ekingery

# This script parses the RCV1 topics into a tree structure
# It can then be exported to json or dotfile format
# For more info on RCV1, see
# http://jmlr.csail.mit.edu/papers/volume5/lewis04a/lewis04a.pdf

import re
from treelib import Tree
from treelib.plugins import export_to_dot

# read topics from flat file into a list of lists