def test(self):
passed = True
dc = DataCollection()
dc.dataclass = TrainData_test
dc.sourceList = [f for f in self.files.filenames]
dc.createDataFromRoot(TrainData_test, outputDir=self.dcoutdir.path)
gen = dc.invokeGenerator()
gen.setBatchSize(self.n_per_batch)
for epoch in range(10):
gen.prepareNextEpoch()
print("epoch",epoch,'batches',gen.getNBatches())
for b in range(gen.getNBatches()):
d,_ = next(gen.feedNumpyData())
data,rs = d[0],d[1]
rs = np.array(rs[:,0],dtype='int')
rs = rs[:rs[-1]]
#print(data)
#print(rs[-1])
if not raggedtester.checkData(data, rs):
print('epoch',epoch, 'batch',b,'broken')
passed=False
break
if rs[-1] > self.n_per_batch:
print('maximum batch size exceeded for batch ',b, 'epoch', epoch)
print('shuffling')
gen.shuffleFilelist()
return passed
raise Exception('wrong class selection')
if not ".dc" in infile:
raise Exception('wrong input file '+infile)
dir = os.path.dirname(infile)
dcold = DCOld()
dcold.readRawFromFile(infile)
dcnew = DataCollection()
dcnew.dataclass = traind()
dcnew.samples = [s[:-4]+'djctd' for s in dcold.samples]
print(dcnew.samples)
dcnew.sourceList = dcold.originRoots
# leave traindata undefined no way to convert.
dcnew.__nsamples = 0 # determine again, also check
outfile = infile[:-2] +'djcdc'
print("infile: ", infile, " outfile", outfile)
def worker(i):
td = TDOld()
tdnew = TrainData()
print("converting",dcold.samples[i])
td.readIn(dir + dcold.samples[i])
x = td.x
y = td.y