def read_stream(stream, stratified=False):
total, bad = 0, 0
data = {}
for row in reader(stream):
if not stratified:
key, values = "#", row
else:
key, values = row[0], row[1:]
total += len(values)
values2 = []
for v in values:
try:
values2.append(float(v))
except:
warn("bad value:", v)
bad += 1
inner = data.setdefault(key, [])
inner += values2
if bad > 0:
warn("bad values: %d (%.2f%%)" % (bad, 100 * bad / float(total)))
data = {k: v for k, v in data.items() if len(v) > 0}
return data
# ---------------------------------------------------------------
# load all data
# ---------------------------------------------------------------
dictTableData = {}
# modified for faster looking up 4/2/2015
dictFeatureIndex = {}
for iDex, strPath in enumerate(args.input):
print >> sys.stderr, "Loading", iDex + 1, "of", len(
args.input), ":", strPath
aastrData = []
strColhead = path2name(strPath)
with open(strPath) as fh:
for astrItems in reader(fh):
aastrData.append(
[astrItems[args.key_col], astrItems[args.val_col]]),
if args.strip_comments:
aastrData = [astrRow for astrRow in aastrData if astrRow[0][0] != "#"]
if args.use_headers:
strColhead = aastrData[0][1]
if args.strip_headers:
aastrData = aastrData[1:]
if args.key_pattern:
aastrData = [
astrRow for astrRow in aastrData
if re.search(args.key_pattern, astrRow[0])
]
for strFeature, strValue in aastrData:
if strFeature not in dictFeatureIndex:
aFloatableFields = ["s", "alpha", "zorder"]
# argument parsing ( python argparse )
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--input', help='')
parser.add_argument('-o', '--output', help='')
parser.add_argument('-n', '--logmin', type=float, help='')
parser.add_argument('-x', '--logmax', type=float, help='')
args = parser.parse_args()
# parse the input file for x,y values and kwargs
aX, aY = [], []
kwargs = {}
with open(args.input) as fh:
aHeaders = fh.readline().strip().split("\t")
for aItems in reader(fh):
aX.append(float(aItems[0]))
aY.append(float(aItems[1]))
if len(aItems) > 2:
for i, value in enumerate(aItems[2:]):
header = aHeaders[i + 2]
value = float(value) if header in aFloatableFields else value
kwargs.setdefault(header, []).append(value)
# execute plot
fig = plt.figure()
fig.set_size_inches(5, 5)
ax = plt.subplot(111)
# note: if args.logmin/max not specified, they will pass None ( which ZillPlot expects )
zillplot(ax, aX, aY, logmin=args.logmin, logmax=args.logmax, **kwargs)
def describe_median_rank ( m ):
""" """
cuts = [0.05, 0.2, 0.4, 0.6, 0.8, 0.95, 1.0]
names = ["very low", "low", "medium low", "trivial", "medium high", "high", "very high"]
for cut, name in zip( cuts, names ):
if m < cut:
return name
# ---------------------------------------------------------------
# counting
# ---------------------------------------------------------------
counter = 0
kmer2term = {}
kmer2rank = {}
for items in reader( fh ):
counter += 1
term = items[0].strip()
original = term
if simplify:
term = line.lower()
term = re.sub( "[^a-z0-9]", " ", term )
term = re.sub( " +", " ", term )
kmers = term.split( " " ) if args.words else [term[j:j+k] for j in range( 0, len( term ) - k + 1 )]
for kmer in kmers:
temp = kmer2term.setdefault( kmer, {} )
temp[original] = 1
temp = kmer2rank.setdefault( kmer, {} )
temp[counter] = 1
# ---------------------------------------------------------------
total = 0
bad = 0
parser = argparse.ArgumentParser()
parser.add_argument(
'-z',
"--zerozero",
action="store_true",
help="if set: 0,0 points EXCLUDED",
)
args = parser.parse_args()
# read in data
rows = []
for row in reader(sys.stdin):
total += 1
if len(row) == 2:
row = ["<#s>"] + row
elif len(row) == 3 and total == 1:
print >> sys.stderr, "stratifying on first field, e.g.:", row[0]
try:
row[1] = float(row[1])
row[2] = float(row[2])
rows.append(row)
except:
print >> sys.stderr, "ignoring", "\t".join(map(str, row))
bad += 1
# stratify
data = {}
def load_from_handle(fh):
return coerce([row for row in reader(fh)])
