python - 设置长度的python中的契约(Contract)词

Question

我目前正在尝试制作一种“单词混合器”:对于两个给定的单词和指定的所需长度，程序应返回这两个单词的“混合”。然而，它可以是任何类型的混合:它可以是第一个单词的前半部分与第二个单词的后半部分相结合，它可以是随机混合，任何东西。

例子:

鱼+蛋糕，长度5:fiske

狗 + 猫，长度 4:doga

后期+交叉，长度6:losste

我写了一个非常草率的代码(如下所示)，我很感激关于我做错了什么的一些提示(因为我的输出不是很好)以及是否有任何可以改进的地方。

from random import randint

name1 = "domingues"
name2 = "signorelli"
names = [name1,name2]
# a list of the desired lengths
lengths = [5,6,7]
mixes = []

def sizes(size):
    if size == 5:
        letters1 = randint(2,3)
    else:
        letters1 = randint(2,size-2)
    letters2 = size-letters1
    return letters1, letters2

def mix(letters1, letters2):
    n = randint(0,1)
    if n == 1:
        a = 0
    else:
        a = 1
    n1 = names[n]
    n2 = names[a]
    result = n1[0:letters2]+n2[-letters1::]
    return result

file = open("results.txt","w+")
for leng in lengths:
    file.write("RESULTS WITH "+str(leng)+" LETTERS \n")
    file.write("\n")
    for i in range(10):
        let1, let2 = sizes(leng)
        result = mix(let1,let2)
        while result == name1 or result == name2:
            result = mix(let2)
        if result not in mixes:
            mixes.append(result)
    for m in mixes:
        if m not in file:
            file.write(m+" \n")
            file.write("\n")
file.close()

(顺便说一句，感谢您花时间帮助我，非常感谢!)

Answer 1

一般来说，这是与人工智能相关的问题，因为我们隐含地想要获得可读的混合词。我只是编写了简单(而且很脏)的代码，试图从训练数据中捕获元音和辅音的序列，并根据捕获的规则构建混合词。

import random

consonants_pat = 'BCDFGHJKLMNPQRSTVXZ'.lower()
vowels_pat = 'aeiouy'

train_data = '''
                This our sentence to be used as a training dataset
                It should be longer
                '''

def build_mixer(train_data, num=3, mixed_len=(2, 4)):

    def _get_random_pattern(td, wlen):
        td_splitted = td.lower().split()
        while True:
            w = random.choice(list(filter(lambda x: len(x)>=wlen, td_splitted)))
            for j in range(len(w)-wlen):
                yield tuple(map(lambda x: 0 if x in vowels_pat else 1,  w[j:j + wlen]))

    def _select_vowels(w):
        return 


    def _mixer(w1, w2, num=num, mixed_len=mixed_len):
        allowed_letters = w1.lower().strip() + w2.lower().strip()
        ind = 1
        for j in range(num):
            wlen = random.choice(range(*mixed_len))
            pattern = _get_random_pattern(train_data, wlen)
            _aux = allowed_letters
            word = ''
            try:
                for pat in pattern:
                    for k in pat:
                        if k == 0:
                            choiced = random.choice(list(filter(lambda x: x in vowels_pat,  _aux)))
                            word += choiced
                        else:
                            choiced = random.choice(list(filter(lambda x: x in consonants_pat,  _aux)))
                            word += choiced
                        l = list(_aux)
                        l.remove(choiced)
                        _aux = ''.join(l)
                    ind += 1
                    yield word
                    if ind>num:
                        raise StopIteration
            except IndexError:
                continue

    return _mixer


mixer = build_mixer(train_data, num=6, mixed_len=(3,6))
for mixed in mixer('this', 'horse'):
    print(mixed)

我得到了以下的话:

het hetihs hetihssro sheo hsio tohir