INNER CODE UNIT · Python

H

AlexShakaev/backtesting_and_algotrading_options_with_Interactive_Brokers_API · utils/bocd.py:71

        H = self.H(np.array(range(t + 1)))

        # Evaluate the growth probabilities - shift the probabilities down and to
        # the right, scaled by the hazard function and the predictive
        # probabilities.
        self.R[1 : t + 2, t + 1] = self.R[0 : t + 1, t] * predprobs * (1 - H)

        # Evaluate the probability that there *was* a changepoint and we're
        # accumulating the mass back down at r = 0.
        self.R[0, t + 1] = np.sum(self.R[0    : t + 1, t] * predprobs * H)

        # Renormalize the run length probabilities for improved numerical
        # stability.
        self.R[:, t + 1] = self.R[:, t + 1] / np.sum(self.R[:, t + 1])
        
        # Update the parameter sets for each possible run length.
        self.observation_likelihood.update_theta(x)    
        

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…