def test_tuple_array_dump(self):
t = (1, 2, 3)
expect = pbjson.dumps(list(t))
# Default is True
sio = BytesIO()
pbjson.dump(t, sio)
self.assertEqual(expect, sio.getvalue())
# Ensure that the "default" does not get called
sio = BytesIO()
pbjson.dump(t, sio, convert=repr)
self.assertEqual(expect, sio.getvalue())
def main():
parser = argparse.ArgumentParser(
description='Convert between pbjson and json',
epilog='If converting a PBJSON file with binary elements, you may need to use `--repr` since JSON cannot handle binary data.')
parser.add_argument('-r', '--repr', action='store_true', help='instead of converting to JSON, just output the `repr` of the object')
parser.add_argument('-p', '--pretty', action='store_true', help='make it nice for humans')
if yaml is not None:
parser.add_argument('-y', '--yaml', action='store_true', help='input or output is YAML instead of JSON')
parser.add_argument('infile', nargs='?', type=argparse.FileType('rb'), default=sys.stdin, help='filename to convert from or to pbjson (default: stdin)')
parser.add_argument('outfile', nargs='?', type=argparse.FileType('wb'), default=sys.stdout, help='filename to write the converted file to (default: stdout)')
args = parser.parse_args()
contents = args.infile.read()
try:
text = contents.decode()
except Exception:
text = None
if text:
if yaml is not None and args.yaml:
try:
obj = yaml.load(text, Loader=Loader)
except ValueError:
raise SystemExit(sys.exc_info()[1])
else:
try:
obj = json.loads(text, object_pairs_hook=OrderedDict)
except ValueError:
if yaml is None:
raise SystemExit(sys.exc_info()[1])
try:
obj = yaml.load(text, Loader=Loader)
except ValueError:
raise SystemExit(sys.exc_info()[1])
pbjson.dump(obj, args.outfile)
else:
try:
obj = pbjson.loads(contents, document_class=OrderedDict)
except ValueError:
raise SystemExit(sys.exc_info()[1])
if yaml is not None and args.yaml:
j = yaml.dump(obj, Dumper=Dumper)
elif args.repr:
j = pprint.pformat(obj, indent=1) if args.pretty else repr(obj)
else:
kw = {'ensure_ascii': False} if does_unicode else {}
j = json.dumps(obj, sort_keys=True, indent=4 if args.pretty else None, **kw)
if args.outfile == sys.stdout:
j += '\n'
else:
j = j.encode()
args.outfile.write(j)
frequent_itemsets['length'] = frequent_itemsets['itemsets'].apply(lambda x: len(x))
k_frequent_itemsets = frequent_itemsets[frequent_itemsets['length'] == max_k]
# create hash table from frequent itemsets
if verbose:
print('Creating hash table')
track_hash = defaultdict(set)
itemset_list = k_frequent_itemsets['itemsets'].to_list()
print('Num itemsets %d' % len(itemset_list))
coverage = set()
for fr_set in itemset_list:
for item in fr_set:
track_hash[item] = track_hash[item].union(fr_set) # each track points to the set of the union of itemsets the track is in
coverage |= fr_set
print('Song Coverage: {:.5f}%'.format(len(coverage) / unique_songs * 100))
# dump hash table as 'model'
if verbose:
print('Writing model')
f = open(config['model']['FrequentItemsetsModel'], 'wb+')
f.truncate(0)
pbjson.dump(track_hash, f)
f.close()
# we are done
if verbose:
print('Done')
