(params0=beta0)
print("\n\n======== Results kmpfit errors in Y only =========")
print("Fitted parameters: ", fitobj2.params)
print("Covariance errors: ", fitobj2.xerror)
elif i == 3:
pderiv[3] = 1.0
pderiv /= -err
return pderiv
# Artificial data
N = 100
x = numpy.linspace(-5, 10, N)
truepars = [10.0, 5.0, 1.0, 0.0]
p0 = [9, 4.5, 0.8, 0]
y = my_model(truepars, x) + 0.3*numpy.random.randn(len(x))
err = 0.3*numpy.random.randn(N)
# The fit
fitobj = kmpfit.Fitter(residuals=my_residuals, deriv=my_derivs, data=(x, y, err))
try:
fitobj.fit(params0=p0)
except Exception as mes:
print("Something wrong with fit: ", mes)
raise SystemExit
print("\n\n======== Results kmpfit with explicit partial derivatives =========")
print("Params: ", fitobj.params)
print("Errors from covariance matrix : ", fitobj.xerror)
print("Uncertainties assuming reduced Chi^2=1: ", fitobj.stderr)
print("Chi^2 min: ", fitobj.chi2_min)
print("Reduced Chi^2: ", fitobj.rchi2_min)
print("Iterations: ", fitobj.niter)
print("Function ev: ", fitobj.nfev)
print("Status: ", fitobj.status)
def residuals(p, my_arrays):
x, y, err = my_arrays
a, b = p
return (y - model(p, x)) / err
x = numpy.array([1.0, 2, 3, 4, 5, 6, 7])
y = numpy.array([6.9, 11.95, 16.8, 22.5, 26.2, 33.5, 41.0])
N = len(y)
err = numpy.ones(N)
errw = numpy.array([0.05, 0.1, 0.2, 0.5, 0.8, 1.5, 4.0])
print("Data x:", x)
print("Data y:", y)
print("Errors:", errw)
fitobj = kmpfit.Fitter(residuals=residuals, data=(x, y, err))
fitobj.fit(params0=[1, 1])
print("\n-- Results kmpfit unit weighting wi=1.0:")
print("Best-fit parameters: ", fitobj.params)
print("Parameter errors using measurement uncertainties: ", fitobj.xerror)
print("Parameter errors unit-/relative weighted fit: ", fitobj.stderr)
print("Minimum chi^2: ", fitobj.chi2_min)
print("Covariance matrix:")
print(fitobj.covar)
fitobj = kmpfit.Fitter(residuals=residuals, data=(x, y, 10 * err))
fitobj.fit(params0=[1, 1])
print("\n-- Results kmpfit with (scaled) equal weights wi=10*1.0:")
print("Best-fit parameters: ", fitobj.params)
print("Parameter errors using measurement uncertainties: ", fitobj.xerror)
print("Parameter errors unit-/relative weighted fit: ", fitobj.stderr)
def linefitting(x,
y,
xerr=None,
yerr=None,
xrange=[-5, 5],
color='b',
prob=.95,
yoffset=0):
# Initial guess from simple linear regression
sorted = np.argsort(x)
b, a, rval, pval, std_err = stats.linregress(x[sorted], y[sorted])
print("\nLineregress parameters: ", a, b)
# Run the fit
fitobj = kmpfit.Fitter(residuals=residuals, data=(x, y, xerr, yerr))
fitobj.fit(params0=[a, b])
print("\n======== Results kmpfit with effective variance =========")
print("Fitted parameters: ", fitobj.params)
print("Covariance errors: ", fitobj.xerror)
print("Standard errors: ", fitobj.stderr)
print("Chi^2 min: ", fitobj.chi2_min)
print("Reduced Chi^2: ", fitobj.rchi2_min)
print("Status Message:", fitobj.message)
c, d = fitobj.params
e, f = fitobj.stderr
# Alternative method using Orthogonal Distance Regression
linear = odr.Model(model)
mydata = odr.RealData(x, y, sx=xerr, sy=yerr)
myodr = odr.ODR(mydata, linear, beta0=[a, b])
myoutput = myodr.run()
myoutput.pprint()
# Plot the results
xmod = np.linspace(xrange[0], xrange[1], 50)
#ymod0 = model([a, b], xmod)
ymod = model([c, d], xmod)
plt.plot(xmod, ymod, linestyle='--', color=color, zorder=1)
axes = plt.gca()
dfdp = [1, xmod]
ydummy, upperband, lowerband = fitobj.confidence_band(
xmod, dfdp, prob, model)
verts = list(zip(xmod, lowerband)) + list(zip(xmod[::-1], upperband[::-1]))
poly = Polygon(verts,
closed=True,
fc='c',
ec='c',
alpha=0.3,
label="{:g}% conf.".format(prob * 100))
axes.add_patch(poly)
# The slope
axes.text(0.03,
0.95 - yoffset,
'a = $%4.2f$ ' % d + u'\u00B1' + ' $%4.2f$' % f,
size=10,
transform=axes.transAxes,
color=color)
# The intercept
axes.text(0.03,
0.90 - yoffset,
'b = $%4.2f$ ' % c + u'\u00B1' + ' $%4.2f$' % e,
size=10,
transform=axes.transAxes,
color=color)
return
# Artificial data
#================
N = 50 # Number of data points
mean = 0.0
sigma = 0.6 # Characteristics of the noise we add
xstart = 2.0
xend = 10.0
x = numpy.linspace(3.0, 10.0, N)
paramsreal = [1.0, 1.0]
noise = numpy.random.normal(mean, sigma, N)
y = model(paramsreal, x) + noise
# Prepare a 'Fitter' object'
#===========================
arrays = (x, y)
fitobj = kmpfit.Fitter(residuals, data=arrays)
paramsinitial = (0.0, 0.0)
fitobj.fit(params0=paramsinitial)
if (fitobj.status <= 0):
print('Error message = ', fitobj.errmsg)
else:
print("Optimal parameters: ", fitobj.params)
# Plot the result
#================
rc('legend', fontsize=8)
fig = figure()
xp = numpy.linspace(xstart - 1, xend + 1, 200)
frame = fig.add_subplot(1, 1, 1, aspect=1.0)
frame.plot(x, y, 'ro', label="Data")
# Artificial data
x = numpy.array([2, 4, 6, 8, 10, 12])
y = numpy.array([3.5, 7.2, 9.5, 17.1, 20.0, 25.5])
err = numpy.array([0.55, 0.65, 0.74, 0.5, 0.85, 0.6])
# Prepare plot
fig = figure()
rc('legend', fontsize=8)
frame = fig.add_subplot(1, 1, 1)
frame.plot(x, y, 'go', label="data")
frame.set_xlabel("x")
frame.set_ylabel("y")
frame.set_title("Exclude poor data with criterion of Chauvenet")
params0 = (1, 1)
fitter = kmpfit.Fitter(residuals=residuals, data=(x, y, err))
fitter.fit(params0=params0)
print("======== Fit results all data included ==========")
print("Params: ", fitter.params)
print("Uncertainties: ", fitter.xerror)
print("Errors assuming red.chi^2=1: ", fitter.stderr)
print("Iterations: ", fitter.niter)
print("Function ev: ", fitter.nfev)
print("dof: ", fitter.dof)
print("chi^2, rchi2: ", fitter.chi2_min, fitter.rchi2_min)
print("Status: ", fitter.status)
from scipy.stats import chi2
rv = chi2(fitter.dof)
print("If H0 was correct, then")
m, n, r_value, p_value, std_err = stats.linregress(x_i, y_i)
m_vector[k], n_vector[k] = m, n
#Lmfit
result_lmfit = lmod.fit(y_i, x=x_i, m=0.005, n=0.24709)
lmfit_matrix[:, k] = array(result_lmfit.params.valuesdict().values())
lmfit_error[:, k] = array(
[result_lmfit.params['m'].stderr, result_lmfit.params['n'].stderr])
#Curvefit
best_vals, covar = curve_fit(linear_model, x_i, y_i, p0=p0)
curvefit_matrix[:, k] = best_vals
#kapteyn
fitobj = kmpfit.Fitter(residuals=residuals_lin, data=(x_i, y_i))
fitobj.fit(params0=p0)
kapteyn_matrix[:, k] = fitobj.params
#Get fit mean values
n_Median, n_16th, n_84th = median(n_vector), percentile(n_vector,
16), percentile(
n_vector, 84)
m_Median, m_16th, m_84th = median(m_vector), percentile(m_vector,
16), percentile(
m_vector, 84)
m_Median_lm, m_16th_lm, m_84th_lm = median(lmfit_matrix[0, :]), percentile(
lmfit_matrix[0, :], 16), percentile(lmfit_matrix[0, :], 84)
n_Median_lm, n_16th_lm, n_84th_lm = median(lmfit_matrix[1, :]), percentile(
lmfit_matrix[1, :], 16), percentile(lmfit_matrix[1, :], 84)
m_Median_lm_error, n_Median_lm_error = median(lmfit_error[0, :]), median(
pv = Plots_Manager()
dz = Fitting_Gaussians()
mu, sigma = 0, 1
A = (1 / ((2 * 3.1415)**0.5) * sigma)
x_true = linspace(-2, 2, 100)
y = A * exp(-(x_true - mu)**2 / (2 * sigma**2))
zerolev = zeros(len(x_true))
p_1, conv = leastsq(Residuals_Gaussian, [A, mu, sigma], [x_true, y, zerolev])
print 'predictions initial', p_1
L = exp(-y / 2)
p0 = [-0.2, 0, 1, max(L)]
fitterG = kmpfit.Fitter(residuals=residualsG, data=(x_true, L))
fitterG.fit(params0=p0)
print fitterG.params
gaus_inv = funcG(fitterG.params, x_true)
y_frac = y / 3
p_2, conv = leastsq(Residuals_Gaussian, [A / 5, mu, sigma],
[x_true, y_frac, zerolev])
print 'predictions by3', p_2
gaus_inv = SingleGaussian_Cont([x_true, zerolev], p_2[0], p_2[1], p_2[2])
# dz.SingleGaussian_Cont(Ind_Variables, A, mu, sigma)
plt.plot(x_true, y, '-', color='black')
plt.plot(x_true, gaus_inv, '-', color='red')
# plt.plot(x_true, y_frac, '-', color = 'orange')
import numpy as np
import pandas as pd
from matplotlib.pyplot import figure, show
from kapteyn import kmpfit
def model(p, v, x, w):
a, b, c, d, e, f, g, h, i, j, k = p #coefficients to the polynomials
return a * v**2 + b * x**2 + c * w**2 + d * v * x + e * v * w + f * x * w + g * v + h * x + i * y + k
def residuals(p, data): # Function needed by fit routine
v, x, w, z = data # The values for v, x, w and the measured hypersurface z
a, b, c, d, e, f, g, h, i, j, k = p #coefficients to the polynomials
return (z - model(p, v, x, w)) # Returns an array of residuals.
#This should (z-model(p,v,x,w))/err if
# there are error bars on the measured z values
#initial guess at parameters. Avoid using 0.0 as initial guess
par0 = [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
#create a fitting object. data should be in the form
#that the functions above are looking for, i.e. a Nx4
#list of lists/tuples like (v,x,w,z)
data = pd.read_csv("data.csv")
print(data)
fitobj = kmpfit.Fitter(residuals=residuals, data=data)
# call the fitter
fitobj.fit(params0=par0)
