python - 收到错误 TypeError: unorderable types: NoneType() > float() at line which is in粗体下面的代码

Question

from nltk import word_tokenize, pos_tag
from nltk.corpus import wordnet as wn

def penn_to_wn(tag):
    """ Convert between a Penn Treebank tag to a simplified Wordnet tag """
    if tag.startswith('N'):
        return 'n'

    if tag.startswith('V'):
        return 'v'

    if tag.startswith('J'):
        return 'a'

    if tag.startswith('R'):
        return 'r'

    return None

def tagged_to_synset(word, tag):
    wn_tag = penn_to_wn(tag)
    if wn_tag is None:
        return None

    try:
        return wn.synsets(word, wn_tag)[0]
    except:
        return None

def sentence_similarity(sentence1, sentence2):
    """ compute the sentence similarity using Wordnet """
    # Tokenize and tag
    sentence1 = pos_tag(word_tokenize(sentence1))
    sentence2 = pos_tag(word_tokenize(sentence2))

    # Get the synsets for the tagged words
    synsets1 = [tagged_to_synset(*tagged_word) for tagged_word in sentence1]
    synsets2 = [tagged_to_synset(*tagged_word) for tagged_word in sentence2]

    # Filter out the Nones
    synsets1 = [ss for ss in synsets1 if ss]
    synsets2 = [ss for ss in synsets2 if ss]

    score, count = 0.0, 0

    # For each word in the first sentence
    for synset in synsets1:
        # Get the similarity value of the most similar word in the other sentence

            **best_score = max([(synset.path_similarity(ss)) for ss in synsets2])**


        # Check that the similarity could have been computed
    if best_score is not None:
            score += best_score
            count += 1

    # Average the values
    score /= count
    return score

if __name__ == '__main__':
 sentences = [
    'Password should not be less than 8 characters.',
    'The user should enter valid user name and password.',
    'User name should not have special characters.',
    'Datta passed out from IIT',
]

focus_sentence = 'The user should enter valid user name and password and password should have greater than or equal to 8 characters.'
for sentence in sentences:
    print(sentence_similarity(focus_sentence, sentence))

Answer 1

正如@Chris_Rands 所述，您的问题是该函数path_similarity()可以返回None然后max()调用失败。这是一个验证这种情况何时发生的问题。一种可能的解决方案是创建一个列表，simlist从. 如果为空，则跳过当前迭代，如果不是，则调用 max() 并继续其余的迭代。Nonepath_similarity()simlist

# For each word in the first sentence
for synset in synsets1:
    # Get the similarity value of the most similar word in the other sentence
    simlist = [synset.path_similarity(ss) for ss in synsets2 if synset.path_similarity(ss) is not None]
    if not simlist:
        continue;
    best_score = max(simlist)

    # Check that the similarity could have been computed
    score += best_score
    count += 1

if count == 0:
return 0

# Average the values
score /= count
return score

Answer 2

对于第一句话中的每个单词

    for synset in synsets1:
 Get the similarity value of the most similar word in the other sentence
    simlist = [synset.path_similarity(ss) for ss in synsets2 if synset.path_similarity(ss) is not None]
    if not simlist:
        continue;
    best_score = max(simlist)

检查是否可以计算相似度 score += best_score count += 1

 if count == 0:
    return 0

 Average the values
    score /= count
    return score

它正在工作