train_doc2vec.py 文件源码

def train(input_jlgz, *, size, limit, min_df, max_features):
    print('FAST_VERSION', FAST_VERSION)
    documents = Documents(input_jlgz, limit=limit)
    model = Doc2Vec(
        documents=documents,
        size=size,
        min_count=min_df,
        max_vocab_size=max_features,
        workers=multiprocessing.cpu_count(),
        sample=1e-5,
    )
    return model