示例#1
0
 def __init__(self, n_left=2, n_right=2):
     self.chunker = BILOUChunkEncoder()
     self.n_left = n_left
     self.n_right = n_right
示例#2
0
                        default=1,
                        type=int,
                        metavar='n',
                        dest='n_jobs',
                        help='Set num threads to use (default: 1)')
    args = parser.parse_args()

    if len(sys.argv) == 1:
        parser.print_help()
        sys.exit(1)

    # Determine ltfs to process.
    if not args.scpf is None:
        with open(args.scpf, 'r') as f:
            args.ltfs = [l.strip() for l in f.readlines()]

    # Initialize chunker, aligner, and encoder.
    chunker = BILOUChunkEncoder()
    aligner = Aligner()
    encf = os.path.join(args.model_dir, 'tagger.enc')
    with open(encf, 'r') as f:
        enc = cPickle.load(f)

    # Perform tagging in parallel, dumping results to args.tagged_dir.
    n_jobs = min(len(args.ltfs), args.n_jobs)
    modelf = os.path.join(args.model_dir, 'tagger.crf')
    f = delayed(tag_file)
    Parallel(n_jobs=n_jobs, verbose=0)(
        f(ltf, aligner, enc, chunker, modelf, args.tagged_dir, args.ext)
        for ltf in args.ltfs)