def svm_local(isDecision=False, n_predict=0, n_neighbors=5000, isSgd=True):
start = time.time()
db_manager = DbManager()
db_manager.connect('../db/annotated.db')
print("Start converting train points")
train_points_tmp = train_points.tolist()
train_classes_tmp = train_classes.tolist()
print("Conversion finished in time {0}s".format(time.time()-start))
predict_classes = []
for point_id, point_vector in enumerate(test_points):
if point_id >= 100:
break
if point_id % 10 == 0:
print("Start query test point {0}".format(point_id))
neighbors = [int(x) for x in db_manager.query_knn('../db/annotated.db', point_id, n_neighbors=n_neighbors)[0].split()]
neighbor_points = [train_points_tmp[neighbor_id] for neighbor_id in neighbors]
neighbor_classes = [train_classes_tmp[neighbor_id] for neighbor_id in neighbors]
svmManager = SvmManager(None, verbose=verbose, isSgd=isSgd)
svmManager.fit(np.array(neighbor_points), np.array(neighbor_classes), store=False)
if not isDecision:
predict_classes.append(svmManager.predict([point_vector])[0]) #only one class result
else:
predict_classes.append(svmManager.decision_function([point_vector], n_predict)[0] )
end = time.time()
logging.info("testing local svm finished in {0}s with {1}".format(end - start, model_file))
return predict_classes
def benchmark_knn():
db_manager = DbManager()
db_manager.connect()
train_classes_tmp = train_classes.tolist()
class_count_dict = {}
for point_id, point_vector in enumerate(test_points):
# test_folder = test_names[point_id][0].split('_')[0]
test_class = test_classes[point_id]
# if test_folder not in good_folders:
# continue
if point_id >= 1000:
break
if point_id % 10 == 0:
print("Start query test point {0}".format(point_id))
neighbors = [int(x) for x in db_manager.query_knn(point_id, n_neighbors=n_neighbors)[0].split()]
neighbor_classes = [train_classes_tmp[neighbor_id] for neighbor_id in neighbors]
correct_classes = neighbor_classes.count(test_class)
print( "{0} {1}".format( correct_classes, float(correct_classes)/len(neighbor_classes)))
if test_class not in class_count_dict:
class_count_dict[test_class] = [0,0];
else:
class_count_dict[test_class][0] += correct_classes
class_count_dict[test_class][1] += len(neighbor_classes) #200, 1000, 5000
print(class_count_dict)
