def getFamiliesBarplot(experiment_id, iteration, label):
if iteration == 'None':
iteration = None
family_counts = annotations_db_tools.getFamiliesCounts(
session, experiment_id, iteration_max=iteration, label=label)
df = pd.DataFrame({
'families':
list(family_counts.keys()),
'counts': [family_counts[k] for k in list(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 getTopWeightedFeatures(experiment_id, inst_exp_id, instance_id, size,
fold_id):
if fold_id == 'all':
return None
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
experiment_dir = exp.getOutputDirectory()
if fold_id != 'None':
experiment_dir = path.join(experiment_dir, fold_id)
pipeline = joblib.load(path.join(experiment_dir, 'model', 'model.out'))
# 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 = list(
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]
features_names = [x[0] for x in features]
features_values = [x[1] for x in features]
features_weighted_values = [x[2] for x in features]
max_length = max([len(f) for f in features_names])
if max_length > 30:
labels = [str(i) for i in range(len(features_names))]
tooltips = [
features_names[i] + ' (' + str(features_values[i]) + ')'
for i in range(len(features_names))
]
else:
labels = features_names
tooltips = features_values
barplot = BarPlot(labels)
dataset = PlotDataset(features_weighted_values, None)
dataset.setColor(colors_tools.red)
barplot.addDataset(dataset)
return jsonify(barplot.toJson(tooltip_data=tooltips))
def getClusterStats(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
clustering = ClusteringExp.fromJson(experiment.getOutputDirectory())
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 getTopModelFeatures(experiment_id, size, train_test, fold_id):
size = int(size)
exp = updateCurrentExperiment(experiment_id)
directory = exp.getOutputDirectory()
if fold_id != 'None' and fold_id != 'all':
directory = path.join(directory, fold_id)
directory = path.join(directory, train_test)
filename = path.join(directory, 'model_coefficients.csv')
with open(filename, 'r') as f:
coefficients_df = pd.read_csv(f, header=0, index_col=0)
model_coefficients = list(coefficients_df['mean'])
features_names = list(map(str, coefficients_df.index))
coefficients = list(
map(lambda name, coef: (name, coef), features_names,
model_coefficients))
coefficients.sort(key=lambda tup: abs(tup[1]))
coefficients = coefficients[:-size - 1:-1]
coefficients_names = [coef[0] for coef in coefficients]
coefficients_values = [coef[1] for coef in coefficients]
max_length = max([len(coef) for coef in coefficients_names])
if max_length > 30:
coefficients_ids = [str(i) for i in range(len(coefficients_names))]
coefficients_names = [
name.replace(' WHERE', '\nWHERE')
for name in coefficients_names
]
barplot = BarPlot(coefficients_ids)
dataset = PlotDataset(coefficients_values, None)
if exp.conf.featureImportance() == 'weight':
dataset.setColor(colors_tools.red)
barplot.addDataset(dataset)
return jsonify(barplot.toJson(tooltip_data=coefficients_names))
else:
barplot = BarPlot(coefficients_names)
dataset = PlotDataset(coefficients_values, None)
if exp.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_ground_truth:
hist, bin_edges = np.histogram(self.plot_datasets['all'].values,
bins=10,
density=False)
else:
hist, bin_edges = np.histogram(
self.plot_datasets[labels_tools.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.items():
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 = path.join(self.output_directory, 'histogram.json')
with open(output_filename, 'w') as f:
barplot.exportJson(f)
def getFamiliesPerformance(experiment_id, train_test, label, threshold):
experiment = updateCurrentExperiment(experiment_id)
directory = path.join(experiment.getOutputDirectory(), train_test,
'families')
if label == labels_tools.MALICIOUS:
filename = 'tp_'
tp_fp = 'Detection Rate'
elif label == labels_tools.BENIGN:
filename = 'fp_'
tp_fp = 'False Positive Rate'
filename += 'families_thresholds.csv'
with open(path.join(directory, 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())
def generateBinaryHistogram(self):
barplot = BarPlot(['0', '1'])
for label, dataset in self.plot_datasets.items():
num_0 = sum(dataset.values == 0)
num_1 = sum(dataset.values == 1)
hist_dataset = PlotDataset([num_0, num_1], dataset.label)
hist_dataset.setColor(dataset.color)
barplot.addDataset(hist_dataset)
output_filename = path.join(self.output_directory,
'binary_histogram.json')
with open(output_filename, 'w') as f:
barplot.exportJson(f)
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)), 'numInstances')
dataset.setColor(colors_tools.getLabelColor('all'))
barplot.addDataset(dataset)
else:
self.displayLabel(barplot, labels_tools.MALICIOUS)
self.displayLabel(barplot, labels_tools.BENIGN)
filename = path.join(directory, 'predictions_barplot.json')
with open(filename, 'w') as f:
barplot.exportJson(f)