def templateClusterAllocationOneDimensionData(self, ccore_flag):
input_data = [ [random()] for i in range(10) ] + [ [random() + 3] for i in range(10) ] + [ [random() + 5] for i in range(10) ] + [ [random() + 8] for i in range(10) ];
rock_instance = rock(input_data, 1, 4, 0.5, ccore_flag);
rock_instance.process();
clusters = rock_instance.get_clusters();
assert len(clusters) == 4;
for cluster in clusters:
assert len(cluster) == 10;
def templateClusterAllocationOneDimensionData(self, ccore_flag):
input_data = [ [random()] for i in range(10) ] + [ [random() + 3] for i in range(10) ] + [ [random() + 5] for i in range(10) ] + [ [random() + 8] for i in range(10) ];
rock_instance = rock(input_data, 1, 4, 0.5, ccore_flag);
rock_instance.process();
clusters = rock_instance.get_clusters();
assert len(clusters) == 4;
for cluster in clusters:
assert len(cluster) == 10;
def get_modelo(self, algoritmo, eps, neig):
print(algoritmo + ' ' + str(eps) + ' - ' + str(neig))
instance = None
if algoritmo == 'AGNES':
instance = agglomerative(self.amostras,
self.numero_clusters,
link=None)
elif algoritmo == 'BIRCH':
instance = birch(self.amostras,
self.numero_clusters,
entry_size_limit=10000)
elif algoritmo == 'CLARANS':
instance = clarans(self.amostras,
self.numero_clusters,
numlocal=100,
maxneighbor=1)
elif algoritmo == 'CURE':
instance = cure(self.amostras,
self.numero_clusters,
number_represent_points=5,
compression=0.5)
elif algoritmo == 'DBSCAN':
instance = dbscan(self.amostras, eps=eps, neighbors=neig)
elif algoritmo == 'FCM':
initial_centers = kmeans_plusplus_initializer(
self.amostras, self.numero_clusters).initialize()
instance = fcm(self.amostras, initial_centers)
elif algoritmo == 'KMEANS':
initial_centers = kmeans_plusplus_initializer(
self.amostras, self.numero_clusters).initialize()
instance = kmeans(self.amostras, initial_centers, tolerance=0.001)
elif algoritmo == 'KMEDOIDS':
instance = kmedoids(self.amostras,
initial_index_medoids=[0, 0, 0, 0, 0, 0, 0],
tolerance=0.0001) #ajustar o n_de cluster
elif algoritmo == 'OPTICS':
instance = optics(self.amostras, eps=eps, minpts=neig)
elif algoritmo == 'ROCK':
instance = rock(self.amostras,
eps=eps,
number_clusters=self.numero_clusters,
threshold=0.5)
else:
pass
instance.process()
lista_agrupada = self.get_lista_agrupada(instance.get_clusters())
lista_agrupada = np.array(lista_agrupada)
if (neig != 0):
n_grupos = len(np.unique(lista_agrupada))
if n_grupos > self.numero_clusters:
lista_agrupada = self.get_modelo(algoritmo, eps, neig + 1)
return lista_agrupada
def template_clustering(path, radius, cluster_numbers, threshold, draw = True, ccore = True):
sample = read_sample(path);
rock_instance = rock(sample, radius, cluster_numbers, threshold, ccore);
(ticks, result) = timedcall(rock_instance.process);
clusters = rock_instance.get_clusters();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
if (draw == True):
draw_clusters(sample, clusters);
def rock(cls, data, eps, number_clusters, threshold=0.5, ccore=False):
"""
Constructor of the ROCK cluster analysis algorithm
:param eps: Connectivity radius (similarity threshold), points are neighbors if distance between them is less than connectivity radius
:param number_clusters: Defines number of clusters that should be allocated from the input data set
:param threshold: Value that defines degree of normalization that influences on choice of clusters for merging during processing
:param ccore: Defines should be CCORE (C++ pyclustering library) used instead of Python code or not.
:return: The resulting clustering.rst object
"""
data = cls.input_preprocess(data)
model = rock(data, eps, number_clusters, threshold, ccore)
return cls(model)
def templateLengthProcessData(self, path_to_file, radius, cluster_numbers, threshold, expected_cluster_length, ccore = False):
sample = read_sample(path_to_file);
rock_instance = rock(sample, radius, cluster_numbers, threshold, ccore);
rock_instance.process();
clusters = rock_instance.get_clusters();
length = sum([len(cluster) for cluster in clusters]);
assert len(sample) == length;
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
assert obtained_cluster_sizes == expected_cluster_length;
def templateLengthProcessData(self, path_to_file, radius, cluster_numbers, threshold, expected_cluster_length, ccore = False):
sample = read_sample(path_to_file);
rock_instance = rock(sample, radius, cluster_numbers, threshold, ccore);
rock_instance.process();
clusters = rock_instance.get_clusters();
length = sum([len(cluster) for cluster in clusters]);
assert len(sample) == length;
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
assert obtained_cluster_sizes == expected_cluster_length;
def rocAlgo(filename, col_name):
df = pd.read_csv(filename, usecols=[col_name])
df[col_name] = df[col_name]
rock_instance = rock(col_name, 1.0, 100)
# Run cluster analysis
rock_instance.process()
# Obtain results of clustering
clusters = rock_instance.get_clusters()
print(clusters)
print(timeit.timeit('"-".join(str(n) for n in range(100))', number=10000))
#Visualize clusters:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, col_name)
visualizer.show(display=False)
plt.savefig(
"C:/Users/Nupura Hajare/Desktop/flask_app/web/static/img/Roc.png")
def testCoreInterfaceIntInputData(self):
optics_instance = rock([[1], [2], [3], [20], [21], [22]], 3, 2, 0.5,
True)
optics_instance.process()
assert len(optics_instance.get_clusters()) == 2
def process_rock(sample):
instance = rock(sample, 1, NUMBER_CLUSTERS, 0.5)
(ticks, _) = timedcall(instance.process)
return ticks
def process_rock(sample):
instance = rock(sample, 1, NUMBER_CLUSTERS, 0.5)
(ticks, _) = timedcall(instance.process)
return ticks
df = pd.read_excel('chosen12345610percent.xlsx')
features = df.columns
print(features)
f = ['RPy', 'edu', 'role', 'industry', 'most_often']
#print(df.values)
df.loc[df['RPy'].isna(), 'RPy'] = 0
df.loc[df['edu'].isna(), 'edu'] = 0
df.loc[df['role'].isna(), 'role'] = 0
df.loc[df['industry'].isna(), 'industry'] = 0
df.loc[df['most_often'].isna(), 'most_often'] = 0
data = df[features]
scaler = MinMaxScaler().fit(data)
x = pd.DataFrame(scaler.transform(data))
# Create instance of ROCK algorithm for cluster analysis. Seven clusters should be allocated.
rock_instance = rock(x.values, 1.0, 7)
# Run cluster analysis.
rock_instance.process()
# Obtain results of clustering.
clusters = rock_instance.get_clusters()
print(clusters)
# Visualize clustering results.
#visualizer = cluster_visualizer()
#visualizer.append_clusters(clusters, x.values)
#visualizer.show()
from pyclustering.cluster import cluster_visualizer from pyclustering.cluster.rock import rock from pyclustering.samples.definitions import FCPS_SAMPLES from pyclustering.utils import read_sample # Read sample for clustering from file. sample = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA) # Create instance of ROCK algorithm for cluster analysis. Seven clusters should be allocated. rock_instance = rock(sample, 1.0, 7) # Run cluster analysis. rock_instance.process() # Obtain results of clustering. clusters = rock_instance.get_clusters() # Visualize clustering results. visualizer = cluster_visualizer() visualizer.append_clusters(clusters, sample) visualizer.show()
