def summary(cvsfile, write_func, *args):
"""Show the column names.
"""
fsnames = cvsfile.fieldnames
data_dict = {}
for f in fsnames:
data_dict[f] = []
# print "\n".join(map( lambda x:":".join(map(str,x)) ,enumerate(fsnames)) )
for l in cvsfile:
for f in fsnames:
v = l.setdefault(f, None)
if v and v != "NA":
data_dict[f].append(v)
write_func("colnum:colname\tsum,mean,median,std,cutoff\n")
for (i, f) in enumerate(fsnames):
try:
v_array = map(float, data_dict[f])
v_sum = "%.2f" % sum(v_array)
v_mean = "%.2f" % mean(v_array)
v_median = "%.2f" % median(v_array)
v_std = "%.2f" % std(v_array, float(v_mean))
v_cutoff = "%.2f" % (float(v_mean) + float(v_std))
except ValueError:
(v_sum, v_mean, v_median, v_std, v_cutoff) = ["NA"] * 5
write_func("%d:%s\t%s,%s,%s,%s,%s\n" % (i, f, v_sum, v_mean, v_median, v_std, v_cutoff))
def summary(cvsfile, write_func, *args):
"""Show the column names.
"""
fsnames = cvsfile.fieldnames
data_dict = {}
for f in fsnames:
data_dict[f] = []
#print "\n".join(map( lambda x:":".join(map(str,x)) ,enumerate(fsnames)) )
for l in cvsfile:
for f in fsnames:
v = l.setdefault(f, None)
if v and v != "NA":
data_dict[f].append(v)
write_func("colnum:colname\tsum,mean,median,std,cutoff\n")
for (i, f) in enumerate(fsnames):
try:
v_array = map(float, data_dict[f])
v_sum = "%.2f" % sum(v_array)
v_mean = "%.2f" % mean(v_array)
v_median = "%.2f" % median(v_array)
v_std = "%.2f" % std(v_array, float(v_mean))
v_cutoff = "%.2f" % (float(v_mean) + float(v_std))
except ValueError:
(v_sum, v_mean, v_median, v_std, v_cutoff) = ["NA"] * 5
write_func("%d:%s\t%s,%s,%s,%s,%s\n" %
(i, f, v_sum, v_mean, v_median, v_std, v_cutoff))
# Time-stamp: <2011-01-31 17:17:00 Tao Liu>
# simple normalization script for a bedGraph file from wig2bedGraphBins.py script
import re
import sys
from taolib.CoreLib.BasicStat.Func import mean,std
if len(sys.argv) < 2:
sys.stderr.write("normalize bg file from wig2bedGraphBins.py, output zscores.\nneed 1 para: %s <bedGraph with fixed bins>\n" % sys.argv[0])
sys.exit(1)
fhd = open(sys.argv[1])
d = []
v = []
for i in fhd:
fs = i.rstrip().split()
d.append( ["\t".join(fs[:3]),fs[3]] )
if fs[3] != "NA":
v.append(float(fs[3]))
m = mean(v)
s = std(v,n_mean=m)
for (i,j) in d:
if j!="NA":
print "%s\t%.6f" % (i,(float(j)-m)/s)
else:
print i+"\t"+j
# simple normalization script for a bedGraph file from wig2bedGraphBins.py script
import re
import sys
from taolib.CoreLib.BasicStat.Func import mean, std
if len(sys.argv) < 2:
sys.stderr.write(
"normalize bg file from wig2bedGraphBins.py, output zscores.\nneed 1 para: %s <bedGraph with fixed bins>\n"
% sys.argv[0])
sys.exit(1)
fhd = open(sys.argv[1])
d = []
v = []
for i in fhd:
fs = i.rstrip().split()
d.append(["\t".join(fs[:3]), fs[3]])
if fs[3] != "NA":
v.append(float(fs[3]))
m = mean(v)
s = std(v, n_mean=m)
for (i, j) in d:
if j != "NA":
print "%s\t%.6f" % (i, (float(j) - m) / s)
else:
print i + "\t" + j
