def fitness(self):
clusterer = HDBSCAN(
algorithm=self.parametros["algorithm"],
min_cluster_size=self.parametros["min_cluster_size"],
min_samples=self.parametros["min_samples"],
cluster_selection_method=self.
parametros["cluster_selection_method"],
cluster_selection_epsilon=self.
parametros["cluster_selection_epsilon"])
clusterer.fit(self.data)
self.labels = clusterer.labels_
silhouette_score = self.silhouette_score(self.data, self.labels)
# balance = self.balance(clusterer.labels_)
# percents = self.calc_percents(clusterer.labels_)
# len_labels = self.len_labels(clusterer.labels_)
# noise_percents = [item for item in percents if item[0] == -1][0][1]
score = silhouette_score
# print(percents)
# print("\n")
# print('\'' + str(json.dumps(self.parametros)) + '\'')
# print("\n")
# print(score)
# print("---------------------\n\n")
return score
def clustering(umap_embedding_fit, umap_embedding_predict, min_cluster_size, prediction_data):
print("clustering...")
hdbscan = HDBSCAN(min_cluster_size=min_cluster_size, prediction_data=prediction_data).fit(umap_embedding_fit)
clustering = hdbscan.fit_predict(umap_embedding_predict)
labels = hdbscan.labels_
return clustering, labels
def test_hdbscan_allow_single_cluster_with_epsilon():
np.random.seed(0)
no_structure = np.random.rand(150, 2)
# without epsilon we should see many noise points as children of root.
labels = HDBSCAN(
min_cluster_size=5,
cluster_selection_epsilon=0.0,
cluster_selection_method="eom",
allow_single_cluster=True,
).fit_predict(no_structure)
unique_labels, counts = np.unique(labels, return_counts=True)
assert len(unique_labels) == 2
assert counts[unique_labels == -1] == 46
# for this random seed an epsilon of 0.2 will produce exactly 2 noise
# points at that cut in single linkage.
labels = HDBSCAN(
min_cluster_size=5,
cluster_selection_epsilon=0.2,
cluster_selection_method="eom",
allow_single_cluster=True,
).fit_predict(no_structure)
unique_labels, counts = np.unique(labels, return_counts=True)
assert len(unique_labels) == 2
assert counts[unique_labels == -1] == 2
def hdbscan_samples(data, min_samples, n, filename):
hdbscan = HDBSCAN(min_samples=min_samples, metric='haversine')
data = data[np.random.randint(low=0, high=len(data), size=n), :]
t0 = time.time()
hdbscan.fit(np.radians(data))
t1 = time.time() - t0
clusters = len(np.unique(hdbscan.labels_))
project = os.path.realpath('.')
csv = os.path.join(project, filename)
if not os.path.exists(csv):
with open(csv, mode='w') as timing:
timing.write('min_samples,n,clusters,seconds\n')
with open(csv, mode='a') as timing:
timing.write('{},{},{},{}\n'.format(min_samples, n, clusters, t1))
print('HDBSCAN: {} samples, {} clusters, {} seconds'.format(
n, clusters, t1))
return t1
def test_switch_to_leaf():
"""
Verify that when we request more clusters than 'eom' can handle,
method switches to 'leaf' and the results match 'leaf'.
"""
# Given the max number of clusters that can be produced by 'eom',
# (these are produced for epsilon=0) (??? Needs verification)
clusterer = HDBSCAN(cluster_selection_method='eom',
cluster_selection_epsilon=0).fit(X)
max_clusters = n_clusters_from_labels(clusterer.labels_)
with warnings.catch_warnings(record=True) as w:
# When we try flat clustering with 'eom' method for more n_clusters,
clusterer_flat = HDBSCAN_flat(X,
cluster_selection_method='eom',
n_clusters=max_clusters + 2)
# Then, a warning is raised saying 'eom' can't get this clustering,
assert len(w) > 0
assert issubclass(w[-1].category, UserWarning)
assert "Cannot predict" in str(w[-1].message)
# the resulting clusterer switches to using method 'leaf',
assert clusterer_flat.cluster_selection_method == 'leaf', (
"cluster selection method has not switched to 'leaf'")
# and the resulting probabilities and labels must match
epsilon = clusterer_flat.cluster_selection_epsilon
clusterer_leaf = HDBSCAN(cluster_selection_method='leaf',
cluster_selection_epsilon=epsilon).fit(X)
assert_array_equal(clusterer_flat.labels_, clusterer_leaf.labels_)
assert_array_equal(clusterer_flat.probabilities_,
clusterer_leaf.probabilities_)
return
def apply(self, fX):
from hdbscan import HDBSCAN
clusterer = HDBSCAN(min_cluster_size=self.min_cluster_size,
min_samples=self.min_samples,
metric='precomputed')
distance_matrix = squareform(pdist(fX, metric=self.metric))
# apply clustering
cluster_labels = clusterer.fit_predict(distance_matrix)
# cluster embedding
n_clusters = np.max(cluster_labels) + 1
if n_clusters < 2:
return np.zeros(fX.shape[0], dtype=np.int)
fC = l2_normalize(
np.vstack([np.sum(fX[cluster_labels == k, :], axis=0)
for k in range(n_clusters)]))
# tag each undefined embedding to closest cluster
undefined = cluster_labels == -1
closest_cluster = np.argmin(
cdist(fC, fX[undefined, :], metric=self.metric), axis=0)
cluster_labels[undefined] = closest_cluster
return cluster_labels
def test_flat_base_default():
"""
Verify that the default clustering of HDBSCAN is preserved.
"""
# Given, the base HDBSCAN with method 'eom'
clusterer = HDBSCAN(cluster_selection_method='eom').fit(X)
n_clusters = n_clusters_from_labels(clusterer.labels_)
# When we ask for flat clustering with same n_clusters,
clusterer_flat = HDBSCAN_flat(X,
n_clusters=n_clusters,
cluster_selection_method='eom')
# Then, the labels and probabilities should match
assert_array_equal(clusterer_flat.labels_, clusterer.labels_)
assert_array_equal(clusterer_flat.probabilities_, clusterer.probabilities_)
# Given, the base HDBSCAN with method 'leaf'
clusterer = HDBSCAN(cluster_selection_method='leaf').fit(X)
n_clusters = n_clusters_from_labels(clusterer.labels_)
# When we ask for flat clustering with same n_clusters,
clusterer_flat = HDBSCAN_flat(X,
n_clusters=n_clusters,
cluster_selection_method='leaf')
# Then, the labels and probabilities should match
assert_array_equal(clusterer_flat.labels_, clusterer.labels_)
assert_array_equal(clusterer_flat.probabilities_, clusterer.probabilities_)
return
def hdbscan_clustering(self,
min_cluster_size=10,
min_cluster_portion=None,
min_samples=1,
metric='hamming',
cluster_selection_method='eom',
allow_single_cluster=True,
epsilon=0.2):
if min_cluster_portion is not None:
if min_cluster_size is None:
min_cluster_size = 0
min_cluster_size = max(min_cluster_size,
self.n_obs * min_cluster_portion)
else:
if min_cluster_size is None:
raise ValueError(
'Either min_cluster_size or min_cluster_portion should be provided'
)
runner = HDBSCAN(min_cluster_size=int(min_cluster_size),
min_samples=int(min_samples),
metric=metric,
cluster_selection_method=cluster_selection_method,
allow_single_cluster=allow_single_cluster)
if self.leiden_result_df is None:
raise ValueError(
'Run multi_leiden_clustering first before hdbscan_clustering')
runner.fit(self.leiden_result_df)
self.hdbscan = runner
self.reselect_clusters(epsilon=epsilon,
min_cluster_size=min_cluster_size)
return
def _cluster_train(df):
start_time = time.time()
# Note: Issue #88 open, prediction_data cannot be used with Haervsine metrics https://github.com/scikit-learn-contrib/hdbscan/issues/88
db = HDBSCAN(min_samples=1,
metric='haversine',
core_dist_n_jobs=-1,
memory='./__pycache__/',
prediction_data=True)
coords = df[['latitude', 'longitude']] * np.pi / 180
df = df.assign(cluster=db.fit_predict(coords))
# get the number of clusters
num_clusters = db.labels_.max()
message = 'Clustered {:,} points down to {:,} clusters, for {:.1f}% compression in {:,.2f} seconds'
print(
message.format(len(df), num_clusters,
100 * (1 - float(num_clusters) / len(df)),
time.time() - start_time))
# Get the list of the point most in the center of each clusters
cluster_centers = df[[
'cluster', 'latitude', 'longitude'
]].groupby('cluster')['latitude', 'longitude'].agg(
lambda x: _get_centermost_point(x.values))
df = df.merge(cluster_centers,
left_on='cluster',
right_index=True,
how='left',
suffixes=('', '_cluster'))
return db, cluster_centers, df
def run(self):
if self.isStopped():
self.canceled.emit()
return False
options = self.options
clusterer = HDBSCAN(min_cluster_size=options.min_cluster_size,
min_samples=options.min_samples,
cluster_selection_epsilon=options.cluster_selection_epsilon,
cluster_selection_method=options.cluster_selection_method)
layout_data = self._widget.get_layout_data()
isolated_nodes = layout_data['isolated_nodes']
layout = layout_data['layout']
mask = np.ones_like(layout, dtype=bool)
mask[isolated_nodes] = False
x = layout[mask].reshape(-1, 2)
clusterer.fit(x.astype(np.float64))
i = 0
result = []
for n in self._widget.scene().nodes():
if n.index() in isolated_nodes:
result.append("Noise")
else:
result.append(f"Cluster {clusterer.labels_[i] + 1}" if clusterer.labels_[i] > 0 else "Noise")
i += 1
if not self.isStopped():
return result
else:
self.canceled.emit()
def get_clusters(self, coordinates, original_df, coordinates_df,
csv_path):
"""
It employs the HDBSCAN method to gather the supplied coordinates
into clusters.
Parameters
----------
coordinates : numpy.array
The array of coordinates that will be clustered. Its shape must
fulfill the following dimensions: [M, N, 3], where M is the
total number of models that have been sampled with PELE and
N is the total number of atoms belonging to the residue that
is being analyzed
original_df : pandas.DataFrame
Original dataframe from Analysis to be overwritten
coordinates_df : pandas.DataFrame
The filtered dataframe which was used to extract coordinates for
clustering
csv_path : str
Directory where the CSV will be saved
Returns
-------
clusters : numpy.array
The array of cluster labels assigned to each conformer from
the supplied array
"""
from hdbscan import HDBSCAN
coordinates = Clustering.fix_coordinates_shape(coordinates)
clustering_method = HDBSCAN(cluster_selection_epsilon=self._bandwidth)
clusters = clustering_method.fit_predict(coordinates)
self._save_cluster_info(original_df, coordinates_df,
clusters, csv_path)
return clusters
def cluster_data_points(data_points,
cluster_size=5,
distance_metric_func="Fractional"):
points = [d['encoding'] for d in data_points]
points = np.vstack(points)
scaler = StandardScaler()
scaler.fit(points)
points = scaler.transform(points)
dist_metric = Similarity()
if distance_metric_func == "Fractional":
dist_metric_func = dist_metric.fractional_distance
else:
dist_metric_func = dist_metric.euclidean_distance
clusterer = HDBSCAN(min_cluster_size=cluster_size,
metric='pyfunc',
func=dist_metric_func)
clusterer.fit(points)
logging.info("Fit complete.")
results = {}
labelIDs = np.unique(clusterer.labels_)
for labelID in labelIDs:
paths = []
encodings = []
idxs = np.where(clusterer.labels_ == labelID)[0]
for i in idxs:
data = data_points[i]
paths.append(data['path'])
encodings.append(data['encoding'])
results[labelID] = {
'paths': paths,
'mean_encoding': np.mean(np.asarray(encodings), axis=0),
'std_dev': np.std(encodings, axis=0),
'sample_size': len(paths)
}
return results
def hdbscan(X, min_cluster_size=5, gen_min_span_tree=True, **kwargs):
"""Clustering with Hierarchical DBSCAN.
Parameters
----------
X : array-like
n x k attribute data
min_cluster_size : int, default: 5
the minimum number of points necessary to generate a cluster
gen_min_span_tree : bool
Description of parameter `gen_min_span_tree` (the default is True).
kwargs
Returns
-------
fitted cluster instance: hdbscan.hdbscan.HDBSCAN
"""
try:
from hdbscan import HDBSCAN
except ImportError:
raise ImportError(
"You must have the hdbscan package installed to use this function")
model = HDBSCAN(min_cluster_size=min_cluster_size)
model.fit(X)
return model
def HDBSCAN(
self, parameters
): # data, min_cluster_size, min_samples, alpha, cluster_selection_method):
result = {}
default_min_cluster_size = 3
default_min_samples = 3
default_alpha = 0.5 #大于1的float
default_cluster_selection_method = "eom" # "eom", "leaf"
data = np.array(parameters['data'])
data = preprocessing.MinMaxScaler().fit_transform(data)
if parameters.get('min_cluster_size') is not None:
default_min_cluster_size = int(parameters['min_cluster_size'])
if parameters.get('min_samples') is not None:
default_min_samples = int(parameters['min_samples'])
if parameters.get('alpha') is not None:
default_alpha = float(parameters['alpha'])
if parameters.get('cluster_selection_method') is not None:
default_cluster_selection_method = str(
parameters['cluster_selection_method'])
model = HDBSCAN(
min_cluster_size=default_min_cluster_size,
min_samples=default_min_samples,
alpha=default_alpha,
cluster_selection_method=default_cluster_selection_method,
allow_single_cluster=True)
clustering = model.fit(data)
result['clustering'] = clustering
return result
def clusterFromDistMatrix(distanceMatrix):
clusterer = HDBSCAN(min_cluster_size=2, metric='precomputed')
clusterer.fit(distanceMatrix)
labels = clusterer.labels_
probs = clusterer.probabilities_
labels = np.array((labels))[np.newaxis]
labels = labels.T
probs = np.array((probs))[np.newaxis]
probs = probs.T
results = np.concatenate((probs, gv.medSequenceMatrix), axis=1)
results = np.concatenate((labels, results), axis=1)
results = np.array(sorted(results, key=lambda a_entry: a_entry[0]))
with open('treatmentClusters.txt', 'w') as csvfile:
csvfile.write(
"Cluster; Probability; ID; Month 1; Month 2; Month 3; Month 4; Month 5; Month 6"
)
csvfile.write('\n')
for i in range(results.shape[0]):
csvfile.write(str(results[i, 0]))
csvfile.write(';')
csvfile.write(str(results[i, 1]))
csvfile.write(';')
csvfile.write(str(results[i, 2]))
csvfile.write(';')
for j in range(3, results.shape[1]):
csvfile.write(
str(results[i, j]).replace('{', '').replace('}', ''))
csvfile.write(';')
csvfile.write('\n')
def TrainCluster(x):
clusterer = HDBSCAN(min_cluster_size=1250,
gen_min_span_tree=True,
prediction_data=True) # creating a clustering object
hdb = clusterer.fit(x) #Fitting cluster object on training data
hdb.prediction_data
del (x)
return hdb
def cluster_hdbscan(above_gps):
sample_by_feature = above_gps.to_numpy()
print(sample_by_feature.shape)
clusterer = HDBSCAN()
clusterer.fit(sample_by_feature)
cluster_ids = list(clusterer.labels_)
return cluster_ids
def hdbscan_cluster(df: pd.DataFrame,
min_cluster_size: int = 10,
gen_min_span_tree: bool = True):
clusterer = HDBSCAN(min_cluster_size=min_cluster_size,
gen_min_span_tree=gen_min_span_tree)
clusterer.fit(df)
return clusterer.labels_, clusterer.probabilities_
def test_hdbscan_min_span_tree_availability():
clusterer = HDBSCAN().fit(X)
tree = clusterer.minimum_spanning_tree_
assert tree is None
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
HDBSCAN(metric='precomputed').fit(D)
tree = clusterer.minimum_spanning_tree_
assert tree is None
def test_hdbscan_caching():
cachedir = mkdtemp()
labels1 = HDBSCAN(memory=cachedir, min_samples=5).fit(X).labels_
labels2 = HDBSCAN(memory=cachedir, min_samples=5,
min_cluster_size=6).fit(X).labels_
n_clusters1 = len(set(labels1)) - int(-1 in labels1)
n_clusters2 = len(set(labels2)) - int(-1 in labels2)
assert n_clusters1 == n_clusters2
def hdbscan_clustering(S,X,config):
'''
Computes H-DBSCAN clustering from an input similarity matrix.
Returns the labels associated with the clustering.
'''
from hdbscan import HDBSCAN
min_size = config.as_int("min_cluster_size")
clf = HDBSCAN(min_cluster_size=min_size)
return clf.fit_predict(X)
def hdbscan_clustering(S, X, config):
'''
Computes H-DBSCAN clustering from an input similarity matrix.
Returns the labels associated with the clustering.
'''
from hdbscan import HDBSCAN
min_size = config.as_int("min_cluster_size")
clf = HDBSCAN(min_cluster_size=min_size)
return clf.fit_predict(X)
def test_missing_data():
"""Tests if nan data are treated as infinite distance from all other points and assigned to -1 cluster"""
model = HDBSCAN().fit(X_missing_data)
assert model.labels_[0] == -1
assert model.labels_[5] == -1
assert model.probabilities_[0] == 0
assert model.probabilities_[5] == 0
assert model.probabilities_[5] == 0
clean_indices = list(range(1, 5)) + list(range(6, 200))
clean_model = HDBSCAN().fit(X_missing_data[clean_indices])
assert np.allclose(clean_model.labels_, model.labels_[clean_indices])
def fit(self, data, min_cluster_size, min_samples, alpha,
cluster_selection_method):
data = np.array(data)
data = preprocessing.MinMaxScaler().fit_transform(data)
model = HDBSCAN(min_cluster_size=min_cluster_size,
min_samples=min_samples,
alpha=alpha,
cluster_selection_method=cluster_selection_method,
allow_single_cluster=True)
clustering = model.fit(data)
return clustering
def test_hdbscan_centroids_medoids():
centers = [(0.0, 0.0), (3.0, 3.0)]
H, y = make_blobs(n_samples=1000, random_state=0, centers=centers, cluster_std=0.5)
clusterer = HDBSCAN().fit(H)
for idx, center in enumerate(centers):
centroid = clusterer.weighted_cluster_centroid(idx)
assert_array_almost_equal(centroid, center, decimal=1)
medoid = clusterer.weighted_cluster_medoid(idx)
assert_array_almost_equal(medoid, center, decimal=1)
def hdbscan(self, args):
start = time.time()
model = HDBSCAN(
min_cluster_size=args["min_cluster_size"],
metric=args["metric"],
leaf_size=args["leaf_size"],
allow_single_cluster=args["allow_single_cluster"],
).fit(self.data_matrix)
labels = model.predict(self.data_matrix)
end = time.time()
return labels, (end - start)
def hdbscan(self, min_cluster_size=10, prediction_data=False):
""" DBSCAN but allows for varying density clusters and no longer
requires epsilon parameter, which is difficult to tune.
http://hdbscan.readthedocs.io/en/latest/how_hdbscan_works.html
Scales slightly worse than DBSCAN, but with a more intuitive parameter.
"""
hdbscan = HDBSCAN(min_cluster_size=min_cluster_size,
prediction_data=prediction_data)
if prediction_data:
return hdbscan.fit(self._safe_dense(self.matrix))
else:
return hdbscan.fit(self.matrix)
def _run_hdbscan(affinity: np.ndarray, min_cluster_size_for_hdbscan: int, min_cluster_size: int, max_cluster_size: int):
assert affinity.shape[0] == affinity.shape[1]
if affinity.shape[0] > max_cluster_size:
allow_single_cluster = False
else:
allow_single_cluster = True
db = HDBSCAN(metric='precomputed',
min_cluster_size=min_cluster_size_for_hdbscan,
min_samples=1,
allow_single_cluster=allow_single_cluster)
db.fit(affinity)
return db
def cluster(df, min_size=4, allow_single_cluster=True):
"""Use HDBSCAN --
(Hierarchical Density-Based Spatial Clustering of Applications with Noise)
to find the best clusters for the meander.
"""
clusterer = HDBSCAN(min_cluster_size=min_size,
min_samples=3,
metric='haversine',
allow_single_cluster=allow_single_cluster)
clusterer.fit(df[['lat', 'lng']])
df.loc[:, 'label'] = ['ABCDEFGHIJKLMN'[i] for i in clusterer.labels_]
return df.sort_values('label').reset_index(drop=True)
def perform_hdbscan(self, min_cluster_size=15):
hdbscan_clusterer = HDBSCAN(min_cluster_size, metric="precomputed")
hdbscan_clusterer.fit(self.distance_matrix)
self.hdbscan_results = {
"parameters": hdbscan_clusterer.get_params(),
"labels": hdbscan_clusterer.labels_,
"probabilities": hdbscan_clusterer.probabilities_,
"n_clusters": np.unique(hdbscan_clusterer.labels_).max() + 1,
'clusters': label_cnt_dict(hdbscan_clusterer.labels_)
}
print_dict(self.hdbscan_results)
class HDBSCAN:
def __init__(self):
self.cluster = HDBSCANBase(algorithm='best',
approx_min_span_tree=True,
gen_min_span_tree=False,
leaf_size=40,
metric='euclidean',
min_cluster_size=15,
min_samples=15,
p=None)
def fit(self, X, y=None):
self.cluster.fit(X)
from vispy.visuals.transforms import STTransform
phy.gui.create_app()
mua = MUA(filename='S:/pcie.bin')
spk = mua.tospk()
fet = spk.tofet('pca')
# spike sort a channel centered spiking events
ch = 26
min_cluster_size = 5
leaf_size = 10
hdbcluster = HDBSCAN(min_cluster_size=min_cluster_size,
leaf_size=leaf_size,
gen_min_span_tree=True,
algorithm='boruvka_kdtree')
clu = hdbcluster.fit_predict(fet[ch])
print 'get clusters', np.unique(clu)
#
from phy.gui import GUI, create_app, run_app
create_app()
gui = GUI(position=(400, 200), size=(600, 400))
scatter_view = view_scatter_3d()
scatter_view.attach(gui)
scatter_view.set_data(fet[ch], clu)
def fit(self, X, y=None, sample_weight=None):
"""X is a dataframe."""
if self.method not in ("dbscan", "hdbscan", "spark"):
raise ValueError("Unsupported method '%s'" % self.method)
if not self.dbscan_params:
self.dbscan_params = dict(
min_samples=20, n_jobs=-1, algorithm='brute',
metric=partial(distance_dataframe, X, **dict(
junction_dist=StringDistance(),
correct=False, tol=0)))
if not self.hdbscan_params and self.method == 'hdbscan':
self.hdbscan_params = dict(
min_samples=20, n_jobs=-1,
metric=partial(distance_dataframe, X, **dict(
junction_dist=StringDistance(),
correct=False, tol=0)))
self.dbscan_params['eps'] = self.eps
# new part: group by junction and v genes
if self.method == 'hdbscan' and False:
# no grouping; unsupported sample_weight
groups_values = [[x] for x in np.arange(X.shape[0])]
else:
# list of lists
groups_values = X.groupby(
["v_gene_set_str", self.model + "junc"]).groups.values()
idxs = np.array([elem[0] for elem in groups_values]) # take one of them
sample_weight = np.array([len(elem) for elem in groups_values])
X_all = idxs.reshape(-1, 1)
if self.kmeans_params.get('n_clusters', True):
# ensure the number of clusters is higher than points
self.kmeans_params['n_clusters'] = min(
self.kmeans_params['n_clusters'], X_all.shape[0])
kmeans = MiniBatchKMeans(**self.kmeans_params)
lengths = X[self.model + 'junction_length'].values
kmeans.fit(lengths[idxs].reshape(-1, 1))
dbscan_labels = np.zeros_like(kmeans.labels_).ravel()
if self.method == 'hdbscan':
from hdbscan import HDBSCAN
from hdbscan.prediction import all_points_membership_vectors
dbscan_sk = HDBSCAN(**self.hdbscan_params)
else:
dbscan_sk = DBSCAN(**self.dbscan_params)
if self.method == 'spark':
from pyspark import SparkContext
from icing.externals.pypardis import dbscan as dbpard
sc = SparkContext.getOrCreate()
sample_weight_map = dict(zip(idxs, sample_weight))
# self.dbscan_params.pop('n_jobs', None)
dbscan = dbpard.DBSCAN(
dbscan_params=self.dbscan_params,
**self.dbspark_params)
# else:
for i, label in enumerate(np.unique(kmeans.labels_)):
idx_row = np.where(kmeans.labels_ == label)[0]
if self.verbose:
print("Iteration %d/%d" % (i, np.unique(kmeans.labels_).size),
"(%d seqs)" % idx_row.size, end='\r')
X_idx = idxs[idx_row].reshape(-1, 1).astype('float64')
weights = sample_weight[idx_row]
if idx_row.size == 1:
db_labels = np.array([0])
elif self.method == 'spark' and idx_row.size > 5000:
test_data = sc.parallelize(enumerate(X_idx))
dbscan.train(test_data, sample_weight=sample_weight_map)
db_labels = np.array(dbscan.assignments())[:, 1]
elif self.method == 'hdbscan':
db_labels = dbscan_sk.fit_predict(X_idx) # unsupported weights
# avoid noise samples
soft_clusters = all_points_membership_vectors(dbscan_sk)
db_labels = np.array([np.argmax(x) for x in soft_clusters])
else:
db_labels = dbscan_sk.fit_predict(
X_idx, sample_weight=weights)
if len(dbscan_sk.core_sample_indices_) < 1:
db_labels[:] = 0
if -1 in db_labels:
balltree = BallTree(
X_idx[dbscan_sk.core_sample_indices_],
metric=dbscan_sk.metric)
noise_labels = balltree.query(
X_idx[db_labels == -1], k=1, return_distance=False).ravel()
# get labels for core points, then assign to noise points based
# on balltree
dbscan_noise_labels = db_labels[
dbscan_sk.core_sample_indices_][noise_labels]
db_labels[db_labels == -1] = dbscan_noise_labels
# hopefully, there are no noisy samples at this time
db_labels[db_labels > -1] = db_labels[db_labels > -1] + np.max(dbscan_labels) + 1
dbscan_labels[idx_row] = db_labels # + np.max(dbscan_labels) + 1
if self.method == 'spark':
sc.stop()
labels = dbscan_labels
# new part: put together the labels
labels_ext = np.zeros(X.shape[0], dtype=int)
labels_ext[idxs] = labels
for i, list_ in enumerate(groups_values):
labels_ext[list_] = labels[i]
self.labels_ = labels_ext
