def overlapPrevious(post):
check_tokenized(post)
overlaps = []
for p in post.thread.posts:
if p == post: break
overlaps.append(overlap(post.token_index, p.token_index))
return max(overlaps) if overlaps != [] else 0.0
def overlapDistance(post):
check_tokenized(post)
overlaps = []
for i,p in enumerate(post.thread.posts):
if p == post: break
overlaps.append(overlap(post.token_index, p.token_index))
return (i - overlaps.index(max(overlaps))) if overlaps != [] else 0
def mostSimilarTextRelative(post):
check_tokenized(post.thread)
position = post.position
if position == 0: return 0
def similarity(other_post):
return cosine_similarity(post.token_index, other_post.token_index)
most_similar = max(post.thread.posts[:position], key=similarity)
return position - most_similar.position
def onThreadTopic(post):
check_tokenized(post)
# Leading post is treated specially
if post == post.thread.posts[0]:
title_tokens = post.tokenizer(post.thread.title)
r = overlap(post.token_index, title_tokens)
else:
r = overlap(post.token_index, post.thread.posts[0].token_index)
return r