added options for x and y normalization
This commit is contained in:
Tias Maiti
parent
d8260b12df
commit
5257a2161f
|
|
@ -18,24 +18,28 @@ Produces a binned grid of two columns from an ASCIItable, i.e. a two-dimensional
|
||||||
|
|
||||||
""", version = scriptID)
|
""", version = scriptID)
|
||||||
|
|
||||||
parser.add_option('-d','--data', dest='data', nargs=2, type='int', metavar='int int',
|
parser.add_option('-d','--data', dest='data', nargs=2, type='string', metavar='string string',
|
||||||
help='columns containing x and y %default')
|
help='column labels containing x and y %default')
|
||||||
parser.add_option('-w','--weight', dest='weight', metavar='int', type='int',
|
parser.add_option('-w','--weight', dest='weight', metavar='string', type='string',
|
||||||
help='column containing weight of (x,y) point [%default]')
|
help='column label containing weight of (x,y) point [%default]')
|
||||||
parser.add_option('-b','--bins', dest='bins', nargs=2, type='int', metavar='int int',
|
parser.add_option('-b','--bins', dest='bins', nargs=2, type='int', metavar='int int',
|
||||||
help='number of bins in x and y direction %default')
|
help='number of bins in x and y direction %default')
|
||||||
parser.add_option('-t','--type', dest='type', nargs=3, metavar='string string string',
|
parser.add_option('-t','--type', dest='type', nargs=3, metavar='string string string',
|
||||||
help='type (linear/log) of x, y, and z axis [linear]')
|
help='type (linear/log) of x, y, and z axis [linear]')
|
||||||
parser.add_option('-x','--xrange', dest='xrange', nargs=2, type='float', metavar='float float',
|
parser.add_option('-x','--xrange', dest='xrange', nargs=2, type='float', metavar='float float',
|
||||||
help='value range in x direction [auto]')
|
help='value minmax in x direction [auto]')
|
||||||
parser.add_option('-y','--yrange', dest='yrange', nargs=2, type='float', metavar='float float',
|
parser.add_option('-y','--yrange', dest='yrange', nargs=2, type='float', metavar='float float',
|
||||||
help='value range in y direction [auto]')
|
help='value minmax in y direction [auto]')
|
||||||
parser.add_option('-z','--zrange', dest='zrange', nargs=2, type='float', metavar='float float',
|
parser.add_option('-z','--zrange', dest='zrange', nargs=2, type='float', metavar='float float',
|
||||||
help='value range in z direction [auto]')
|
help='value minmax in z direction [auto]')
|
||||||
parser.add_option('-i','--invert', dest='invert', action='store_true',
|
parser.add_option('-i','--invert', dest='invert', action='store_true',
|
||||||
help='invert probability density [%default]')
|
help='invert probability density [%default]')
|
||||||
|
parser.add_option('-r','--rownormalize', dest='normRow', action='store_true',
|
||||||
|
help='normalize probability density in each row [%default]')
|
||||||
|
parser.add_option('-c','--colnormalize', dest='normCol', action='store_true',
|
||||||
|
help='normalize probability density in each column [%default]')
|
||||||
|
|
||||||
parser.set_defaults(data = (1,2))
|
parser.set_defaults(data = None)
|
||||||
parser.set_defaults(weight = None)
|
parser.set_defaults(weight = None)
|
||||||
parser.set_defaults(bins = (10,10))
|
parser.set_defaults(bins = (10,10))
|
||||||
parser.set_defaults(type = ('linear','linear','linear'))
|
parser.set_defaults(type = ('linear','linear','linear'))
|
||||||
|
|
@ -43,76 +47,113 @@ parser.set_defaults(xrange = (0.0,0.0))
|
||||||
parser.set_defaults(yrange = (0.0,0.0))
|
parser.set_defaults(yrange = (0.0,0.0))
|
||||||
parser.set_defaults(zrange = (0.0,0.0))
|
parser.set_defaults(zrange = (0.0,0.0))
|
||||||
parser.set_defaults(invert = False)
|
parser.set_defaults(invert = False)
|
||||||
|
parser.set_defaults(normRow = False)
|
||||||
|
parser.set_defaults(normCol = False)
|
||||||
|
|
||||||
(options,filenames) = parser.parse_args()
|
(options,filenames) = parser.parse_args()
|
||||||
|
|
||||||
range = np.array([np.array(options.xrange),
|
minmax = np.array([np.array(options.xrange),
|
||||||
np.array(options.yrange),
|
np.array(options.yrange),
|
||||||
np.array(options.zrange)])
|
np.array(options.zrange)])
|
||||||
grid = np.zeros(options.bins,'i')
|
grid = np.zeros(options.bins,'i')
|
||||||
result = np.zeros((options.bins[0]*options.bins[1],3),'f')
|
result = np.zeros((options.bins[0],options.bins[1],3),'f')
|
||||||
|
|
||||||
prefix='binned%i-%i_'%(options.data[0],options.data[1])+ \
|
datainfo = { # list of requested labels per datatype
|
||||||
('weighted%i_'%(options.weight) if options.weight != None else '')
|
'scalar': {'len':1,
|
||||||
|
'label':[]},
|
||||||
|
}
|
||||||
|
|
||||||
# ------------------------------------------ setup file handles ------------------------------------
|
if options.data != None: datainfo['scalar']['label'] += options.data
|
||||||
files = []
|
if options.weight != None: datainfo['scalar']['label'] += options.weight
|
||||||
|
|
||||||
|
if len(datainfo['scalar']['label']) < 2:
|
||||||
|
parser.error('missing column labels')
|
||||||
|
|
||||||
|
# --- loop over input files -------------------------------------------------------------------------
|
||||||
if filenames == []:
|
if filenames == []:
|
||||||
files.append({'name':'STDIN', 'input':sys.stdin, 'output':sys.stdout, 'croak':sys.stderr})
|
filenames = ['STDIN']
|
||||||
else:
|
|
||||||
for name in filenames:
|
|
||||||
if os.path.exists(name):
|
|
||||||
files.append({'name':name, 'input':open(name), 'output':open(name+'_tmp','w'), 'croak':sys.stderr})
|
|
||||||
|
|
||||||
# ------------------------------------------ loop over input files ---------------------------------
|
for name in filenames:
|
||||||
for file in files:
|
if name == 'STDIN':
|
||||||
if file['name'] != 'STDIN': file['croak'].write('\033[1m'+scriptName+'\033[0m: '+file['name']+'\n')
|
file = {'name':'STDIN', 'input':sys.stdin, 'output':sys.stdout, 'croak':sys.stderr}
|
||||||
else: file['croak'].write('\033[1m'+scriptName+'\033[0m\n')
|
file['croak'].write('\033[1m'+scriptName+'\033[0m\n')
|
||||||
|
else:
|
||||||
|
if not os.path.exists(name): continue
|
||||||
|
file = {'name':name, 'input':open(name), 'output':open(name+'_tmp','w'), 'croak':sys.stderr}
|
||||||
|
file['croak'].write('\033[1m'+scriptName+'\033[0m: '+file['name']+'\n')
|
||||||
|
|
||||||
skip = int(file['input'].readline().split()[0])
|
table = damask.ASCIItable(file['input'],file['output'],buffered = False) # make unbuffered ASCII_table
|
||||||
for i in xrange(skip): headers = file['input'].readline().split()
|
table.head_read() # read ASCII header info
|
||||||
data = np.loadtxt(file['input'],usecols=np.array(options.data+((options.weight,) if options.weight != None else ()))-1)
|
|
||||||
file['input'].close() # close input ASCII table
|
|
||||||
|
|
||||||
for i in (0,1): # check data range for x and y
|
# --------------- figure out columns to process ---------------------------------------------------
|
||||||
if (range[i] == 0.0).all(): range[i] = [data[:,i].min(),data[:,i].max()]
|
active = []
|
||||||
|
column = {}
|
||||||
|
|
||||||
|
for label in datainfo['scalar']['label']:
|
||||||
|
if label in table.labels:
|
||||||
|
active.append(label)
|
||||||
|
column[label] = table.labels.index(label) # remember columns of requested data
|
||||||
|
else:
|
||||||
|
file['croak'].write('column %s not found...\n'%label)
|
||||||
|
|
||||||
|
# ------------------------------------------ assemble header ---------------------------------------
|
||||||
|
table.info_clear()
|
||||||
|
table.info_append(scriptID + '\t' + ' '.join(sys.argv[1:]))
|
||||||
|
table.labels = ['bin_%s'%options.data[0],'bin_%s'%options.data[1],'z']
|
||||||
|
table.head_write()
|
||||||
|
|
||||||
|
# ------------------------------------------ process data ------------------------------------------
|
||||||
|
table.data_readArray([column[label] for label in active])
|
||||||
|
|
||||||
|
for i in (0,1): # check data minmax for x and y
|
||||||
|
if (minmax[i] == 0.0).all(): minmax[i] = [table.data[:,i].min(),table.data[:,i].max()]
|
||||||
if options.type[i].lower() == 'log': # if log scale
|
if options.type[i].lower() == 'log': # if log scale
|
||||||
data[:,i] = np.log(data[:,i]) # change x,y coordinates to log
|
table.data[:,i] = np.log(table.data[:,i]) # change x,y coordinates to log
|
||||||
range[i] = np.log(range[i]) # change range to log, too
|
minmax[i] = np.log(minmax[i]) # change minmax to log, too
|
||||||
|
|
||||||
delta = range[:,1]-range[:,0]
|
delta = minmax[:,1]-minmax[:,0]
|
||||||
|
|
||||||
for i in xrange(len(data)):
|
for i in xrange(len(table.data)):
|
||||||
x = int(options.bins[0]*(data[i,0]-range[0,0])/delta[0])
|
x = int(options.bins[0]*(table.data[i,0]-minmax[0,0])/delta[0])
|
||||||
y = int(options.bins[1]*(data[i,1]-range[1,0])/delta[1])
|
y = int(options.bins[1]*(table.data[i,1]-minmax[1,0])/delta[1])
|
||||||
if x >=0 and x < options.bins[0] and y >= 0 and y < options.bins[1]: grid[x,y] += 1 if options.weight == None else data[i,2]
|
if x >= 0 and x < options.bins[0] and y >= 0 and y < options.bins[1]:
|
||||||
|
grid[x,y] += 1 if options.weight == None else table.data[i,2] # count (weighted) occurrences
|
||||||
|
|
||||||
if (range[2] == 0.0).all(): range[2] = [grid.min(),grid.max()]
|
if (minmax[2] == 0.0).all(): minmax[2] = [grid.min(),grid.max()] # auto scale from data
|
||||||
if (range[2] == 0.0).all(): # no data in grid?
|
if minmax[2,0] == minmax[2,1]:
|
||||||
|
minmax[2,0] -= 1.
|
||||||
|
minmax[2,1] += 1.
|
||||||
|
if (minmax[2] == 0.0).all(): # no data in grid?
|
||||||
file['croak'].write('no data found on grid...\n')
|
file['croak'].write('no data found on grid...\n')
|
||||||
range[2,:] = np.array([0.0,1.0]) # making up arbitrary z range
|
minmax[2,:] = np.array([0.0,1.0]) # making up arbitrary z minmax
|
||||||
if options.type[2].lower() == 'log':
|
if options.type[2].lower() == 'log':
|
||||||
grid = np.log(grid)
|
grid = np.log(grid)
|
||||||
range[2] = np.log(range[2])
|
minmax[2] = np.log(minmax[2])
|
||||||
|
|
||||||
delta[2] = range[2,1]-range[2,0]
|
delta[2] = minmax[2,1]-minmax[2,0]
|
||||||
|
|
||||||
|
|
||||||
i = 0
|
|
||||||
for x in xrange(options.bins[0]):
|
for x in xrange(options.bins[0]):
|
||||||
for y in xrange(options.bins[1]):
|
for y in xrange(options.bins[1]):
|
||||||
result[i,:] = [range[0,0]+delta[0]/options.bins[0]*(x+0.5),
|
result[x,y,:] = [minmax[0,0]+delta[0]/options.bins[0]*(x+0.5),
|
||||||
range[1,0]+delta[1]/options.bins[1]*(y+0.5),
|
minmax[1,0]+delta[1]/options.bins[1]*(y+0.5),
|
||||||
min(1.0,max(0.0,(grid[x,y]-range[2,0])/delta[2]))]
|
min(1.0,max(0.0,(grid[x,y]-minmax[2,0])/delta[2]))]
|
||||||
if options.type[0].lower() == 'log': result[i,0] = np.exp(result[i,0])
|
|
||||||
if options.type[1].lower() == 'log': result[i,1] = np.exp(result[i,1])
|
if options.normCol:
|
||||||
if options.invert: result[i,2] = 1.0-result[i,2]
|
for x in xrange(options.bins[0]):
|
||||||
i += 1
|
result[x,:,2] /= np.sum(result[x,:,2])
|
||||||
|
if options.normRow:
|
||||||
|
for y in xrange(options.bins[1]):
|
||||||
|
result[:,y,2] /= np.sum(result[:,y,2])
|
||||||
|
|
||||||
|
for i in xrange(2):
|
||||||
|
if options.type[i].lower() == 'log': result[:,:,i] = np.exp(result[:,:,i])
|
||||||
|
|
||||||
|
if options.invert: result[:,:,2] = 1.0-result[:,:,2]
|
||||||
|
|
||||||
# ------------------------------------------ output result -----------------------------------------
|
# ------------------------------------------ output result -----------------------------------------
|
||||||
file['output'].write('1\thead\n')
|
prefix = 'binned%s-%s_'%(options.data[0],options.data[1])+ \
|
||||||
file['output'].write('bin_%s\tbin_%s\tz\n'%(headers[options.data[0]-1],headers[options.data[1]-1]))
|
('weighted%s_'%(options.weight) if options.weight != None else '')
|
||||||
np.savetxt(file['output'],result)
|
np.savetxt(file['output'],result.reshape(options.bins[0]*options.bins[1],3))
|
||||||
file['output'].close() # close output ASCII table
|
file['output'].close() # close output ASCII table
|
||||||
if file['name'] != 'STDIN':
|
if file['name'] != 'STDIN':
|
||||||
os.rename(file['name']+'_tmp',\
|
os.rename(file['name']+'_tmp',\
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue