reuters_classifier.py 文件源码

def collection_stats():
    # list of documents
    documents_stat = reuters.fileids()
    print(str(len(documents)) + " documents")

    train_docs_stat = list(filter(lambda doc: doc.startswith("train"), documents_stat))
    print(str(len(train_docs_stat)) + " total training documents")

    test_docs_stat = list(filter(lambda doc: doc.startswith("test"), documents_stat))
    print(str(len(test_docs_stat) + " total test documents"))

    # list of categories
    categories = reuters.categories()
    print(str(len(categories)) + " categories")

    # get the documents in a category
    category_docs = reuters.fileids("acq")

    # words for a document
    document_id = category_docs[0]
    document_words = reuters.words(category_docs[0])
    print(document_words)

    # print the raw document
    print(reuters.raw(document_id))