Python 最小二乘法多项式拟合曲线numpy.polyfit(),numpy.poly1d(),pylab

原文地址：http://wiki.klniu.com/zh-hans/Python/Modules/Scipy

import numpy as npfrom scipy.optimize import leastsqimport pylab as plx = np.arange(1, 17, 1)y = np.array([4.00, 6.40, 8.00, 8.80, 9.22, 9.50, 9.70, 9.86, 10.00, 10.20, 10.32, 10.42, 10.50, 10.55, 10.58, 10.60])#第一个拟合，自由度为3z1 = np.polyfit(x, y, 3)# 生成多项式对象p1 = np.poly1d(z1)print(z1)print(p1)# 第二个拟合，自由度为6z2 = np.polyfit(x, y, 6)# 生成多项式对象

p2 = np.poly1d(z2)print(z2)print(p2) # 绘制曲线 # 原曲线pl.plot(x, y, 'b^-', label='Origin Line')pl.plot(x, p1(x), 'gv--', label='Poly Fitting Line(deg=3)')pl.plot(x, p2(x), 'r*', label='Poly Fitting Line(deg=6)')pl.axis([0, 18, 0, 18])pl.legend()# Save figurepl.savefig('scipy02.png', dpi=96)输出结果：

[ 0.00624491 -0.20371114  2.18193147  2.57208791]3          20.006245 x - 0.2037 x + 2.182 x + 2.572[ -1.89843481e-06   1.90557772e-04  -6.80682074e-03   1.16832830e-01-1.04793542e+00   4.90253564e+00   1.76057692e-02]6             5            4          3         2-1.898e-06 x + 0.0001906 x - 0.006807 x + 0.1168 x - 1.048 x + 4.903 x + 0.01761

图像：