在Python上基于Markov链生成伪随机文本的教程

import random
 
class Markov(object):
  
 def __init__(self, open_file):
  self.cache = {}
  self.open_file = open_file
  self.words = self.file_to_words()
  self.word_size = len(self.words)
  self.database()
   
  
 def file_to_words(self):
  self.open_file.seek(0)
  data = self.open_file.read()
  words = data.split()
  return words
   
  
 def triples(self):
  """ Generates triples from the given data string. So if our string were
    "What a lovely day", we'd generate (What, a, lovely) and then
    (a, lovely, day).
  """
   
  if len(self.words) < 3:
   return
   
  for i in range(len(self.words) - 2):
   yield (self.words[i], self.words[i+1], self.words[i+2])
    
 def database(self):
  for w1, w2, w3 in self.triples():
   key = (w1, w2)
   if key in self.cache:
    self.cache[key].append(w3)
   else:
    self.cache[key] = [w3]
     
 def generate_markov_text(self, size=25):
  seed = random.randint(0, self.word_size-3)
  seed_word, next_word = self.words[seed], self.words[seed+1]
  w1, w2 = seed_word, next_word
  gen_words = []
  for i in xrange(size):
   gen_words.append(w1)
   w1, w2 = w2, random.choice(self.cache[(w1, w2)])
  gen_words.append(w2)
  return ' '.join(gen_words)

为了看到一个示例结果，我们从古腾堡计划中拿了沃德豪斯的《My man jeeves》作为文本，示例结果如下。

In [1]: file_ = open('/home/shabda/jeeves.txt')
 
In [2]: import markovgen
 
In [3]: markov = markovgen.Markov(file_)
 
In [4]: markov.generate_markov_text()
Out[4]: 'Can you put a few years of your twin-brother Alfred,
who was apt to rally round a bit. I should strongly advocate
the blue with milk'

{('The', 'quick'): ['brown'],
 ('brown', 'fox'): ['jumps', 'who', 'who'],
 ('fox', 'jumps'): ['over'],
 ('fox', 'who'): ['is', 'is'],
 ('is', 'slow'): ['jumps'],
 ('jumps', 'over'): ['the', 'the'],
 ('over', 'the'): ['brown', 'brown'],
 ('quick', 'brown'): ['fox'],
 ('slow', 'jumps'): ['over'],
 ('the', 'brown'): ['fox', 'fox'],
 ('who', 'is'): ['slow', 'dead.']}