Python预测分词的实现

if __name__ == "__main__":
    MODEL_PATH = "123"
    HanLP.Config.CoreDictionaryPath = MODEL_PATH + ".txt"
    HanLP.Config.BiGramDictionaryPath = MODEL_PATH + ".ngram.txt"
    CoreDictionary = SafeJClass("com.hankcs.hanlp.dictionary.CoreDictionary")
    CoreBiGramTableDictionary = SafeJClass('com.hankcs.hanlp.dictionary.CoreBiGramTableDictionary')
    print(CoreDictionary.getTermFrequency("秦机"))
    print(CoreBiGramTableDictionary.getBiFrequency("秦机","的"))

[始##始]
[秦机]
[]
[和，和科]
[科技]
[技]
[末##末]

def build_Wordnet(sent, trie):
    jstring = JClass('java.lang.String')
    Vertex = JClass('com.hankcs.hanlp.seg.common.Vertex')
    WordNet = JClass('com.hankcs.hanlp.seg.common.WordNet')
    searcher = trie.getSearcher(JString(sent), 0)
    wordnet = WordNet(sent)
    while searcher.next():
        wordnet.add(searcher.begin + 1,
                    Vertex(sent[searcher.begin:searcher.begin + searcher.length], searcher.value, searcher.index))
    # 原子分词，保证图连通
    vertexes = wordnet.getVertexes()
    i = 0
    while i < len(vertexes):
        if len(vertexes[i]) == 0:  # 空白行
            j = i + 1
            for j in range(i + 1, len(vertexes) - 1):  # 寻找第一个非空行 j
                if len(vertexes[j]):
                    break
            wordnet.add(i, Vertex.newPunctuationInstance(sent[i - 1: j - 1]))  # 填充[i, j)之间的空白行
            i = j
        else:
            i += len(vertexes[i][-1].realWord)

    return wordnet


if __name__ == "__main__":
    MODEL_PATH = "123"
    HanLP.Config.CoreDictionaryPath = MODEL_PATH + ".txt"
    HanLP.Config.BiGramDictionaryPath = MODEL_PATH + ".ngram.txt"
    CoreDictionary = SafeJClass("com.hankcs.hanlp.dictionary.CoreDictionary")
    CoreBiGramTableDictionary = SafeJClass('com.hankcs.hanlp.dictionary.CoreBiGramTableDictionary')
    print(build_wordnet("秦机和科技", CoreDictionary.trie))

def viterbi(wordnet):
    nodes = wordnet.getVertexes()
    # 前向遍历
    for i in range(0, len(nodes) - 1):
        for node in nodes[i]:
            for to in nodes[i + len(node.realWord)]:
                # 根据距离公式计算节点距离，并维护最短路径上的前驱指针from
                to.updateFrom(node)
    # 后向回溯
    # 最短路径
    path = []
    # 从终点回溯
    f = nodes[len(nodes) - 1].getFirst()
    while f:
        path.insert(0, f)
        # 按前驱指针from回溯
        f = f.getFrom()
    return [v.realWord for v in path]

if __name__ == "__main__":
    MODEL_PATH = "123"
    corpus_path = r"E:\ProgramData\Anaconda3\Lib\site-packages\pyhanlp\static\data\test\icwb2-data\gold\msr_test_gold.utf8"
    train_model(corpus_path, MODEL_PATH)
    HanLP.Config.CoreDictionaryPath = MODEL_PATH + ".txt"
    HanLP.Config.BiGramDictionaryPath = MODEL_PATH + ".ngram.txt"
    CoreDictionary = SafeJClass("com.hankcs.hanlp.dictionary.CoreDictionary")
    CoreBiGramTableDictionary = SafeJClass('com.hankcs.hanlp.dictionary.CoreBiGramTableDictionary')
    ViterbiSegment = JClass('com.hankcs.hanlp.seg.Viterbi.ViterbiSegment')
    MODEL_PATH = "123"
    HanLP.Config.CoreDictionaryPath = MODEL_PATH + ".txt"
    HanLP.Config.BiGramDictionaryPath = MODEL_PATH + ".ngram.txt"
    sent = "秦机和科技"
    wordnet = build_wordnet(sent, CoreDictionary.trie)
    print(viterbi(wordnet))