authorship.py

import numpy as np
def create_transition_matrix(text):
    transition_matrix = np.zeros((27, 27))
    
    for i in range(len(text)-1):
        current_char = text[i].lower()
        next_char = text[i+1].lower()
        
        if (current_char in state) & (next_char in state):
            current_char_id = char2id_dict[current_char]
            next_char_id = char2id_dict[next_char]
            transition_matrix[current_char_id][next_char_id] = transition_matrix[current_char_id][next_char_id] + 1
sum_of_each_row_all  = np.sum(transition_matrix, 1)
    
    for i in range (27):
            single_row_sum = sum_of_each_row_all[i]
            if (sum_of_each_row_all [i] == 0):
                single_row_sum = 1
            
            transition_matrix[ i,: ] =  transition_matrix[ i,: ] / single_row_sum
    return transition_matrix
TM_emma = create_transition_matrix(emma)
TM_caesar = create_transition_matrix(caesar)