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 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 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())