inf = open(filename,'r')
reader = csv.reader(inf,delimiter='\t')
ls = []
for row in reader:
one_row = []
for data in row[1:]: #first column is gene name
if data == 'NA':
data=random.randint(-800,800)
elif data=='': #some datasets' last column is None
continue
else:
data = float(data)
one_row.append(data)
ls.append(one_row)
instance = biclustering.biclustering(hscore_cut_off,min_height, min_width, bThreshold)
biclustering.set_module_and_type('Numeric', 'ArrayType')
instance.data_read_in(array(ls))
ls1 = instance.return_matrix_data()
#output the matrix read in by the class
writer = csv.writer(open('/tmp/test_biclustering.out', 'w'), delimiter='\t')
for row in ls1:
writer.writerow(row)
del writer
print "the first row is "
print ls1[0]
print "the penultimate row is "
print ls1[-2]
print "the final row is "
test_biclustering.py INPUTFILE
Decription:
A program to test the biclustering module.
INPUTFILE is tab-delimited format. First column is the label.
'NA' denotes Not avaible.
"""
import csv,sys
import biclustering
if len(sys.argv)!=2:
print __doc__
sys.exit(0)
instance = biclustering.biclustering(50,5,6,100)
filename=sys.argv[1]
inf = open(filename,'r')
reader = csv.reader(inf,delimiter='\t')
ls = []
for row in reader:
if row[-1]: #some datasets' last column is None
ls.append(row[1:])
else:
ls.append(row[1:-1])
instance.data_read_in(ls)
ls1 = instance.return_matrix_data()
#output the matrix read in by the class
writer = csv.writer(open('/tmp/test_biclustering.out', 'w'), delimiter='\t')
for row in ls1:
