quantopian curve fitting log

start = '2008-01-01'
end = '2018-01-01'
price = get_pricing('XOM', fields='price', start_date=start, end_date=end)
price.plot()

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

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

#log(0) = -infinity, so x starts at 1
x = np.linspace(1,1+len(price),len(price))

coefficients, pcov = curve_fit(logfit, x, price.values)

print coefficients
print pcov

y = logfit(x, *coefficients)

f = pd.Series(y, index=price.index, name='log fit')

pd.concat([price, f], axis=1).plot()

#a, b, c value
[  7.16530113  60.29273375  -7.21702861]

[[  3.37758673e-02   4.82782411e+04  -5.73784558e+03]
 [  4.82782231e+04   3.17949296e+14  -3.77856886e+13]
 [ -5.73784353e+03  -3.77856886e+13   4.49052185e+12]]

fit exxon mobile performance with log function

try fit for apple

try fit for deutsche bank

reference:
http://chuanshuoge2.blogspot.com/2019/12/python-curve-fitting.html