def setUp(self):
filename = "./Example/Example.xlsx"
set0 = data.read_sets_from_Excel(filename, 2, 0, 2)[0]
equation = Linear('Linear')
self.fs = SingleFitSession(set0, equation)
self.fs.fit()
self.fs.calculate_errors()
class TestRegressionLinearFit:
""" """
def setUp(self):
filename = "./Example/Example.xlsx"
set0 = data.read_sets_from_Excel(filename, 2, 0, 2)[0]
equation = Linear('Linear')
self.fs = SingleFitSession(set0, equation)
self.fs.fit()
self.fs.calculate_errors()
def test_degree_of_feedom(self):
assert self.fs.ndf == 8
def test_fitted_parameters(self):
np.testing.assert_almost_equal(self.fs.eq.pars[0], 3.666, 3)
np.testing.assert_almost_equal(self.fs.eq.pars[1], 5.204, 3)
def test_approximate_SD(self):
np.testing.assert_almost_equal(self.fs.aproxSD[0], 5.216871572087441,
9)
np.testing.assert_almost_equal(self.fs.aproxSD[1], 1.5729459621912463,
9)
def test_Smin(self):
np.testing.assert_almost_equal(self.fs.Smin, 395.8654399999999, 9)
def test_maxLogLik(self):
np.testing.assert_almost_equal(self.fs.Lmax, -32.581831644727835, 9)
def test_lik_limits(self):
self.fs.Llimits[0][0] is None
np.testing.assert_almost_equal(self.fs.Llimits[0][1],
16.001557751460275, 9)
np.testing.assert_almost_equal(self.fs.Llimits[1][0],
1.4776049950866297, 9)
np.testing.assert_almost_equal(self.fs.Llimits[1][1],
8.923310603763344, 9)
import os
import pylab as plt
from cvfit import data
from cvfit.equations import GHK as eqfit
from cvfit.fitting import SingleFitSession
from cvfit.data import XYDataSet
if __name__ == "__main__":
filename = "./Example/Example.xlsx"
set0 = data.read_sets_from_Excel(filename, 2, 0, 3)[0]
print("Loaded: " + os.path.split(str(filename))[1])
print (str(set0))
equation = eqfit('GHK', pars=[1.0, 150.0, 145.0, 5.0])
fsession = SingleFitSession(set0, equation)
fsession.fit()
fsession.calculate_errors()
print(fsession.string_estimates())
fsession.calculate_errors()
print(fsession.string_liklimits())
plX, plY = equation.calculate_plot(set0.X, equation.pars)
rlim = fsession.Llimits[0]
plX1, plY1 = equation.calculate_plot(set0.X, [rlim[0], 150.0, 145.0, 5.0])
plX2, plY2 = equation.calculate_plot(set0.X, [rlim[1], 150.0, 145.0, 5.0])
#avdat = XYDataSet()
#avdat.pool(set0.X, set0.Y, seto.S)
set0.average_pooled()
from cvfit.equations import Hill
from cvfit.data import XYDataSet
from cvfit.fitting import SingleFitSession
if __name__ == "__main__":
conc = np.array([0.1, 0.3, 1.0, 3.0, 10.0]) # , 30.0, 100.0
sd = 0.1
res = []
for i in range(100):
eq = Hill('Hill', pars=[0.0, 1.0, 1.0, 1.0])
resp = eq.calculate_random(conc, sd)
set = XYDataSet()
set.from_columns(conc, resp)
#print (set)
fs = SingleFitSession(set, eq)
fs.fit()
res.append(eq.pars)
results = np.array(res)
plt.subplot(231)
plt.hist(results[:, 1])
plt.xlabel('Ymax')
plt.ylabel('Number')
plt.xlim(0,2)
plt.subplot(232)
plt.hist(results[:, 2])
plt.xlabel('K')
plt.ylabel('Number')
plt.xlim(0,7)
def return_equation(self):
fits = MultipleFitSession(self.log)
for i in range(len(self.data)):
fits.add(
SingleFitSession(self.data[i], self.equations[i], self.log))
return fits
print('File {0} loaded'.format(fname))
print('{0:d} sets found.'.format(len(datasets)))
for i in range(len(datasets)):
print('\nSet #{0:d}:'.format(i + 1))
print(datasets[i])
# load equation
eqname = 'Hill'
if eqname == 'Hill' or eqname == 'Langmuir':
from cvfit.equations import Hill
# initiate fitting sessions, fit data and print results
fitsessions = MultipleFitSession()
for each in datasets:
equation = Hill(eqname)
fs = SingleFitSession(each, equation)
fs.fit()
fs.calculate_errors()
print('\n*************************************************')
print('\t' + fs.data.title + ' fit finished')
print(fs.string_estimates())
print(fs.string_liklimits())
fitsessions.add(fs)
print('\n*************************************************')
print('\tAverage of all fits:')
print(fitsessions.string_average_estimates())
# plot fitted
fplots = fitsessions.prepare_fplot('fit')
fig = plots.cvfit_plot(datasets,
fig=None,