Markov model

markov.py

inputs = """red pepper pasta
garlic noodles
pizza
biryani
roti curry
flat rice noodles
hakka noodles
bhel puri
sushi
ramen"""

dishes = inputs.split("\n")

import random
sequence = []
for i in range(100):
  sequence.append(random.sample(dishes, 1)[0])
  
def markov(sequence):
    # Initialize an empty dictionary to store the transition probabilities
  transitions = {}

  # Initialize the current state to be the first event in the sequence
  current_state = sequence[0]

  # Loop through the sequence starting from the second event
  for event in sequence[1:]:

      # If the current state is not already in the dictionary, add it with an empty dictionary
      if current_state not in transitions:
          transitions[current_state] = {}

      # If the next event is not already in the dictionary for the current state, add it with count 1
      if event not in transitions[current_state]:
          transitions[current_state][event] = 1

      # If the next event is already in the dictionary for the current state, increment its count by 1
      else:
          transitions[current_state][event] += 1

      # Set the current state to be the next event
      current_state = event

  # Loop through the transition probabilities dictionary and normalize the counts to get probabilities
  for state in transitions:
      total_count = sum(transitions[state].values())
      for next_state in transitions[state]:
          transitions[state][next_state] /= total_count
          
  return transitions

likelihoods = markov(sequence)

prev_dish = likelihoods["garlic noodles"]

next_dish = max(prev_dish, key=prev_dish.get)
print(f"If you had garlic noodles, you will likely to have {next_dish} next")