ir_eval.py 文件源码

def is_embedded(sentence, embedding, analyzer):
    """
    >>> embedding = ["a", "b", "c"]
    >>> queries =  ["a b c", "a", "b", "c", "a b c d", "d", "a b c"  ]
    >>> analyzer = lambda x: x.split()
    >>> [query for query in queries if is_embedded(query, embedding, analyzer)]
    ['a b c', 'a', 'b', 'c', 'a b c']
    >>> analyzer = CountVectorizer().build_analyzer()
    >>> [query for query in queries if is_embedded(query, embedding, analyzer)]
    ['a b c', 'a', 'b', 'c', 'a b c']
    """
    for word in analyzer(sentence):
        if word not in embedding:
            print("Dropping:", sentence, file=sys.stderr)
            return False

    return True