def main_hopf_1(): dx_dt = abc.dx_dt # simplest system with hopf bifurcation orig_theta = [2.2] orig_ds = abc.generate_dataset(dx_dt, orig_theta) #orig_ds = abc.add_gaussian_noise_full(orig_ds) param_range = np.arange(1, 4, 0.05) likelihood_vals = [] for th in param_range: sim_ds = abc.generate_dataset(dx_dt, [th]) likelihood_vals.append(log_likelihood(sim_ds, orig_ds)) print "max: ", max(likelihood_vals) print "max val: ", param_range[likelihood_vals.index(max(likelihood_vals))] plt.plot(param_range, likelihood_vals) plt.show()
def main_lv(): lv = abc.lv orig_theta = [1.] t = np.linspace(0, 90, 1000) orig_ds = abc.generate_dataset(lv, orig_theta) param_range = np.linspace(0, 4, 100) likelihood_vals = [] for th in param_range: sim_ds = abc.generate_dataset(lv, [th]) likelihood_vals.append(log_likelihood(sim_ds, orig_ds)) plt.plot(param_range, likelihood_vals) #plt.figure() #plt.plot(t, orig_ds) plt.show()
def lv_test(): theta = [1, 1] ds = abc.generate_dataset(lv, theta) ds = abc.add_gaussian_noise(ds) population = abc.smc(lv, ds, [30.0, 16.0, 6.0, 5.0, 4.3]) sys.exit(0)
def lv_test(): theta = [1,1] ds = abc.generate_dataset(lv, theta) ds = abc.add_gaussian_noise(ds) population = abc.smc(lv, ds, [30.0, 16.0, 6.0, 5.0, 4.3]) sys.exit(0)