def get_data(**kwargs):
''' Returns data from audio tracks
'''
if os.path.exists(DATAFILE_MAT):
Data = GroupXData.LoadFromFile(DATAFILE_MAT)
else:
obs = []
doc_range = [0]
count = 0
with h5py.File('../tracks.h5', 'r') as tracks:
for track, grp in ProgressBar(tracks.items()):
if 'gfccs' not in grp:
continue
data = grp['gfccs']
count += data.shape[0]
doc_range.append(count)
obs.append(data.value.astype(np.float64))
X = np.vstack(obs)
Data = GroupXData(X=X, doc_range=doc_range)
Data.save_to_mat(DATAFILE_MAT)
Data.name = 'AudioCorpus'
Data.summary = 'Audio Corpus. obs=10.5M docs=559'
return Data
def loadDataForBatch(self, batchID):
''' Load the data assigned to a particular batch
Returns
-------
Dchunk : bnpy.data.DataObj subclass
'''
dpath = self.datafileList[batchID]
if dpath.endswith('.ldac'):
return BagOfWordsData.LoadFromFile_ldac(dpath, **self.DataInfo)
elif self.dataset_type == 'GroupXData':
return GroupXData.LoadFromFile(dpath, **self.DataInfo)
else:
return XData.read_file(dpath, **self.DataInfo)
def loadDataForSlice(filepath='', dataset_type='', **kwargs):
""" Return data object loaded from specific file.
Keyword args
------------
workerID
nWorkers
"""
if filepath.endswith('.ldac'):
return BagOfWordsData.LoadFromFile_ldac(filepath, **kwargs)
else:
if dataset_type == 'GroupXData':
return GroupXData.LoadFromFile(filepath, **kwargs)
else:
return XData.LoadFromFile(filepath, **kwargs)