def runTest(self):
print "------------------ Test3 Populate from MP coeffs ---------"
fileIndex = 2
RandomAudioFilePath = file_names[fileIndex]
print 'Working on %s' % RandomAudioFilePath
sizes = [2**j for j in range(7, 15)]
segDuration = 5
nbAtom = 20
pySig = signals.Signal(op.join(audio_files_path, RandomAudioFilePath),
mono=True,
normalize=True)
segmentLength = ((segDuration * pySig.fs) / sizes[-1]) * sizes[-1]
nbSeg = floor(pySig.length / segmentLength)
# cropping
pySig.crop(0, segmentLength)
# create dictionary
pyDico = Dico(sizes)
approx, decay = mp.mp(pySig, pyDico, 20, nbAtom, pad=True, debug=0)
ppdb = XMDCTBDB('MPdb.db', load=False)
# ppdb.keyformat = None
ppdb.populate(approx, None, fileIndex)
nKeys = ppdb.get_stats()['ndata']
# compare the number of keys in the base to the number of atoms
print ppdb.get_stats()
self.assertEqual(nKeys, approx.atom_number)
# now try to recover the fileIndex knowing one of the atoms
Key = [
log(approx.atoms[0].length, 2),
approx.atoms[0].reduced_frequency * pySig.fs
]
T, fileI = ppdb.get(Key)
Treal = (float(approx.atoms[0].time_position) / float(pySig.fs))
print T, Treal
self.assertEqual(fileI[0], fileIndex)
Tpy = np.array(T)
self.assertTrue((np.abs(Tpy - Treal)).min() < 0.1)
# last check: what does a request for non-existing atom in base return?
T, fileI = ppdb.get((11, 120.0))
self.assertEqual(T, [])
self.assertEqual(fileI, [])
# now let's just retrieve the atoms from the base and see if they are
# the same
histograms = ppdb.retrieve(approx, None, offset=0)
# plt.figure()
# plt.imshow(histograms[0:10,:])
# plt.show()
del ppdb
def runTest(self):
ppdb = XMDCTBDB('tempdb.db',
load=False,
persistent=True,
time_max=500.0)
pySig = signals.LongSignal(op.join(audio_files_path, file_names[0]),
frame_duration=5,
mono=False,
Noverlap=0)
self.assertEqual(pySig.segment_size, 5.0 * pySig.fs)
max_nb_seg = 10
nb_atoms = 150
scales = SpreadDico([8192], penalty=0.1, mask_time=2, mask_freq=20)
# scales = Dico([8192])
for segIdx in range(min(max_nb_seg, pySig.n_seg)):
pySigLocal = pySig.get_sub_signal(segIdx,
1,
mono=True,
normalize=False,
channel=0,
pad=scales.get_pad())
print "MP on segment %d" % segIdx
# run the decomposition
approx, decay = mp.mp(pySigLocal, scales, 2, nb_atoms, pad=False)
print "Populating database with offset " + str(
segIdx * pySig.segment_size / pySig.fs)
ppdb.populate(approx,
None,
0,
offset=float((segIdx * pySig.segment_size) -
scales.get_pad()) / float(pySig.fs))
# ok we have a DB with only 1 file and different segments, now
nb_test_seg = 15
long_sig_test = signals.LongSignal(op.join(audio_files_path,
file_names[0]),
frame_duration=5,
mono=False,
Noverlap=0.5)
count = 0
for segIdx in range(min(nb_test_seg, long_sig_test.n_seg)):
pySigLocal = long_sig_test.get_sub_signal(segIdx,
1,
mono=True,
normalize=False,
channel=0,
pad=scales.get_pad())
# print "MP on segment %d" % segIdx
# run the decomposition
approx, decay = mp.mp(pySigLocal, scales, 2, nb_atoms, pad=False)
print approx.atom_number
histograms = ppdb.retrieve(approx, None, nbCandidates=1)
maxI = np.argmax(histograms[:])
OffsetI = maxI / 1
estFileI = maxI % 1
oracle_value = segIdx * long_sig_test.segment_size * (
1 - long_sig_test.overlap) / long_sig_test.fs
print "Seg %d Oracle: %1.1f - found %1.1f" % (segIdx, oracle_value,
OffsetI)
if abs(OffsetI - oracle_value) < 5:
count += 1
glob = float(count) / float(min(nb_test_seg, long_sig_test.n_seg))
print "Global Score of %1.3f" % glob
self.assertGreater(glob, 0.8)
def runTest(self):
''' time to test the fingerprinting scheme, create a base with 10 atoms for 8 songs, then
Construct the histograms and retrieve the fileIndex and time offset that is the most
plausible '''
print "------------------ Test5 DB construction ---------"
# # create the base : persistent
ppdb = XMDCTBDB('LargeMPdb.db', load=False, time_res=0.2)
print ppdb
padZ = 2 * sizes[-1]
# BUGFIX: pour le cas MP classique: certains atome reviennent : pas
# cool car paire key/data existe deja!
pyDico = LODico(sizes)
segDuration = 5
nbAtom = 50
sig = signals.LongSignal(op.join(audio_files_path, file_names[0]),
frame_size=sizes[-1],
mono=False,
Noverlap=0)
segmentLength = ((segDuration * sig.fs) / sizes[-1]) * sizes[-1]
max_seg_num = 5
# " run MP on a number of files"
nbFiles = 8
keycount = 0
for fileIndex in range(nbFiles):
RandomAudioFilePath = file_names[fileIndex]
print fileIndex, RandomAudioFilePath
if not (RandomAudioFilePath[-3:] == 'wav'):
continue
pySig = signals.LongSignal(op.join(audio_files_path,
RandomAudioFilePath),
frame_size=segmentLength,
mono=False,
Noverlap=0)
nbSeg = int(pySig.n_seg)
print 'Working on ' + str(RandomAudioFilePath) + ' with ' + str(
nbSeg) + ' segments'
for segIdx in range(min(nbSeg, max_seg_num)):
pySigLocal = pySig.get_sub_signal(segIdx,
1,
True,
True,
channel=0,
pad=padZ)
print "MP on segment %d" % segIdx
# run the decomposition
approx, decay = mp.mp(pySigLocal,
pyDico,
40,
nbAtom,
pad=False)
print "Populating database with offset " + str(
segIdx * segmentLength / sig.fs)
ppdb.populate(approx,
None,
fileIndex,
offset=float((segIdx * segmentLength) - padZ) /
sig.fs)
keycount += approx.atom_number
print ppdb.get_stats()