def _get_filename(catID, out):
"""
Return filename for testcase data's output.
@param catID ID of the category
@param out data to be written into file
@return string with the filename
"""
params = []
name = category.get_name(catID)
for key, val in out.iteritems():
if _is_excluded_from_filename(key):
continue
if key == name:
continue
cname = val.__class__.__name__
if cname == 'bool' or cname == 'float' or cname == 'int' or cname == 'str':
val = str(val)
val = val.replace('-', 'n')
val = val.replace('+', 'p')
params.append(val)
params = '_'.join(params).replace('.', '')
if len(params) > 0:
params = '_' + params
else: # otherwise problems with one interface (FIXME: find out which)
params = '_fnord'
dir = DIR_OUTPUT + os.sep + category.get_as_string(catID) + os.sep
return dir + out[name] + params + EXT_OUTPUT
def write(catID, out):
"""
Write given testcase data to a file.
@param cat ID of the category, like category.KERNEL
@param out data to be written into file
@return Success of operation
"""
fnam = _get_filename(catID, out)
print 'Writing for '+category.get_as_string(catID).upper()+': '+ \
os.path.basename(fnam)
dirname = os.path.dirname(fnam)
if not os.path.isdir(dirname):
os.mkdir(dirname)
mfile = open(fnam, mode='w')
for key, val in out.iteritems():
cname = val.__class__.__name__
if cname == 'bool' or cname == 'str':
mfile.write("%s = '%s';\n" % (key, val))
elif cname == 'ndarray' or cname == 'matrix':
mfile.write("%s;\n" % _get_matrix(key, val))
else:
mfile.write("%s = %s;\n" % (key, val))
mfile.close()
return True
def _get_filename (catID, out):
"""
Return filename for testcase data's output.
@param catID ID of the category
@param out data to be written into file
@return string with the filename
"""
params=[]
name=category.get_name(catID)
for key, val in out.iteritems():
if _is_excluded_from_filename(key):
continue
if key==name:
continue
cname=val.__class__.__name__
if cname=='bool' or cname=='float' or cname=='int' or cname=='str':
val=str(val)
val=val.replace('-', 'n')
val=val.replace('+', 'p')
params.append(val)
params='_'.join(params).replace('.', '')
if len(params)>0:
params='_'+params
else: # otherwise problems with one interface (FIXME: find out which)
params='_fnord'
dir=DIR_OUTPUT+os.sep+category.get_as_string(catID)+os.sep
return dir+out[name]+params+EXT_OUTPUT
def write (catID, out):
"""
Write given testcase data to a file.
@param cat ID of the category, like category.KERNEL
@param out data to be written into file
@return Success of operation
"""
fnam=_get_filename(catID, out)
print 'Writing for '+category.get_as_string(catID).upper()+': '+ \
os.path.basename(fnam)
dirname=os.path.dirname(fnam)
if not os.path.isdir(dirname):
os.mkdir(dirname)
mfile=open(fnam, mode='w')
for key, val in out.iteritems():
cname=val.__class__.__name__
if cname=='bool' or cname=='str':
mfile.write("%s = '%s';\n"%(key, val))
elif cname=='ndarray' or cname=='matrix':
mfile.write("%s;\n"%_get_matrix(key, val))
else:
mfile.write("%s = %s;\n"%(key, val))
mfile.close()
return True
def get_output(catID, params, prefix=''):
"""
Return output data to be written into the testcase's file.
After computations, the gathered data is structured and
put into one data structure which can conveniently be written to a
file that will represent the testcase.
@param catID ID of entity's category, e.g. category.DISTANCE
@param params hash with parameters to entity
@param prefix prefix for parameter's name, e.g. 'subkernel'
@return Dict containing testcase data ready to be written to file
"""
out = {}
prefix = category.get_as_string(catID) + '_' + prefix
if catID == category.CLASSIFIER:
out = _get_output_classifier(params, prefix)
elif catID == category.CLUSTERING:
out = _get_output_distribution(params, prefix)
elif catID == category.DISTANCE:
out = _get_output_distance(params, prefix)
elif catID == category.DISTRIBUTION:
out = _get_output_distribution(params, prefix)
elif catID == category.KERNEL:
out = _get_output_kernel(params, prefix)
elif catID == category.PREPROC:
out = _get_output_preproc(params, prefix)
elif catID == category.REGRESSION:
out = _get_output_regression(params, prefix)
else:
return out
out[prefix + 'name'] = params['name']
if params.has_key('accuracy'):
out[prefix + 'accuracy'] = params['accuracy']
# example data
if params.has_key('data'):
out[prefix + 'data_train'] = matrix(params['data']['train'])
out[prefix + 'data_test'] = matrix(params['data']['test'])
# params wrt feature class & type
if params.has_key('feature_class'):
fclass = params['feature_class']
ftype = params['feature_type']
out[prefix + 'feature_class'] = fclass
out[prefix + 'feature_type'] = ftype
if fclass == 'string' or (fclass == 'simple' and ftype == 'Char'):
if params.has_key('alphabet'):
out[prefix + 'alphabet'] = params['alphabet']
else:
out[prefix + 'alphabet'] = 'DNA'
out[prefix + 'seqlen'] = dataop.LEN_SEQ
elif fclass == 'simple' and ftype == 'Byte':
out[prefix + 'alphabet'] = 'RAWBYTE'
out[prefix + 'seqlen'] = dataop.LEN_SEQ
elif fclass == 'string_complex':
if params.has_key('alphabet'):
out[prefix + 'alphabet'] = params['alphabet']
else:
out[prefix + 'alphabet'] = 'DNA'
if params.has_key('order'):
out[prefix + 'order'] = params['order']
else:
out[prefix + 'order'] = featop.WORDSTRING_ORDER
if params.has_key('gap'):
out[prefix + 'gap'] = params['gap']
else:
out[prefix + 'gap'] = featop.WORDSTRING_GAP
if params.has_key('reverse'):
out[prefix + 'reverse'] = params['reverse']
else:
out[prefix + 'reverse'] = featop.WORDSTRING_REVERSE
if params.has_key('seqlen'):
out[prefix + 'seqlen'] = params['seqlen']
else:
out[prefix + 'seqlen'] = dataop.LEN_SEQ
out['init_random'] = dataop.INIT_RANDOM
return out
def get_output (catID, params, prefix=''):
"""
Return output data to be written into the testcase's file.
After computations, the gathered data is structured and
put into one data structure which can conveniently be written to a
file that will represent the testcase.
@param catID ID of entity's category, e.g. category.DISTANCE
@param params hash with parameters to entity
@param prefix prefix for parameter's name, e.g. 'subkernel'
@return Dict containing testcase data ready to be written to file
"""
out={}
prefix=category.get_as_string(catID)+'_'+prefix
if catID==category.CLASSIFIER:
out=_get_output_classifier(params, prefix)
elif catID==category.CLUSTERING:
out=_get_output_distribution(params, prefix)
elif catID==category.DISTANCE:
out=_get_output_distance(params, prefix)
elif catID==category.DISTRIBUTION:
out=_get_output_distribution(params, prefix)
elif catID==category.KERNEL:
out=_get_output_kernel(params, prefix)
elif catID==category.PREPROC:
out=_get_output_preproc(params, prefix)
elif catID==category.REGRESSION:
out=_get_output_regression(params, prefix)
else:
return out
out[prefix+'name']=params['name']
if params.has_key('accuracy'):
out[prefix+'accuracy']=params['accuracy']
# example data
if params.has_key('data'):
out[prefix+'data_train']=matrix(params['data']['train'])
out[prefix+'data_test']=matrix(params['data']['test'])
# params wrt feature class & type
if params.has_key('feature_class'):
fclass=params['feature_class']
ftype=params['feature_type']
out[prefix+'feature_class']=fclass
out[prefix+'feature_type']=ftype
if fclass=='string' or (fclass=='simple' and ftype=='Char'):
if params.has_key('alphabet'):
out[prefix+'alphabet']=params['alphabet']
else:
out[prefix+'alphabet']='DNA'
out[prefix+'seqlen']=dataop.LEN_SEQ
elif fclass=='simple' and ftype=='Byte':
out[prefix+'alphabet']='RAWBYTE'
out[prefix+'seqlen']=dataop.LEN_SEQ
elif fclass=='string_complex':
if params.has_key('alphabet'):
out[prefix+'alphabet']=params['alphabet']
else:
out[prefix+'alphabet']='DNA'
if params.has_key('order'):
out[prefix+'order']=params['order']
else:
out[prefix+'order']=featop.WORDSTRING_ORDER
if params.has_key('gap'):
out[prefix+'gap']=params['gap']
else:
out[prefix+'gap']=featop.WORDSTRING_GAP
if params.has_key('reverse'):
out[prefix+'reverse']=params['reverse']
else:
out[prefix+'reverse']=featop.WORDSTRING_REVERSE
if params.has_key('seqlen'):
out[prefix+'seqlen']=params['seqlen']
else:
out[prefix+'seqlen']=dataop.LEN_SEQ
out['init_random']=dataop.INIT_RANDOM
return out
