最近在一次面试中,我被给了以下问题:
编写一个可在命令行上作为Python运行的脚本
它应该在命令行上接收两个单词(或者如果您愿意,可以通过控制台查询用户来提供这两个单词)。
给定这两个单词: a. 确保它们长度相等 b. 确保它们都是英语词汇表中有效单词 (您下载的英语词汇表)中存在的单词。
如果是这样,请计算是否可以通过以下一系列步骤从第一个单词到达第二个单词 a. 您可以每次更改一个字母 b. 每次更改字母时,所得到的单词必须也存在于词典中 c. 您不能添加或删除字母
如果两个单词是可达的,则脚本应打印出作为单个、最短路径从一个单词到另一个单词的路径。
您可以使用 /usr/share/dict/words 作为您的单词词典。
我的解决方案是使用广度优先搜索来查找两个单词之间的最短路径。但显然这还不足以得到这份工作 :(
您们知道我可能做错了什么吗?非常感谢。
import collections
import functools
import re
def time_func(func):
import time
def wrapper(*args, **kwargs):
start = time.time()
res = func(*args, **kwargs)
timed = time.time() - start
setattr(wrapper, 'time_taken', timed)
return res
functools.update_wrapper(wrapper, func)
return wrapper
class OneLetterGame:
def __init__(self, dict_path):
self.dict_path = dict_path
self.words = set()
def run(self, start_word, end_word):
'''Runs the one letter game with the given start and end words.
'''
assert len(start_word) == len(end_word), \
'Start word and end word must of the same length.'
self.read_dict(len(start_word))
path = self.shortest_path(start_word, end_word)
if not path:
print 'There is no path between %s and %s (took %.2f sec.)' % (
start_word, end_word, find_shortest_path.time_taken)
else:
print 'The shortest path (found in %.2f sec.) is:\n=> %s' % (
self.shortest_path.time_taken, ' -- '.join(path))
def _bfs(self, start):
'''Implementation of breadth first search as a generator.
The portion of the graph to explore is given on demand using get_neighboors.
Care was taken so that a vertex / node is explored only once.
'''
queue = collections.deque([(None, start)])
inqueue = set([start])
while queue:
parent, node = queue.popleft()
yield parent, node
new = set(self.get_neighbours(node)) - inqueue
inqueue = inqueue | new
queue.extend([(node, child) for child in new])
@time_func
def shortest_path(self, start, end):
'''Returns the shortest path from start to end using bfs.
'''
assert start in self.words, 'Start word not in dictionnary.'
assert end in self.words, 'End word not in dictionnary.'
paths = {None: []}
for parent, child in self._bfs(start):
paths[child] = paths[parent] + [child]
if child == end:
return paths[child]
return None
def get_neighbours(self, word):
'''Gets every word one letter away from the a given word.
We do not keep these words in memory because bfs accesses
a given vertex only once.
'''
neighbours = []
p_word = ['^' + word[0:i] + '\w' + word[i+1:] + '$'
for i, w in enumerate(word)]
p_word = '|'.join(p_word)
for w in self.words:
if w != word and re.match(p_word, w, re.I|re.U):
neighbours += [w]
return neighbours
def read_dict(self, size):
'''Loads every word of a specific size from the dictionnary into memory.
'''
for l in open(self.dict_path):
l = l.decode('latin-1').strip().lower()
if len(l) == size:
self.words.add(l)
if __name__ == '__main__':
import sys
if len(sys.argv) not in [3, 4]:
print 'Usage: python one_letter_game.py start_word end_word'
else:
g = OneLetterGame(dict_path = '/usr/share/dict/words')
try:
g.run(*sys.argv[1:])
except AssertionError, e:
print e
感谢您提供的所有非常好的答案。我认为真正让我惊讶的是,每次考虑可能的单词邻居时,我都会迭代字典中的所有单词。相反,我可以像Duncan和Matt Anderson指出的那样使用倒排索引。 A*算法肯定也有帮助。非常感谢,现在我知道我做错了什么。
以下是使用倒排索引的相同代码:
import collections
import functools
import re
def time_func(func):
import time
def wrapper(*args, **kwargs):
start = time.time()
res = func(*args, **kwargs)
timed = time.time() - start
setattr(wrapper, 'time_taken', timed)
return res
functools.update_wrapper(wrapper, func)
return wrapper
class OneLetterGame:
def __init__(self, dict_path):
self.dict_path = dict_path
self.words = {}
def run(self, start_word, end_word):
'''Runs the one letter game with the given start and end words.
'''
assert len(start_word) == len(end_word), \
'Start word and end word must of the same length.'
self.read_dict(len(start_word))
path = self.shortest_path(start_word, end_word)
if not path:
print 'There is no path between %s and %s (took %.2f sec.)' % (
start_word, end_word, self.shortest_path.time_taken)
else:
print 'The shortest path (found in %.2f sec.) is:\n=> %s' % (
self.shortest_path.time_taken, ' -- '.join(path))
def _bfs(self, start):
'''Implementation of breadth first search as a generator.
The portion of the graph to explore is given on demand using get_neighboors.
Care was taken so that a vertex / node is explored only once.
'''
queue = collections.deque([(None, start)])
inqueue = set([start])
while queue:
parent, node = queue.popleft()
yield parent, node
new = set(self.get_neighbours(node)) - inqueue
inqueue = inqueue | new
queue.extend([(node, child) for child in new])
@time_func
def shortest_path(self, start, end):
'''Returns the shortest path from start to end using bfs.
'''
assert self.in_dictionnary(start), 'Start word not in dictionnary.'
assert self.in_dictionnary(end), 'End word not in dictionnary.'
paths = {None: []}
for parent, child in self._bfs(start):
paths[child] = paths[parent] + [child]
if child == end:
return paths[child]
return None
def in_dictionnary(self, word):
for s in self.get_steps(word):
if s in self.words:
return True
return False
def get_neighbours(self, word):
'''Gets every word one letter away from the a given word.
'''
for step in self.get_steps(word):
for neighbour in self.words[step]:
yield neighbour
def get_steps(self, word):
return (word[0:i] + '*' + word[i+1:]
for i, w in enumerate(word))
def read_dict(self, size):
'''Loads every word of a specific size from the dictionnary into an inverted index.
'''
for w in open(self.dict_path):
w = w.decode('latin-1').strip().lower()
if len(w) != size:
continue
for step in self.get_steps(w):
if step not in self.words:
self.words[step] = []
self.words[step].append(w)
if __name__ == '__main__':
import sys
if len(sys.argv) not in [3, 4]:
print 'Usage: python one_letter_game.py start_word end_word'
else:
g = OneLetterGame(dict_path = '/usr/share/dict/words')
try:
g.run(*sys.argv[1:])
except AssertionError, e:
print e
以下是时间比较:
% python one_letter_game_old.py happy hello 最短路径(在91.57秒内找到)为:
=> happy -- harpy -- harps -- harts -- halts -- halls -- hells -- hello% python one_letter_game.py happy hello 最短路径(在1.71秒内找到)为:
=> happy -- harpy -- harps -- harts -- halts -- halls -- hells -- hello