Skip to main content

Symbolic Fitting; fitting as it should be.

Project description

Project Goals

The goal of this project is simple: to make fitting in Python sexy and pythonic. What does pythonic fitting look like? Well, there’s a simple test. If I can give you pieces of example code and don’t have to use any additional words to explain what it does, it’s pythonic.

from symfit import parameters, variables, Fit

xdata = [1.0, 2.0, 3.0, 4.0, 5.0]
ydata = [2.3, 3.3, 4.1, 5.5, 6.7]
yerr = [0.1, 0.1, 0.1, 0.1, 0.1]

a, b = parameters('a, b')
x, y = variables('x, y')
model = {y: a * x + b}

fit = Fit(model, x=xdata, y=ydata, sigma_y=yerr)
fit_result = fit.execute()

Cool right? So now that we have done a fit, how do can we use the results?

import matplotlib.pyplot as plt

y = model(x=xdata, **fit_result.params)
plt.plot(xdata, y)
plt.show()
Linear Fit

Need I say more? How about I let another code example do the talking?

from symfit import parameters, Maximize, Equality, GreaterThan

x, y = parameters('x, y')
model = 2 * x * y + 2 * x - x**2 - 2 * y**2
constraints = [
    Equality(x**3, y),
    GreaterThan(y, 1),
]

fit = Maximize(model, constraints=constraints)
fit_result = fit.execute()

“But what if I need to fit to an ODE?”

from symfit import variables, Parameter, ODEModel, Fit, D

tdata = np.array([10, 26, 44, 70, 120])
adata = 10e-4 * np.array([44, 34, 27, 20, 14])

a, b, t = variables('a, b, t')
k = Parameter(0.1)

model_dict = {
    D(a, t): - k * a**2,
    D(b, t): k * a**2,
}

ode_model = ODEModel(model_dict, initial={t: 0.0, a: 54 * 10e-4, b: 0.0})

fit = Fit(ode_model, t=tdata, a=adata, b=None)
fit_result = fit.execute()

For more fitting delight, check the docs at http://symfit.readthedocs.org.

Project details


Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page