【python】scipy.optimize.curve_fit

Function

Fit a function using nonlinear least squares

Features

Official document

input

parameter	Value
f	function, it must take xdata as the first input parameter
xdata	Measured Independent Data
ydata	The associated data, nominally the result of f(xdata,…)

output

output	Value
popt	The optimal value, that is, the value output by the fitting function according to x
pcov	covariance matrix of popt
infodict	a dictionary of optional outputs with the keys (returned only if full_output is True)
message	Related information (returned only if full_output is True)
ier	An integer flag. If it is equal to 1, 2, 3 or 4, the solution was found. Otherwise, the solution was not found. In either case, the optional output variable mesg gives more information. (returned only if full_output is True)

example

official example

import numpy as np
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit

def official_demo_func(x, a, b, c):
    return a * np.exp(-b * x) + c


def official_demo():
    x = np.linspace(0, 4, 50)
    y = official_demo_func(x, 2.5, 1.3, 0.5)
    rng = np.random.default_rng()
    y_noise = 0.2 * rng.normal(size=x.size)
    ydata = y + y_noise
    plt.plot(x, ydata, 'b-', label='data')

    popt, pcov = curve_fit(official_demo_func, x, ydata)
    print(popt)

    plt.plot(x, official_demo_func(x, *popt), 'g--',
             label='fit: a=%5.3f, b=%5.3f, c=%5.3f' % tuple(popt))

    plt.xlabel('x')
    plt.ylabel('y')
    plt.legend()
    plt.show()


official_demo()

The output fitting result is

[2.61499295 1.35033395 0.51541771]

It is still very close to the input value [2.5, 1.3, 0.5].