def build_tag_index(recent_media):
"""
Transforms recent_media into dictionaries of tags and edges
(input) [list of media]
(return) {'nodes':{}, 'edges':{}}
"""
nodes = {}
edges = {}
for media in recent_media[:10]:
try:
tags = media.tags
except:
tags = []
for tag in tags:
tname = tag.name.encode('ascii', 'ignore')
nodes[tname] = nodes.get(tname, 0) + 1
tags.remove(tag)
tnames = [t.name.encode('ascii', 'ignore') for t in tags]
if tname in edges:
edges[tname] += tnames
else:
print "{1} new edges for {0}".format(tname, len(tnames))
edges[tag.name] = tnames
for name, tags in edges.items():
edge_freq = vec_count(tags)
edges[name] = edge_freq
return {'nodes': nodes, 'edges': edges}
def tag_cooccurence(all_tags, min_count=3):
"""
creates a mapping of {tag: {neighbor: count}}
<all_tags> = list of tags
"""
tag_map = {}
tag_counts = get_tag_counts(all_tags, min_count)
for tags in all_tags:
for tag in list(set(tags)):
tgcpy = tags[:]
if tag in tag_counts:
tgcpy.remove(tag)
tag_map[tag] = tag_map.get(tag, []) + tgcpy
for tag, neighbors in tag_map.iteritems():
tag_map[tag] = vec_count(neighbors)
return {'counts': tag_counts, 'mapping': tag_map}
