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 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 = "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 main():
print "starting debugging:"
SPLIT_POINTER = 1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(434)
# flags
flags = {}
flags["normalize_cost"] = False
flags["epsilon"] = 1.0
#0.005
flags["kernel_cache"] = 200
flags["use_bias"] = False
# arts params
flags["svm_type"] = "liblineardual"
flags["degree"] = 24
flags["degree_spectrum"] = 4
flags["shifts"] = 0 #32
flags["center_offset"] = 70
flags["train_factor"] = 1
#create mock param object by freezable struct
param = Options()
param.kernel = "Promoter"
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.flags = flags
param.taxonomy = multi_split_set.taxonomy
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 main():
print "starting debugging:"
SPLIT_POINTER = 1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(432)
# flags
flags = {}
flags["normalize_cost"] = False
#flags["epsilon"] = 0.005
flags["kernel_cache"] = 200
flags["use_bias"] = False
# arts params
flags["svm_type"] = "liblineardual"
flags["degree"] = 24
flags["degree_spectrum"] = 4
flags["shifts"] = 0 #32
flags["center_offset"] = 70
flags["train_factor"] = 1
flags["local"] = False
flags["mem"] = "6G"
flags["maxNumThreads"] = 1
#create mock param object by freezable struct
param = Options()
param.kernel = "Promoter"
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.flags = flags
param.taxonomy = multi_split_set.taxonomy.data
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 main():
print "starting debugging:"
SPLIT_POINTER = 1
from expenv import MultiSplitSet
# select dataset
multi_split_set = MultiSplitSet.get(384)
# flags
flags = {}
flags["normalize_cost"] = False
#flags["epsilon"] = 0.005
flags["kernel_cache"] = 200
flags["use_bias"] = False
# arts params
#flags["svm_type"] = "liblineardual"
flags["degree"] = 24
flags["local"] = False
flags["mem"] = "6G"
flags["maxNumThreads"] = 1
#create mock param object by freezable struct
param = Options()
#param.kernel = "GaussianKernel"
param.kernel = "PolyKernel"
param.sigma = 3.0
param.cost = 10.0
param.transform = 1.0
param.id = 666
param.flags = flags
param.taxonomy = multi_split_set.taxonomy.data
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 main():
print "starting debugging:"
SPLIT_POINTER = -1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(399)
#dataset_name = multi_split_set.description
flags = {}
flags["normalize_cost"] = False
flags["epsilon"] = 0.05
flags["cache_size"] = 7
#flags["solver_type"] = "ST_DIRECT" #ST_CPLEX #ST_GLPK) #ST_DIRECT) #ST_NEWTON)
flags["normalize_trace"] = True
flags["interleaved"] = True
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 1
param.cost = 1
param.transform = 1 #2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
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(379)
dataset_name = multi_split_set.description
print "dataset_name", dataset_name
#create mock taxonomy object by freezable struct
#taxonomy = Options()
#taxonomy.data = taxonomy_graph.data
#taxonomy.description = dataset_name
#taxonomy.freeze()
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 1
param.cost = 1.0
param.transform = 2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train hierarchical xval
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
from task_similarities import fetch_gammas
# select dataset
multi_split_set = MultiSplitSet.get(317)
#multi_split_set = MultiSplitSet.get(374)
#multi_split_set = MultiSplitSet.get(2)
dataset_name = multi_split_set.description
transform = 1.0
base = 1.0
similarity_matrix = fetch_gammas(transform, base, dataset_name)
#create mock taxonomy object by freezable struct
taxonomy = Options()
taxonomy.data = similarity_matrix
taxonomy.description = dataset_name
taxonomy.freeze()
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 1
param.cost = 1.0
param.transform = 1.0
param.taxonomy = taxonomy
param.id = 666
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
create_plot_inner(param, data_train, data_eval)
def main():
print "starting debugging:"
SPLIT_POINTER = -1
from expenv import MultiSplitSet
from helper import Options
# select dataset
multi_split_set = MultiSplitSet.get(399)
#dataset_name = multi_split_set.description
flags = {}
flags["normalize_cost"] = False
flags["epsilon"] = 0.05
flags["cache_size"] = 7
#flags["solver_type"] = "ST_DIRECT" #ST_CPLEX #ST_GLPK) #ST_DIRECT) #ST_NEWTON)
flags["normalize_trace"] = True
flags["interleaved"] = True
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 1
param.cost = 1
param.transform = 1 #2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
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(379)
dataset_name = multi_split_set.description
print "dataset_name", dataset_name
#create mock taxonomy object by freezable struct
#taxonomy = Options()
#taxonomy.data = taxonomy_graph.data
#taxonomy.description = dataset_name
#taxonomy.freeze()
#create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 1
param.cost = 1.0
param.transform = 2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
# train hierarchical xval
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(386)
#dataset_name = multi_split_set.description
# create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"#"PolyKernel"
param.wdk_degree = 1
param.cost = 1
param.transform = 2 #2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
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(386)
#dataset_name = multi_split_set.description
# create mock param object by freezable struct
param = Options()
param.kernel = "WeightedDegreeStringKernel"#"PolyKernel"
param.wdk_degree = 1
param.cost = 100
param.transform = 2 #2.0
param.taxonomy = multi_split_set.taxonomy
param.id = 666
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:"
from expenv import MultiSplitSet
from helper import Options
from task_similarities import dataset_to_hierarchy
# select dataset
#multi_split_set = MultiSplitSet.get(317)
multi_split_set = MultiSplitSet.get(432)
#multi_split_set = MultiSplitSet.get(2) #small splicing
#multi_split_set = MultiSplitSet.get(377) #medium splicing
dataset_name = multi_split_set.description
# flags
flags = {}
flags["normalize_cost"] = False
flags["epsilon"] = 1.0
#0.005
flags["kernel_cache"] = 1000
flags["use_bias"] = False
# arts params
flags["svm_type"] = "liblineardual"
flags["degree"] = 24
flags["degree_spectrum"] = 4
flags["shifts"] = 0 #32
flags["train_factor"] = 1
flags["center_offset"] = 70
flags["center_pos"] = 500
#create mock param object by freezable struct
param = Options()
param.kernel = "Promoter"
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.flags = flags
param.taxonomy = multi_split_set.taxonomy
param.freeze()
data_train = multi_split_set.get_train_data(SPLIT_POINTER)
data_eval = multi_split_set.get_eval_data(SPLIT_POINTER)
(perf_xval, final_pred, best_idx_cost) = create_plot_inner(param, data_train, data_eval)
perf_regular = create_plot_regular(param, data_train, data_eval)
# plot performances
import pylab
if TARGET_PARAM=="both":
#X,Y = pylab.meshgrid(range(len(RANGE)), range(len(RANGE)))
cmap = pylab.cm.get_cmap('jet', 20) # 10 discrete colors
pylab.contourf(RANGE, RANGE, perf_xval, cmap=cmap)
#im = pylab.imshow(perf_xval, cmap=cmap, interpolation='bilinear')
pylab.axis('on')
pylab.colorbar()
pylab.title("mss:" + str(multi_split_set.id) + ", task:" + TARGET_TASK + " , param:" + TARGET_PARAM + ", split:" + str(SPLIT_POINTER))
pylab.show()
else:
pylab.semilogx(RANGE, perf_regular, "g-o")
pylab.semilogx(RANGE, perf_xval, "b-o")
#pylab.semilogx([a*0.66 for a in RANGE], perf_xval, "b-o")
#pylab.plot(numpy.array(perf_regular) - numpy.array(perf_xval), "y-o")
#pylab.plot([best_idx_cost], [final_pred], "r+")
pylab.axhline(y=final_pred, color="r")
pylab.axvline(x=RANGE[best_idx_cost], color="r")
pylab.axvline(x=1.0, color="g")
pylab.ylabel(TARGET_MEASURE)
pylab.xlabel(TARGET_PARAM)
pylab.legend( ("outer", "inner xval"), loc="best")
pylab.title("mss:" + str(multi_split_set.id) + ", task:" + TARGET_TASK + " , degree:" + str(param.wdk_degree) + ", split:" + str(SPLIT_POINTER))
pylab.show()
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)
