def get_data_maxener(pSize=4,
keyInv=True,
downBeatInv=False,
bars=1,
partialbar=1,
offset=0):
"""
Util function for something we do all the time
Remove the empty patterns
INPUT:
- pSize (default: 16)
- keyInv (default: True)
- downBeatInv (default: False)
- bars (default: 2)
"""
import data_iterator
import feats_utils as FU
import numpy as np
import time
# start time
tstart = time.time()
# get maltab files
allfiles = FU.get_all_matfiles('.')
print len(allfiles), ' .mat files found'
# create and set iterator
data_iter = data_iterator.DataIterator()
data_iter.setMatfiles(allfiles) # set matfiles
if bars > 0:
data_iter.useBars(bars) # a pattern spans 'bars' bars
if partialbar < 1:
assert (bars == 1)
data_iter.usePartialBar(partialbar)
else:
data_iter.useBars(0) # important to set it to zero!
data_iter.setFeatsize(pSize) # a pattern is a num. of beats
if offset > 0:
data_iter.setOffset(offset)
data_iter.stopAfterOnePass(True) # stop after one full iteration
# get features
featsNorm = [
FU.normalize_pattern_maxenergy(p, pSize, keyInv,
downBeatInv).flatten()
for p in data_iter
]
print 'found ', len(featsNorm), ' patterns before removing empty ones'
# make it an array
featsNorm = np.array(featsNorm)
# remove empyt patterns
res = [np.sum(r) > 0 for r in featsNorm]
res2 = np.where(res)
featsNorm = featsNorm[res2]
# time?
print 'all patterns acquired and normalized in ' + str(time.time() -
tstart) + 'seconds'
print 'featsNorm.shape = ', featsNorm.shape
return featsNorm
def get_data_maxener(pSize=4,keyInv=True,downBeatInv=False,bars=1,partialbar=1,offset=0):
"""
Util function for something we do all the time
Remove the empty patterns
INPUT:
- pSize (default: 16)
- keyInv (default: True)
- downBeatInv (default: False)
- bars (default: 2)
"""
import data_iterator
import feats_utils as FU
import numpy as np
import time
# start time
tstart = time.time()
# get maltab files
allfiles = FU.get_all_matfiles('.')
print len(allfiles),' .mat files found'
# create and set iterator
data_iter = data_iterator.DataIterator()
data_iter.setMatfiles(allfiles) # set matfiles
if bars > 0:
data_iter.useBars( bars ) # a pattern spans 'bars' bars
if partialbar < 1:
assert(bars==1)
data_iter.usePartialBar( partialbar )
else:
data_iter.useBars(0) # important to set it to zero!
data_iter.setFeatsize( pSize ) # a pattern is a num. of beats
if offset > 0:
data_iter.setOffset(offset)
data_iter.stopAfterOnePass(True)# stop after one full iteration
# get features
featsNorm = [FU.normalize_pattern_maxenergy(p,pSize,keyInv,downBeatInv).flatten() for p in data_iter]
print 'found ', len(featsNorm),' patterns before removing empty ones'
# make it an array
featsNorm = np.array(featsNorm)
# remove empyt patterns
res = [np.sum(r) > 0 for r in featsNorm]
res2 = np.where(res)
featsNorm = featsNorm[res2]
# time?
print 'all patterns acquired and normalized in ' + str(time.time()-tstart) + 'seconds'
print 'featsNorm.shape = ',featsNorm.shape
return featsNorm
def get_all_barfeats():
"""
Returns all barfeats, we assume we're at the top of beatFeats dir
"""
import data_iterator
import feats_utils as FU
import numpy as np
import time
# get maltab files
allfiles = FU.get_all_matfiles('.')
# create and set iterator
data_iter = data_iterator.DataIterator()
data_iter.setMatfiles(allfiles) # set matfiles
data_iter.useBars(2) # a pattern spans two bars
data_iter.stopAfterOnePass(True) # stop after one full iteration
# get all feats
tstart = time.time()
featsNorm = [
FU.normalize_pattern(np.array(p), 16, True, True).flatten()
for p in data_iter
]
print 'all patterns acquired and normalized in ' + str(time.time() -
tstart) + 'seconds'
# some stats
print 'number of matfiles: ' + str(len(allfiles))
print 'number of patterns: ' + str(len(featsNorm))
# get one nice big matrix
featsNorm = np.array(featsNorm)
# and... we're done, let's launch the algo!
import scipy.cluster
import scipy.cluster.vq as SCVQ
# run a 20 iteration, looking for a codebook of size 10
tstart = time.time()
codebook, distortion = SCVQ.kmeans2(featsNorm, 10, 20, minit='points')
print 'kmeans performed in ' + str(time.time() - tstart) + 'seconds'
def get_all_barfeats():
"""
Returns all barfeats, we assume we're at the top of beatFeats dir
"""
import data_iterator
import feats_utils as FU
import numpy as np
import time
# get maltab files
allfiles = FU.get_all_matfiles('.')
# create and set iterator
data_iter = data_iterator.DataIterator()
data_iter.setMatfiles(allfiles) # set matfiles
data_iter.useBars(2) # a pattern spans two bars
data_iter.stopAfterOnePass(True)# stop after one full iteration
# get all feats
tstart = time.time()
featsNorm = [FU.normalize_pattern(np.array(p),16,True,True).flatten() for p in data_iter]
print 'all patterns acquired and normalized in ' + str(time.time()-tstart) + 'seconds'
# some stats
print 'number of matfiles: ' + str(len(allfiles))
print 'number of patterns: ' + str(len(featsNorm))
# get one nice big matrix
featsNorm = np.array(featsNorm)
# and... we're done, let's launch the algo!
import scipy.cluster
import scipy.cluster.vq as SCVQ
# run a 20 iteration, looking for a codebook of size 10
tstart = time.time()
codebook, distortion = SCVQ.kmeans2(featsNorm,10,20,minit='points')
print 'kmeans performed in ' + str(time.time()-tstart) + 'seconds'
x2 = min(x2, self.currfeats.shape[1])
return self.currfeats[:, startidx:x2]
def __iter__(self):
""" Returns itself, part of the python iterator interface """
return self
# debugging
if __name__ == '__main__':
print 'debugging iterator'
dt = DataIterator()
# find all files from current dir
allfiles = FU.get_all_matfiles('.')
# SET THE DATA ITERATOR
dt.setMatfiles(allfiles) # set the matlab files
dt.useBars(2) # work based on bars, 2 bars at a time
featsize = 4
dt.setFeatsize(featsize) # useless because we work on bars
dt.stopAfterOnePass(True) # stop after one pass, otherwise never stops
print dt.stats() # print basic stats
cnt = 0
maxIter = 500000
#bestPattern = np.random.rand(12,featsize)
#maxP = -1000
#minP = 1000
def __iter__(self):
""" Returns itself, part of the python iterator interface """
return self
# debugging
if __name__ == '__main__' :
print 'debugging iterator'
dt = DataIterator()
# find all files from current dir
allfiles = FU.get_all_matfiles('.')
# SET THE DATA ITERATOR
dt.setMatfiles(allfiles) # set the matlab files
dt.useBars(2) # work based on bars, 2 bars at a time
featsize = 4
dt.setFeatsize(featsize) # useless because we work on bars
dt.stopAfterOnePass(True)# stop after one pass, otherwise never stops
print dt.stats() # print basic stats
cnt = 0
maxIter = 500000
#bestPattern = np.random.rand(12,featsize)
#maxP = -1000
#minP = 1000
