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)
barplot.addDataset(map(len, self.ranges),
colors_tools.getLabelColor('all'), 'numInstances')
filename = directory + 'predictions_barplot.json'
with open(filename, 'w') as f:
barplot.display(f)
barplot = BarPlot(labels)
malicious_ranges = map(lambda l: filter(lambda x: x['true_label'], l),
self.ranges)
benign_ranges = map(lambda l: filter(lambda x: not x['true_label'], l),
self.ranges)
barplot.addDataset(map(len, malicious_ranges),
colors_tools.getLabelColor('malicious'),
'malicious')
barplot.addDataset(map(len, benign_ranges),
colors_tools.getLabelColor('benign'), 'benign')
filename = directory
filename += 'predictions_barplot_labels.json'
with open(filename, 'w') as f:
barplot.display(f)
def getTopWeightedFeatures(project, dataset, experiment, instance_dataset,
inst_exp_id, instance_id, size):
instance_id = int(instance_id)
model_experiment_obj = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment, db, cursor)
validation_experiment = ExperimentFactory.getFactory().fromJson(
project, instance_dataset, inst_exp_id, db, cursor)
#get the features
features_names, features_values = validation_experiment.getFeatures(
instance_id)
features_values = [float(value) for value in features_values]
#get the pipeline with scaler and logistic model
pipeline = model_experiment_obj.getModelPipeline()
#scale the features
scaled_values = pipeline.named_steps['scaler'].transform(
np.reshape(features_values, (1, -1)))
weighted_values = np.multiply(scaled_values,
pipeline.named_steps['model'].coef_)
features = map(lambda name, value, w_value: (name, value, w_value),
features_names, features_values, weighted_values[0])
features.sort(key=lambda tup: abs(tup[2]))
features = features[:-int(size) - 1:-1]
tooltips = [x[1] for x in features]
barplot = BarPlot([x[0] for x in features])
barplot.addDataset([x[2] for x in features], colors_tools.red, None)
barplot.addTooltips(tooltips)
return jsonify(barplot.barplot)
def plotEvolutionMonitoring(self):
barplot = BarPlot(self.families)
for i in range(self.data.shape[0]):
barplot.addDataset(list(self.data.iloc[i, 1:]), 'blue', str(i))
filename = self.output_directory
filename += self.label + '_families_evolution.json'
with open(filename, 'w') as f:
barplot.display(f)
def plotEvolutionMonitoring(self):
barplot = BarPlot(self.families)
for i in range(self.data.shape[0]):
dataset = PlotDataset([self.data.iloc[i, 1]], str(i))
barplot.addDataset(dataset)
filename = self.output_directory
filename += self.label + '_families_evolution.json'
with open(filename, 'w') as f:
barplot.exportJson(f)
def generateBinaryHistogram(self):
barplot = BarPlot(['0', '1'])
for label, dataset in self.plot_datasets.iteritems():
num_0 = sum(dataset.values == 0)
num_1 = sum(dataset.values == 1)
barplot.addDataset([num_0, num_1], dataset.color, dataset.label)
output_filename = self.output_directory + 'binary_histogram.json'
with open(output_filename, 'w') as f:
barplot.display(f)
def plotEvolutionMonitoring(self, evolution_file, monitoring_dir):
data = self.loadEvolutionMonitoring(evolution_file)
barplot = BarPlot(self.families)
for i in range(data.shape[0]):
dataset = PlotDataset([data.iloc[i, 1]], str(i))
barplot.addDataset(dataset)
filename = monitoring_dir
filename += self.label + '_families_evolution.json'
with open(filename, 'w') as f:
barplot.exportJson(f)
def getTopModelCoefficients(project, dataset, experiment, size):
size = int(size)
model_experiment_obj = ExperimentFactory.getFactory().fromJson(project, dataset, experiment, db, cursor)
pipeline = model_experiment_obj.getModelPipeline()
model_coefficients = pipeline.named_steps['model'].coef_[0]
features_names = model_experiment_obj.getFeaturesNames()
coefficients = map(lambda name, coef: (name, coef),
features_names, model_coefficients)
coefficients.sort(key = lambda tup: abs(tup[1]))
coefficients = coefficients[:-size-1:-1]
barplot = BarPlot([x[0] for x in coefficients])
barplot.addDataset([x[1] for x in coefficients], '#d9534f', None)
return jsonify(barplot.barplot)
def getTopModelFeatures(experiment_id, size):
size = int(size)
exp = ExperimentFactory.getFactory().fromJson(experiment_id, session)
model_coefficients = exp.getTopFeatures()
features_names = exp.getFeaturesNames()
coefficients = map(lambda name, coef: (name, coef), features_names,
model_coefficients)
coefficients.sort(key=lambda tup: abs(tup[1]))
coefficients = coefficients[:-size - 1:-1]
barplot = BarPlot([x[0] for x in coefficients])
dataset = PlotDataset([x[1] for x in coefficients], None)
if (exp.classification_conf.featureImportance() == 'weight'):
dataset.setColor(colors_tools.red)
barplot.addDataset(dataset)
return jsonify(barplot.toJson())
def generateHistogram(self):
# 10 equal-width bins computed on all the data
if not self.has_true_labels:
hist, bin_edges = np.histogram(self.plot_datasets['all'].values, bins = 10, density = False)
else:
hist, bin_edges = np.histogram(self.plot_datasets['malicious'].values, bins = 10, density = False)
x_labels = [str(bin_edges[e]) + ' - ' + str(bin_edges[e+1]) for e in range(len(bin_edges)-1)]
barplot = BarPlot(x_labels)
for label, dataset in self.plot_datasets.iteritems():
hist, bin_edges = np.histogram(dataset.values, bins = bin_edges, density = False)
hist_dataset = PlotDataset(hist, dataset.label)
hist_dataset.setColor(dataset.color)
barplot.addDataset(hist_dataset)
output_filename = self.output_directory + 'histogram.json'
with open(output_filename, 'w') as f:
barplot.exportJson(f)
def getClusterStats(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(project, dataset, experiment_id,
db, cursor)
clustering = Clustering.fromJson(experiment)
num_clusters = clustering.num_clusters
num_instances_v = []
labels = []
mysql_tools.useDatabase(cursor, project, dataset)
for c in range(num_clusters):
instances_in_cluster = clustering.clusters[c].instances_ids
num_instances = len(instances_in_cluster)
# the empty clusters are not displayed
if num_instances > 0:
num_instances_v.append(num_instances)
labels.append('c_' + str(c))
barplot = BarPlot(labels)
barplot.addDataset(num_instances_v, colors_tools.blue, 'Num. Instances')
return jsonify(barplot.barplot)
def getClusterStats(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
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)
# the empty clusters are not displayed
#if num_instances > 0:
num_instances_v.append(num_instances)
#labels.append('c_' + str(c))
labels.append(clustering.clusters[c].label)
barplot = BarPlot(labels)
dataset = PlotDataset(num_instances_v, 'Num. Instances')
barplot.addDataset(dataset)
return jsonify(barplot.toJson())
def getFamiliesPerformance(project, dataset, experiment, train_test, label, threshold):
filename = getDir(project, dataset, experiment) + train_test + '/families/'
if label == 'malicious':
filename += 'tp_'
tp_fp = 'Detection Rate'
elif label == 'benign':
filename += 'fp_'
tp_fp = 'False Positive Rate'
filename += 'families_thresholds.csv'
with open(filename, 'r') as f:
perf = pd.read_csv(f, header = 0, index_col = 0)
families = list(perf.columns.values[:-1])
threshold = float(threshold)/100
thresholds = list(perf.index[:-1])
threshold_value = min(enumerate(thresholds), key=lambda x: abs(x[1]-threshold))[1]
perf = list(perf.loc[threshold_value])
barplot = BarPlot(families)
barplot.addDataset(perf, colors_tools.getLabelColor('all'), tp_fp)
return jsonify(barplot.barplot);
def getFamiliesBarplot(project, dataset, experiment_id, iteration, label):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
experiment_label_id = experiment.experiment_label_id
if iteration == 'None':
iteration = None
family_counts = labels_tools.getFamiliesCounts(cursor,
experiment_label_id,
iteration_max=iteration,
label=label)
df = pd.DataFrame({
'families':
family_counts.keys(),
'counts': [family_counts[k] for k in family_counts.keys()]
})
matrix_tools.sortDataFrame(df, 'families', ascending=True, inplace=True)
barplot = BarPlot(list(df['families']))
barplot.addDataset(list(df['counts']), colors_tools.getLabelColor(label),
'Num. Instances')
return jsonify(barplot.barplot)
def getFamiliesBarplot(experiment_id, iteration, label):
experiment = updateCurrentExperiment(experiment_id)
experiment_label_id = experiment.labels_id
if iteration == 'None':
iteration = None
family_counts = labels_tools.getFamiliesCounts(experiment.session,
experiment_label_id,
iteration_max=iteration,
label=label)
df = pd.DataFrame({
'families':
family_counts.keys(),
'counts': [family_counts[k] for k in family_counts.keys()]
})
matrix_tools.sortDataFrame(df, 'families', ascending=True, inplace=True)
barplot = BarPlot(list(df['families']))
dataset = PlotDataset(list(df['counts']), 'Num. Instances')
dataset.setColor(colors_tools.getLabelColor(label))
barplot.addDataset(dataset)
return jsonify(barplot.toJson())
def getFamiliesPerformance(experiment_id, train_test, label, threshold):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + train_test + '/families/'
if label == 'malicious':
filename += 'tp_'
tp_fp = 'Detection Rate'
elif label == 'benign':
filename += 'fp_'
tp_fp = 'False Positive Rate'
filename += 'families_thresholds.csv'
with open(filename, 'r') as f:
perf = pd.read_csv(f, header=0, index_col=0)
families = list(perf.columns.values[:-1])
threshold = float(threshold) / 100
thresholds = list(perf.index[:-1])
threshold_value = min(enumerate(thresholds),
key=lambda x: abs(x[1] - threshold))[1]
perf = list(perf.loc[threshold_value])
barplot = BarPlot(families)
barplot.addDataset(PlotDataset(perf, tp_fp))
return jsonify(barplot.toJson())