def getTopWeightedFeatures(experiment_id, inst_exp_id, instance_id, size):
instance_id = int(instance_id)
exp = ExperimentFactory.getFactory().fromJson(experiment_id, session)
validation_experiment = ExperimentFactory.getFactory().fromJson(
inst_exp_id, session)
#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 = exp.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])
dataset = PlotDataset([x[2] for x in features], None)
dataset.setColor(colors_tools.red)
barplot.addDataset(dataset)
return jsonify(barplot.toJson(tooltip_data=tooltips))
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 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 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())