0x2620/pandora_cdosea
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

overview

Browse source
This commit is contained in:
j 2017-03-02 23:31:27 +00:00
commit d96c9ffa82
1 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
keyword_overview.py
View file

@ -58,7 +58,7 @@ for letter in sorted(KEYWORDS):
durations = {c['out'] - c['in'] for c in letter_clips} durations = {c['out'] - c['in'] for c in letter_clips}
duration = ox.format_duration(sum(durations) * 1000) duration = ox.format_duration(sum(durations) * 1000)
print('%s: %s clips with %s of %s tags total duration: %s' % (letter, len(letter_clips), len(letter_tags), len(KEYWORDS[letter]), duration)) print('%s: %s clips with %s of %s tags total duration: %s' % (letter, len(letter_clips), len(letter_tags), len(KEYWORDS[letter]), duration))
if len(letter_tags) != len(KEYWORDS[letter]): if set(KEYWORDS[letter]) - set(letter_tags):
print('missing tags:', ', '.join(set(KEYWORDS[letter]) - set(letter_tags))) print('missing tags:', ', '.join(set(KEYWORDS[letter]) - set(letter_tags)))
buckets = {} buckets = {}
@ -69,16 +69,21 @@ for letter in sorted(KEYWORDS):
buckets[i+1] = letter_clips[p:+p+size[i]] buckets[i+1] = letter_clips[p:+p+size[i]]
p += size[i] p += size[i]
for size in buckets: for size in buckets:
bucket_tags = {c['value'] for c in buckets[size]} bucket_tags = Counter([c['value'] for c in buckets[size]])
durations = {c['out'] - c['in'] for c in buckets[size]} durations = {c['out'] - c['in'] for c in buckets[size]}
dmin = min(durations) dmin = min(durations)
dmax = max(durations) dmax = max(durations)
print(size) print(size)
print('\t', len(buckets[size]), 'clips', len(bucket_tags), 'tags', 'durations from %.3f to %.3f' % (dmin, dmax)) print('\t', len(buckets[size]), 'clips', len(bucket_tags), 'tags', 'durations from %.3f to %.3f' % (dmin, dmax))
if set(letter_tags) - bucket_tags: if set(letter_tags) - set(bucket_tags):
print('\t', 'used tags:', ', '.join(bucket_tags)) used_tags = [
print('\t', 'missing tags:', ', '.join(set(letter_tags) - bucket_tags)) '%s (%d)' % (t, bucket_tags[t])
for t in sorted(bucket_tags, key=lambda t: (-bucket_tags[t],t))
]
print('\t', 'used tags:', ', '.join(used_tags))
if set(letter_tags) - set(bucket_tags):
print('\t', 'missing tags:', ', '.join(sorted(set(letter_tags) - set(bucket_tags))))
for tag in sorted(known_tags): for tag in sorted(known_tags):