In [9]:
%load_ext autoreload
%autoreload 2
%matplotlib inline
import eden
import matplotlib.pyplot as plt
from eden.util import configure_logging
import logging
The autoreload extension is already loaded. To reload it, use:
%reload_ext autoreload
In [10]:
from itertools import tee, chain, islice
import numpy as np
import random
from time import time
import datetime
from graphlearn.graphlearn import GraphLearnSampler
from eden.util import fit,estimate
from eden.graph import Vectorizer
import random
# get data
from eden.converter.graph.gspan import gspan_to_eden
from itertools import islice
def get_graphs(dataset_fname, size=100):
return islice(gspan_to_eden(dataset_fname),size)
In [11]:
def fit_sample(graphs, random_state=42):
graphs, graphs_ = tee(graphs)
sampler=GraphLearnSampler(radius_list=[0,1],thickness_list=[2],
min_cip_count=2, min_interface_count=2,
vectorizer=Vectorizer(5), random_state=random_state)
sampler.fit(graphs, nu=0.25, n_jobs=-1)
logger.info('graph grammar stats:')
dataset_size, interface_counts, core_counts, cip_counts = sampler.grammar().size()
logger.info('#instances:%d #interfaces: %d #cores: %d #core-interface-pairs: %d' % (dataset_size, interface_counts, core_counts, cip_counts))
graphs = sampler.sample(graphs_,
n_steps=5, n_samples=4,
target_orig_cip=False,
probabilistic_core_choice=False,
score_core_choice= False,
max_core_size_diff=3,
burnin=1,
omit_seed=True,
max_cycle_size=6,
improving_threshold=0.25,
accept_static_penalty=0,
n_jobs=-1,
select_cip_max_tries=200,
keep_duplicates=True,
generator_mode=True)
return graphs
In [12]:
def fit_and_evaluate(pos_original, neg_original,
pos_sampled, neg_sampled,
pos_test, neg_test,
random_state=42):
# create graph sets...orig augmented and sampled
pos_orig,pos_orig_ = tee(pos_original)
neg_orig,neg_orig_ = tee(neg_original)
pos_sampled, pos_sampled_ = tee(pos_sampled)
neg_sampled, neg_sampled_ = tee(neg_sampled)
pos_augmented = chain(pos_orig_,pos_sampled_)
neg_augmented = chain(neg_orig_,neg_sampled_)
predictive_performances = []
for desc,pos_train,neg_train in [('original',pos_orig, neg_orig),
('sample',pos_sampled,neg_sampled),
('original+sample',pos_augmented, neg_augmented)]:
pos_train,pos_train_ = tee(pos_train)
neg_train,neg_train_ = tee(neg_train)
pos_size=sum(1 for x in pos_train_)
neg_size=sum(1 for x in neg_train_)
logger.info( "-"*80)
logger.info('working on %s'%(desc))
logger.info('training set sizes: #pos: %d #neg: %d'%(pos_size, neg_size))
if pos_size == 0 or neg_size == 0:
logger.info('WARNING: empty dataset')
predictive_performances.append(0)
else:
start=time()
pos_test,pos_test_ = tee(pos_test)
neg_test,neg_test_ = tee(neg_test)
local_estimator = fit(pos_train, neg_train, Vectorizer(4), n_jobs=-1, n_iter_search=1)
apr, roc = estimate(pos_test_, neg_test_, local_estimator, Vectorizer(4))
predictive_performances.append(roc)
logger.info( 'elapsed: %.1f sec'%(time()-start))
return predictive_performances
In [13]:
def evaluate(pos_fname, neg_fname, size=None, percentages=None, n_repetitions=None, train_test_split=None):
# initializing
graphs_pos = get_graphs(pos_fname, size=size)
graphs_neg = get_graphs(neg_fname, size=size)
# train/test split
from eden.util import random_bipartition_iter
pos_train_global,pos_test_global = random_bipartition_iter(graphs_pos,train_test_split,random_state=random.random()*1000)
neg_train_global,neg_test_global = random_bipartition_iter(graphs_neg,train_test_split,random_state=random.random()*1000)
original_repetitions = []
original_sample_repetitions = []
sample_repetitions = []
for percentage in percentages:
originals = []
originals_samples = []
samples = []
for repetition in range(n_repetitions):
random_state = int(313379*percentage+repetition)
random.seed(random_state)
pos_train_global,pos_train_global_ = tee(pos_train_global)
neg_train_global,neg_train_global_ = tee(neg_train_global)
pos_test_global,pos_test_global_ = tee(pos_test_global)
neg_test_global,neg_test_global_ = tee(neg_test_global)
# use shuffled list to create test and sample set
pos,pos_reminder = random_bipartition_iter(pos_train_global_,percentage)
pos,pos_ = tee(pos)
neg,neg_reminder = random_bipartition_iter(neg_train_global_,percentage)
neg,neg_ = tee(neg)
#sample independently from the 2 classes
logger.info('Positive')
sampled_pos = fit_sample(pos_, random_state=random_state)
logger.info('Negative')
sampled_neg = fit_sample(neg_, random_state=random_state)
#evaluate the predictive performance on held out test set
start=time()
logger.info( "="*80)
logger.info( 'repetition: %d/%d'%(repetition+1, n_repetitions))
logger.info( "training percentage:"+str(percentage))
perf_orig,\
perf_samp,\
perf_orig_samp = fit_and_evaluate(pos,neg,
sampled_pos,sampled_neg,
pos_test_global_,neg_test_global_)
logger.info( 'Time elapsed for full repetition: %.1f sec'%((time()-start)))
originals.append(perf_orig)
originals_samples.append(perf_orig_samp)
samples.append(perf_samp)
original_repetitions.append(originals)
original_sample_repetitions.append(originals_samples)
sample_repetitions.append(samples)
return original_repetitions, original_sample_repetitions, sample_repetitions
In [14]:
def plot(dataset, percentages, original_sample_repetitions, original_repetitions, sample_repetitions):
gc={'color':'g'}
rc={'color':'r'}
bc={'color':'b'}
ws = 0.02
os = np.mean(original_sample_repetitions, axis=1)
o = np.mean(original_repetitions, axis=1)
s = np.mean(sample_repetitions, axis=1)
plt.figure(figsize=(18,8))
plt.grid()
plt.boxplot(original_sample_repetitions, positions=percentages, widths=ws, capprops=gc, medianprops=gc, boxprops=gc, whiskerprops=gc, flierprops=gc)
plt.plot(percentages,os, color='g', marker='o', markeredgewidth=1, markersize=7, markeredgecolor='g', markerfacecolor='w', label='original+sample')
plt.boxplot(original_repetitions, positions=percentages, widths=ws, capprops=rc, medianprops=rc, boxprops=rc, whiskerprops=rc, flierprops=rc)
plt.plot(percentages,o, color='r', marker='o', markeredgewidth=1, markersize=7, markeredgecolor='r', markerfacecolor='w', label='original')
plt.boxplot(sample_repetitions, positions=percentages, widths=ws, capprops=bc, medianprops=bc, boxprops=bc, whiskerprops=bc, flierprops=bc)
plt.plot(percentages,s, color='b', marker='o', markeredgewidth=1, markersize=7, markeredgecolor='b', markerfacecolor='w', label='sample')
plt.xlim(percentages[0]-.05,percentages[-1]+.05)
plt.title(dataset+'\n',fontsize=17)
plt.legend(loc='lower right',fontsize=16)
plt.ylabel('ROC AUC',fontsize=16)
plt.xlabel('Dataset size (fraction)',fontsize=16)
plt.savefig('%s_plot_predictive_performance_of_samples.pdf' % dataset)
In [15]:
def save_results(result_fname,percentages, original_repetitions,original_sample_repetitions,sample_repetitions):
with open(result_fname,'w') as f:
f.write('dataset sizes list:\n')
for perc in percentages:
f.write('%s '% perc)
f.write('\n')
f.write('AUC scores:\n')
for repetitions in original_repetitions,original_sample_repetitions,sample_repetitions:
f.write('%s\n' % len(repetitions))
for repetition in repetitions:
for auc in repetition:
f.write('%s ' % auc)
f.write('\n')
def load_results(result_fname):
with open(result_fname) as f:
comment = next(f)
line = next(f)
percentages = [float(x) for x in line.split()]
comment = next(f)
original_repetitions = []
size = int(next(f))
for i in range(size):
line = next(f)
repetition = [float(x) for x in line.split()]
original_repetitions.append(repetition)
original_sample_repetitions = []
size = int(next(f))
for i in range(size):
line = next(f)
repetition = [float(x) for x in line.split()]
original_sample_repetitions.append(repetition)
sample_repetitions = []
size = int(next(f))
for i in range(size):
line = next(f)
repetition = [float(x) for x in line.split()]
sample_repetitions.append(repetition)
return percentages, original_repetitions,original_sample_repetitions,sample_repetitions
In [ ]:
%%time
#special case: bursi
dataset='bursi'
#logging
logger = logging.getLogger()
if True:
logger_fname = '%s_predictive_performance_of_samples.log'%dataset
else:
logger_fname = None
configure_logging(logger,verbosity=1, filename=logger_fname)
#main
start=time()
print( 'Working with dataset: %s' % dataset )
logger.info( 'Working with dataset: %s' % dataset )
pos_dataset_fname = 'bursi.pos.gspan'
neg_dataset_fname = 'bursi.neg.gspan'
percentages=[.05,.2,.4,.6,.8,.95]
original_repetitions,\
original_sample_repetitions,\
sample_repetitions = evaluate(pos_dataset_fname,
neg_dataset_fname,
size=400,
percentages=percentages,
n_repetitions=10,
train_test_split=0.7)
#save and display results
result_fname='%s_predictive_performance_of_samples.data'%dataset
save_results(result_fname,percentages, original_repetitions,original_sample_repetitions,sample_repetitions)
percentages_l, original_repetitions_l,original_sample_repetitions_l,sample_repetitions_l = load_results(result_fname)
plot(dataset, percentages_l, original_sample_repetitions_l, original_repetitions_l, sample_repetitions_l)
print('Time elapsed: %s'%(datetime.timedelta(seconds=(time() - start))))
Working with dataset: bursi
Working with dataset: bursi
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 1/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.67 0.67 120
1 0.67 0.68 0.68 120
avg / total 0.68 0.68 0.67 240
APR: 0.666
ROC: 0.716
Cross-validated estimate
accuracy: 0.812 +- 0.026
precision: 0.841 +- 0.031
recall: 0.775 +- 0.077
f1: 0.803 +- 0.037
average_precision: 0.852 +- 0.042
roc_auc: 0.861 +- 0.005
elapsed: 4.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 26
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.64 0.72 0.68 120
1 0.69 0.60 0.64 120
avg / total 0.67 0.66 0.66 240
APR: 0.717
ROC: 0.729
Cross-validated estimate
accuracy: 0.800 +- 0.039
precision: 0.838 +- 0.058
recall: 0.750 +- 0.065
f1: 0.789 +- 0.043
average_precision: 0.848 +- 0.036
roc_auc: 0.856 +- 0.017
elapsed: 4.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 40
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.67 0.68 120
1 0.68 0.70 0.69 120
avg / total 0.68 0.68 0.68 240
APR: 0.704
ROC: 0.736
Cross-validated estimate
accuracy: 0.804 +- 0.049
precision: 0.840 +- 0.021
recall: 0.750 +- 0.105
f1: 0.789 +- 0.070
average_precision: 0.850 +- 0.008
roc_auc: 0.857 +- 0.018
elapsed: 4.5 sec
Time elapsed: 20.0 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 2/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.56 0.64 120
1 0.65 0.82 0.73 120
avg / total 0.71 0.69 0.69 240
APR: 0.678
ROC: 0.730
Cross-validated estimate
accuracy: 0.796 +- 0.033
precision: 0.837 +- 0.048
recall: 0.742 +- 0.085
f1: 0.782 +- 0.047
average_precision: 0.866 +- 0.016
roc_auc: 0.867 +- 0.013
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.61 0.66 120
1 0.66 0.78 0.72 120
avg / total 0.70 0.69 0.69 240
APR: 0.679
ROC: 0.728
Cross-validated estimate
accuracy: 0.800 +- 0.028
precision: 0.860 +- 0.053
recall: 0.725 +- 0.077
f1: 0.782 +- 0.040
average_precision: 0.857 +- 0.036
roc_auc: 0.861 +- 0.012
elapsed: 4.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.72 0.70 120
1 0.71 0.68 0.69 120
avg / total 0.70 0.70 0.70 240
APR: 0.723
ROC: 0.751
Cross-validated estimate
accuracy: 0.800 +- 0.043
precision: 0.834 +- 0.038
recall: 0.750 +- 0.087
f1: 0.787 +- 0.057
average_precision: 0.861 +- 0.023
roc_auc: 0.857 +- 0.007
elapsed: 4.3 sec
Time elapsed: 18.8 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 3/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.66 0.67 120
1 0.67 0.68 0.67 120
avg / total 0.67 0.67 0.67 240
APR: 0.712
ROC: 0.735
Cross-validated estimate
accuracy: 0.796 +- 0.031
precision: 0.840 +- 0.055
recall: 0.742 +- 0.085
f1: 0.782 +- 0.039
average_precision: 0.861 +- 0.037
roc_auc: 0.870 +- 0.016
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.76 0.73 120
1 0.73 0.67 0.70 120
avg / total 0.71 0.71 0.71 240
APR: 0.766
ROC: 0.775
Cross-validated estimate
accuracy: 0.804 +- 0.041
precision: 0.831 +- 0.039
recall: 0.767 +- 0.094
f1: 0.794 +- 0.057
average_precision: 0.861 +- 0.024
roc_auc: 0.860 +- 0.012
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.72 0.70 120
1 0.70 0.66 0.68 120
avg / total 0.69 0.69 0.69 240
APR: 0.748
ROC: 0.760
Cross-validated estimate
accuracy: 0.800 +- 0.028
precision: 0.824 +- 0.028
recall: 0.767 +- 0.082
f1: 0.791 +- 0.041
average_precision: 0.864 +- 0.017
roc_auc: 0.866 +- 0.007
elapsed: 4.5 sec
Time elapsed: 18.9 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 4/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.66 0.67 120
1 0.67 0.69 0.68 120
avg / total 0.68 0.68 0.67 240
APR: 0.703
ROC: 0.724
Cross-validated estimate
accuracy: 0.796 +- 0.050
precision: 0.840 +- 0.026
recall: 0.733 +- 0.128
f1: 0.776 +- 0.078
average_precision: 0.870 +- 0.017
roc_auc: 0.860 +- 0.024
elapsed: 4.1 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.66 0.69 120
1 0.69 0.75 0.72 120
avg / total 0.71 0.70 0.70 240
APR: 0.729
ROC: 0.750
Cross-validated estimate
accuracy: 0.804 +- 0.031
precision: 0.832 +- 0.037
recall: 0.767 +- 0.082
f1: 0.795 +- 0.043
average_precision: 0.855 +- 0.018
roc_auc: 0.860 +- 0.019
elapsed: 4.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.65 0.72 0.68 120
1 0.69 0.62 0.65 120
avg / total 0.67 0.67 0.67 240
APR: 0.715
ROC: 0.736
Cross-validated estimate
accuracy: 0.808 +- 0.042
precision: 0.826 +- 0.029
recall: 0.783 +- 0.103
f1: 0.800 +- 0.060
average_precision: 0.864 +- 0.025
roc_auc: 0.870 +- 0.013
elapsed: 4.6 sec
Time elapsed: 19.0 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 5/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.60 0.66 120
1 0.66 0.78 0.71 120
avg / total 0.69 0.69 0.69 240
APR: 0.677
ROC: 0.736
Cross-validated estimate
accuracy: 0.804 +- 0.025
precision: 0.851 +- 0.066
recall: 0.750 +- 0.065
f1: 0.792 +- 0.028
average_precision: 0.859 +- 0.033
roc_auc: 0.864 +- 0.018
elapsed: 4.5 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 26
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.60 0.75 0.67 120
1 0.67 0.50 0.57 120
avg / total 0.63 0.62 0.62 240
APR: 0.655
ROC: 0.697
Cross-validated estimate
accuracy: 0.796 +- 0.040
precision: 0.848 +- 0.040
recall: 0.725 +- 0.094
f1: 0.777 +- 0.059
average_precision: 0.847 +- 0.041
roc_auc: 0.851 +- 0.012
elapsed: 4.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 40
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.64 0.69 120
1 0.69 0.79 0.74 120
avg / total 0.72 0.72 0.72 240
APR: 0.692
ROC: 0.750
Cross-validated estimate
accuracy: 0.788 +- 0.044
precision: 0.823 +- 0.040
recall: 0.733 +- 0.094
f1: 0.773 +- 0.059
average_precision: 0.851 +- 0.028
roc_auc: 0.855 +- 0.009
elapsed: 4.4 sec
Time elapsed: 19.1 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 6/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.70 0.68 0.69 120
1 0.69 0.72 0.70 120
avg / total 0.70 0.70 0.70 240
APR: 0.729
ROC: 0.746
Cross-validated estimate
accuracy: 0.804 +- 0.028
precision: 0.835 +- 0.015
recall: 0.758 +- 0.067
f1: 0.793 +- 0.040
average_precision: 0.866 +- 0.028
roc_auc: 0.869 +- 0.021
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.56 0.63 120
1 0.64 0.79 0.71 120
avg / total 0.69 0.68 0.67 240
APR: 0.753
ROC: 0.767
Cross-validated estimate
accuracy: 0.792 +- 0.035
precision: 0.836 +- 0.039
recall: 0.733 +- 0.111
f1: 0.774 +- 0.058
average_precision: 0.849 +- 0.028
roc_auc: 0.853 +- 0.012
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.63 0.66 120
1 0.66 0.70 0.68 120
avg / total 0.67 0.67 0.67 240
APR: 0.694
ROC: 0.722
Cross-validated estimate
accuracy: 0.817 +- 0.024
precision: 0.865 +- 0.043
recall: 0.758 +- 0.093
f1: 0.802 +- 0.043
average_precision: 0.858 +- 0.021
roc_auc: 0.859 +- 0.005
elapsed: 4.5 sec
Time elapsed: 19.4 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 7/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.64 0.67 120
1 0.67 0.73 0.70 120
avg / total 0.69 0.69 0.69 240
APR: 0.695
ROC: 0.723
Cross-validated estimate
accuracy: 0.808 +- 0.048
precision: 0.845 +- 0.027
recall: 0.758 +- 0.122
f1: 0.793 +- 0.071
average_precision: 0.853 +- 0.019
roc_auc: 0.859 +- 0.015
elapsed: 4.3 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 26
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.71 0.70 120
1 0.70 0.68 0.69 120
avg / total 0.70 0.70 0.70 240
APR: 0.702
ROC: 0.736
Cross-validated estimate
accuracy: 0.808 +- 0.036
precision: 0.838 +- 0.035
recall: 0.767 +- 0.082
f1: 0.798 +- 0.047
average_precision: 0.872 +- 0.032
roc_auc: 0.872 +- 0.011
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 40
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.67 0.82 0.74 120
1 0.77 0.60 0.67 120
avg / total 0.72 0.71 0.70 240
APR: 0.729
ROC: 0.766
Cross-validated estimate
accuracy: 0.808 +- 0.033
precision: 0.842 +- 0.041
recall: 0.767 +- 0.101
f1: 0.797 +- 0.051
average_precision: 0.863 +- 0.007
roc_auc: 0.865 +- 0.018
elapsed: 4.4 sec
Time elapsed: 19.0 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 8/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.65 0.72 0.68 120
1 0.68 0.61 0.64 120
avg / total 0.66 0.66 0.66 240
APR: 0.685
ROC: 0.712
Cross-validated estimate
accuracy: 0.812 +- 0.040
precision: 0.854 +- 0.039
recall: 0.758 +- 0.093
f1: 0.799 +- 0.055
average_precision: 0.860 +- 0.013
roc_auc: 0.859 +- 0.023
elapsed: 4.1 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 14 #neg: 26
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.59 0.72 0.64 120
1 0.63 0.49 0.55 120
avg / total 0.61 0.60 0.60 240
APR: 0.642
ROC: 0.699
Cross-validated estimate
accuracy: 0.796 +- 0.038
precision: 0.816 +- 0.035
recall: 0.767 +- 0.090
f1: 0.787 +- 0.050
average_precision: 0.861 +- 0.025
roc_auc: 0.862 +- 0.009
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 28 #neg: 40
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.68 0.70 120
1 0.70 0.72 0.71 120
avg / total 0.70 0.70 0.70 240
APR: 0.720
ROC: 0.757
Cross-validated estimate
accuracy: 0.812 +- 0.046
precision: 0.840 +- 0.041
recall: 0.775 +- 0.097
f1: 0.802 +- 0.061
average_precision: 0.862 +- 0.030
roc_auc: 0.854 +- 0.020
elapsed: 4.4 sec
Time elapsed: 18.7 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 9/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.67 0.64 0.66 120
1 0.66 0.68 0.67 120
avg / total 0.66 0.66 0.66 240
APR: 0.714
ROC: 0.735
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.840 +- 0.019
recall: 0.733 +- 0.101
f1: 0.778 +- 0.058
average_precision: 0.850 +- 0.038
roc_auc: 0.856 +- 0.009
elapsed: 4.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.67 0.69 0.68 120
1 0.68 0.67 0.68 120
avg / total 0.68 0.68 0.68 240
APR: 0.721
ROC: 0.739
Cross-validated estimate
accuracy: 0.812 +- 0.037
precision: 0.845 +- 0.028
recall: 0.767 +- 0.086
f1: 0.801 +- 0.050
average_precision: 0.864 +- 0.027
roc_auc: 0.871 +- 0.020
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.77 0.74 120
1 0.75 0.69 0.72 120
avg / total 0.73 0.73 0.73 240
APR: 0.752
ROC: 0.782
Cross-validated estimate
accuracy: 0.804 +- 0.043
precision: 0.817 +- 0.035
recall: 0.783 +- 0.072
f1: 0.799 +- 0.050
average_precision: 0.862 +- 0.022
roc_auc: 0.869 +- 0.016
elapsed: 4.3 sec
Time elapsed: 19.0 sec
Positive
graph grammar stats:
#instances:14 #interfaces: 4 #cores: 9 #core-interface-pairs: 10
Negative
graph grammar stats:
#instances:14 #interfaces: 9 #cores: 9 #core-interface-pairs: 20
================================================================================
repetition: 10/10
training percentage:0.05
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 14 #neg: 14
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.65 0.68 0.67 120
1 0.67 0.63 0.65 120
avg / total 0.66 0.66 0.66 240
APR: 0.700
ROC: 0.720
Cross-validated estimate
accuracy: 0.833 +- 0.042
precision: 0.855 +- 0.043
recall: 0.808 +- 0.101
f1: 0.826 +- 0.054
average_precision: 0.863 +- 0.039
roc_auc: 0.870 +- 0.010
elapsed: 4.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 16 #neg: 25
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.64 0.85 0.73 120
1 0.78 0.52 0.62 120
avg / total 0.71 0.68 0.67 240
APR: 0.713
ROC: 0.748
Cross-validated estimate
accuracy: 0.792 +- 0.037
precision: 0.824 +- 0.036
recall: 0.750 +- 0.118
f1: 0.778 +- 0.061
average_precision: 0.870 +- 0.010
roc_auc: 0.866 +- 0.016
elapsed: 4.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 30 #neg: 39
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.67 0.80 0.73 120
1 0.75 0.61 0.67 120
avg / total 0.71 0.70 0.70 240
APR: 0.692
ROC: 0.740
Cross-validated estimate
accuracy: 0.808 +- 0.040
precision: 0.847 +- 0.035
recall: 0.758 +- 0.113
f1: 0.794 +- 0.059
average_precision: 0.849 +- 0.016
roc_auc: 0.857 +- 0.014
elapsed: 4.2 sec
Time elapsed: 18.6 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 1/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.78 0.78 120
1 0.78 0.78 0.78 120
avg / total 0.78 0.78 0.78 240
APR: 0.804
ROC: 0.825
Cross-validated estimate
accuracy: 0.800 +- 0.039
precision: 0.842 +- 0.034
recall: 0.742 +- 0.089
f1: 0.785 +- 0.053
average_precision: 0.864 +- 0.010
roc_auc: 0.860 +- 0.018
elapsed: 4.9 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.70 0.69 120
1 0.69 0.68 0.69 120
avg / total 0.69 0.69 0.69 240
APR: 0.748
ROC: 0.757
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.843 +- 0.034
recall: 0.733 +- 0.107
f1: 0.778 +- 0.058
average_precision: 0.850 +- 0.029
roc_auc: 0.857 +- 0.013
elapsed: 7.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.74 0.77 0.75 120
1 0.76 0.73 0.75 120
avg / total 0.75 0.75 0.75 240
APR: 0.777
ROC: 0.812
Cross-validated estimate
accuracy: 0.821 +- 0.045
precision: 0.841 +- 0.043
recall: 0.792 +- 0.070
f1: 0.814 +- 0.051
average_precision: 0.860 +- 0.044
roc_auc: 0.863 +- 0.015
elapsed: 8.0 sec
Time elapsed: 29.3 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 2/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.78 0.76 120
1 0.77 0.74 0.75 120
avg / total 0.76 0.76 0.76 240
APR: 0.798
ROC: 0.815
Cross-validated estimate
accuracy: 0.821 +- 0.021
precision: 0.851 +- 0.040
recall: 0.783 +- 0.061
f1: 0.813 +- 0.028
average_precision: 0.861 +- 0.021
roc_auc: 0.862 +- 0.011
elapsed: 5.3 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.70 0.69 0.70 120
1 0.70 0.71 0.70 120
avg / total 0.70 0.70 0.70 240
APR: 0.735
ROC: 0.769
Cross-validated estimate
accuracy: 0.787 +- 0.033
precision: 0.808 +- 0.029
recall: 0.758 +- 0.100
f1: 0.778 +- 0.051
average_precision: 0.842 +- 0.030
roc_auc: 0.849 +- 0.013
elapsed: 5.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.70 0.72 0.71 120
1 0.71 0.70 0.71 120
avg / total 0.71 0.71 0.71 240
APR: 0.750
ROC: 0.788
Cross-validated estimate
accuracy: 0.804 +- 0.049
precision: 0.840 +- 0.041
recall: 0.750 +- 0.087
f1: 0.791 +- 0.062
average_precision: 0.856 +- 0.038
roc_auc: 0.865 +- 0.023
elapsed: 5.9 sec
Time elapsed: 24.9 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 3/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.73 0.73 120
1 0.73 0.73 0.73 120
avg / total 0.73 0.73 0.73 240
APR: 0.785
ROC: 0.806
Cross-validated estimate
accuracy: 0.812 +- 0.032
precision: 0.847 +- 0.027
recall: 0.767 +- 0.094
f1: 0.800 +- 0.050
average_precision: 0.849 +- 0.025
roc_auc: 0.861 +- 0.015
elapsed: 4.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.65 0.73 0.69 120
1 0.70 0.61 0.65 120
avg / total 0.67 0.67 0.67 240
APR: 0.737
ROC: 0.735
Cross-validated estimate
accuracy: 0.817 +- 0.028
precision: 0.871 +- 0.042
recall: 0.750 +- 0.087
f1: 0.801 +- 0.044
average_precision: 0.855 +- 0.032
roc_auc: 0.862 +- 0.015
elapsed: 5.7 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.82 0.76 120
1 0.79 0.68 0.73 120
avg / total 0.75 0.75 0.74 240
APR: 0.815
ROC: 0.814
Cross-validated estimate
accuracy: 0.812 +- 0.029
precision: 0.842 +- 0.042
recall: 0.775 +- 0.073
f1: 0.804 +- 0.037
average_precision: 0.868 +- 0.025
roc_auc: 0.870 +- 0.012
elapsed: 6.3 sec
Time elapsed: 24.8 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 4/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.78 0.76 120
1 0.77 0.72 0.74 120
avg / total 0.75 0.75 0.75 240
APR: 0.781
ROC: 0.798
Cross-validated estimate
accuracy: 0.812 +- 0.051
precision: 0.838 +- 0.042
recall: 0.775 +- 0.097
f1: 0.802 +- 0.062
average_precision: 0.859 +- 0.039
roc_auc: 0.864 +- 0.009
elapsed: 4.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.78 0.74 120
1 0.75 0.68 0.72 120
avg / total 0.73 0.73 0.73 240
APR: 0.757
ROC: 0.773
Cross-validated estimate
accuracy: 0.800 +- 0.039
precision: 0.828 +- 0.017
recall: 0.758 +- 0.100
f1: 0.788 +- 0.057
average_precision: 0.851 +- 0.042
roc_auc: 0.866 +- 0.003
elapsed: 7.0 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.76 0.75 120
1 0.75 0.72 0.74 120
avg / total 0.74 0.74 0.74 240
APR: 0.808
ROC: 0.817
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.821 +- 0.020
recall: 0.758 +- 0.100
f1: 0.784 +- 0.054
average_precision: 0.852 +- 0.035
roc_auc: 0.855 +- 0.019
elapsed: 8.4 sec
Time elapsed: 29.0 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 5/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.79 0.77 120
1 0.78 0.74 0.76 120
avg / total 0.77 0.77 0.77 240
APR: 0.833
ROC: 0.835
Cross-validated estimate
accuracy: 0.825 +- 0.028
precision: 0.851 +- 0.019
recall: 0.792 +- 0.087
f1: 0.816 +- 0.044
average_precision: 0.859 +- 0.037
roc_auc: 0.865 +- 0.009
elapsed: 4.9 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.69 0.72 0.70 120
1 0.70 0.68 0.69 120
avg / total 0.70 0.70 0.70 240
APR: 0.751
ROC: 0.750
Cross-validated estimate
accuracy: 0.808 +- 0.020
precision: 0.862 +- 0.046
recall: 0.742 +- 0.081
f1: 0.792 +- 0.037
average_precision: 0.862 +- 0.027
roc_auc: 0.868 +- 0.012
elapsed: 5.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.78 0.75 120
1 0.76 0.71 0.73 120
avg / total 0.74 0.74 0.74 240
APR: 0.792
ROC: 0.812
Cross-validated estimate
accuracy: 0.796 +- 0.044
precision: 0.839 +- 0.041
recall: 0.733 +- 0.082
f1: 0.780 +- 0.057
average_precision: 0.862 +- 0.029
roc_auc: 0.863 +- 0.015
elapsed: 6.1 sec
Time elapsed: 24.1 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 6/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.74 0.75 0.74 120
1 0.75 0.73 0.74 120
avg / total 0.74 0.74 0.74 240
APR: 0.779
ROC: 0.808
Cross-validated estimate
accuracy: 0.812 +- 0.040
precision: 0.848 +- 0.039
recall: 0.767 +- 0.097
f1: 0.800 +- 0.055
average_precision: 0.859 +- 0.037
roc_auc: 0.857 +- 0.012
elapsed: 4.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.68 0.70 120
1 0.69 0.73 0.71 120
avg / total 0.70 0.70 0.70 240
APR: 0.788
ROC: 0.774
Cross-validated estimate
accuracy: 0.808 +- 0.024
precision: 0.834 +- 0.038
recall: 0.775 +- 0.068
f1: 0.800 +- 0.032
average_precision: 0.864 +- 0.014
roc_auc: 0.867 +- 0.018
elapsed: 6.7 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.78 0.75 120
1 0.76 0.70 0.73 120
avg / total 0.74 0.74 0.74 240
APR: 0.795
ROC: 0.801
Cross-validated estimate
accuracy: 0.808 +- 0.024
precision: 0.834 +- 0.040
recall: 0.775 +- 0.073
f1: 0.800 +- 0.033
average_precision: 0.864 +- 0.019
roc_auc: 0.866 +- 0.013
elapsed: 8.2 sec
Time elapsed: 29.9 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 7/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.81 0.76 120
1 0.78 0.68 0.73 120
avg / total 0.75 0.75 0.74 240
APR: 0.782
ROC: 0.805
Cross-validated estimate
accuracy: 0.804 +- 0.039
precision: 0.851 +- 0.039
recall: 0.742 +- 0.093
f1: 0.788 +- 0.054
average_precision: 0.852 +- 0.020
roc_auc: 0.852 +- 0.007
elapsed: 10.9 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 106
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.63 0.67 120
1 0.67 0.74 0.70 120
avg / total 0.69 0.69 0.69 240
APR: 0.757
ROC: 0.769
Cross-validated estimate
accuracy: 0.787 +- 0.048
precision: 0.817 +- 0.045
recall: 0.742 +- 0.089
f1: 0.775 +- 0.062
average_precision: 0.838 +- 0.056
roc_auc: 0.854 +- 0.019
elapsed: 9.0 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 162
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.74 0.75 0.74 120
1 0.75 0.73 0.74 120
avg / total 0.74 0.74 0.74 240
APR: 0.770
ROC: 0.802
Cross-validated estimate
accuracy: 0.808 +- 0.042
precision: 0.835 +- 0.029
recall: 0.767 +- 0.073
f1: 0.798 +- 0.053
average_precision: 0.854 +- 0.041
roc_auc: 0.867 +- 0.013
elapsed: 9.3 sec
Time elapsed: 44.9 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 8/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.82 0.77 120
1 0.79 0.70 0.74 120
avg / total 0.76 0.76 0.76 240
APR: 0.814
ROC: 0.826
Cross-validated estimate
accuracy: 0.808 +- 0.031
precision: 0.850 +- 0.026
recall: 0.750 +- 0.075
f1: 0.795 +- 0.043
average_precision: 0.885 +- 0.009
roc_auc: 0.878 +- 0.016
elapsed: 4.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 105
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.68 0.67 0.67 120
1 0.67 0.68 0.68 120
avg / total 0.68 0.68 0.67 240
APR: 0.766
ROC: 0.758
Cross-validated estimate
accuracy: 0.779 +- 0.063
precision: 0.806 +- 0.066
recall: 0.733 +- 0.082
f1: 0.767 +- 0.071
average_precision: 0.856 +- 0.023
roc_auc: 0.860 +- 0.010
elapsed: 5.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 161
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.72 0.74 0.73 120
1 0.74 0.72 0.73 120
avg / total 0.73 0.73 0.73 240
APR: 0.776
ROC: 0.799
Cross-validated estimate
accuracy: 0.812 +- 0.013
precision: 0.864 +- 0.045
recall: 0.750 +- 0.075
f1: 0.798 +- 0.028
average_precision: 0.861 +- 0.025
roc_auc: 0.859 +- 0.008
elapsed: 5.9 sec
Time elapsed: 23.9 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 9/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.74 0.80 0.77 120
1 0.78 0.72 0.75 120
avg / total 0.76 0.76 0.76 240
APR: 0.802
ROC: 0.819
Cross-validated estimate
accuracy: 0.787 +- 0.036
precision: 0.831 +- 0.031
recall: 0.725 +- 0.094
f1: 0.770 +- 0.056
average_precision: 0.854 +- 0.033
roc_auc: 0.859 +- 0.011
elapsed: 4.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 105
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.72 0.73 120
1 0.73 0.73 0.73 120
avg / total 0.73 0.73 0.73 240
APR: 0.785
ROC: 0.791
Cross-validated estimate
accuracy: 0.817 +- 0.028
precision: 0.848 +- 0.052
recall: 0.783 +- 0.103
f1: 0.807 +- 0.047
average_precision: 0.852 +- 0.036
roc_auc: 0.860 +- 0.010
elapsed: 5.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 161
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.80 0.77 120
1 0.79 0.73 0.76 120
avg / total 0.77 0.77 0.77 240
APR: 0.803
ROC: 0.809
Cross-validated estimate
accuracy: 0.812 +- 0.053
precision: 0.844 +- 0.037
recall: 0.767 +- 0.114
f1: 0.799 +- 0.070
average_precision: 0.863 +- 0.029
roc_auc: 0.867 +- 0.009
elapsed: 6.2 sec
Time elapsed: 24.6 sec
Positive
graph grammar stats:
#instances:56 #interfaces: 23 #cores: 25 #core-interface-pairs: 65
Negative
graph grammar stats:
#instances:56 #interfaces: 38 #cores: 33 #core-interface-pairs: 104
================================================================================
repetition: 10/10
training percentage:0.2
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 56 #neg: 56
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.81 0.78 120
1 0.79 0.72 0.76 120
avg / total 0.77 0.77 0.77 240
APR: 0.798
ROC: 0.821
Cross-validated estimate
accuracy: 0.804 +- 0.034
precision: 0.844 +- 0.043
recall: 0.750 +- 0.075
f1: 0.791 +- 0.043
average_precision: 0.852 +- 0.049
roc_auc: 0.864 +- 0.019
elapsed: 4.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 106 #neg: 105
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.70 0.72 0.71 120
1 0.71 0.68 0.70 120
avg / total 0.70 0.70 0.70 240
APR: 0.746
ROC: 0.773
Cross-validated estimate
accuracy: 0.812 +- 0.023
precision: 0.840 +- 0.049
recall: 0.783 +- 0.100
f1: 0.803 +- 0.043
average_precision: 0.870 +- 0.023
roc_auc: 0.873 +- 0.021
elapsed: 5.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 162 #neg: 161
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.71 0.78 0.75 120
1 0.76 0.68 0.72 120
avg / total 0.74 0.73 0.73 240
APR: 0.803
ROC: 0.809
Cross-validated estimate
accuracy: 0.808 +- 0.042
precision: 0.832 +- 0.033
recall: 0.775 +- 0.101
f1: 0.798 +- 0.059
average_precision: 0.861 +- 0.015
roc_auc: 0.865 +- 0.008
elapsed: 6.3 sec
Time elapsed: 24.8 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 1/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.84 0.79 120
1 0.82 0.72 0.76 120
avg / total 0.78 0.78 0.78 240
APR: 0.827
ROC: 0.843
Cross-validated estimate
accuracy: 0.808 +- 0.036
precision: 0.846 +- 0.027
recall: 0.758 +- 0.100
f1: 0.795 +- 0.054
average_precision: 0.854 +- 0.032
roc_auc: 0.861 +- 0.013
elapsed: 5.5 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.67 0.74 120
1 0.72 0.87 0.79 120
avg / total 0.78 0.77 0.76 240
APR: 0.817
ROC: 0.825
Cross-validated estimate
accuracy: 0.812 +- 0.035
precision: 0.840 +- 0.035
recall: 0.775 +- 0.077
f1: 0.803 +- 0.046
average_precision: 0.856 +- 0.038
roc_auc: 0.869 +- 0.012
elapsed: 9.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.78 0.80 120
1 0.79 0.82 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.829
ROC: 0.838
Cross-validated estimate
accuracy: 0.787 +- 0.061
precision: 0.833 +- 0.038
recall: 0.717 +- 0.122
f1: 0.766 +- 0.086
average_precision: 0.856 +- 0.025
roc_auc: 0.861 +- 0.007
elapsed: 8.5 sec
Time elapsed: 40.1 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 2/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.73 0.86 0.79 120
1 0.83 0.68 0.75 120
avg / total 0.78 0.77 0.77 240
APR: 0.846
ROC: 0.851
Cross-validated estimate
accuracy: 0.787 +- 0.028
precision: 0.834 +- 0.049
recall: 0.725 +- 0.073
f1: 0.772 +- 0.039
average_precision: 0.863 +- 0.025
roc_auc: 0.859 +- 0.006
elapsed: 5.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.76 0.77 120
1 0.76 0.78 0.77 120
avg / total 0.77 0.77 0.77 240
APR: 0.818
ROC: 0.824
Cross-validated estimate
accuracy: 0.817 +- 0.033
precision: 0.855 +- 0.041
recall: 0.767 +- 0.073
f1: 0.805 +- 0.043
average_precision: 0.867 +- 0.028
roc_auc: 0.866 +- 0.010
elapsed: 9.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.80 0.79 120
1 0.79 0.77 0.78 120
avg / total 0.78 0.78 0.78 240
APR: 0.844
ROC: 0.849
Cross-validated estimate
accuracy: 0.817 +- 0.016
precision: 0.848 +- 0.025
recall: 0.775 +- 0.057
f1: 0.808 +- 0.025
average_precision: 0.859 +- 0.048
roc_auc: 0.868 +- 0.013
elapsed: 8.6 sec
Time elapsed: 39.3 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 3/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.87 0.81 120
1 0.85 0.73 0.79 120
avg / total 0.81 0.80 0.80 240
APR: 0.843
ROC: 0.852
Cross-validated estimate
accuracy: 0.808 +- 0.024
precision: 0.839 +- 0.031
recall: 0.767 +- 0.073
f1: 0.798 +- 0.036
average_precision: 0.865 +- 0.016
roc_auc: 0.865 +- 0.008
elapsed: 5.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.68 0.72 120
1 0.71 0.81 0.76 120
avg / total 0.75 0.74 0.74 240
APR: 0.819
ROC: 0.817
Cross-validated estimate
accuracy: 0.808 +- 0.040
precision: 0.845 +- 0.017
recall: 0.758 +- 0.110
f1: 0.794 +- 0.064
average_precision: 0.857 +- 0.038
roc_auc: 0.864 +- 0.014
elapsed: 7.8 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.76 0.77 120
1 0.76 0.78 0.77 120
avg / total 0.77 0.77 0.77 240
APR: 0.818
ROC: 0.830
Cross-validated estimate
accuracy: 0.800 +- 0.028
precision: 0.842 +- 0.021
recall: 0.742 +- 0.085
f1: 0.785 +- 0.045
average_precision: 0.859 +- 0.021
roc_auc: 0.861 +- 0.006
elapsed: 8.7 sec
Time elapsed: 37.2 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 4/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.83 0.79 120
1 0.81 0.73 0.77 120
avg / total 0.79 0.78 0.78 240
APR: 0.823
ROC: 0.833
Cross-validated estimate
accuracy: 0.796 +- 0.031
precision: 0.833 +- 0.025
recall: 0.742 +- 0.072
f1: 0.782 +- 0.042
average_precision: 0.857 +- 0.029
roc_auc: 0.860 +- 0.009
elapsed: 5.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.62 0.70 120
1 0.69 0.85 0.76 120
avg / total 0.75 0.74 0.73 240
APR: 0.839
ROC: 0.837
Cross-validated estimate
accuracy: 0.804 +- 0.039
precision: 0.846 +- 0.050
recall: 0.750 +- 0.083
f1: 0.791 +- 0.051
average_precision: 0.839 +- 0.043
roc_auc: 0.856 +- 0.010
elapsed: 7.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.82 0.81 120
1 0.81 0.80 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.838
ROC: 0.854
Cross-validated estimate
accuracy: 0.796 +- 0.033
precision: 0.826 +- 0.026
recall: 0.750 +- 0.070
f1: 0.784 +- 0.043
average_precision: 0.856 +- 0.016
roc_auc: 0.854 +- 0.006
elapsed: 8.0 sec
Time elapsed: 36.8 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 5/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.82 0.80 120
1 0.81 0.75 0.78 120
avg / total 0.79 0.79 0.79 240
APR: 0.829
ROC: 0.840
Cross-validated estimate
accuracy: 0.787 +- 0.024
precision: 0.831 +- 0.037
recall: 0.725 +- 0.057
f1: 0.772 +- 0.031
average_precision: 0.861 +- 0.015
roc_auc: 0.867 +- 0.012
elapsed: 5.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.71 0.75 120
1 0.73 0.81 0.77 120
avg / total 0.76 0.76 0.76 240
APR: 0.816
ROC: 0.824
Cross-validated estimate
accuracy: 0.775 +- 0.055
precision: 0.803 +- 0.035
recall: 0.725 +- 0.117
f1: 0.758 +- 0.080
average_precision: 0.856 +- 0.039
roc_auc: 0.866 +- 0.015
elapsed: 7.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.79 0.79 120
1 0.79 0.79 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.840
ROC: 0.853
Cross-validated estimate
accuracy: 0.808 +- 0.031
precision: 0.858 +- 0.029
recall: 0.742 +- 0.081
f1: 0.792 +- 0.047
average_precision: 0.852 +- 0.048
roc_auc: 0.864 +- 0.012
elapsed: 8.2 sec
Time elapsed: 37.8 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 6/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.84 0.80 120
1 0.82 0.74 0.78 120
avg / total 0.79 0.79 0.79 240
APR: 0.837
ROC: 0.846
Cross-validated estimate
accuracy: 0.800 +- 0.043
precision: 0.829 +- 0.039
recall: 0.758 +- 0.096
f1: 0.788 +- 0.058
average_precision: 0.859 +- 0.021
roc_auc: 0.854 +- 0.011
elapsed: 5.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.73 0.75 120
1 0.75 0.78 0.76 120
avg / total 0.76 0.76 0.76 240
APR: 0.814
ROC: 0.822
Cross-validated estimate
accuracy: 0.812 +- 0.044
precision: 0.851 +- 0.030
recall: 0.758 +- 0.093
f1: 0.799 +- 0.060
average_precision: 0.858 +- 0.009
roc_auc: 0.858 +- 0.011
elapsed: 7.8 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.81 0.80 120
1 0.80 0.78 0.79 120
avg / total 0.80 0.80 0.80 240
APR: 0.833
ROC: 0.842
Cross-validated estimate
accuracy: 0.817 +- 0.040
precision: 0.854 +- 0.031
recall: 0.767 +- 0.101
f1: 0.804 +- 0.058
average_precision: 0.860 +- 0.037
roc_auc: 0.870 +- 0.005
elapsed: 8.9 sec
Time elapsed: 38.1 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 7/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.87 0.81 120
1 0.84 0.72 0.78 120
avg / total 0.80 0.80 0.79 240
APR: 0.829
ROC: 0.850
Cross-validated estimate
accuracy: 0.796 +- 0.048
precision: 0.840 +- 0.056
recall: 0.733 +- 0.082
f1: 0.780 +- 0.060
average_precision: 0.854 +- 0.021
roc_auc: 0.852 +- 0.014
elapsed: 5.5 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.75 0.72 0.74 120
1 0.73 0.76 0.75 120
avg / total 0.74 0.74 0.74 240
APR: 0.766
ROC: 0.790
Cross-validated estimate
accuracy: 0.817 +- 0.028
precision: 0.859 +- 0.045
recall: 0.767 +- 0.094
f1: 0.804 +- 0.045
average_precision: 0.863 +- 0.017
roc_auc: 0.868 +- 0.008
elapsed: 7.8 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.75 0.78 120
1 0.77 0.83 0.80 120
avg / total 0.79 0.79 0.79 240
APR: 0.835
ROC: 0.842
Cross-validated estimate
accuracy: 0.775 +- 0.016
precision: 0.815 +- 0.034
recall: 0.717 +- 0.067
f1: 0.760 +- 0.028
average_precision: 0.854 +- 0.037
roc_auc: 0.867 +- 0.017
elapsed: 8.4 sec
Time elapsed: 37.3 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 8/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.86 0.81 120
1 0.84 0.73 0.78 120
avg / total 0.80 0.80 0.80 240
APR: 0.834
ROC: 0.844
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.829 +- 0.022
recall: 0.750 +- 0.109
f1: 0.781 +- 0.060
average_precision: 0.842 +- 0.032
roc_auc: 0.856 +- 0.009
elapsed: 5.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.66 0.72 120
1 0.71 0.82 0.76 120
avg / total 0.75 0.74 0.74 240
APR: 0.812
ROC: 0.824
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.827 +- 0.057
recall: 0.758 +- 0.089
f1: 0.786 +- 0.048
average_precision: 0.853 +- 0.020
roc_auc: 0.855 +- 0.009
elapsed: 7.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.78 0.79 120
1 0.78 0.81 0.80 120
avg / total 0.79 0.79 0.79 240
APR: 0.832
ROC: 0.856
Cross-validated estimate
accuracy: 0.812 +- 0.037
precision: 0.853 +- 0.041
recall: 0.758 +- 0.081
f1: 0.800 +- 0.048
average_precision: 0.875 +- 0.021
roc_auc: 0.873 +- 0.010
elapsed: 8.4 sec
Time elapsed: 37.4 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 9/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.74 0.84 0.79 120
1 0.82 0.70 0.75 120
avg / total 0.78 0.77 0.77 240
APR: 0.817
ROC: 0.825
Cross-validated estimate
accuracy: 0.808 +- 0.040
precision: 0.844 +- 0.040
recall: 0.758 +- 0.072
f1: 0.797 +- 0.049
average_precision: 0.864 +- 0.045
roc_auc: 0.870 +- 0.012
elapsed: 5.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.66 0.71 120
1 0.70 0.81 0.75 120
avg / total 0.74 0.73 0.73 240
APR: 0.817
ROC: 0.808
Cross-validated estimate
accuracy: 0.800 +- 0.028
precision: 0.832 +- 0.034
recall: 0.758 +- 0.100
f1: 0.788 +- 0.047
average_precision: 0.855 +- 0.037
roc_auc: 0.853 +- 0.012
elapsed: 7.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.82 0.81 120
1 0.81 0.79 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.842
ROC: 0.857
Cross-validated estimate
accuracy: 0.804 +- 0.039
precision: 0.843 +- 0.035
recall: 0.750 +- 0.087
f1: 0.790 +- 0.054
average_precision: 0.868 +- 0.021
roc_auc: 0.870 +- 0.008
elapsed: 8.1 sec
Time elapsed: 36.6 sec
Positive
graph grammar stats:
#instances:112 #interfaces: 44 #cores: 31 #core-interface-pairs: 136
Negative
graph grammar stats:
#instances:112 #interfaces: 72 #cores: 42 #core-interface-pairs: 216
================================================================================
repetition: 10/10
training percentage:0.4
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 112 #neg: 112
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.86 0.81 120
1 0.84 0.74 0.79 120
avg / total 0.80 0.80 0.80 240
APR: 0.815
ROC: 0.830
Cross-validated estimate
accuracy: 0.808 +- 0.036
precision: 0.851 +- 0.033
recall: 0.750 +- 0.087
f1: 0.794 +- 0.052
average_precision: 0.863 +- 0.005
roc_auc: 0.863 +- 0.018
elapsed: 5.5 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 218 #neg: 216
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.76 0.59 0.67 120
1 0.67 0.82 0.73 120
avg / total 0.72 0.70 0.70 240
APR: 0.794
ROC: 0.790
Cross-validated estimate
accuracy: 0.796 +- 0.020
precision: 0.824 +- 0.038
recall: 0.758 +- 0.076
f1: 0.786 +- 0.033
average_precision: 0.847 +- 0.048
roc_auc: 0.863 +- 0.006
elapsed: 8.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 330 #neg: 328
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.78 0.78 120
1 0.78 0.80 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.812
ROC: 0.830
Cross-validated estimate
accuracy: 0.800 +- 0.028
precision: 0.839 +- 0.038
recall: 0.750 +- 0.102
f1: 0.786 +- 0.047
average_precision: 0.850 +- 0.044
roc_auc: 0.859 +- 0.010
elapsed: 8.2 sec
Time elapsed: 36.9 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 1/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.83 0.81 120
1 0.82 0.78 0.80 120
avg / total 0.81 0.80 0.80 240
APR: 0.845
ROC: 0.855
Cross-validated estimate
accuracy: 0.787 +- 0.036
precision: 0.820 +- 0.043
recall: 0.742 +- 0.096
f1: 0.774 +- 0.052
average_precision: 0.854 +- 0.022
roc_auc: 0.853 +- 0.009
elapsed: 6.1 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.64 0.72 120
1 0.71 0.86 0.77 120
avg / total 0.76 0.75 0.75 240
APR: 0.836
ROC: 0.843
Cross-validated estimate
accuracy: 0.804 +- 0.039
precision: 0.838 +- 0.026
recall: 0.758 +- 0.110
f1: 0.791 +- 0.057
average_precision: 0.856 +- 0.036
roc_auc: 0.862 +- 0.006
elapsed: 8.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.78 0.79 120
1 0.79 0.79 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.849
ROC: 0.854
Cross-validated estimate
accuracy: 0.817 +- 0.024
precision: 0.855 +- 0.053
recall: 0.775 +- 0.104
f1: 0.805 +- 0.045
average_precision: 0.862 +- 0.021
roc_auc: 0.864 +- 0.009
elapsed: 9.9 sec
Time elapsed: 44.6 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 2/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.83 0.81 120
1 0.82 0.77 0.79 120
avg / total 0.80 0.80 0.80 240
APR: 0.849
ROC: 0.854
Cross-validated estimate
accuracy: 0.825 +- 0.025
precision: 0.863 +- 0.032
recall: 0.775 +- 0.057
f1: 0.815 +- 0.032
average_precision: 0.856 +- 0.038
roc_auc: 0.865 +- 0.010
elapsed: 6.4 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.61 0.69 120
1 0.68 0.85 0.76 120
avg / total 0.74 0.73 0.73 240
APR: 0.831
ROC: 0.828
Cross-validated estimate
accuracy: 0.821 +- 0.045
precision: 0.862 +- 0.029
recall: 0.767 +- 0.107
f1: 0.807 +- 0.062
average_precision: 0.863 +- 0.025
roc_auc: 0.866 +- 0.013
elapsed: 8.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.76 0.79 120
1 0.78 0.84 0.81 120
avg / total 0.80 0.80 0.80 240
APR: 0.859
ROC: 0.864
Cross-validated estimate
accuracy: 0.804 +- 0.043
precision: 0.841 +- 0.032
recall: 0.750 +- 0.087
f1: 0.790 +- 0.058
average_precision: 0.867 +- 0.017
roc_auc: 0.871 +- 0.010
elapsed: 10.8 sec
Time elapsed: 47.0 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 3/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.86 0.82 120
1 0.84 0.76 0.80 120
avg / total 0.81 0.81 0.81 240
APR: 0.858
ROC: 0.861
Cross-validated estimate
accuracy: 0.800 +- 0.025
precision: 0.853 +- 0.048
recall: 0.733 +- 0.086
f1: 0.783 +- 0.041
average_precision: 0.863 +- 0.017
roc_auc: 0.864 +- 0.013
elapsed: 6.0 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.65 0.73 120
1 0.71 0.86 0.78 120
avg / total 0.77 0.75 0.75 240
APR: 0.854
ROC: 0.851
Cross-validated estimate
accuracy: 0.812 +- 0.023
precision: 0.832 +- 0.037
recall: 0.792 +- 0.095
f1: 0.806 +- 0.039
average_precision: 0.863 +- 0.031
roc_auc: 0.867 +- 0.007
elapsed: 8.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.82 0.82 120
1 0.82 0.82 0.82 120
avg / total 0.82 0.82 0.82 240
APR: 0.857
ROC: 0.874
Cross-validated estimate
accuracy: 0.800 +- 0.017
precision: 0.837 +- 0.029
recall: 0.750 +- 0.070
f1: 0.788 +- 0.030
average_precision: 0.855 +- 0.039
roc_auc: 0.866 +- 0.013
elapsed: 10.2 sec
Time elapsed: 45.0 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 4/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.88 0.82 120
1 0.85 0.73 0.79 120
avg / total 0.81 0.80 0.80 240
APR: 0.848
ROC: 0.845
Cross-validated estimate
accuracy: 0.812 +- 0.048
precision: 0.853 +- 0.036
recall: 0.758 +- 0.116
f1: 0.797 +- 0.070
average_precision: 0.866 +- 0.022
roc_auc: 0.863 +- 0.022
elapsed: 6.4 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.57 0.67 120
1 0.67 0.88 0.76 120
avg / total 0.74 0.72 0.71 240
APR: 0.829
ROC: 0.842
Cross-validated estimate
accuracy: 0.825 +- 0.039
precision: 0.857 +- 0.028
recall: 0.783 +- 0.103
f1: 0.814 +- 0.057
average_precision: 0.877 +- 0.013
roc_auc: 0.876 +- 0.005
elapsed: 8.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.80 0.80 120
1 0.80 0.81 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.855
ROC: 0.859
Cross-validated estimate
accuracy: 0.825 +- 0.039
precision: 0.856 +- 0.014
recall: 0.783 +- 0.107
f1: 0.813 +- 0.058
average_precision: 0.858 +- 0.042
roc_auc: 0.861 +- 0.009
elapsed: 10.7 sec
Time elapsed: 46.8 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 5/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.82 0.80 120
1 0.82 0.78 0.79 120
avg / total 0.80 0.80 0.80 240
APR: 0.866
ROC: 0.859
Cross-validated estimate
accuracy: 0.821 +- 0.045
precision: 0.861 +- 0.031
recall: 0.767 +- 0.101
f1: 0.807 +- 0.061
average_precision: 0.866 +- 0.049
roc_auc: 0.876 +- 0.013
elapsed: 6.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.74 0.77 120
1 0.76 0.82 0.79 120
avg / total 0.78 0.78 0.78 240
APR: 0.833
ROC: 0.830
Cross-validated estimate
accuracy: 0.804 +- 0.039
precision: 0.838 +- 0.039
recall: 0.758 +- 0.093
f1: 0.792 +- 0.054
average_precision: 0.860 +- 0.028
roc_auc: 0.868 +- 0.005
elapsed: 8.5 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.83 0.82 120
1 0.83 0.79 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.851
ROC: 0.856
Cross-validated estimate
accuracy: 0.812 +- 0.037
precision: 0.846 +- 0.021
recall: 0.767 +- 0.101
f1: 0.800 +- 0.055
average_precision: 0.876 +- 0.009
roc_auc: 0.870 +- 0.017
elapsed: 11.2 sec
Time elapsed: 48.1 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 6/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.82 0.81 120
1 0.82 0.78 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.847
ROC: 0.846
Cross-validated estimate
accuracy: 0.800 +- 0.050
precision: 0.828 +- 0.038
recall: 0.758 +- 0.103
f1: 0.788 +- 0.065
average_precision: 0.864 +- 0.011
roc_auc: 0.859 +- 0.017
elapsed: 6.0 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.74 0.76 120
1 0.76 0.80 0.78 120
avg / total 0.77 0.77 0.77 240
APR: 0.829
ROC: 0.840
Cross-validated estimate
accuracy: 0.796 +- 0.033
precision: 0.841 +- 0.035
recall: 0.733 +- 0.077
f1: 0.780 +- 0.047
average_precision: 0.852 +- 0.026
roc_auc: 0.857 +- 0.008
elapsed: 8.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.80 0.79 120
1 0.80 0.78 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.834
ROC: 0.857
Cross-validated estimate
accuracy: 0.787 +- 0.044
precision: 0.826 +- 0.028
recall: 0.733 +- 0.125
f1: 0.769 +- 0.073
average_precision: 0.855 +- 0.024
roc_auc: 0.854 +- 0.005
elapsed: 10.4 sec
Time elapsed: 46.0 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 7/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.84 0.82 120
1 0.83 0.80 0.82 120
avg / total 0.82 0.82 0.82 240
APR: 0.853
ROC: 0.849
Cross-validated estimate
accuracy: 0.796 +- 0.028
precision: 0.835 +- 0.029
recall: 0.742 +- 0.085
f1: 0.782 +- 0.044
average_precision: 0.859 +- 0.020
roc_auc: 0.861 +- 0.006
elapsed: 6.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.72 0.75 120
1 0.74 0.79 0.77 120
avg / total 0.76 0.76 0.76 240
APR: 0.856
ROC: 0.849
Cross-validated estimate
accuracy: 0.796 +- 0.024
precision: 0.832 +- 0.050
recall: 0.750 +- 0.070
f1: 0.785 +- 0.031
average_precision: 0.860 +- 0.025
roc_auc: 0.866 +- 0.007
elapsed: 8.5 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.82 0.81 120
1 0.81 0.80 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.860
ROC: 0.863
Cross-validated estimate
accuracy: 0.817 +- 0.028
precision: 0.865 +- 0.044
recall: 0.758 +- 0.096
f1: 0.802 +- 0.046
average_precision: 0.867 +- 0.021
roc_auc: 0.862 +- 0.011
elapsed: 10.8 sec
Time elapsed: 48.6 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 8/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.82 0.79 120
1 0.80 0.75 0.78 120
avg / total 0.78 0.78 0.78 240
APR: 0.845
ROC: 0.846
Cross-validated estimate
accuracy: 0.808 +- 0.028
precision: 0.851 +- 0.057
recall: 0.758 +- 0.089
f1: 0.796 +- 0.042
average_precision: 0.866 +- 0.032
roc_auc: 0.867 +- 0.024
elapsed: 6.1 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.62 0.70 120
1 0.69 0.87 0.77 120
avg / total 0.76 0.74 0.74 240
APR: 0.816
ROC: 0.830
Cross-validated estimate
accuracy: 0.800 +- 0.034
precision: 0.836 +- 0.028
recall: 0.750 +- 0.099
f1: 0.786 +- 0.052
average_precision: 0.855 +- 0.028
roc_auc: 0.860 +- 0.010
elapsed: 9.0 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.77 0.79 120
1 0.78 0.82 0.80 120
avg / total 0.79 0.79 0.79 240
APR: 0.834
ROC: 0.845
Cross-validated estimate
accuracy: 0.808 +- 0.024
precision: 0.841 +- 0.068
recall: 0.775 +- 0.086
f1: 0.800 +- 0.033
average_precision: 0.859 +- 0.040
roc_auc: 0.868 +- 0.013
elapsed: 10.4 sec
Time elapsed: 46.2 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 9/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.82 0.80 120
1 0.81 0.78 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.853
ROC: 0.859
Cross-validated estimate
accuracy: 0.812 +- 0.029
precision: 0.844 +- 0.020
recall: 0.767 +- 0.057
f1: 0.802 +- 0.037
average_precision: 0.855 +- 0.040
roc_auc: 0.868 +- 0.006
elapsed: 6.3 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.68 0.73 120
1 0.72 0.82 0.77 120
avg / total 0.75 0.75 0.75 240
APR: 0.782
ROC: 0.821
Cross-validated estimate
accuracy: 0.800 +- 0.039
precision: 0.845 +- 0.050
recall: 0.742 +- 0.085
f1: 0.785 +- 0.051
average_precision: 0.852 +- 0.049
roc_auc: 0.857 +- 0.012
elapsed: 9.0 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.82 0.81 120
1 0.82 0.80 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.835
ROC: 0.859
Cross-validated estimate
accuracy: 0.800 +- 0.047
precision: 0.825 +- 0.028
recall: 0.758 +- 0.089
f1: 0.789 +- 0.062
average_precision: 0.848 +- 0.012
roc_auc: 0.854 +- 0.018
elapsed: 10.7 sec
Time elapsed: 47.6 sec
Positive
graph grammar stats:
#instances:168 #interfaces: 71 #cores: 40 #core-interface-pairs: 213
Negative
graph grammar stats:
#instances:168 #interfaces: 97 #cores: 47 #core-interface-pairs: 310
================================================================================
repetition: 10/10
training percentage:0.6
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 168 #neg: 168
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.83 0.80 120
1 0.82 0.75 0.78 120
avg / total 0.79 0.79 0.79 240
APR: 0.840
ROC: 0.842
Cross-validated estimate
accuracy: 0.804 +- 0.043
precision: 0.829 +- 0.040
recall: 0.767 +- 0.082
f1: 0.795 +- 0.053
average_precision: 0.856 +- 0.018
roc_auc: 0.855 +- 0.021
elapsed: 6.2 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 328 #neg: 320
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.65 0.73 120
1 0.71 0.86 0.78 120
avg / total 0.77 0.75 0.75 240
APR: 0.856
ROC: 0.849
Cross-validated estimate
accuracy: 0.804 +- 0.041
precision: 0.838 +- 0.027
recall: 0.758 +- 0.110
f1: 0.790 +- 0.064
average_precision: 0.870 +- 0.028
roc_auc: 0.872 +- 0.006
elapsed: 8.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 496 #neg: 488
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.78 0.80 120
1 0.79 0.82 0.81 120
avg / total 0.80 0.80 0.80 240
APR: 0.859
ROC: 0.869
Cross-validated estimate
accuracy: 0.800 +- 0.043
precision: 0.849 +- 0.045
recall: 0.733 +- 0.086
f1: 0.783 +- 0.055
average_precision: 0.862 +- 0.034
roc_auc: 0.861 +- 0.004
elapsed: 9.9 sec
Time elapsed: 44.5 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 1/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.83 0.82 120
1 0.83 0.79 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.863
ROC: 0.866
Cross-validated estimate
accuracy: 0.783 +- 0.017
precision: 0.806 +- 0.023
recall: 0.750 +- 0.070
f1: 0.774 +- 0.031
average_precision: 0.854 +- 0.026
roc_auc: 0.863 +- 0.012
elapsed: 6.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.84 0.63 0.72 120
1 0.70 0.88 0.78 120
avg / total 0.77 0.75 0.75 240
APR: 0.841
ROC: 0.844
Cross-validated estimate
accuracy: 0.808 +- 0.040
precision: 0.845 +- 0.062
recall: 0.767 +- 0.111
f1: 0.796 +- 0.056
average_precision: 0.860 +- 0.030
roc_auc: 0.856 +- 0.015
elapsed: 2592.8 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.80 0.81 120
1 0.81 0.83 0.82 120
avg / total 0.82 0.82 0.82 240
APR: 0.862
ROC: 0.865
Cross-validated estimate
accuracy: 0.792 +- 0.044
precision: 0.835 +- 0.054
recall: 0.733 +- 0.086
f1: 0.777 +- 0.054
average_precision: 0.850 +- 0.044
roc_auc: 0.860 +- 0.008
elapsed: 13.9 sec
Time elapsed: 2641.4 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 2/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.86 0.83 120
1 0.85 0.78 0.81 120
avg / total 0.82 0.82 0.82 240
APR: 0.861
ROC: 0.855
Cross-validated estimate
accuracy: 0.787 +- 0.053
precision: 0.826 +- 0.052
recall: 0.733 +- 0.125
f1: 0.770 +- 0.079
average_precision: 0.854 +- 0.023
roc_auc: 0.864 +- 0.012
elapsed: 7.0 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.86 0.64 0.73 120
1 0.71 0.89 0.79 120
avg / total 0.78 0.77 0.76 240
APR: 0.814
ROC: 0.843
Cross-validated estimate
accuracy: 0.796 +- 0.031
precision: 0.825 +- 0.039
recall: 0.758 +- 0.100
f1: 0.785 +- 0.046
average_precision: 0.863 +- 0.015
roc_auc: 0.864 +- 0.011
elapsed: 9.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.77 0.80 120
1 0.78 0.84 0.81 120
avg / total 0.81 0.80 0.80 240
APR: 0.831
ROC: 0.864
Cross-validated estimate
accuracy: 0.812 +- 0.044
precision: 0.845 +- 0.057
recall: 0.775 +- 0.097
f1: 0.803 +- 0.056
average_precision: 0.839 +- 0.054
roc_auc: 0.849 +- 0.014
elapsed: 12.0 sec
Time elapsed: 56.3 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 3/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.83 0.81 120
1 0.82 0.78 0.80 120
avg / total 0.81 0.80 0.80 240
APR: 0.858
ROC: 0.856
Cross-validated estimate
accuracy: 0.817 +- 0.024
precision: 0.849 +- 0.026
recall: 0.775 +- 0.086
f1: 0.806 +- 0.040
average_precision: 0.849 +- 0.036
roc_auc: 0.859 +- 0.012
elapsed: 6.9 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.64 0.72 120
1 0.70 0.85 0.77 120
avg / total 0.76 0.75 0.74 240
APR: 0.820
ROC: 0.836
Cross-validated estimate
accuracy: 0.800 +- 0.036
precision: 0.833 +- 0.056
recall: 0.758 +- 0.072
f1: 0.790 +- 0.042
average_precision: 0.855 +- 0.023
roc_auc: 0.856 +- 0.010
elapsed: 10.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.77 0.78 120
1 0.78 0.81 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.840
ROC: 0.848
Cross-validated estimate
accuracy: 0.783 +- 0.049
precision: 0.813 +- 0.043
recall: 0.742 +- 0.119
f1: 0.769 +- 0.069
average_precision: 0.858 +- 0.023
roc_auc: 0.861 +- 0.014
elapsed: 11.9 sec
Time elapsed: 56.1 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 4/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.83 0.81 120
1 0.82 0.78 0.80 120
avg / total 0.81 0.80 0.80 240
APR: 0.847
ROC: 0.851
Cross-validated estimate
accuracy: 0.812 +- 0.044
precision: 0.852 +- 0.016
recall: 0.758 +- 0.113
f1: 0.797 +- 0.067
average_precision: 0.870 +- 0.027
roc_auc: 0.866 +- 0.011
elapsed: 6.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.71 0.74 120
1 0.73 0.80 0.76 120
avg / total 0.76 0.75 0.75 240
APR: 0.815
ROC: 0.830
Cross-validated estimate
accuracy: 0.796 +- 0.042
precision: 0.815 +- 0.045
recall: 0.767 +- 0.077
f1: 0.788 +- 0.052
average_precision: 0.858 +- 0.024
roc_auc: 0.857 +- 0.006
elapsed: 10.0 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.82 0.82 120
1 0.82 0.82 0.82 120
avg / total 0.82 0.82 0.82 240
APR: 0.848
ROC: 0.865
Cross-validated estimate
accuracy: 0.792 +- 0.026
precision: 0.830 +- 0.076
recall: 0.750 +- 0.065
f1: 0.782 +- 0.025
average_precision: 0.861 +- 0.022
roc_auc: 0.858 +- 0.012
elapsed: 11.8 sec
Time elapsed: 54.9 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 5/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.82 0.80 120
1 0.81 0.78 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.855
ROC: 0.860
Cross-validated estimate
accuracy: 0.796 +- 0.046
precision: 0.832 +- 0.050
recall: 0.742 +- 0.061
f1: 0.783 +- 0.053
average_precision: 0.864 +- 0.028
roc_auc: 0.868 +- 0.014
elapsed: 6.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.65 0.72 120
1 0.71 0.85 0.77 120
avg / total 0.76 0.75 0.75 240
APR: 0.835
ROC: 0.836
Cross-validated estimate
accuracy: 0.800 +- 0.039
precision: 0.836 +- 0.033
recall: 0.750 +- 0.095
f1: 0.786 +- 0.054
average_precision: 0.869 +- 0.018
roc_auc: 0.865 +- 0.009
elapsed: 10.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.78 0.80 120
1 0.79 0.83 0.81 120
avg / total 0.81 0.80 0.80 240
APR: 0.857
ROC: 0.864
Cross-validated estimate
accuracy: 0.812 +- 0.042
precision: 0.841 +- 0.035
recall: 0.775 +- 0.107
f1: 0.801 +- 0.059
average_precision: 0.860 +- 0.025
roc_auc: 0.861 +- 0.008
elapsed: 12.0 sec
Time elapsed: 54.9 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 6/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.82 0.82 120
1 0.82 0.81 0.82 120
avg / total 0.82 0.82 0.82 240
APR: 0.860
ROC: 0.857
Cross-validated estimate
accuracy: 0.808 +- 0.044
precision: 0.836 +- 0.016
recall: 0.767 +- 0.101
f1: 0.796 +- 0.062
average_precision: 0.863 +- 0.033
roc_auc: 0.869 +- 0.017
elapsed: 6.4 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.72 0.76 120
1 0.75 0.82 0.78 120
avg / total 0.77 0.77 0.77 240
APR: 0.828
ROC: 0.840
Cross-validated estimate
accuracy: 0.804 +- 0.031
precision: 0.843 +- 0.020
recall: 0.750 +- 0.091
f1: 0.790 +- 0.049
average_precision: 0.851 +- 0.024
roc_auc: 0.861 +- 0.010
elapsed: 9.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.80 0.81 120
1 0.80 0.82 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.865
ROC: 0.872
Cross-validated estimate
accuracy: 0.821 +- 0.045
precision: 0.862 +- 0.029
recall: 0.767 +- 0.107
f1: 0.807 +- 0.062
average_precision: 0.869 +- 0.015
roc_auc: 0.864 +- 0.017
elapsed: 12.1 sec
Time elapsed: 54.5 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 7/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.82 0.80 120
1 0.81 0.78 0.79 120
avg / total 0.80 0.80 0.80 240
APR: 0.851
ROC: 0.853
Cross-validated estimate
accuracy: 0.804 +- 0.036
precision: 0.823 +- 0.012
recall: 0.775 +- 0.094
f1: 0.795 +- 0.051
average_precision: 0.859 +- 0.029
roc_auc: 0.866 +- 0.016
elapsed: 6.6 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.61 0.68 120
1 0.68 0.82 0.74 120
avg / total 0.73 0.72 0.71 240
APR: 0.822
ROC: 0.815
Cross-validated estimate
accuracy: 0.787 +- 0.052
precision: 0.820 +- 0.055
recall: 0.742 +- 0.100
f1: 0.774 +- 0.068
average_precision: 0.864 +- 0.019
roc_auc: 0.861 +- 0.006
elapsed: 9.9 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.78 0.78 0.78 120
1 0.78 0.78 0.78 120
avg / total 0.78 0.78 0.78 240
APR: 0.854
ROC: 0.852
Cross-validated estimate
accuracy: 0.817 +- 0.031
precision: 0.834 +- 0.049
recall: 0.800 +- 0.100
f1: 0.811 +- 0.044
average_precision: 0.868 +- 0.020
roc_auc: 0.866 +- 0.008
elapsed: 11.9 sec
Time elapsed: 54.4 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 8/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.85 0.82 120
1 0.84 0.78 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.864
ROC: 0.866
Cross-validated estimate
accuracy: 0.796 +- 0.036
precision: 0.816 +- 0.023
recall: 0.767 +- 0.094
f1: 0.787 +- 0.053
average_precision: 0.858 +- 0.011
roc_auc: 0.856 +- 0.014
elapsed: 6.7 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.67 0.74 120
1 0.72 0.86 0.78 120
avg / total 0.77 0.76 0.76 240
APR: 0.831
ROC: 0.837
Cross-validated estimate
accuracy: 0.804 +- 0.034
precision: 0.830 +- 0.019
recall: 0.767 +- 0.086
f1: 0.794 +- 0.047
average_precision: 0.867 +- 0.027
roc_auc: 0.868 +- 0.012
elapsed: 10.2 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.77 0.79 120
1 0.78 0.82 0.80 120
avg / total 0.79 0.79 0.79 240
APR: 0.862
ROC: 0.869
Cross-validated estimate
accuracy: 0.796 +- 0.044
precision: 0.827 +- 0.040
recall: 0.750 +- 0.099
f1: 0.783 +- 0.060
average_precision: 0.840 +- 0.041
roc_auc: 0.848 +- 0.015
elapsed: 12.1 sec
Time elapsed: 54.7 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 9/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.77 0.82 0.79 120
1 0.81 0.76 0.78 120
avg / total 0.79 0.79 0.79 240
APR: 0.857
ROC: 0.855
Cross-validated estimate
accuracy: 0.812 +- 0.044
precision: 0.845 +- 0.034
recall: 0.767 +- 0.101
f1: 0.800 +- 0.061
average_precision: 0.863 +- 0.029
roc_auc: 0.863 +- 0.016
elapsed: 6.4 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.62 0.70 120
1 0.69 0.85 0.76 120
avg / total 0.75 0.73 0.73 240
APR: 0.797
ROC: 0.817
Cross-validated estimate
accuracy: 0.796 +- 0.033
precision: 0.841 +- 0.033
recall: 0.733 +- 0.082
f1: 0.780 +- 0.048
average_precision: 0.864 +- 0.027
roc_auc: 0.866 +- 0.015
elapsed: 10.4 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.74 0.77 120
1 0.76 0.82 0.79 120
avg / total 0.78 0.78 0.78 240
APR: 0.860
ROC: 0.869
Cross-validated estimate
accuracy: 0.796 +- 0.040
precision: 0.826 +- 0.042
recall: 0.750 +- 0.065
f1: 0.785 +- 0.049
average_precision: 0.855 +- 0.034
roc_auc: 0.853 +- 0.016
elapsed: 11.9 sec
Time elapsed: 56.4 sec
Positive
graph grammar stats:
#instances:224 #interfaces: 95 #cores: 52 #core-interface-pairs: 292
Negative
graph grammar stats:
#instances:224 #interfaces: 129 #cores: 51 #core-interface-pairs: 408
================================================================================
repetition: 10/10
training percentage:0.8
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 224 #neg: 224
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.84 0.82 120
1 0.83 0.78 0.81 120
avg / total 0.81 0.81 0.81 240
APR: 0.865
ROC: 0.869
Cross-validated estimate
accuracy: 0.792 +- 0.029
precision: 0.823 +- 0.034
recall: 0.750 +- 0.095
f1: 0.779 +- 0.047
average_precision: 0.860 +- 0.021
roc_auc: 0.858 +- 0.012
elapsed: 6.8 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 438 #neg: 432
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.86 0.61 0.71 120
1 0.70 0.90 0.79 120
avg / total 0.78 0.75 0.75 240
APR: 0.804
ROC: 0.824
Cross-validated estimate
accuracy: 0.825 +- 0.031
precision: 0.851 +- 0.035
recall: 0.792 +- 0.070
f1: 0.818 +- 0.038
average_precision: 0.862 +- 0.012
roc_auc: 0.867 +- 0.021
elapsed: 10.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 662 #neg: 656
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.76 0.79 120
1 0.78 0.84 0.81 120
avg / total 0.80 0.80 0.80 240
APR: 0.848
ROC: 0.864
Cross-validated estimate
accuracy: 0.792 +- 0.026
precision: 0.826 +- 0.054
recall: 0.750 +- 0.091
f1: 0.780 +- 0.042
average_precision: 0.843 +- 0.043
roc_auc: 0.856 +- 0.009
elapsed: 12.2 sec
Time elapsed: 56.7 sec
Positive
graph grammar stats:
#instances:266 #interfaces: 117 #cores: 55 #core-interface-pairs: 357
Negative
graph grammar stats:
#instances:266 #interfaces: 153 #cores: 51 #core-interface-pairs: 474
================================================================================
repetition: 1/10
training percentage:0.95
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 266 #neg: 266
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.88 0.85 120
1 0.87 0.82 0.84 120
avg / total 0.85 0.85 0.85 240
APR: 0.878
ROC: 0.876
Cross-validated estimate
accuracy: 0.792 +- 0.049
precision: 0.830 +- 0.048
recall: 0.733 +- 0.077
f1: 0.777 +- 0.061
average_precision: 0.855 +- 0.043
roc_auc: 0.858 +- 0.015
elapsed: 7.3 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 522 #neg: 514
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.69 0.74 120
1 0.73 0.82 0.77 120
avg / total 0.76 0.75 0.75 240
APR: 0.841
ROC: 0.851
Cross-validated estimate
accuracy: 0.808 +- 0.046
precision: 0.847 +- 0.044
recall: 0.758 +- 0.110
f1: 0.794 +- 0.067
average_precision: 0.868 +- 0.015
roc_auc: 0.866 +- 0.014
elapsed: 11.1 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 788 #neg: 780
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.83 0.83 120
1 0.83 0.82 0.82 120
avg / total 0.83 0.82 0.82 240
APR: 0.880
ROC: 0.886
Cross-validated estimate
accuracy: 0.812 +- 0.037
precision: 0.853 +- 0.032
recall: 0.758 +- 0.093
f1: 0.799 +- 0.054
average_precision: 0.865 +- 0.017
roc_auc: 0.869 +- 0.016
elapsed: 13.5 sec
Time elapsed: 64.6 sec
Positive
graph grammar stats:
#instances:266 #interfaces: 117 #cores: 55 #core-interface-pairs: 357
Negative
graph grammar stats:
#instances:266 #interfaces: 153 #cores: 51 #core-interface-pairs: 474
================================================================================
repetition: 2/10
training percentage:0.95
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 266 #neg: 266
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.86 0.83 120
1 0.85 0.79 0.82 120
avg / total 0.83 0.82 0.82 240
APR: 0.880
ROC: 0.878
Cross-validated estimate
accuracy: 0.792 +- 0.026
precision: 0.823 +- 0.044
recall: 0.750 +- 0.075
f1: 0.781 +- 0.036
average_precision: 0.849 +- 0.023
roc_auc: 0.857 +- 0.015
elapsed: 7.4 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 522 #neg: 514
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.79 0.62 0.70 120
1 0.69 0.83 0.75 120
avg / total 0.74 0.73 0.73 240
APR: 0.806
ROC: 0.827
Cross-validated estimate
accuracy: 0.804 +- 0.043
precision: 0.836 +- 0.037
recall: 0.758 +- 0.089
f1: 0.792 +- 0.058
average_precision: 0.867 +- 0.035
roc_auc: 0.869 +- 0.018
elapsed: 21.5 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 788 #neg: 780
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.79 0.80 120
1 0.80 0.81 0.80 120
avg / total 0.80 0.80 0.80 240
APR: 0.839
ROC: 0.855
Cross-validated estimate
accuracy: 0.817 +- 0.024
precision: 0.852 +- 0.041
recall: 0.775 +- 0.094
f1: 0.806 +- 0.039
average_precision: 0.867 +- 0.012
roc_auc: 0.863 +- 0.013
elapsed: 38.7 sec
Time elapsed: 100.8 sec
Positive
graph grammar stats:
#instances:266 #interfaces: 117 #cores: 55 #core-interface-pairs: 357
Negative
graph grammar stats:
#instances:266 #interfaces: 153 #cores: 51 #core-interface-pairs: 474
================================================================================
repetition: 3/10
training percentage:0.95
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 266 #neg: 266
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.83 0.83 120
1 0.83 0.82 0.82 120
avg / total 0.83 0.82 0.82 240
APR: 0.870
ROC: 0.874
Cross-validated estimate
accuracy: 0.792 +- 0.054
precision: 0.816 +- 0.034
recall: 0.750 +- 0.105
f1: 0.779 +- 0.074
average_precision: 0.842 +- 0.030
roc_auc: 0.852 +- 0.003
elapsed: 9.0 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 522 #neg: 514
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.80 0.66 0.72 120
1 0.71 0.83 0.77 120
avg / total 0.75 0.75 0.74 240
APR: 0.818
ROC: 0.829
Cross-validated estimate
accuracy: 0.808 +- 0.033
precision: 0.857 +- 0.058
recall: 0.750 +- 0.087
f1: 0.794 +- 0.046
average_precision: 0.857 +- 0.051
roc_auc: 0.865 +- 0.012
elapsed: 20.6 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 788 #neg: 780
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.77 0.79 120
1 0.78 0.83 0.81 120
avg / total 0.80 0.80 0.80 240
APR: 0.868
ROC: 0.869
Cross-validated estimate
accuracy: 0.800 +- 0.025
precision: 0.842 +- 0.020
recall: 0.742 +- 0.081
f1: 0.785 +- 0.043
average_precision: 0.855 +- 0.018
roc_auc: 0.857 +- 0.015
elapsed: 23.8 sec
Time elapsed: 93.3 sec
Positive
graph grammar stats:
#instances:266 #interfaces: 117 #cores: 55 #core-interface-pairs: 357
Negative
graph grammar stats:
#instances:266 #interfaces: 153 #cores: 51 #core-interface-pairs: 474
================================================================================
repetition: 4/10
training percentage:0.95
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 266 #neg: 266
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.83 0.86 0.84 120
1 0.85 0.82 0.84 120
avg / total 0.84 0.84 0.84 240
APR: 0.874
ROC: 0.875
Cross-validated estimate
accuracy: 0.808 +- 0.020
precision: 0.834 +- 0.033
recall: 0.775 +- 0.077
f1: 0.800 +- 0.034
average_precision: 0.855 +- 0.034
roc_auc: 0.863 +- 0.008
elapsed: 8.1 sec
--------------------------------------------------------------------------------
working on sample
training set sizes: #pos: 522 #neg: 514
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.86 0.67 0.75 120
1 0.73 0.89 0.80 120
avg / total 0.79 0.78 0.78 240
APR: 0.837
ROC: 0.861
Cross-validated estimate
accuracy: 0.796 +- 0.042
precision: 0.841 +- 0.042
recall: 0.733 +- 0.101
f1: 0.779 +- 0.058
average_precision: 0.856 +- 0.026
roc_auc: 0.856 +- 0.011
elapsed: 17.3 sec
--------------------------------------------------------------------------------
working on original+sample
training set sizes: #pos: 788 #neg: 780
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.81 0.76 0.78 120
1 0.77 0.82 0.79 120
avg / total 0.79 0.79 0.79 240
APR: 0.853
ROC: 0.869
Cross-validated estimate
accuracy: 0.817 +- 0.031
precision: 0.848 +- 0.030
recall: 0.775 +- 0.086
f1: 0.806 +- 0.044
average_precision: 0.868 +- 0.014
roc_auc: 0.863 +- 0.015
elapsed: 25.2 sec
Time elapsed: 87.9 sec
Positive
graph grammar stats:
#instances:266 #interfaces: 117 #cores: 55 #core-interface-pairs: 357
Negative
graph grammar stats:
#instances:266 #interfaces: 153 #cores: 51 #core-interface-pairs: 474
================================================================================
repetition: 5/10
training percentage:0.95
--------------------------------------------------------------------------------
working on original
training set sizes: #pos: 266 #neg: 266
Test set
Instances: 240 ; Features: 1048577 with an avg of 298 features per instance
--------------------------------------------------------------------------------
Test Estimate
precision recall f1-score support
-1 0.82 0.83 0.83 120
1 0.83 0.82 0.82 120
avg / total 0.83 0.82 0.82 240
APR: 0.864
ROC: 0.870
Cross-validated estimate
accuracy: 0.787 +- 0.036
precision: 0.826 +- 0.042
recall: 0.733 +- 0.086
f1: 0.773 +- 0.050
average_precision: 0.864 +- 0.011
roc_auc: 0.860 +- 0.015
elapsed: 13.2 sec
In [16]:
#setup
dataset_names = !cat NCI60/names
random.shuffle(dataset_names)
In [ ]:
%%time
for dataset in dataset_names:
#logging
logger = logging.getLogger()
if True:
logger_fname = '%s_predictive_performance_of_samples.log'%dataset
else:
logger_fname = None
configure_logging(logger,verbosity=1, filename=logger_fname)
#main
start=time()
print( 'Working with dataset: %s' % dataset )
logger.info( 'Working with dataset: %s' % dataset )
pos_dataset_fname = 'NCI60/' + dataset + '_orig_pos.gspan'
neg_dataset_fname = 'NCI60/' + dataset + '_orig_neg.gspan'
#pos_dataset_fname = 'bursi.pos.gspan'
#neg_dataset_fname = 'bursi.neg.gspan'
percentages=[.05,.2,.4,.6,.8,.95]
original_repetitions,\
original_sample_repetitions,\
sample_repetitions = evaluate(pos_dataset_fname,
neg_dataset_fname,
size=400,
percentages=percentages,
n_repetitions=3,
train_test_split=0.7)
#save and display results
result_fname='%s_predictive_performance_of_samples.data'%dataset
save_results(result_fname,percentages, original_repetitions,original_sample_repetitions,sample_repetitions)
percentages_l, original_repetitions_l,original_sample_repetitions_l,sample_repetitions_l = load_results(result_fname)
plot(dataset, percentages_l, original_sample_repetitions_l, original_repetitions_l, sample_repetitions_l)
print('Time elapsed: %s'%(datetime.timedelta(seconds=(time() - start))))
In [ ]:
#display
for dataset in dataset_names:
result_fname='%s_predictive_performance_of_samples.data'%dataset
percentages_l, original_repetitions_l,original_sample_repetitions_l,sample_repetitions_l = load_results(result_fname)
plot(dataset, percentages_l, original_sample_repetitions_l, original_repetitions_l, sample_repetitions_l)
.
Content source: fabriziocosta/GraphLearn_examples
Similar notebooks: