def constructFromFile(self, fileName, **args):
matrix = ckernel.KernelMatrix()
matrix.thisown = 0
patternID = []
delim = None
delim = misc.getDelim(fileName)
idColumn = 0
if 'idColumn' in args:
idColumn = args['idColumn']
if idColumn is None:
firstColumn = 0
else:
firstColumn = 1
print firstColumn
print idColumn
matrixFile = myio.myopen(fileName)
firstRow = True
for line in matrixFile:
# skip comments:
if line[0] in ["%", "#"]: continue
tokens = line.split(delim)
# check if the file is in gist format:
if firstRow:
firstRow = False
try:
float(tokens[-1])
except:
continue
if (('headerRow' in args and args['headerRow'])
or ('gistFormat' in args and args['gistFormat'])):
continue
values = arrayWrap.floatVector(
[float(token) for token in tokens[firstColumn:]])
matrix.addRow(values)
if idColumn is not None:
patternID.append(tokens[0])
ckerneldata.KernelData.__init__(self, matrix)
if 'labelsFile' in args:
self.attachLabels(labels.Labels(args['labelsFile'], **args))
else:
self.attachLabels(labels.Labels(None, patternID=patternID))
def constructFromFile(self, fileName, **args):
matrix = ckernel.KernelMatrix()
matrix.thisown = 0
patternID = []
delim = None
delim = misc.getDelim(fileName)
idColumn = 0
if "idColumn" in args:
idColumn = args["idColumn"]
if idColumn is None:
firstColumn = 0
else:
firstColumn = 1
print firstColumn
print idColumn
matrixFile = myio.myopen(fileName)
firstRow = True
for line in matrixFile:
# skip comments:
if line[0] in ["%", "#"]:
continue
tokens = line.split(delim)
# check if the file is in gist format:
if firstRow:
firstRow = False
try:
float(tokens[-1])
except:
continue
if ("headerRow" in args and args["headerRow"]) or ("gistFormat" in args and args["gistFormat"]):
continue
values = arrayWrap.floatVector([float(token) for token in tokens[firstColumn:]])
matrix.addRow(values)
if idColumn is not None:
patternID.append(tokens[0])
ckerneldata.KernelData.__init__(self, matrix)
if "labelsFile" in args:
self.attachLabels(labels.Labels(args["labelsFile"], **args))
else:
self.attachLabels(labels.Labels(None, patternID=patternID))
def combineKernels(ker1file, ker2file, kerOutFile, operation = 'add', **args) :
"""combine two kernels by either adding or multiplying them.
In the case of addition the resulting kernel is of the form:
K_out(i,j) = weight * K1(i,j) + (1-weight) * K2(i,j)
where the default weight is 0.5
In the case of multiplication the resulting kernel is:
K_out(i,j) = (const1 + K1(i,j)) * (const2 + K2(i, j))
where const1 and const2 are 0 by default.
Notes: It is assumed that the kernels have the same size and the ids
are in the same order (an exception is raised if this is not satisfied).
:Parameters:
- `operation` - which operation to perform between the kernels; it is
a string with supported values 'add' or 'multiply' (add by default)
:Keywords:
- `weight` - weighting of kernels for kernel addition
- `const1,const2` - additive factor in case of kernel multiplication
"""
weight = 0.5
if 'weight' in args :
weight = args['weight']
const1 = 0
if 'const1' in args :
const1 = args['const1']
const2 = 0
if 'const2' in args :
const2 = args['const2']
import misc
delim1 = misc.getDelim(ker1file)
delim2 = misc.getDelim(ker2file)
ker1 = open(ker1file)
ker2 = open(ker2file)
kerOut = open(kerOutFile, 'w')
# check if kernel is in gist format
line1 = ker1.readline()
try :
float(line1.split(delim1)[-1])
except :
line1 = ker1.readline()
line2 = ker2.readline()
try :
float(line2.split(delim2)[-1])
except :
line2 = ker2.readline()
# check if there's a pattern id:
firstToken = 0
try :
float(tokens1[0])
except :
firstToken = 1
while len(line1) > 0 :
tokens1 = line1.split(delim1)
tokens2 = line2.split(delim2)
if firstToken > 0 :
if tokens1[0] != tokens2[0] :
print tokens1[0], tokens2[0]
raise ValueError, 'kernels do not have the same ids'
kerOut.write(tokens1[0] + delim1)
if operation == 'add' :
outTokens = [str(float(tokens1[i]) * weight +
float(tokens2[i]) * (1-weight))
for i in range(firstToken, len(tokens1))]
else :
outTokens = [str((const1 + float(tokens1[i])) *
(const2 + float(tokens2[i])))
for i in range(firstToken, len(tokens1))]
kerOut.write(delim1.join(outTokens) + '\n')
line1 = ker1.readline()
line2 = ker2.readline()
