Homepage

Lesson 11: Data and data fitting

Lesson 11: Data and data fitting 數據與數據擬合

Example Code

import scipy as sp

import matplotlib.pyplot as plt

xPoins=sp.arange(0, 6, 0.01)

sinDATA = sp.sin(xPoins)

NoiseSigma1= sp.random.randn(len(sinDATA))*0.1

sinDATAwithNoise = sinDATA+NoiseSigma1

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,sinDATAwithNoise,'b.')

plt.show()

z = sp.polyfit(xPoins, sinDATAwithNoise, 1)

fitFun = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

#print(z)

z = sp.polyfit(xPoins, sinDATAwithNoise, 2)

fitFun2 = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun2(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

z = sp.polyfit(xPoins, sinDATAwithNoise, 3)

fitFun3 = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun3(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

Lesson 11: Data and data fitting

Lesson 11: Data and data fitting 數據與數據擬合

Example Code

import scipy as sp

import matplotlib.pyplot as plt

xPoins=sp.arange(0, 6, 0.01)

sinDATA = sp.sin(xPoins)

NoiseSigma1= sp.random.randn(len(sinDATA))*0.1

sinDATAwithNoise = sinDATA+NoiseSigma1

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,sinDATAwithNoise,'b.')

plt.show()

z = sp.polyfit(xPoins, sinDATAwithNoise, 1)

fitFun = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

#print(z)

z = sp.polyfit(xPoins, sinDATAwithNoise, 2)

fitFun2 = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun2(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

z = sp.polyfit(xPoins, sinDATAwithNoise, 3)

fitFun3 = sp.poly1d(z)

plt.plot(xPoins,sinDATA,'r')

plt.plot(xPoins,fitFun3(xPoins),'#000000')

plt.plot(xPoins,sinDATAwithNoise,'b.', alpha=0.1)

plt.show()

Lesson 11: Data and data fitting 數據與數據擬合

Example Code

import scipy as sp

import matplotlib.pyplot as plt

from scipy.optimize import curve_fit

xPoins=sp.arange(0, 6,0.01)

sinDATA = sp.sin(xPoins)

SNratio=1

NoiseSigma1= sp.random.randn(len(sinDATA))*SNratio

sinDATAwithNoise = sinDATA+NoiseSigma1

plt.plot(xPoins,sinDATA,'r--')

plt.plot(xPoins,sinDATAwithNoise,'b.')

def fitfunc(x, a, b):

return a * sp.sin(b* x)

popt, pcov = curve_fit(fitfunc, xPoins, sinDATAwithNoise)

print(popt)

print(pcov)

plt.show()

plt.plot(xPoins, sinDATA,'r--')

plt.plot(xPoins, fitfunc(xPoins, *popt))

plt.show()