Python - Markov Chain State Transition Simulation

Simulation des Übergangs von drei Zuständen gemäß der Wahrscheinlichkeit der Matrix PROB_MATRIX (Beispiel: Die Wahrscheinlichkeit, von Zustand 0 nach 2 zu wechseln, beträgt PROB_MATRIX [0] [2] = 0,2)

MarkovChainSimulation1.py

import numpy as np

INIT_STATE = 0

PROB_MATRIX = [[0.7, 0.1, 0.2],
               [0.2, 0.1, 0.7],
               [0.7, 0.2, 0.1]]

def get_next_state(prob_array):
    normalization_factor = sum(prob_array)
    rand_num = np.random.rand(1)
    s = 0
    for i in range(len(prob_array)):
        s += prob_array[i]/normalization_factor
        if rand_num < s:
            return i
    return -1
    
if __name__ == "__main__":
    print("Initial State: " + str(INIT_STATE))
    cur_state = INIT_STATE
    for i in range(30):
        cur_state = get_next_state(PROB_MATRIX[cur_state])
        print("State" + str(i+1) + " : " + str(cur_state))

> python MarkovChainSimulation1.py
Initial State: 0
State1 : 1
State2 : 2
State3 : 0
State4 : 0
State5 : 0
State6 : 0
State7 : 2
State8 : 0
State9 : 0
State10 : 0
State11 : 1
State12 : 2
State13 : 0
State14 : 0
State15 : 2
State16 : 0
State17 : 0
State18 : 0
State19 : 0
State20 : 0
State21 : 0
State22 : 2
State23 : 2
State24 : 0
State25 : 0
State26 : 2
State27 : 0
State28 : 0
State29 : 0
State30 : 2