def main(argv=None):
if argv == None: argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-n",
"--nonull",
dest="nonull",
action="store_true",
help="no null [default=%default]")
parser.add_option("-e",
"--show-empty",
dest="empty_bins",
action="store_true",
help="show empty bins [default=%default]")
parser.add_option("-o",
"--normalize",
dest="normalize",
action="store_true",
help="normalize histogram [default=%default]")
parser.add_option("-i",
"--titles",
dest="titles",
action="store_true",
help="use titles supplied in ... [default=%default]")
parser.add_option("--cumulative",
dest="cumulative",
action="store_true",
help="compute cumulative histogram [default=%default]")
parser.add_option(
"--reverse-cumulative",
dest="reverse_cumulative",
action="store_true",
help="compute reverse cumulative histogram [default=%default]")
parser.add_option("-c",
"--column",
dest="column",
type="int",
help="columns to take [default=%default]")
parser.add_option("-b",
"--bin-size",
dest="bin_size",
type="float",
help="bin size to use [default=%default]")
parser.add_option("-u",
"--upper",
dest="upper_limit",
type="float",
help="upper limit to use [default=%default]")
parser.add_option("-l",
"--lower",
dest="lower_limit",
type="float",
help="lower limit to use [default=%default]")
parser.add_option("-s",
"--scale",
dest="scale",
type="float",
help="scale to use [default=%default]")
parser.add_option("-a",
"--append",
dest="append",
type="choice",
action="append",
choices=("normalize", ),
help="append columns [default=%default]")
parser.set_defaults(nonull=None,
columns=[
0,
],
empty_bins=True,
titles=False,
lower_limit=None,
upper_limit=None,
bin_size=None,
scale=None,
normalize=None,
append=[],
cumulative=False,
reverse_cumulative=False)
## add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if options.columns:
if options.columns != "all":
options.columns = [int(x) - 1 for x in options.columns.split(",")]
else:
options.columns.append(0)
histograms = []
vals = []
for x in options.columns:
vals.append([])
# retrieve histogram
lines = filter(lambda x: x[0] <> "#", sys.stdin.readlines())
ncols = len(string.split(lines[0][:-1], "\t"))
if options.columns == "all":
options.columns = range(ncols)
for x in options.columns:
vals.append([])
if options.titles:
data = lines[0][:-1].split("\t")
del lines[0]
options.titles = map(lambda x: data[x], options.columns)
for l in lines:
data = string.split(l[:-1], "\t")
for x in range(len(options.columns)):
try:
v = string.atof(data[options.columns[x]])
except IndexError:
print "# IndexError in line:", l[:-1]
continue
except ValueError:
continue
if options.scale:
v *= options.scale
if options.upper_limit != None and v > options.upper_limit:
v = options.upper_limit
if options.lower_limit != None and v < options.lower_limit:
v = options.lower_limit
vals[x].append(v)
lines = None
hists = []
titles = []
for x in range(len(options.columns)):
E.info("column=%i, num_values=%i" % (options.columns[x], len(vals[x])))
if len(vals[x]) == 0: continue
h = Histogram.Calculate(vals[x],
no_empty_bins=options.empty_bins,
increment=options.bin_size)
if options.scale: h = Histogram.Scale(h, 1.0 / options.scale)
if options.normalize: h = Histogram.Normalize(h)
if options.cumulative: h = Histogram.Cumulate(h)
if options.reverse_cumulative: h = Histogram.Cumulate(h, direction=0)
hists.append(h)
for m in options.append:
if m == "normalize":
hists.append(Histogram.Normalize(h))
if options.titles:
titles.append(options.titles[x])
if titles:
options.stdout.write("bin\t" + "\t".join(titles) + "\n")
if len(hists) == 1:
Histogram.Print(hists[0], nonull=options.nonull)
else:
combined_histogram = Histogram.Combine(hists)
Histogram.Print(combined_histogram, nonull=options.nonull)
E.Stop()
def main(argv=None):
if not argv:
argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: data2histogram.py 2782 2009-09-10 11:40:29Z andreas $"
)
parser.add_option("-r",
"--range",
dest="range",
type="string",
help="range to calculate histogram for.")
parser.add_option("-b",
"--bin-size",
dest="bin_size",
type="string",
help="bin size.")
parser.add_option("-i",
"--titles",
dest="titles",
action="store_true",
help="use supplied column titles.")
parser.add_option("--no-null",
dest="nonull",
action="store_true",
help="do not output null values")
parser.add_option("--no-titles",
dest="titles",
action="store_false",
help="no column titles given.")
parser.add_option("-c",
"--columns",
dest="columns",
type="string",
help="columns to take for calculating histograms.")
parser.add_option(
"--min-data",
dest="min_data",
type="int",
help=
"minimum amount of data required, if less data, then the histogram will be empty [default=%default]."
)
parser.add_option("--min-value",
dest="min_value",
type="float",
help="minimum value for histogram.")
parser.add_option("--max-value",
dest="max_value",
type="float",
help="maximum value for histogram.")
parser.add_option("--no-empty-bins",
dest="no_empty_bins",
action="store_true",
help="do not display empty bins.")
parser.add_option("--with-empty-bins",
dest="no_empty_bins",
action="store_false",
help="display empty bins.")
parser.add_option("--normalize",
dest="normalize",
action="store_true",
help="normalize histogram.")
parser.add_option("--cumulative",
dest="cumulative",
action="store_true",
help="calculate cumulative histogram.")
parser.add_option("--reverse-cumulative",
dest="reverse_cumulative",
action="store_true",
help="calculate reverse cumulative histogram.")
parser.add_option("--header-names",
dest="headers",
type="string",
help="use the following headers.")
parser.add_option(
"--ignore-out-of-range",
dest="ignore_out_of_range",
action="store_true",
help=
"ignore values that are out of range (as opposed to truncating them to range border."
)
parser.add_option("--missing-value",
dest="missing_value",
type="string",
help="entry for missing values [%default].")
parser.add_option("--use-dynamic-bins",
dest="dynamic_bins",
action="store_true",
help="each value constitutes its own bin.")
parser.add_option(
"--on-the-fly",
dest="on_the_fly",
action="store_true",
help=
"on the fly computation of histograms. Requires setting of min-value, max-value and bin_size."
)
parser.set_defaults(
bin_size=None,
range=None,
titles=True,
columns="all",
append=(),
no_empty_bins=True,
min_value=None,
max_value=None,
normalize=False,
cumulative=False,
reverse_cumulative=False,
nonull=None,
ignore_out_of_range=False,
min_data=1,
headers=None,
missing_value="na",
dynamic_bins=False,
on_the_fly=False,
bin_format="%.2f",
value_format="%6.4f",
)
(options, args) = E.Start(parser)
if options.columns != "all":
options.columns = [int(x) - 1 for x in options.columns.split(",")]
if options.range:
options.min_value, options.max_value = list(
map(float, options.range.split(",")))
if options.headers:
options.headers = options.headers.split(",")
if options.on_the_fly:
if options.min_value is None or options.max_value is None or \
options.bin_size is None:
raise ValueError("please supply columns, min-value, max-value and "
"bin-size for on-the-fly computation.")
# try to glean titles from table:
if options.titles:
while 1:
line = sys.stdin.readline()
if not line:
break
if line[0] == "#":
continue
data = line[:-1].split("\t")
break
if options.columns == "all":
options.titles = data
options.columns = list(range(len(data)))
else:
options.titles = [data[x] for x in options.columns]
bins = numpy.arange(options.min_value, options.max_value,
float(options.bin_size))
hh = Histogram.fillHistograms(
sys.stdin, options.columns,
[bins for x in range(len(options.columns))])
n = len(hh)
titles = ['bin']
if options.headers:
titles.append(options.headers[x])
elif options.titles:
titles.append(options.titles[x])
else:
for x in options.columns:
titles.append("col%i" % (x + 1))
if len(titles) > 1:
options.stdout.write("\t".join(titles) + "\n")
for x in range(len(bins)):
v = []
v.append(options.bin_format % bins[x])
for c in range(n):
v.append(options.value_format % hh[c][x])
options.stdout.write("\t".join(v) + "\n")
else:
# in-situ computation of histograms
# retrieve data
first = True
vals = []
# parse data, convert to floats
for l in options.stdin:
if l[0] == "#":
continue
data = l[:-1].split("\t")
if first:
first = False
ncols = len(data)
if options.columns == "all":
options.columns = list(range(ncols))
vals = [[] for x in options.columns]
if options.titles:
try:
options.titles = [data[x] for x in options.columns]
except IndexError:
raise IndexError(
"not all columns %s found in data %s" %
(str(options.columns), str(data)))
continue
for x in range(len(options.columns)):
try:
v = float(data[options.columns[x]])
except IndexError:
print("# IndexError in line:", l[:-1])
continue
except ValueError:
continue
vals[x].append(v)
lines = None
hists = []
titles = []
if not vals:
if options.loglevel >= 1:
options.stdlog.write("# no data\n")
E.Stop()
sys.exit(0)
for x in range(len(options.columns)):
if options.loglevel >= 1:
options.stdlog.write("# column=%i, num_values=%i\n" %
(options.columns[x], len(vals[x])))
if len(vals[x]) < options.min_data:
continue
h = Histogram.Calculate(
vals[x],
no_empty_bins=options.no_empty_bins,
increment=options.bin_size,
min_value=options.min_value,
max_value=options.max_value,
dynamic_bins=options.dynamic_bins,
ignore_out_of_range=options.ignore_out_of_range)
if options.normalize:
h = Histogram.Normalize(h)
if options.cumulative:
h = Histogram.Cumulate(h)
if options.reverse_cumulative:
h = Histogram.Cumulate(h, direction=0)
hists.append(h)
for m in options.append:
if m == "normalize":
hists.append(Histogram.Normalize(h))
if options.headers:
titles.append(options.headers[x])
elif options.titles:
titles.append(options.titles[x])
else:
titles.append("col%i" % options.columns[x])
if titles:
options.stdout.write("bin\t" + "\t".join(titles) + "\n")
if len(hists) == 1:
Histogram.Print(hists[0],
nonull=options.nonull,
format_bin=options.bin_format)
else:
combined_histogram = Histogram.Combine(
hists, missing_value=options.missing_value)
Histogram.Print(combined_histogram,
nonull=options.nonull,
format_bin=options.bin_format)
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: graph2stats.py 2782 2009-09-10 11:40:29Z andreas $"
)
parser.add_option("-r",
"--range",
dest="range",
type="string",
help="range to calculate histogram for.")
parser.add_option("-b",
"--bin-size",
dest="bin_size",
type="string",
help="bin size.")
parser.add_option("-i",
"--titles",
dest="titles",
action="store_true",
help="use supplied column titles.")
parser.add_option("-s",
"--make-symmetric",
dest="make_symmetric",
action="store_true",
help="symmetrize graph.")
parser.add_option("-c",
"--columns",
dest="columns",
type="string",
help="columns to take for calculating histograms.")
parser.add_option("-p",
"--output-pattern",
dest="output_pattern",
type="string",
help="pattern for output files.")
parser.add_option("-m",
"--method",
dest="method",
type="string",
help="method.")
parser.add_option("-o",
"--output-format",
dest="output_format",
type="string",
help="output format.")
parser.add_option("--min-value",
dest="min_value",
type="float",
help="minimum value for histogram.")
parser.add_option("--max-value",
dest="max_value",
type="float",
help="maximum value for histogram.")
parser.set_defaults(bin_size=None,
range=None,
titles=False,
columns="all",
append=(),
empty_bins=False,
min_value=None,
max_value=None,
normalize=False,
cumulative=False,
reverse_cumulative=False,
nonull=None,
make_symmetric=False,
output_pattern="%s.hist",
method="histograms",
output_format="semi")
(options, args) = E.Start(parser)
if options.columns != "all":
options.columns = map(lambda x: int(x) - 1, options.columns.split(","))
if options.range:
options.min_value, options.max_value = map(float,
options.range(split(",")))
# retrieve data
lines = filter(lambda x: x[0] <> "#", sys.stdin.readlines())
vals = {}
if options.method == "histograms":
## read data
for line in lines:
v1, v2, w = line[:-1].split("\t")[:3]
try:
w[3] = float(w[3])
except ValueError:
nerrors += 1
continnue
if v1 not in vals: vals[v1] = {}
if v2 not in vals[v1]: vals[v1][v2] = []
vals[v1][v2].append(w)
if options.make_symmetric:
if v2 not in vals: vals[v2] = {}
if v1 not in vals[v2]: vals[v2][v1] = []
vals[v2][v1].append(w)
## convert to histograms
for k1, vv in vals.items():
for k2 in vv.keys():
if len(vv[k2]) == 0: continue
h = Histogram.Calculate(vv[k2],
no_empty_bins=options.empty_bins,
increment=options.bin_size,
min_value=options.min_value,
max_value=options.max_value)
if options.normalize: h = Histogram.Normalize(h)
if options.cumulative: h = Histogram.Cumulate(h)
if options.reverse_cumulative:
h = Histogram.Cumulate(h, direction=0)
vv[k2] = h
## write output
if options.output == "semi":
for k1, vv in vals.items():
outfile = open(options.output_pattern % k1)
kk2 = vv.keys()
kk2.sort()
hists = []
for k2 in kk2:
hists.append(vv[k2])
PrintHistograms(outfile, kk2, hists, options)
outfile.close()
elif options.method == "counts":
## read data
for line in lines:
v1, v2 = line[:-1].split("\t")[:2]
if v1 not in vals: vals[v1] = {}
if v2 not in vals[v1]: vals[v1][v2] = 0
vals[v1][v2] += 1
if options.make_symmetric:
if v2 not in vals: vals[v2] = {}
if v1 not in vals[v2]: vals[v2][v1] = 0
vals[v2][v1] += 1
## convert to histograms
for k1, vv in vals.items():
for k2 in vv.keys():
options.stdout.write("%s\t%s\t%i\n" % (k1, k2, vv[k2]))
E.Stop()
