def processTexFileForCPIDs(textFileName):
textFile = open(textFileName, 'r')
i = 1
for line in textFile:
#print line
if line.find("CPID $") != -1:
cpid = "CPID $" + line.split("CPID $")[1].strip()
print cpid
cpidMap[i] = cpid
i = i + 1
if line.find("Introduction") == 0:
toCSV(cpidMap, cpidOutFileName)
if os.path.isfile(cpidOutFileName):
transposer.transpose(i=cpidOutFileName, o="DiagnosticsValidationCPIDTransposed"+'.csv')
print "Found "+cpidOutFileName+" transposing it for easy analysing data"
return
def test_column_to_row_with_write(self):
test_in_file = '/tmp/in.csv'
test_out_file = '/tmp/rows.csv'
test_in_data = [
['FirstName', 'LastName', 'Age'],
['Frank', 'Jones', '42'],
['Samantha', 'Clemons', '24'],
['Keith', 'Hamilton', '35'],
]
# write test in data
f = open(test_in_file, 'w')
for l in test_in_data:
f.write(','.join(l) + '\n')
f.close()
out_data = transposer.transpose(i=test_in_file, o=test_out_file, d=',')
# read in output
f = open(test_out_file, 'r')
lines = f.readlines()
f.close()
self.assertEqual(['FirstName', 'Frank', 'Samantha', 'Keith'],
lines[0].strip().split(','))
self.assertEqual('LastName,Jones,Clemons,Hamilton', lines[1].strip())
self.assertEqual('Age,42,24,35', lines[2].strip())
for i, x in enumerate(out_data):
self.assertEqual(out_data[i], lines[i].strip())
def test_row_to_column_no_write(self):
original_in_file = '/tmp/in.csv'
test_in_file = '/tmp/rows.csv'
test_out_file = '/tmp/cols.csv'
out_data = transposer.transpose(i=test_in_file, o=None, d=',')
self.assertFalse(os.path.exists(test_out_file))
# read in original input
g = open(original_in_file, 'r')
original_lines = g.readlines()
g.close()
for i, x in enumerate(out_data):
self.assertEqual(out_data[i].strip(), original_lines[i].strip())
if line_idx % 100000 == 0:
print(line_idx)
print 'Finished vcf: ', vcf
print 'mean r2: ', numpy.mean(r2_list)
print 'Screened sites for vcf: ', vcf_num_screened
print 'Tot sites for vcf: ', vcf_sites
# This section transposes the temporary files created during this replicate and adds headers, so that they are formatted according to structure
structtempfile.close()
subtempfile.close()
# Transposes file
jj = transposer.transpose(
i=args.v + 'LD_Pruned/' + args.o + ".rep" + str(rep) +
".LD_Pruned.TransposedStruct.txt",
d="\t",
)
kk = transposer.transpose(
i=args.v + 'LD_Pruned/' + args.o + ".rep" + str(rep) +
".LD_Pruned.TransposedStructSubSample.txt",
d="\t",
)
# Write header names for each marker
for marker in markernames:
structfile.write("%s\t" % marker)
if args.s == 'true':
subfile.write("%s\t" % marker)
structfile.write("\n")
if args.s == 'true':
#pool 1
g = open('randomAmanitaP1.txt', 'w')
for x in times:
p1list = []
for num in number_coord:
v = random.choice(pool1) #of 100 from p1
p1list.append(v)
for thing in p1list:
g.write(thing + ',')
g.write('\n')
g.close()
# pool 2
h = open('randomAmanitaP2.txt', 'w')
for x in times:
p2list = []
for num in number_coord:
v = random.choice(pool2) #of 100 from p1
p2list.append(v)
for thing in p2list:
h.write(thing + ',')
h.write('\n')
h.close()
#transpose the tab delimited file
transposer.transpose(i='randomAmanitaP1.txt', o='outputAmanitaP1.csv')
transposer.transpose(i='randomAmanitaP2.txt', o='outputAmanitaP2.csv')
#Patern: BOOT-TIME| DomainServiceController : com.gm.server.erasedataservice.GMEraseDataService : phase : 4 : took |14
domainServiceInfo = line.split("DomainServiceController")
if len(domainServiceInfo) > 1:
ds = domainServiceInfo[1]
name = ds.split(':')[1].strip()
time = ds.split('|')[-1].strip()
processTimeMap[name] = time
processOrder[name] = i
#print name, time
i = i + 1
if line.find("HMIReady") != -1: #work around for HMIReady which is out of pattern
processTimeMap["HMIReady"] = line.split('|')[-1].strip()
processOrder["HMIReady"] = 99
#print processTimeMap
if processOrderInsertFlag == True: #To insert the number for ease of sorting in excel
toCSV(processOrder, parsedFile, "ProcessOrder")
processOrderInsertFlag = False
toCSV(processTimeMap, parsedFile, logFileName)
logFile.close()
print "Processing the folder <before>..."
processFile(beforeDir)
print "Processing the folder <after>..."
processFile(afterDir)
if os.path.isfile(parsedFile+".csv"):
transposer.transpose(i=parsedFile+'.csv', o=parsedFile+"Transposed"+'.csv')
print "Found "+parsedFile+".csv, transposing it for easy analysing data"
def main():
args = parse_args()
transposer.transpose(i=args.file_in, o=args.file_out, d=args.delimiter)
def transpose():
files = sort()
for file in files:
if file.endswith('.csv'):
print file
transposer.transpose(i=file, o=file)
