def test_warning_no_fit_performed(self):
_fit = XYFit(xy_data=self._ref_data)
_fit.add_error('y', 0.1)
_plot = Plot(fit_objects=_fit)
with self.assertWarns(Warning) as w:
_plot.plot()
self.assertIn("Did you forget to run fit.do_fit()?", str(w.warning))
class TestXYPlot(unittest.TestCase):
def setUp(self):
self._ref_data = [[1, 2, 3], [1, 2, 3]]
self._ref_dataset_label = 'My Dataset'
self._ref_x_label = '$U$ [V]'
self._ref_y_label = '$I$ [A]'
self._ref_model_label = 'My Model'
self._ref_error_label = self._ref_model_label + r' $\pm 1\sigma$'
self.fit = XYFit(xy_data=self._ref_data)
self.fit.add_error('y', 0.1)
self.fit.do_fit()
self.fit.data_container.label = self._ref_dataset_label
self.fit.data_container.axis_labels = (self._ref_x_label,
self._ref_y_label)
self.fit.model_label = self._ref_model_label
self.plot = Plot(self.fit)
def test_labels_after_plotting(self):
self.plot.plot()
self.assertEqual(self.plot.axes[0]['main'].get_xlabel(),
self._ref_x_label)
self.assertEqual(self.plot.axes[0]['main'].get_ylabel(),
self._ref_y_label)
_, labels = self.plot.axes[0]['main'].get_legend_handles_labels()
self.assertIn(self._ref_dataset_label, labels)
self.assertIn(self._ref_model_label, labels)
self.assertIn(self._ref_error_label, labels)
def test_remove_labels(self):
self.fit.data_container.label = '__del__'
self.fit.data_container.axis_labels = ('__del__', '__del__')
self.fit.model_label = '__del__'
self.plot.plot()
_, labels = self.plot.axes[0]['main'].get_legend_handles_labels()
self.assertEqual(self.plot.axes[0]['main'].get_xlabel(), '')
self.assertEqual(self.plot.axes[0]['main'].get_ylabel(), '')
self.assertTrue(len(labels) == 0)
def test_warning_no_fit_performed(self):
_fit = XYFit(xy_data=self._ref_data)
_fit.add_error('y', 0.1)
_plot = Plot(fit_objects=_fit)
with self.assertWarns(Warning) as w:
_plot.plot()
self.assertIn("Did you forget to run fit.do_fit()?", str(w.warning))
xy_fit_gaussian_full = XYFit(
xy_data=[years_of_death, measured_c14_activity_full],
model_function=expected_activity_per_day
)
xy_fit_gaussian_full.add_error(axis='y', err_val=np.sqrt(measured_c14_activity_full))
xy_fit_gaussian_full.add_parameter_constraint(name='T_12_C14', value=5730, uncertainty=40)
xy_fit_gaussian_full.do_fit()
xy_fit_poisson_full = XYFit(
xy_data=[years_of_death, measured_c14_activity_full],
model_function=expected_activity_per_day,
cost_function=XYCostFunction_NegLogLikelihood(data_point_distribution='poisson')
)
xy_fit_poisson_full.add_parameter_constraint(name='T_12_C14', value=5730, uncertainty=40)
xy_fit_poisson_full.do_fit()
Delta_T_poisson_full = xy_fit_poisson_full.parameter_values[0]
Delta_T_gaussian_full = xy_fit_gaussian_full.parameter_values[0]
relative_error_full = abs((Delta_T_gaussian_full - Delta_T_poisson_full) / Delta_T_poisson_full)
# Print out the results:
print('Relative errors from Gaussian approximation:')
print('For N~10:', relative_error_sparse)
print('For N~6000:', relative_error_full)
# Optional: create a plot of the fit results using Plot
xy_plot_poisson_sparse = Plot([xy_fit_gaussian_sparse, xy_fit_poisson_sparse])
xy_plot_poisson_sparse.plot(fit_info=True)
plt.show()
xy_d2.axis_labels = ['x', 'y(2) & f(x)']
# 3. create the Fit objects
xyFit1 = Fit(xy_d1, model1)
xyFit2 = Fit(xy_d2, model2)
# set meaningful names for model
xyFit1.model_label = 'Lineares Modell'
xyFit2.model_label = 'Lineares Modell'
# add the parameter constraints
xyFit1.add_parameter_constraint(name='g1', value=c1, uncertainty=ec1)
xyFit2.add_parameter_constraint(name='g2', value=c2, uncertainty=ec2)
# combine the two fit objects to form a MultiFit
multiFit = MultiFit(fit_list=[xyFit1, xyFit2])
# 4. perform the fit
multiFit.do_fit()
# 5. report fit results
multiFit.report()
# 6. create and draw plots
multiPlot = Plot(multiFit)
##multiPlot = Plot(multiFit, separate_figures=True)
multiPlot.plot(figsize=(13., 7.))
# 7. show or save plots #
##for i, fig in enumerate(multiPlot.figures):
## fig.savefig("MultiFit-"+str(i)+".pdf")
plt.show()
linear_fit.assign_model_function_latex_expression("{a}{x} + {b}")
exponential_fit.assign_parameter_latex_names(A0='A_0', x0='x_0')
exponential_fit.assign_model_function_latex_expression("{A0} e^{{{x}/{x0}}}")
# Perform the fits.
linear_fit.do_fit()
exponential_fit.do_fit()
# Optional: Print out a report on the result of each fit.
linear_fit.report()
exponential_fit.report()
# Optional: Create a plot of the fit results using Plot.
p = Plot(fit_objects=[linear_fit, exponential_fit], separate_figures=False)
# Optional: Customize the plot appearance: only show the data points once.
p.customize('data', 'color', values=['k',
'none']) # hide points for second fit
p.customize('data', 'label', values=['data points',
None]) # no second legend entry
# Do the plotting.
p.plot(fit_info=True)
# Optional: Create a contour plot for the exponential fit to show the parameter correlations.
cpf = ContoursProfiler(exponential_fit)
cpf.plot_profiles_contours_matrix(show_grid_for='contours')
# Show the fit results.
plt.show()
To get to the height of a bin, please multiply the results of the fitted function with the amount of entries N of the
histogram.
"""
import numpy as np
import matplotlib.pyplot as plt
from kafe2 import HistContainer, HistFit, Plot
def normal_distribution_pdf(x, mu, sigma):
return np.exp(-0.5 * ((x - mu) / sigma) ** 2) / np.sqrt(2.0 * np.pi * sigma ** 2)
# create a random dataset of 100 random values, following a normal distribution with mu=0 and sigma=1
data = np.random.normal(loc=0, scale=1, size=100)
# Create a histogram from the dataset by specifying the bin range and the amount of bins.
# Alternatively the bin edges can be set.
histogram = HistContainer(n_bins=10, bin_range=(-5, 5), fill_data=data)
# create the Fit object by specifying a density function
fit = HistFit(data=histogram, model_density_function=normal_distribution_pdf)
fit.do_fit() # do the fit
fit.report() # Optional: print a report to the terminal
# Optional: create a plot and show it
plot = Plot(fit)
plot.plot()
plt.show()
import matplotlib.pyplot as plt
from kafe2 import XYContainer, XYFit, Plot
from kafe2.fit.tools import ContoursProfiler
# Construct a fit with data loaded from a yaml file. The model function is the default of f(x) = a * x + b
nonlinear_fit = XYFit(xy_data=XYContainer.from_file('x_errors.yml'))
# The x errors are much bigger than the y errors. This will cause a distortion of the likelihood function.
nonlinear_fit.add_error('x', 1.0)
nonlinear_fit.add_error('y', 0.1)
# Perform the fit.
nonlinear_fit.do_fit()
# Optional: Print out a report on the fit results on the console.
# Note the asymmetric_parameter_errors flag
nonlinear_fit.report(asymmetric_parameter_errors=True)
# Optional: Create a plot of the fit results using Plot.
# Note the asymmetric_parameter_errors flag
plot = Plot(nonlinear_fit)
plot.plot(fit_info=True, asymmetric_parameter_errors=True)
# Optional: Calculate a detailed representation of the profile likelihood
# Note how the actual chi2 profile differs from the parabolic approximation that you would expect with a linear fit.
profiler = ContoursProfiler(nonlinear_fit)
profiler.plot_profiles_contours_matrix(show_grid_for='all')
plt.show()
def expected_activity_per_day(x, Delta_t=5000, T_12_C14=5730):
# activity = number of radioactive decays
expected_initial_activity_per_day = expected_initial_num_c14_atoms * np.log(2) / (T_12_C14 * days_per_year)
total_years_since_death = Delta_t + current_year - x
return expected_initial_activity_per_day * np.exp(-np.log(2) * total_years_since_death / T_12_C14)
# This is where we tell the fit to assume a poisson distribution for our data.
xy_fit = XYFit(
xy_data=[years_of_death, measured_c14_activity],
model_function=expected_activity_per_day,
cost_function=XYCostFunction_NegLogLikelihood(data_point_distribution='poisson')
)
# The half life of carbon-14 is only known with a precision of +-40 years
xy_fit.add_parameter_constraint(name='T_12_C14', value=5730, uncertainty=40)
# Perform the fit
# Note that since for a Poisson distribution the data error is directly linked to the mean.
# Because of this fits can be performed without explicitly adding data errors.
xy_fit.do_fit()
# Optional: print out a report on the fit results on the console
xy_fit.report()
# Optional: create a plot of the fit results using Plot
xy_plot = Plot(xy_fit)
xy_plot.plot(fit_info=True)
plt.show()
from kafe2 import XYContainer, Fit, Plot import matplotlib.pyplot as plt # Create an XYContainer object to hold the xy data for the fit. xy_data = XYContainer(x_data=[1.0, 2.0, 3.0, 4.0], y_data=[2.3, 4.2, 7.5, 9.4]) # x_data and y_data are combined depending on their order. # The above translates to the points (1.0, 2.3), (2.0, 4.2), and (4.0, 9.4). # Important: Specify uncertainties for the data. xy_data.add_error(axis='x', err_val=0.1) xy_data.add_error(axis='y', err_val=0.4) # Create an XYFit object from the xy data container. # By default, a linear function f=a*x+b will be used as the model function. line_fit = Fit(data=xy_data) # Perform the fit: Find values for a and b that minimize the # difference between the model function and the data. line_fit.do_fit() # This will throw an exception if no errors were specified. # Optional: Print out a report on the fit results on the console. line_fit.report() # Optional: Create a plot of the fit results using Plot. plot = Plot(fit_objects=line_fit) # Create a kafe2 plot object. plot.plot() # Do the plot. # Show the fit result. plt.show()
def exponential(x, A0=1, tau=1):
return A0 * np.exp(-x/tau)
# define the data as simple Python lists
x = [8.018943e-01, 1.839664e+00, 1.941974e+00, 1.276013e+00, 2.839654e+00, 3.488302e+00, 3.775855e+00, 4.555187e+00,
4.477186e+00, 5.376026e+00]
xerr = 3.000000e-01
y = [2.650644e-01, 1.472682e-01, 8.077234e-02, 1.850181e-01, 5.326301e-02, 1.984233e-02, 1.866309e-02, 1.230001e-02,
9.694612e-03, 2.412357e-03]
yerr = [1.060258e-01, 5.890727e-02, 3.230893e-02, 7.400725e-02, 2.130520e-02, 7.936930e-03, 7.465238e-03, 4.920005e-03,
3.877845e-03, 9.649427e-04]
# create a fit object from the data arrays
fit = XYFit(xy_data=[x, y], model_function=exponential)
fit.add_error(axis='x', err_val=xerr) # add the x-error to the fit
fit.add_error(axis='y', err_val=yerr) # add the y-errors to the fit
fit.do_fit() # perform the fit
fit.report(asymmetric_parameter_errors=True) # print a report with asymmetric uncertainties
# Optional: create a plot
plot = Plot(fit)
plot.plot(asymmetric_parameter_errors=True, ratio=True) # add the ratio data/function and asymmetric errors
# Optional: create the contours profiler
cpf = ContoursProfiler(fit)
cpf.plot_profiles_contours_matrix() # plot the contour profile matrix for all parameters
plt.show()
# Constrain model parameters to measurements
fit.add_parameter_constraint(name='l', value=l, uncertainty=delta_l)
fit.add_parameter_constraint(name='r', value=r, uncertainty=delta_r)
fit.add_parameter_constraint(name='y_0',
value=y_0,
uncertainty=delta_y_0,
relative=True)
# Because the model function is oscillating the fit needs to be initialized with near guesses for
# unconstrained parameters in order to converge
g_initial = 9.81 # initial guess for g
c_initial = 0.01 # initial guess for c
fit.set_parameter_values(g=g_initial, c=c_initial)
# Optional: Set the initial values of the remaining parameters to correspond to their constraint
# values (this may help some minimization algorithms converge)
fit.set_parameter_values(y_0=y_0, l=l, r=r)
# Perform the fit
fit.do_fit()
# Optional: Print out a report on the fit results on the console.
fit.report()
# Optional: plot the fit results
plot = Plot(fit)
plot.plot(fit_info=True)
plt.show()
# - sum of distances of principal planes
m_hsums = -m_fs * m_ds * m_ds / (f1 * f2)
# express inputs in terms of model values
m_hus = m_hsums - hgs
m_hgs = m_hsums - hus
return np.concatenate((m_fs, m_hus, m_hgs, m_ds))
f1f2Fit = Fit(iData, all_from_f1f2d)
f1f2Fit.model_label = 'all from f1, f2, d'
f1f2Fit.do_fit()
f1f2Fit.report()
f1f2Plot = Plot(f1f2Fit)
f1f2Plot.plot(residual=True)
print("\n*==*: Fit with PhyPraKit.phyFit/xFit\n")
# the same with PhyPraKit.phyFit.xFit
from PhyPraKit.phyFit import xFit
# define the physics model
# looks slightly different as data is passed to model as 1st argumen
def _from_f1f2d(data, f1=10, f2=20, d1=10., d2=10.):
# calulate f, hu, hg (and d)
#### data = iData.data
nm = len(data) // 4 # expect 4 concatenated arrays as input
p_in = data.reshape((4, nm))
fs = p_in[0] # Brennweiten
def k2hFit(fitf,
data,
bin_edges,
p0=None,
constraints=None,
fixPars=None,
limits=None,
use_GaussApprox=False,
plot=True,
plot_cor=False,
showplots=True,
plot_band=True,
plot_residual=False,
quiet=True,
axis_labels=['x', 'counts/bin = f(x, *par)'],
data_legend='Histogram Data',
model_legend='Model',
model_expression=None,
model_name=None,
model_band=r'$\pm 1 \sigma$',
fit_info=True,
asym_parerrs=True):
"""Wrapper function to fit a density distribution f(x, \*par)
to binned data (histogram) with class mnFit
The cost function is two times the negative log-likelihood of the
Poisson distribution, or - optionally - of the Gaussian approximation.
Uncertainties are determined from the model values in order to avoid biases
and to take account of empty bins of an histogram.
Args:
* fitf: model function to fit, arguments (float:x, float: \*args)
* data: the data to be histogrammed
* bin_edges: bin edges
fit options
* p0: array-like, initial guess of parameters
* constraints: (nested) list(s) [name or id, value, error]
* limits: (nested) list(s) [name or id, min, max]
* use_GaussApprox: Gaussian approximation instead of Poisson
output options
* plot: show data and model if True
* plot_cor: show profile likelihoods and confidence contours
* plot_band: plot uncertainty band around model function
* plot_residual: also plot residuals w.r.t. model
* showplots: show plots on screen
* quiet: suppress printout
* axis_labes: list of tow strings, axis labels
* data_legend: legend entry for data
* model_legend: legend entry for model
* plot: flag to switch off graphical output
* axis_labels: list of strings, axis labels x and y
* model_name: latex name for model function
* model_expression: latex expression for model function
* model_band: legend entry for model uncertainty band
* fit_info: controls display of fit results on figure
* asym_parerrs: show (asymmetric) errors from profile-likelihood scan
Returns:
* list: parameter names
* np-array of float: parameter values
* np-array of float: negative and positive parameter errors
* np-array: cor correlation matrix
* float: goodness-of-fit (equiv. chi2 for large number of entries/bin)
"""
# for fit with kafe2
from kafe2 import HistContainer, Fit, Plot, ContoursProfiler
from kafe2.fit.histogram import HistCostFunction_NegLogLikelihood
# create a data container from input
nbins = len(bin_edges) - 1
bin_range = (bin_edges[0], bin_edges[-1])
hdat = HistContainer(nbins, bin_range, bin_edges=bin_edges, fill_data=data)
# set up fit object
if use_GaussApprox:
print(
'Gauss Approx. for histogram data not yet implemented - exiting!')
exit(1)
## hfit = Fit(hdat, fitf,
## cost_function=CostFunction_GaussApproximation)
else:
hfit = Fit(hdat,
fitf,
cost_function=HistCostFunction_NegLogLikelihood(
data_point_distribution='poisson'))
# text for labeling
hfit.assign_model_function_latex_name(model_name)
hfit.assign_model_function_latex_expression(model_expression)
hfit.model_label = model_legend
# - provide text for labeling ...
hdat.label = data_legend
hdat.axis_labels = axis_labels
# initialize and run fit
if p0 is not None: hfit.set_all_parameter_values(p0)
if constraints is not None:
if not (isinstance(constraints[0], tuple)
or isinstance(constraints[0], list)):
constraints = (constraints, )
for c in constraints:
hfit.add_parameter_constraint(*c)
if limits is not None:
if isinstance(limits[1], list):
for l in limits:
hfit.limit_parameter(l[0], l[1], l[2])
else:
hfit.limit_parameter(limits[0], limits[1], limits[2])
hfit.do_fit()
# harvest results
# par, perr, cov, chi2 = fit.get_results() # for kafe vers. > 1.1.0
parn = np.array(hfit.parameter_names)
parv = np.array(hfit.parameter_values)
pare = np.array(hfit.parameter_errors)
cor = np.array(hfit.parameter_cor_mat)
gof = hfit.goodness_of_fit
if asym_parerrs:
parae = np.array(hfit.asymmetric_parameter_errors)
else:
parae = np.array(list(zip(-pare, pare)))
if not quiet:
hfit.report(asymmetric_parameter_errors=True)
if plot:
# plot data, uncertainties, model line and model uncertainties
kplot = Plot(hfit)
# set some 'nice' options
kplot.customize('data', 'marker', ['o'])
kplot.customize('data', 'markersize', [6])
kplot.customize('data', 'color', ['darkblue'])
## the following not (yet) defined for kafe2 Histogram Fit
## kplot.customize('model_line', 'color', ['darkorange'])
## kplot.customize('model_line', 'linestyle', ['--'])
## if not plot_band:
## kplot.customize('model_error_band', 'hide', [True])
## else:
## kplot.customize('model_error_band', 'color', ['green'])
## kplot.customize('model_error_band', 'label', [model_band])
## kplot.customize('model_error_band', 'alpha', [0.1])
# plot with defined options
kplot.plot(fit_info=fit_info,
residual=plot_residual,
asymmetric_parameter_errors=True)
if plot_cor:
cpf = ContoursProfiler(hfit)
cpf.plot_profiles_contours_matrix(
) # plot profile likelihood and contours
if showplots: plt.show()
return parv, parae, cor, gof
def kafe2go():
_parser = argparse.ArgumentParser(
description=
"Perform a fit with the kafe2 package driven by an input file.\n"
"Example files can be found at "
"https://github.com/dsavoiu/kafe2/tree/master/examples.\n"
"Further information on how to create input files is given at "
"https://kafe2.readthedocs.io/en/latest/parts/user_guide.html#kafe2go."
)
_parser.add_argument('filename',
type=str,
nargs='+',
help="Name(s) of fit input file(s).")
_parser.add_argument('-if',
'--inputformat',
type=str,
default='yaml',
help="File input format. The default format is yaml.")
_parser.add_argument(
'-s',
'--saveplot',
action='store_true',
help="Save plot(s) to file(s). The plot(s) will be saved in the current "
"working directory.")
_parser.add_argument(
'-pf',
'--plotformat',
type=str,
default='pdf',
help="Graphics output file format. E.g. pdf, png, svg, ... "
"The default format is pdf.")
_parser.add_argument('-n',
'--noplot',
action='store_true',
help="Don't show plots on screen.")
_parser.add_argument('-r',
'--ratio',
action='store_true',
help="Show data/model ratio below the main plot.")
_parser.add_argument(
'-a',
'--asymmetric',
action='store_true',
help="Show asymmetric parameter uncertainties when displaying the fit "
"information. This affects the fit report to the terminal as well as "
"the information box of the plot.")
_parser.add_argument('-c',
'--contours',
action='store_true',
help="Plot contours and profiles.")
_parser.add_argument(
'--grid',
type=str,
nargs=1,
default=[None],
help="Add a grid to the contour profiles. Available options are either "
"all, contours or profiles.")
_parser.add_argument(
'--noband',
action='store_true',
help="Don't draw the 1-sigma band around the fitted function. "
"This will only affect plots of XY-fits.")
_parser.add_argument('--noinfobox',
action='store_true',
help="Don't add the model info boxes to the plot(s).")
_parser.add_argument(
'--separate',
action='store_true',
help="Create a separate figure for each fit when plotting.")
_parser.add_argument(
'--noreport',
action='store_true',
help="Don't print fit report(s) to the terminal after fitting.")
if len(sys.argv) == 1: # print help message if no input given
_parser.print_help()
sys.exit(1)
_args = _parser.parse_args()
_filenames = _args.filename
_band = not _args.noband
_contours = _args.contours
_report = not _args.noreport
_infobox = not _args.noinfobox
_ratio = _args.ratio
_asymmetric = _args.asymmetric
_separate = _args.separate
_input_format = _args.inputformat
_plot_format = _args.plotformat
_save_plot = _args.saveplot
_show_plot = not _args.noplot
_grid = _args.grid[0]
_fits = []
for _fname in _filenames:
_fit = FitBase.from_file(_fname, file_format=_input_format)
_fit.do_fit()
if _report:
_fit.report(asymmetric_parameter_errors=_asymmetric)
_fits.append(_fit)
if not _band:
XYPlotAdapter.PLOT_SUBPLOT_TYPES.pop('model_error_band')
_plot = Plot(fit_objects=_fits, separate_figures=_separate)
_plot.plot(fit_info=_infobox,
asymmetric_parameter_errors=_asymmetric,
ratio=_ratio)
_basenames = [name.rsplit('.', 1)[0] for name in _filenames]
if _save_plot:
if len(_plot.figures) == 1:
names = ['_'.join(_basenames)]
else:
names = _basenames
for fig, name in zip(_plot.figures, names):
fig.savefig(fname='{}.{}'.format(name, _plot_format),
format=_plot_format)
if _contours:
for _fit, name in zip(_fits, _basenames):
_profiler = ContoursProfiler(_fit)
_profiler.plot_profiles_contours_matrix(show_grid_for=_grid)
if _save_plot:
for i, fig in enumerate(_profiler.figures):
fig.savefig(fname='{}_contours_{}.{}'.format(
name, i, _plot_format),
format=_plot_format)
if _show_plot:
plt.show()
# declare errors on U
auxiliary_fit.add_error(axis='x', err_val=sigU)
# declare errors on T
auxiliary_fit.add_error(axis='y', err_val=sigT)
# perform the auxiliary fit
auxiliary_fit.do_fit()
# (Optional) print the results
auxiliary_fit.report()
# (Optional) plot the results
auxiliary_plot = Plot(auxiliary_fit)
auxiliary_plot.plot(fit_info=True)
# Step 2: perform the main fit
main_fit = XYFit(xy_data=[U, I], model_function=I_U_model)
# declare errors on U
main_fit.add_error(axis='x', err_val=sigU)
# declare errors on I
main_fit.add_error(axis='y', err_val=sigI)
# constrain the parameters
main_fit.add_matrix_parameter_constraint(
names=auxiliary_fit.parameter_names,
values=auxiliary_fit.parameter_values,
matrix=auxiliary_fit.parameter_cov_mat,
matrix_type=