def test_2d_1cluster(self):
#create simple data:
a = range(0, 11)
print a
d = []
for i in a:
for j in a:
d.append([i*1.0, j*1.0])
dbscanner = Dbscan(np.array(d), 3, 2.0)
dbscanner.run()
plotting.plotting(dbscanner.getClusterList(),dbscanner.getNoise())
def test_plotting(self):
#some dummy data
number, x_coordinate, y_coordinate = loadtxt('testdata/eps3-minpts5-cluster5-noise20.dat', unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
#put in the data we want to use
minNeighbors = 5
#epsilon = 2
data = array(D)
# use dbscan
dbscanner = Dbscan(data, minNeighbors)
result = dbscanner.run()
# use plotting
plotting.plotting(result)
def test_plotting(self):
#some dummy data
number, x_coordinate, y_coordinate = loadtxt('testdata/eps3-minpts5-cluster5-noise20.dat', unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
#put in the data we want to use
minNeighbors = 5
epsilon = 3.
data = np.array(D, dtype=np.float64)
# use dbscan
dbscanner = Dbscan(data, minNeighbors, epsilon)
dbscanner.run()
# use plotting
plotting.plotting(dbscanner.getClusterList(),dbscanner.getNoise())
def test_dbscan2(self):
testdata2='testdata/eps0p01-minpts1-cluster0-noise100.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata2, unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
D=np.array(D)
epsilon=0.01
minNeighbors=1
dbscanner = Dbscan(D, minNeighbors,epsilon)
test1 = dbscanner.run()
datennoise=test1[len(test1)-1]
datennoise=np.array(datennoise)
b=[]
cluster1=test1[:len(test1)-1]
assert cluster1[0]==b
assert datennoise.all()==D.all()
def test_dbscan2(self):
testdata2='testdata/eps0p01-minpts1-cluster0-noise100.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata2, unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
D=np.array(D)
epsilon=0.01
minNeighbors=1
dbscanner = Dbscan(D, minNeighbors, epsilon)
dbscanner.run()
datennoise=dbscanner.getNoise()
datennoise=np.array(datennoise)
b=[]
cluster1=dbscanner.getClusterList()
np.testing.assert_array_equal(cluster1,b)
np.testing.assert_array_equal(datennoise,D)
def test_dbscan1(self):
testdata='testdata/eps2-minpts3-cluster1-noise0.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata, unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
D=np.array(D)
epsilon=4.0
minNeighbors=3
dbscanner = Dbscan(D, minNeighbors, epsilon)
dbscanner.run()
datennoise=dbscanner.getNoise()
Dresultall=[]
for daten in dbscanner.getClusterList():
Dresult=[]
for item in daten:
Dresult.append(item)
Dresultall.append(Dresult) #
#assert D==a
Dr=np.array(Dresultall)
a=np.array([])
np.testing.assert_array_equal(a,datennoise)
def test_dbscan1(self):
testdata='testdata/eps2-minpts3-cluster1-noise0.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata, unpack = True)
D=[None]*len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii]=[x_coordinate[ii],y_coordinate[ii]]
D=np.array(D)
epsilon=2
minNeighbors=3
dbscanner = Dbscan(D,minNeighbors,epsilon,)
test1 = dbscanner.run()
datennoise=test1[len(test1)-1]
Dresultall=[]
for daten in test1[:len(test1)-1]:
Dresult=[]
for item in daten:
Dresult.append(item)
Dresultall.append(Dresult) #
#assert D==a
Dr=np.array(Dresultall)
a=[]
assert datennoise==a
assert D.all()==Dr.all()
def test_2d_1cluster(self):
#create simple data:
a = range(0, 11)
print a
d = []
for i in a:
for j in a:
d.append([i * 1.0, j * 1.0])
dbscanner = Dbscan(np.array(d), 3, 2.0)
dbscanner.run()
plotting.plotting(dbscanner.getClusterList(), dbscanner.getNoise())
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))
def test_plotting(self):
#some dummy data
number, x_coordinate, y_coordinate = loadtxt(
'testdata/eps3-minpts5-cluster5-noise20.dat', unpack=True)
D = [None] * len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii] = [x_coordinate[ii], y_coordinate[ii]]
#put in the data we want to use
minNeighbors = 5
epsilon = 3.
data = np.array(D, dtype=np.float64)
# use dbscan
dbscanner = Dbscan(data, minNeighbors, epsilon)
dbscanner.run()
# use plotting
plotting.plotting(dbscanner.getClusterList(), dbscanner.getNoise())
def test_dbscan2(self):
testdata2 = 'testdata/eps0p01-minpts1-cluster0-noise100.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata2, unpack=True)
D = [None] * len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii] = [x_coordinate[ii], y_coordinate[ii]]
D = np.array(D)
epsilon = 0.01
minNeighbors = 1
dbscanner = Dbscan(D, minNeighbors, epsilon)
dbscanner.run()
datennoise = dbscanner.getNoise()
datennoise = np.array(datennoise)
b = []
cluster1 = dbscanner.getClusterList()
np.testing.assert_array_equal(cluster1, b)
np.testing.assert_array_equal(datennoise, D)
def test_dbscan1(self):
testdata = 'testdata/eps2-minpts3-cluster1-noise0.dat'
number, x_coordinate, y_coordinate = np.loadtxt(testdata, unpack=True)
D = [None] * len(x_coordinate)
for ii in range(len(x_coordinate)):
D[ii] = [x_coordinate[ii], y_coordinate[ii]]
D = np.array(D)
epsilon = 4.0
minNeighbors = 3
dbscanner = Dbscan(D, minNeighbors, epsilon)
dbscanner.run()
datennoise = dbscanner.getNoise()
Dresultall = []
for daten in dbscanner.getClusterList():
Dresult = []
for item in daten:
Dresult.append(item)
Dresultall.append(Dresult) #
#assert D==a
Dr = np.array(Dresultall)
a = np.array([])
np.testing.assert_array_equal(a, datennoise)
from sklearn import metrics
from sklearn.datasets import make_moons
from dbscan import Dbscan
import numpy as np
import matplotlib.pyplot as plt
X, labels_true = make_moons(n_samples=200, noise=0.1, random_state=19)
Y = np.array_split(X, 2)
db = Dbscan(eps=0.25, min_samples=12).partial_fit(Y[0]).partial_fit(Y[1])
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_
# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
n_noise_ = list(labels).count(-1)
print('Estimated number of clusters: %d' % n_clusters_)
print('Estimated number of noise points: %d' % n_noise_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f" % metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f" % metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f" % metrics.silhouette_score(X, labels))
unique_labels = set(labels)
colors = [plt.cm.Spectral(each)
for each in np.linspace(0, 1, len(unique_labels))]
from sklearn import metrics
from sklearn.datasets import make_moons
from dbscan import Dbscan
import numpy as np
import matplotlib.pyplot as plt
X, labels_true = make_moons(n_samples=200, noise=0.1, random_state=19)
db = Dbscan(eps=0.25, min_samples=12).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_
# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
n_noise_ = list(labels).count(-1)
print('Estimated number of clusters: %d' % n_clusters_)
print('Estimated number of noise points: %d' % n_noise_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f" %
metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f" %
metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f" % metrics.silhouette_score(X, labels))
unique_labels = set(labels)
colors = [
plt.cm.Spectral(each) for each in np.linspace(0, 1, len(unique_labels))
]
