def test_residues_dependency(self, aToken):
with open(os.path.join(self.statDir, '%sstat.csv' % aToken), 'w') as wr:
wr.write('%s\n' %('file,%scount,%schars,size_st25,size_st26,r26vs25' %(aToken, aToken)))
files = [f for f in os.listdir(self.inDir) if '.DS' not in f and f.startswith(aToken)]
di = {}
for f in files:
c = St25To26Converter(os.path.join(self.inDir, f))
xmlPath_large = c.generateXmlFile(self.outDir)
xmlPath = cu.cleanAndWriteXmlFile(xmlPath_large)
di[f] = xmlPath
for f in sorted(di.keys()):
fp = os.path.join(self.inDir, f)
currentSize_st25 = os.path.getsize(fp)
currentSize_st26 = os.path.getsize(di[f])
with open(fp, 'r') as f:
s = f.read()
l = s.split('<400> 1')
item211 = re.search('<211>\s+(\d+)', s)
s1Length = int(item211.group(1))
# print l[1]
wr.write('%s,%i,%i,%i,%i,%s\n' %(os.path.basename(fp),
s1Length,
len(l[1]),
currentSize_st25,
currentSize_st26,
'%0.1f' % (float(currentSize_st26)/currentSize_st25),
))
def test_dependency(self, aToken, aTag):
with open(os.path.join(self.statDir, '%sstat.csv' % aToken), 'w') as wr:
wr.write('%s\n' %('file,%scount,size_st25,size_st26,r26vs25,incr_st25,incr_st26' % aToken))
files = [f for f in os.listdir(self.inDir) if '.DS' not in f and f.startswith(aToken)]
di = {}
for f in files:
c = St25To26Converter(os.path.join(self.inDir, f))
xmlPath_large = c.generateXmlFile(self.outDir)
xmlPath = cu.cleanAndWriteXmlFile(xmlPath_large)
di[f] = xmlPath
initialFile = files[0]
prev_size_st25 = os.path.getsize(os.path.join(self.inDir, initialFile))
prev_size_st26 = os.path.getsize(di[initialFile])
# for f in sorted(di.keys(), key=lambda x: os.path.getsize(os.path.join(self.inDir, f))):
if aToken == 'f_':
currentList = self.featureTestFiles
elif aToken == 's_':
currentList = self.sequenceTestFiles
for fp in currentList:
# fp = os.path.join(self.inDir, f)
with open(fp, 'r') as fr:
s = fr.read()
feature_count = s.count(aTag)
currentSize_st25 = os.path.getsize(fp)
bn = os.path.basename(fp)
currentSize_st26 = os.path.getsize(di[bn])
wr.write('%s,%i,%i,%i,%s,%i,%i\n' %(bn,
feature_count,
currentSize_st25,
currentSize_st26,
'%0.1f' % (float(currentSize_st26)/currentSize_st25),
currentSize_st25 - prev_size_st25,
currentSize_st26 - prev_size_st26))
prev_size_st25 = currentSize_st25
prev_size_st26 = currentSize_st26