def test_dbscan(self):
exact_labels = []
label_1 = "Iris-setosa"
label_2 = "Iris-versicolor"
label_3 = "Iris-virginica"
for item in self.data["label"]:
if item == label_1:
exact_labels.append(2)
elif item == label_2:
exact_labels.append(3)
else:
exact_labels.append(1)
epsilon = 2
min_pts = 2
dbscan = Dbscan(epsilon, min_pts)
X_train, X_test, y_train, y_test = train_test_split(self.features,
self.exact_labels,
test_size=0.33,
random_state=42)
dbscan.load_data(X_train.to_numpy().tolist())
dbscan.train()
labels = dbscan.predict(X_test.to_numpy().tolist())
accurate_sum = 0
for i in range(len(labels)):
if labels[i] == y_test[i]:
accurate_sum += 1
print("Akurasi DBScan: ", accurate_sum / len(labels))
clustering_labels = DBSCAN(eps=epsilon,
min_samples=min_pts).fit_predict(X_train)
clustering_labels = [c + 3 for c in clustering_labels]
sklearn_accurate_sum = 0
for i in range(len(labels)):
if clustering_labels[i] == y_test[i]:
sklearn_accurate_sum += 1
print("Akurasi DBScan sklearn: ", sklearn_accurate_sum / len(labels))
