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):
print "------------------ Test2 DB Handle ---------"
print 'Creating a hash table using Berkeley DB'
dbName = 'dummy.db'
ppbdb = XMDCTBDB(dbName, load=False, persistent=False)
ppbdb.keyformat = None
print 'populating with a key from MP'
F = 128
T = 125.0
FileIdx = 104
ppbdb.add(zip((F, ), (T, )), FileIdx)
estT, estFileI = ppbdb.get(F)
# refactoring, renvoi une liste de candidats
self.assertEqual(estFileI[0], FileIdx)
self.assertTrue(abs(estT[0] - T) < 0.01)
print ppbdb.get_stats()
print ppbdb
del ppbdb
def runTest(self):
''' what happens when the same key is used with a different value? we should be able to retrieve
a list of possible songs
'''
print "------------------ Test 7 handling uniqueness ---------"
dummyDb = XMDCTBDB('dummyDb.db', load=False, persistent=False)
dummyDb.keyformat = None
dummyDb.add(zip((440, 128, 440), (12.0, 16.0, 45.0)), 1)
dummyDb.add(zip((512, 320, 440), (54.0, 16.0, 11.0)), 2)
# print dummyDb.get_stats()
self.assertEqual(6, dummyDb.get_stats()['ndata'])
T, fileIndex = dummyDb.get(440)
print zip(T, fileIndex)
def runTest(self):
''' take the base previously constructed and retrieve the song index based on 10 atoms
'''
print "------------------ Test6 recognition ---------"
nbCandidates = 8
ppdb = XMDCTBDB('LargeMPdb.db', load=True)
print 'Large Db of ' + str(ppdb.get_stats()['nkeys']) + ' and ' + str(
ppdb.get_stats()['ndata'])
# Now take a song, decompose it and try to retrieve it
fileIndex = 6
RandomAudioFilePath = file_names[fileIndex]
print 'Working on ' + str(RandomAudioFilePath)
pySig = signals.Signal(op.join(audio_files_path, RandomAudioFilePath),
mono=True)
pyDico = LODico(sizes)
segDuration = 5
offsetDuration = 7
offset = offsetDuration * pySig.fs
nbAtom = 50
segmentLength = ((segDuration * pySig.fs) / sizes[-1]) * sizes[-1]
pySig.crop(offset, offset + segmentLength)
approx, decay = mp.mp(pySig, pyDico, 40, nbAtom, pad=True)
# plt.figure()
# approx.plotTF()
# plt.show()
res = map(ppdb.get, map(ppdb.kform, approx.atoms),
[(a.time_position - pyDico.get_pad()) / approx.fs
for a in approx.atoms])
#
#res = map(bdb.get, map(bdb.kform, approx.atoms))
histogram = np.zeros((600, nbCandidates))
for i in range(approx.atom_number):
print res[i]
histogram[res[i]] += 1
max1 = np.argmax(histogram[:])
Offset1 = max1 / nbCandidates
estFile1 = max1 % nbCandidates
# candidates , offsets = ppdb.retrieve(approx);
# print approx.atom_number
histograms = ppdb.retrieve(approx, None, offset=0, nbCandidates=8)
# print histograms , np.max(histograms) , np.argmax(histograms, axis=0) ,
# np.argmax(histograms, axis=1)
# plt.figure()
# plt.imshow(histograms[0:20,:],interpolation='nearest')
# plt.show()
maxI = np.argmax(histograms[:])
OffsetI = maxI / nbCandidates
estFileI = maxI % nbCandidates
print fileIndex, offsetDuration, estFileI, OffsetI, estFile1, Offset1, max1, maxI
import matplotlib.pyplot as plt
# plt.figure(figsize=(12,6))
# plt.subplot(121)
# plt.imshow(histograms,aspect='auto',interpolation='nearest')
# plt.subplot(122)
# plt.imshow(histogram,aspect='auto',interpolation='nearest')
## plt.imshow(histograms,aspect='auto',interpolation='nearest')
## plt.colorbar()
# plt.show()
print maxI, OffsetI, estFileI
self.assertEqual(histograms[OffsetI, estFileI], np.max(histograms))
self.assertEqual(fileIndex, estFileI)
self.assertTrue(abs(offsetDuration - OffsetI) <= 2.5)
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()