sinusoidal-regression.py

import numpy as np
from scipy.optimize import leastsq
import pylab as plt
import pandas as pd
from scipy.optimize import curve_fit

df = pd.read_csv('unemployment/unemployment_rate.csv')

x = df['index']
y = df['unemployment_rate']



def test(x, a, b):
    return a * np.sin(b * x)

# curve_fit() function takes the test-function
# x-data and y-data as argument and returns
# the coefficients a and b in param and
# the estimated covariance of param in param_cov
param, param_cov = curve_fit(test, x, y)

print("Sine funcion coefficients:")
print(param)
print("Covariance of coefficients:")
print(param_cov)

ans = (param[0] * (np.sin(param[1] * x)))

'''Below 4 lines can be un-commented for plotting results  
using matplotlib as shown in the first example. '''

plt.plot(x, y, 'o', color ='red', label ="data")
plt.plot(x, ans, '--', color ='blue', label ="optimized data")
plt.legend()
plt.show()



'''
guess_mean = np.mean(data)
guess_std = 3*np.std(data)/(2**0.5)/(2**0.5)
guess_phase = 0
guess_freq = 1
guess_amp = 1

# we'll use this to plot our first estimate. This might already be good enough for you
data_first_guess = guess_std*np.sin(t+guess_phase) + guess_mean

# Define the function to optimize, in this case, we want to minimize the difference
# between the actual data and our "guessed" parameters
optimize_func = lambda x: x[0]*np.sin(x[1]*t+x[2]) + x[3] - data
est_amp, est_freq, est_phase, est_mean = leastsq(optimize_func, [guess_amp, guess_freq, guess_phase, guess_mean])[0]

# recreate the fitted curve using the optimized parameters
data_fit = est_amp*np.sin(est_freq*t+est_phase) + est_mean

# recreate the fitted curve using the optimized parameters

fine_t = np.arange(0, max(t), 0.1)
data_fit=est_amp*np.sin(est_freq*fine_t+est_phase)+est_mean

plt.plot(t, data, '.')
plt.plot(t, data_first_guess, label='first guess')
plt.plot(fine_t, data_fit, label='after fitting')
plt.legend()
plt.show()
'''