def calculateRequiredNCDs(featureFileDict, method, dimension, timeDelay,
neighbourhoodSize, downSampleFactor, sequenceLength,
featureName):
requiredNCDs = []
featureFileIds = featureFileDict.keys()
numFeatureFiles = len(featureFileIds)
print 'Creating list of required NCDs...'
for f1 in np.arange(numFeatureFiles - 1):
featureFilePath1 = featureFileDict[featureFileIds[f1]].filePath
pc1Id = featureFileDict[featureFileIds[f1]].pieceId
pc1pfId = featureFileIds[f1]
for f2 in np.arange(f1, numFeatureFiles):
featureFilePath2 = featureFileDict[featureFileIds[f2]].filePath
pc2Id = featureFileDict[featureFileIds[f2]].pieceId
pc2pfId = featureFileIds[f2]
ncdProps = NCDprops(pc1Id, pc1pfId, pc2Id, pc2pfId,
method, dimension, timeDelay,
neighbourhoodSize, downSampleFactor, sequenceLength,
featureName, featureFilePath1, featureFilePath2)
requiredNCDs.append(ncdProps)
print 'Number of NCD files required for combination: %i' % len(requiredNCDs)
return requiredNCDs
def createNCDfiles(existingNCDs,
processPool,
featureName,
downSampleFactor,
timeDelay,
dimension,
method,
neighbourhoodSize,
numFilesPerFolder,
sequenceLength,
weightMatrix=None,
biases=None,
featureOffset=0.0,
featureScaling=1.0):
'''
Inputs:
:existingNCDs: a list of existing NCD files in order to avoid duplication
:processPool: a pool of multiprocessing processes to use for running the script
:featureName: the name of the feature e.g 'chroma', 'mfcc'
:downSampleFactor: the factor to use in downsampling the original signals before creating CRPs
:timeDelay: the time delay to use in creating the CRPs
:method: the method to use in creating the CRPs
:neighbourhoodSize: the neighbourhood size to use in creating the CRPs
:numFilesPerFolder: the number of performances of each piece to use - set to None to use all performances
:sequenceLength: fixed sequence length to normalise CRPs to (use 'var' for variable length)
:weightMatrix: a matrix of weights (inputFeatureLength rows x outputFeatureLength columns)
to transform the input feature files with before calculating the CRPs
'''
mazurkasPath = FeatureFileProps.rootPath[featureName]
mazurkaIds = getFolderNames(mazurkasPath, True)[:20]
if existingNCDs is not None:
existingNCDs = set(existingNCDs) # makes checking faster
# Get performances from folders
featureFileDict = getFeatureFileDictAllFolders(mazurkasPath, mazurkaIds,
featureName,
numFilesPerFolder)
# Create list of required NCD files
requiredNCDs = []
featureFileIds = featureFileDict.keys()
numFeatureFiles = len(featureFileIds)
print 'Checking for existing NCD files...'
for f1 in np.arange(numFeatureFiles - 1):
featureFilePath1 = featureFileDict[featureFileIds[f1]].filePath
pc1Id = featureFileDict[featureFileIds[f1]].pieceId
pc1pfId = featureFileIds[f1]
for f2 in np.arange(f1, numFeatureFiles):
featureFilePath2 = featureFileDict[featureFileIds[f2]].filePath
pc2Id = featureFileDict[featureFileIds[f2]].pieceId
pc2pfId = featureFileIds[f2]
ncdProps = NCDprops(pc1Id, pc1pfId, pc2Id, pc2pfId, method,
dimension, timeDelay, neighbourhoodSize,
downSampleFactor, sequenceLength, featureName,
featureFilePath1, featureFilePath2)
if not NCDexists(ncdProps.getFileName(),
existingNCDs=existingNCDs):
requiredNCDs.append(ncdProps)
print 'Number of NCD files missing for combination: %i' % len(requiredNCDs)
# Create Required CRPs for NCD files
if len(requiredNCDs) > 0:
# Create CRP files and save to the CRPs folder
print 'Calculating # of required CRP files'
requiredCRPs = []
sourceCRPs = []
for requiredNCD in requiredNCDs:
crp1 = requiredNCD.getCRP1()
crp2 = requiredNCD.getCRP2()
sourceCRPs.append(crp1)
sourceCRPs.append(crp2)
if not crp1.hasExistingFile():
requiredCRPs.append(crp1)
if not crp2.hasExistingFile():
requiredCRPs.append(crp2)
requiredCRPs = CRPprops.uniqueCRPprops(requiredCRPs)
sourceCRPs = CRPprops.uniqueCRPprops(sourceCRPs)
numRequiredCRPs = len(requiredCRPs)
print 'Creating %i required CRP files' % numRequiredCRPs
if numRequiredCRPs > 0:
CRPargList = []
for crp in requiredCRPs:
crp.weightMatrix = weightMatrix
crp.biases = biases
crp.featureOffset = featureOffset
crp.featureScaling = featureScaling
CRPargList.append((crp, ))
processPool.map(multi_createCRPfile, CRPargList)
# Load CRP files into memory
print 'Loading %i CRP files' % len(sourceCRPs)
CRPfiles = loadCRPfiles(sourceCRPs)
# Create NCD files
numNCDs = len(requiredNCDs)
print 'Creating %i NCD files' % numNCDs
NCDindex = 0
while NCDindex < numNCDs:
NCDargList = []
for iNCD in np.arange(NCDindex, min(NCDindex + 100, numNCDs)):
requiredNCD = requiredNCDs[iNCD]
NCDfn = requiredNCD.getFileName()
CRPtuple1 = requiredNCD.getCRP1().toTuple(False)
CRPtuple2 = requiredNCD.getCRP2().toTuple(False)
try:
NCDargList.append(
(NCDfn, CRPfiles[CRPtuple1], CRPfiles[CRPtuple2]))
except:
pass
if NCDargList:
processPool.map(multi_createNCDfile, NCDargList)
NCDindex += 100
print '\r%i...' % NCDindex,
# Delete CRP files
print 'Deleting CRP files'
for CRPfilename in getFileNames(CRPpath, '.npy', True):
try:
os.remove(CRPpath + CRPfilename)
except:
pass
def multi_createNCDfile(args):
'''
Run wrapper for createNCDfile()
'''
return NCDprops.createNCDfile(*args)