components.py 文件源码

def create_component_sframe(g, baseid_name='page_id', layer_name='layer'):
    """Get component SFrame enriched with structural properties for each component"""

    columns = g.vertices.column_names()
    columns.remove('__id')
    columns.remove('component_id')

    # Append s to have unique column names (required by graphlab)
    gb_dict = {c + 's': gl.aggregate.CONCAT(c) for c in columns}
    gb_dict['nids'] = gl.aggregate.CONCAT('__id')
    gb_dict['node_count'] = gl.aggregate.COUNT('__id')
    comps = g.vertices.groupby('component_id', gb_dict)

    comps['width'] = comps.apply(lambda x: len(np.unique(x[layer_name + 's'])))
    comps['height'] = comps.apply(lambda x: len(np.unique(x[baseid_name + 's'])))

    edges = g.edges.groupby('component_id', {'src': gl.aggregate.CONCAT('__src_id'),
                                             'tgt': gl.aggregate.CONCAT('__dst_id')})
    comps = comps.join(edges, 'component_id')
    return comps.sort('node_count', False)