def get_size_of_batch_from_file(self, filepath):
if filepath.endswith('.ldac'):
with open(filepath, 'r') as f:
return len(f.readlines())
elif self.dataset_type == 'GroupXData':
return XData.read_file(filepath).nDoc
elif self.dataset_type == 'XData':
return XData.read_file(filepath).nObs
else:
raise ValueError('Unrecognized file type: ' + filepath)
"""
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)
