from collections import defaultdict
import re
import numpy as np

c=0

f = open('/Users/Half_Pint_Boy/Desktop/sentenses.txt', 'r')

for line in f:
    c = c + 1

word_positions = {}

with open('/Users/Half_Pint_Boy/Desktop/sentenses.txt', 'r') as f:
    index = 0
    for word in re.findall(r'[a-z]+', f.read().lower()):
        if word not in word_positions:
            word_positions[word] = index
            index += 1
print(word_positions)

matrix=np.zeros(c,index)