FilesExpand file tree

 master

/

Markov.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

102 lines (73 loc) · 2.72 KB

 master

/

Markov.py

Copy path

Top

File metadata and controls

• Code
• Blame

102 lines (73 loc) · 2.72 KB

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

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

"""This module contains a code example related to

Think Python, 2nd Edition

by Allen Downey

http://thinkpython2.com

Copyright 2015 Allen Downey

License: http://creativecommons.org/licenses/by/4.0/

"""

from __future__ import print_function, division

import sys

import random

from markov import skip_gutenberg_header, shift

class Markov:

"""Encapsulates the statistical summary of a text."""

def __init__(self):

self.suffix_map = {} # map from prefixes to a list of suffixes

self.prefix = () # current tuple of words

def process_file(self, filename, order=2):

"""Reads a file and performs Markov analysis.

filename: string

order: integer number of words in the prefix

Returns: map from prefix to list of possible suffixes.

"""

fp = open(filename)

skip_gutenberg_header(fp)

for line in fp:

for word in line.rstrip().split():

self.process_word(word, order)

def process_word(self, word, order=2):

"""Processes each word.

word: string

order: integer

During the first few iterations, all we do is store up the words;

after that we start adding entries to the dictionary.

"""

if len(self.prefix) < order:

self.prefix += (word,)

return

try:

self.suffix_map[self.prefix].append(word)

except KeyError:

# if there is no entry for this prefix, make one

self.suffix_map[self.prefix] = [word]

self.prefix = shift(self.prefix, word)

def random_text(self, n=100):

"""Generates random wordsfrom the analyzed text.

Starts with a random prefix from the dictionary.

n: number of words to generate

"""

# choose a random prefix (not weighted by frequency)

start = random.choice(list(self.suffix_map.keys()))

for i in range(n):

suffixes = self.suffix_map.get(start, None)

if suffixes == None:

# if the prefix isn't in map, we got to the end of the

# original text, so we have to start again.

self.random_text(n-i)

return

# choose a random suffix

word = random.choice(suffixes)

print(word, end=' ')

start = shift(start, word)

def main(script, filename='emma.txt', n=100, order=2):

try:

n = int(n)

order = int(order)

except ValueError:

print('Usage: %d filename [# of words] [prefix length]' % script)

else:

markov = Markov()

markov.process_file(filename, order)

markov.random_text(n)

if __name__ == '__main__':

main(*sys.argv)