iframe-proxy | Sunbelt Computer Software

This repository was archived by the owner on Jun 1, 2025. It is now read-only.

105 lines (75 loc) · 2.79 KB

"""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 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:
            if line.startswith('*** END OF THIS'): 
                break
            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='158-0.txt', n=100, order=2):
        n = int(n)
        order = int(order)
    except ValueError:
        print('Usage: %d filename [# of words] [prefix length]' % script)
        markov = Markov()
        markov.process_file(filename, order)
        markov.random_text(n)
if __name__ == '__main__':
    main(*sys.argv)

Sunbelt Computer Software

PL/B Language Development and Support

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Sunbelt Computer Software

PL/B Language Development and Support

FilesExpand file tree

markov2.py

Latest commit

History

markov2.py

File metadata and controls