def cluster_clique(self, intervals, threshold):
self.clustering_name = "clique clustering"
X = self.data_frame.get_point_only_df().values
clique_instance = clique(X, intervals, threshold)
clique_instance.process()
clusters = clique_instance.get_clusters()
self.data_frame.add_result_name(self.clustering_name, -2,
ColType.CLUSTER_LABEL)
i = 1
for cluster in clusters:
for index in cluster:
self.data_frame.add_result(self.clustering_name, index, i)
i += 1
self.cluster_count = len(
set(self.data_frame.df[self.clustering_name].tolist()))
self.clustering_result = self.data_frame.df[
self.clustering_name].tolist()
return self.clustering_name
def visualize(path, levels, threshold, ccore_enabled, **kwargs):
sample = read_sample(path)
clique_instance = clique(sample, levels, threshold, ccore=ccore_enabled)
clique_instance.process()
cells = clique_instance.get_cells()
clique_visualizer.show_grid(cells, sample)
def visualize(path, levels, threshold, ccore_enabled, **kwargs):
sample = read_sample(path)
clique_instance = clique(sample, levels, threshold, ccore=ccore_enabled)
clique_instance.process()
cells = clique_instance.get_cells()
clique_visualizer.show_grid(cells, sample)
def fit(self,data):
data = data.values
self.CLIQUE = clique(data,self.intervals,self.threshold)
self.CLIQUE.process()
preds = self.CLIQUE.get_clusters()
self.labels_ = np.empty(data.shape[0],dtype=int)
for id_,pred in enumerate(preds):
for i in pred:
self.labels_[i] = id_
def exception(type, sample_storage, levels, threshold, ccore_enabled):
try:
sample = sample_storage
if isinstance(sample_storage, str):
sample = read_sample(sample_storage)
bang_instance = clique(sample, levels, threshold, ccore=ccore_enabled)
bang_instance.process()
except type:
return
except Exception as ex:
raise AssertionError("Expected: '%s', Actual: '%s'" % (type, type(ex).__name__))
raise AssertionError("Expected: '%s', Actual: 'None'" % type)
def exception(type, sample_storage, levels, threshold, ccore_enabled):
try:
sample = sample_storage
if isinstance(sample_storage, str):
sample = read_sample(sample_storage)
bang_instance = clique(sample, levels, threshold, ccore=ccore_enabled)
bang_instance.process()
except type:
return
except Exception as ex:
raise AssertionError("Expected: '%s', Actual: '%s'" % (type, type(ex).__name__))
raise AssertionError("Expected: '%s', Actual: 'None'" % type)
def analyze_manifold_old(model: VaeWrapper, sess, xs, ys, stage=1):
# TODO (3/17): deprecate
inds = list(range(len(xs)))
cnt = 1000
np.random.shuffle(inds)
xs, ys = xs[inds][:cnt], ys[inds][:cnt]
zs = model.encode(xs, stage=stage)
zst = zs.T
corr = np.corrcoef(zst)
print(corr)
# create CLIQUE algorithm for processing
intervals = 20 # defines amount of cells in grid in each dimension
threshold = 0
clique_instance = clique(zs, intervals, threshold)
# start clustering process and obtain results
clique_instance.process()
clusters = clique_instance.get_clusters() # allocated clusters
# points that are considered as outliers
noise = clique_instance.get_noise()
cells = clique_instance.get_cells() # CLIQUE blocks that forms grid
print("Amount of clusters:", len(clusters))
encodings = clique_instance.get_cluster_encoding()
print(encodings)
if model.latent_dim == 2:
# visualize clustering results
# clique_visualizer.show_grid(cells, zs)
# clique_visualizer.show_clusters(zs, clusters, noise)
import hdbscan
clusterer = hdbscan.HDBSCAN(min_cluster_size=4)
cluster_labels = clusterer.fit_predict(zs)
print("# clusters by HDBSCAN", clusterer.labels_.max())
print("probabilities", clusterer.probabilities_)
print("labels", clusterer.labels_)
clusterer.condensed_tree_.plot()
plt.show()
elif model.latent_dim == 3:
fig = go.Figure(data=[go.Scatter3d(
x=zst[0], y=zst[1], z=zst[2], mode='markers',
marker=dict(size=2, color=ys, colorscale='Viridis', opacity=0.8),
)])
# tight layout
fig.update_layout(margin=dict(l=0, r=0, b=0, t=0))
fig.show()
def setup(self, keywords={}):
"""
Setup the algorithms
"""
for p in keywords.keys():
setattr(self, p, keywords[p])
if self.method == "bang":
self.obj = bang(self.data_list,
self.levels,
ccore=self.ccore,
density_threshold=self.density_threshold,
amount_threshold=self.amount_threshold)
if self.method == "clique":
self.obj = clique(self.data_list,
self.amount_threshold,
self.density_threshold,
ccore=self.ccore)
return
def template_clustering(data_path, intervals, density_threshold, **kwargs):
print("Sample: '%s'." % os.path.basename(data_path))
data = read_sample(data_path)
clique_instance = clique(data, intervals, density_threshold)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
print([len(cluster) for cluster in clusters])
clique_visualizer.show_grid(cells, data)
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, data)
visualizer.append_cluster(noise, data, marker='x')
visualizer.show()
def clustering(path, intervals, density_threshold, expected_clusters, expected_noise, ccore_enabled, **kwargs):
sample = read_sample(path)
dimension = len(sample[0])
clique_instance = clique(sample, intervals, density_threshold, ccore=ccore_enabled)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
assertion.eq(len(cells), pow(intervals, dimension))
obtained_length = len(noise)
obtained_cluster_length = []
for cluster in clusters:
obtained_length += len(cluster)
obtained_cluster_length.append(len(cluster))
obtained_cluster_length.sort()
assertion.eq(len(sample), obtained_length)
assertion.eq(expected_noise, len(noise))
if expected_clusters is not None:
assertion.eq(len(expected_clusters), len(clusters))
assertion.eq(expected_clusters, obtained_cluster_length)
covered_points = set()
for cell in cells:
points = cell.points
for index_point in points:
covered_points.add(index_point)
assertion.eq(len(sample), len(covered_points))
return clique_instance
def clustering(path, intervals, density_threshold, expected_clusters, expected_noise, ccore_enabled, **kwargs):
sample = read_sample(path)
dimension = len(sample[0])
clique_instance = clique(sample, intervals, density_threshold, ccore=ccore_enabled)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
assertion.eq(len(cells), pow(intervals, dimension))
obtained_length = len(noise)
obtained_cluster_length = []
for cluster in clusters:
obtained_length += len(cluster)
obtained_cluster_length.append(len(cluster))
obtained_cluster_length.sort()
assertion.eq(len(sample), obtained_length)
assertion.eq(expected_noise, len(noise))
if expected_clusters is not None:
assertion.eq(len(expected_clusters), len(clusters))
assertion.eq(expected_clusters, obtained_cluster_length)
covered_points = set()
for cell in cells:
points = cell.points
for index_point in points:
covered_points.add(index_point)
assertion.eq(len(sample), len(covered_points))
return clique_instance
data = pd.read_csv("Mall_Customers.csv")
data.rename(columns={
'Annual Income (k$)': 'Annual_Income',
'Spending Score (1-100)': 'Spending_Score'
},
inplace=True)
data['Gender'] = data['Gender'].replace(['Male', 'Female'], [0, 1])
data.drop(["CustomerID"], axis=1, inplace=True)
data_values = data.values
# Define the number of grid cells in each dimension
intervals = 5
# Density threshold
threshold = 0
clique_instance = clique(data_values, intervals, threshold)
clique_instance.process()
clique_cluster = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
print("Amount of clusters:", len(clique_cluster))
for cluster in clique_cluster:
print(cluster)
labelList = [0] * 200
j = 1
for cluster in clique_cluster:
for x in cluster:
sales.date = sales.date.apply(
lambda x: datetime.datetime.strptime(x, '%d.%m.%Y'))
monthly_sales = sales.groupby(["date_block_num", "shop_id",
"item_id"])["date_block_num", "item_price",
"item_cnt_day", "shop_id"].agg({
"date_block_num":
"mean",
"item_price":
"mean",
"item_cnt_day":
"sum",
"shop_id":
"mean"
})
df = pd.DataFrame(monthly_sales)
df = np.array(df)
from pyclustering.cluster.clique import clique, clique_visualizer
from pyclustering.utils import read_sample
from pyclustering.samples.definitions import FCPS_SAMPLES
intervals = 10
threshold = 0
clique_instance = clique(df, intervals, threshold)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
print("Amount of clusters:", len(clusters))
data_M = np.array(data)
return data_M
# file_list = ["five_cluster.txt", "spiral.txt",
# "ThreeCircles.txt", "Twomoons.txt"]
data_M = loadDataSet('Twomoons.txt')
TestData = data_M[:, [1, 2]]
g_truth = data_M[:, 0]
# 创建 CLIQUE 算法进行处理
# 定义每个维度中网格单元的数量
intervals = 15
# 密度阈值
threshold = 10
clique_instance = clique(TestData, intervals, threshold)
'''
five_cluster.txt intervals = 15,threshold = 10 0.812 t=0.039999961853027344
spiral.txt no
ThreeCircles.txt intervals = 20,threshold = 1 0.990563419372745 t=0.0800008773803711
Twomoons.txt intervals = 15,threshold = 1 0.9880159786950732 t=0.04000043869018555
'''
# 开始聚类过程并获得结果
t1 = time.time_ns()
clique_instance.process()
t2 = time.time_ns()
clique_cluster = clique_instance.get_clusters() # allocated clusters
# 被认为是异常值的点（噪点）
noise = clique_instance.get_noise()
# CLIQUE形成的网格单元
def test_high_dimension_data_failure(self):
data = [[0, 1, 2, 1, 3, 4, 5, 1, 2, 3, 3, 1, 3], [0, 1, 0, 1, 3, 8, 5, 5, 3, 3, 3, 0, 0]]
clique_instance = clique(data, 15, 0)
assertion.exception(RuntimeError, clique_instance.process)
del X1, X2, X3, X4, X5
# correct cluster labels in an array
col = []
for i in range(n_cluster):
for j in range(n):
col.append(i)
for i in range(n_noise):
col.append(-1)
col = (col)
del i, j
# apply DBSCAN multiple times
X_cliq = X.values.tolist()
t0 = time.time()
clique_instance = clique(X_cliq, intervall, threshold)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise_c = clique_instance.get_noise()
t1 = time.time()
clusters.append(noise_c)
## plot the result
# array with all the color per cluster
color = []
help_color = np.array([np.zeros(len(X))] * 2).T
counter = 0
for j in range(len(clusters)):
for index, i in enumerate(clusters[j]):
help_color[counter, 0] = i
help_color[counter, 1] = j
