FilesExpand file tree

 master

/

python_markov_chain.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

34 lines (26 loc) · 794 Bytes

 master

/

python_markov_chain.py

Copy path

Top

File metadata and controls

• Code
• Blame

34 lines (26 loc) · 794 Bytes

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

# _*_ coding: utf-8 _*_

import nltk

import random

file = open('Text/Walden.txt', 'r')

walden = file.read()

walden = walden.split()

def makePairs(arr):

pairs = []

for i in range(len(arr)):

if i < len(arr) - 1:

temp = (arr[i], arr[i + 1])

pairs.append(temp)

return pairs

def generate(cfd, word='the', num=500):

for i in range(num):

# make an array with the words shown by proper count

arr = []

for j in cfd[word]:

for k in range(cfd[word][j]):

arr.append(j)

print(word, end=' ')

# choose the word randomly from the conditional distribution

word = arr[int((len(arr)) * random.random())]

pairs = makePairs(walden)

cfd = nltk.ConditionalFreqDist(pairs)

generate(cfd)