plot_out_of_core_classification.py 文件源码

def stream_reuters_documents(data_path=None):
    """Iterate over documents of the Reuters dataset.

    The Reuters archive will automatically be downloaded and uncompressed if
    the `data_path` directory does not exist.

    Documents are represented as dictionaries with 'body' (str),
    'title' (str), 'topics' (list(str)) keys.

    """

    DOWNLOAD_URL = ('http://archive.ics.uci.edu/ml/machine-learning-databases/'
                    'reuters21578-mld/reuters21578.tar.gz')
    ARCHIVE_FILENAME = 'reuters21578.tar.gz'

    if data_path is None:
        data_path = os.path.join(get_data_home(), "reuters")
    if not os.path.exists(data_path):
        """Download the dataset."""
        print("downloading dataset (once and for all) into %s" %
              data_path)
        os.mkdir(data_path)

        def progress(blocknum, bs, size):
            total_sz_mb = '%.2f MB' % (size / 1e6)
            current_sz_mb = '%.2f MB' % ((blocknum * bs) / 1e6)
            if _not_in_sphinx():
                print('\rdownloaded %s / %s' % (current_sz_mb, total_sz_mb),
                      end='')

        archive_path = os.path.join(data_path, ARCHIVE_FILENAME)
        urllib.request.urlretrieve(DOWNLOAD_URL, filename=archive_path,
                                   reporthook=progress)
        if _not_in_sphinx():
            print('\r', end='')
        print("untarring Reuters dataset...")
        tarfile.open(archive_path, 'r:gz').extractall(data_path)
        print("done.")

    parser = ReutersParser()
    for filename in glob(os.path.join(data_path, "*.sgm")):
        for doc in parser.parse(open(filename, 'rb')):
            yield doc


###############################################################################
# Main
# ----
#
# Create the vectorizer and limit the number of features to a reasonable
# maximum