def check_C_testset(mss_id):
import pylab
import expenv
import numpy
from helper import Options
from method_hierarchy_svm_new import Method
#from method_augmented_svm_new import Method
#costs = 10000 #[float(c) for c in numpy.exp(numpy.linspace(numpy.log(10), numpy.log(20000), 6))]
costs = [float(c) for c in numpy.exp(numpy.linspace(numpy.log(0.4), numpy.log(10), 6))]
print costs
mss = expenv.MultiSplitSet.get(mss_id)
train = mss.get_train_data(-1)
test = mss.get_eval_data(-1)
au_roc = []
au_prc = []
for cost in costs:
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 10
param.transform = cost
param.base_similarity = 1.0
param.taxonomy = mss.taxonomy
param.id = 666
#param.cost = cost
param.cost = 10000
param.freeze()
# train
mymethod = Method(param)
mymethod.train(train)
assessment = mymethod.evaluate(test)
au_roc.append(assessment.auROC)
au_prc.append(assessment.auPRC)
print assessment
assessment.destroySelf()
pylab.title("auROC")
pylab.semilogx(costs, au_roc, "-o")
pylab.show()
pylab.figure()
pylab.title("auPRC")
pylab.semilogx(costs, au_prc, "-o")
pylab.show()
return (costs, au_roc, au_prc)
def main():
print "starting debugging:"
SPLIT_POINTER = -1
from expenv import MultiSplitSet
from helper import Options
# select dataset
#multi_split_set = MultiSplitSet.get(387)
#multi_split_set = MultiSplitSet.get(407)
multi_split_set = MultiSplitSet.get(399)
#dataset_name = multi_split_set.description
# create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeRBFKernel" #"WeightedDegreeStringKernel"#"PolyKernel"
param.wdk_degree = 2
param.cost = 1.0
param.transform = 0.2
param.base_similarity = 1.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
flags= {}
#flags["boosting"] = "ones"
#flags["boosting"] = "L1"
flags["boosting"] = "L2"
#flags["boosting"] = "L2_reg"
flags["signum"] = False
flags["normalize_cost"] = True
flags["all_positions"] = False
flags["wdk_rbf_on"] = False
param.flags = flags
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
def main():
print "starting debugging:"
SPLIT_POINTER = -1
from expenv import MultiSplitSet
from helper import Options
# select dataset
#multi_split_set = MultiSplitSet.get(387)
#multi_split_set = MultiSplitSet.get(407)
multi_split_set = MultiSplitSet.get(399)
#dataset_name = multi_split_set.description
# create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"#"PolyKernel"
param.wdk_degree = 2
param.cost = 1.0
param.transform = 0.2
param.base_similarity = 1
param.taxonomy = multi_split_set.taxonomy
param.id = 666
flags= {}
#flags["boosting"] = "ones"
flags["boosting"] = "L1"
#flags["boosting"] = "L2"
#flags["boosting"] = "L2_reg"
flags["signum"] = False
flags["normalize_cost"] = True
flags["all_positions"] = False
flags["wdk_rbf_on"] = False
param.flags = flags
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
def training_for_sigma(sigma):
print "starting debugging:"
from expenv import MultiSplitSet
# select dataset
multi_split_set = MultiSplitSet.get(393)
SPLIT_POINTER = 1
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel" #"WeightedDegreeRBFKernel" # #
param.wdk_degree = 2
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.base_similarity = sigma
param.degree = 2
param.flags = {}
param.flags["wdk_rbf_on"] = False
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
print "training done"
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
return assessment.auROC
def main():
print "starting debugging:"
SPLIT_POINTER = 1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(399)
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeRBFKernel" #"WeightedDegreeStringKernel"# #
param.wdk_degree = 1
param.cost = 1.0
param.transform = 1.0
param.sigma = 1.0
param.id = 666
param.base_similarity = 1
param.degree = 2
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
print "training done"
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
def training_for_sigma(sigma):
print "starting debugging:"
from expenv import MultiSplitSet
# select dataset
multi_split_set = MultiSplitSet.get(393)
SPLIT_POINTER = 1
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel" #"WeightedDegreeRBFKernel" # #
param.wdk_degree = 2
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.base_similarity = sigma
param.degree = 2
param.flags = {}
param.flags["wdk_rbf_on"] = False
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
print "training done"
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
return assessment.auROC
def main():
print "starting debugging:"
SPLIT_POINTER = 1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(399)
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeRBFKernel" #"WeightedDegreeStringKernel"# #
param.wdk_degree = 1
param.cost = 1.0
param.transform = 1.0
param.sigma = 1.0
param.id = 666
param.base_similarity = 1
param.degree = 2
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train
mymethod = Method(param)
mymethod.train(data_train)
print "training done"
assessment = mymethod.evaluate(data_eval)
print assessment
assessment.destroySelf()
def check_C_testset(mss_id):
import pylab
import expenv
import numpy
from helper import Options
from method_hierarchy_svm_new import Method
#from method_augmented_svm_new import Method
#costs = 10000 #[float(c) for c in numpy.exp(numpy.linspace(numpy.log(10), numpy.log(20000), 6))]
costs = [
float(c)
for c in numpy.exp(numpy.linspace(numpy.log(0.4), numpy.log(10), 6))
]
print costs
mss = expenv.MultiSplitSet.get(mss_id)
train = mss.get_train_data(-1)
test = mss.get_eval_data(-1)
au_roc = []
au_prc = []
for cost in costs:
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 10
param.transform = cost
param.base_similarity = 1.0
param.taxonomy = mss.taxonomy
param.id = 666
#param.cost = cost
param.cost = 10000
param.freeze()
# train
mymethod = Method(param)
mymethod.train(train)
assessment = mymethod.evaluate(test)
au_roc.append(assessment.auROC)
au_prc.append(assessment.auPRC)
print assessment
assessment.destroySelf()
pylab.title("auROC")
pylab.semilogx(costs, au_roc, "-o")
pylab.show()
pylab.figure()
pylab.title("auPRC")
pylab.semilogx(costs, au_prc, "-o")
pylab.show()
return (costs, au_roc, au_prc)