def getTopWeightedFeatures(exp_id, instance_id, size):
instance_id = int(instance_id)
classifier = get_classifier(exp_id)
# get the features
exp = update_curr_exp(exp_id)
f_names, f_values = FeaturesFromExp.get_instance(exp, instance_id)
# scale the features
scaled_values = classifier.named_steps['scaler'].transform(
np.reshape(f_values, (1, -1)))
weighted_values = np.multiply(scaled_values,
classifier.named_steps['model'].coef_)
features = list(
map(lambda name, value, w_value: (name, value, w_value), f_names,
f_values, weighted_values[0]))
features.sort(key=lambda tup: abs(tup[2]))
features = features[:-int(size) - 1:-1]
f_names, f_values, f_weighted = list(zip(*features))
labels = [str(name) for name in f_names]
tooltips = [
'%s (%.2f)' % (name, f_values[i]) for i, name in enumerate(f_names)
]
barplot = BarPlot(labels)
dataset = PlotDataset(f_weighted, None)
dataset.set_color(red)
barplot.add_dataset(dataset)
return jsonify(barplot.to_json(tooltip_data=tooltips))
def plot_evolution(self, monitoring_dir):
iterations = list(range(1, self.monitoring.iter_num + 1))
plt.clf()
# Labels
data = self.labels_accuracy.high_confidence_counts.data
values = data['true_suggestions'] / data['num_suggestions']
plot = PlotDataset(values.values, 'Labels Suggestions')
max_value = 1
plt.plot(iterations, plot.values,
label=plot.label,
color=plot.color,
linewidth=plot.linewidth,
marker=plot.marker)
# Families
data = self.families_accuracy.high_confidence_counts.data
values = data['true_suggestions'] / data['num_suggestions']
plot = PlotDataset(values.values, 'Families Suggestions')
max_value = 1
plt.plot(iterations, plot.values,
label=plot.label,
color='purple',
linewidth=plot.linewidth,
marker=plot.marker)
# Plot
plt.ylim(0, max_value)
plt.xlabel('Iteration')
plt.ylabel('Suggestions Accuracy')
lgd = plt.legend(bbox_to_anchor=(0., 1.02, 1., .102), loc=3,
ncol=2, mode='expand', borderaxespad=0.,
fontsize='large')
filename = path.join(monitoring_dir,
'labels_families_high_confidence_suggestions.png')
plt.savefig(filename, bbox_extra_artists=(lgd,), bbox_inches='tight')
plt.clf()
def display_label(self, barplot, label):
label_bool = labels_tools.label_str_to_bool(label)
ranges = [[x for x in l if x['ground_truth_label'] == label_bool]
for l in self.ranges]
dataset = PlotDataset(list(map(len, ranges)), label)
dataset.set_color(get_label_color(label))
barplot.add_dataset(dataset)
def _gen_binary_histogram(self):
self.barplot = BarPlot(['0', '1'])
for label, dataset in self.plot_datasets.items():
if len(dataset.values) > 0:
num_0 = sum(dataset.values == 0)
num_1 = sum(dataset.values == 1)
hist_dataset = PlotDataset([num_0, num_1], label)
hist_dataset.set_color(dataset.color)
self.barplot.add_dataset(hist_dataset)
def _gen_label_plot_dataset(self, instances, label):
if label != 'unlabeled':
instances = instances.get_annotated_instances(label=label)
else:
instances = instances.get_unlabeled_instances()
values = instances.features.get_values_from_index(self.feature_index)
dataset = PlotDataset(values, label)
dataset.set_color(get_label_color(label))
self.plot_datasets[label] = dataset
def display_label(self, barplot, label):
if label != 'all':
label_bool = label_str_to_bool(label)
ranges = [[x for x in l if x['ground_truth_label'] == label_bool]
for l in self.ranges]
else:
ranges = self.ranges
dataset = PlotDataset(np.array([len(r) for r in ranges]), label)
dataset.set_color(get_label_color(label))
barplot.add_dataset(dataset)
def display(self, directory):
labels = ['0-10%', '10-20%', '20-30%', '30-40%', '40-50%',
'50-60%', '60-70%', '70-80%', '80-90%', '90-100%']
barplot = BarPlot(labels)
if not self.has_ground_truth:
dataset = PlotDataset(list(map(len, self.ranges)), 'num_instances')
dataset.set_color(get_label_color('all'))
barplot.add_dataset(dataset)
else:
self.display_label(barplot, MALICIOUS)
self.display_label(barplot, BENIGN)
barplot.export_to_json(path.join(directory, 'predictions_barplot.json'))
def set_predictions(self, predictions):
self.predictions = predictions
self.datasets = {}
if not self.has_ground_truth:
self.datasets['all'] = PlotDataset(predictions.scores, 'all')
else:
for label in [MALICIOUS, BENIGN]:
label_bool = label_str_to_bool(label)
scores = [
predictions.scores[i]
for i in range(predictions.num_instances())
if predictions.ground_truth[i] == label_bool
]
self.datasets[label] = PlotDataset(np.array(scores), label)
def getFamiliesBarplot(annotations_id, iteration, label):
iteration = None if iteration == 'None' else int(iteration)
family_counts = annotations_db_tools.get_families_counts(
session, annotations_id, iter_max=iteration, label=label)
df = pd.DataFrame({
'families':
list(family_counts.keys()),
'counts': [family_counts[k] for k in list(family_counts.keys())]
})
sort_data_frame(df, 'families', ascending=True, inplace=True)
barplot = BarPlot(df['families'].values)
dataset = PlotDataset(df['counts'].values, 'Num. Instances')
dataset.set_color(get_label_color(label))
barplot.add_dataset(dataset)
return jsonify(barplot.to_json())
def _display(self, barplot, labels, error=None):
if error is not None:
values = [
len([
p for p in self.predictions[l]
if (p['ground_truth_label'] == l) != error
]) for l in labels
]
label = 'wrong predictions' if error else 'right predictions'
else:
values = [len(self.predictions[l]) for l in labels]
label = 'all'
dataset = PlotDataset(np.array(values), label)
dataset.set_color(get_error_color(error))
barplot.add_dataset(dataset)
def get_exec_times_display(self):
lr = PlotDataset(None, 'Logistic Regression')
lr.set_linestyle('dotted')
nb = PlotDataset(None, 'Naive Bayes')
nb.set_linestyle('dashed')
v = [lr, nb]
v.extend(CoreAladin.get_exec_times_display(self))
return v
def _gen_histogram(self):
# 10 equal-width bins computed on all the data
_, bin_edges = np.histogram(self.all_values, bins=10, density=False)
x_labels = [
'%.2f - %.2f' % (bin_edges[e], bin_edges[e + 1])
for e in range(len(bin_edges) - 1)
]
self.barplot = BarPlot(x_labels)
for label, dataset in self.plot_datasets.items():
if len(dataset.values) > 0:
hist, _ = np.histogram(dataset.values,
bins=bin_edges,
density=False)
hist_dataset = PlotDataset(hist, label)
hist_dataset.set_color(dataset.color)
self.barplot.add_dataset(hist_dataset)
def plot_evolution(self, evolution_file, monitoring_dir):
data = self.load_evolution(evolution_file)
if self.labels_families == 'labels':
title = 'Labels Suggestions Accuracy'
elif self.labels_families == 'families':
title = 'Families Suggestions Accuracy'
values = data['true_suggestions'] / data['num_suggestions']
plot = PlotDataset(values.values, title)
iterations = list(range(self.monitoring.iter_num))
plt.clf()
max_value = 1
plt.plot(iterations, plot.values,
label=plot.label,
color=plot.color,
linewidth=plot.linewidth,
marker=plot.marker)
plt.ylim(0, max_value)
plt.xlabel('Iteration')
plt.ylabel('Suggestions Accuracy')
lgd = plt.legend(bbox_to_anchor=(0., 1.02, 1., .102), loc=3,
ncol=2, mode='expand', borderaxespad=0.,
fontsize='large')
filename = '_'.join([self.labels_families,
self.kind,
'suggestions.png'])
filename = path.join(monitoring_dir, filename)
plt.savefig(filename, bbox_extra_artists=(lgd,), bbox_inches='tight')
plt.clf()
self.data = data
def _gen_label_plot_dataset(self, instances, label=None, family=None,
color=None):
if label is not None:
if label != 'unlabeled':
instances = instances.get_annotated_instances(label=label)
else:
instances = instances.get_unlabeled_instances()
else:
instances = instances.get_annotated_instances(family=family)
values = instances.features.get_values_from_index(self.feature_index)
if isinstance(values, spmatrix):
values = values.toarray()
plot_label = label if label is not None else family
plot_color = color
if plot_color is None:
plot_color = get_label_color(plot_label)
dataset = PlotDataset(values, plot_label)
dataset.set_color(plot_color)
self.plot_datasets[plot_label] = dataset
def to_barplot(self, directory):
head_coeff = self.coef_summary.head(n=NUM_COEFF_EXPORT)
coefficients = list(head_coeff['mean'])
features_ids = head_coeff.index
tooltip_data = []
user_ids = []
for feature_id in features_ids:
query = self.session.query(FeaturesAlchemy)
query = query.filter(FeaturesAlchemy.id == int(feature_id))
row = query.one()
tooltip_data.append(row.name)
user_ids.append(row.user_id)
barplot = BarPlot(user_ids)
dataset = PlotDataset(coefficients, None)
score = self.classifier_conf.get_feature_importance()
if score == 'weight':
dataset.set_color(red)
barplot.add_dataset(dataset)
out_filename = path.join(directory, 'coeff_barplot.json')
return barplot.export_to_json(out_filename, tooltip_data=tooltip_data)
def getClusterStats(exp_id):
experiment = update_curr_exp(exp_id)
clustering = ClustersExp.from_json(experiment.output_dir())
num_clusters = clustering.num_clusters
num_instances_v = []
labels = []
for c in range(num_clusters):
instances_in_cluster = clustering.clusters[c].instances_ids
num_instances = len(instances_in_cluster)
num_instances_v.append(num_instances)
labels.append(clustering.clusters[c].label)
barplot = BarPlot(labels)
dataset = PlotDataset(num_instances_v, 'Num. Instances')
barplot.add_dataset(dataset)
return jsonify(barplot.to_json())
def plot_perf_evolution(self, estimators, output_filename, data,
output_dir):
iterations = list(range(1, self.iter_num + 1))
plt.clf()
for estimator in estimators:
plot = PlotDataset(data[estimator], estimator)
plt.plot(iterations,
plot.values,
label=plot.label,
color=plot.color,
linewidth=plot.linewidth,
marker=plot.marker)
plt.ylim(0, 1)
plt.xlabel('Iteration')
plt.ylabel('Performance')
lgd = plt.legend(bbox_to_anchor=(0., 1.02, 1., .102),
loc=3,
ncol=3,
mode='expand',
borderaxespad=0.,
fontsize='large')
filename = path.join(output_dir, '%s.png' % self.kind)
plt.savefig(filename, bbox_extra_artists=(lgd, ), bbox_inches='tight')
plt.clf()
def get_exec_times_display(self):
generate_queries = PlotDataset(None, 'Queries generation')
generate_queries.set_color('purple')
return [generate_queries]
def exec_time_display(self):
binary_model = PlotDataset(np.array([]), 'Binary model')
v = [binary_model]
v.extend(CoreRandom.get_exec_times_display(self))
return v
def get_exec_times_display(self):
uncertain = PlotDataset(None, 'Uncertain Queries')
malicious = PlotDataset(None, 'Malicious Queries')
malicious.set_linestyle('dotted')
malicious.set_color(get_label_color(MALICIOUS))
benign = PlotDataset(None, 'Benign Queries')
benign.set_linestyle('dashed')
benign.set_color(get_label_color(BENIGN))
return [malicious, uncertain, benign]
def get_exec_times_display(self):
binary_model = PlotDataset(None, 'Binary model')
v = [binary_model]
v.extend(CoreUncertainty.get_exec_times_display(self))
return v
def get_exec_times_display(self):
v = [PlotDataset(None, 'Analysis')]
v.extend(CoreRcd.get_exec_times_display(self))
return v
def get_exec_times_display(self):
binary_model = PlotDataset(None, 'Binary model')
v = [binary_model]
v.extend(CoreCesaBianchi.get_exec_times_display(self))
return v