8000 [WIP] OPTICS include split points in clusters if not noise by adrinjalali · Pull Request #12049 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[WIP] OPTICS include split points in clusters if not noise #12049

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed

[WIP] OPTICS include split points in clusters if not noise #12049

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
46cd69d
add Xi steep method for split points
adrinjalali Sep 10, 2018
960ddcf
add the test
adrinjalali Sep 10, 2018
e8d3c93
fix last point issue
adrinjalali Sep 10, 2018
62c4ef8
add docstring for xi
adrinjalali Sep 10, 2018
1957020
pep8
adrinjalali Sep 10, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 41 additions & 15 deletions sklearn/cluster/optics_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ def optics(X, min_samples=5, max_eps=np.inf, metric='euclidean',
p=2, metric_params=None, maxima_ratio=.75,
rejection_ratio=.7, similarity_threshold=0.4,
significant_min=.003, min_cluster_size=.005,
min_maxima_ratio=0.001, algorithm='ball_tree',
min_maxima_ratio=0.001, xi=0.9, algorithm='ball_tree',
leaf_size=30, n_jobs=None):
"""Perform OPTICS clustering from vector array

Expand Down Expand Up @@ -103,6 +103,11 @@ def optics(X, min_samples=5, max_eps=np.inf, metric='euclidean',
Each local maxima should be a largest value in a neighborhood
of the `size min_maxima_ratio * len(X)` from left and right.

xi : float between 0 and 1, optional (default=.9)
Defines the steepness used to include/explude a split point and
the last point of a split in that cluster. Setting `xi` to 1
would always exclude those split points.

algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
Algorithm used to compute the nearest neighbors:

Expand Down 10000 Expand Up @@ -153,7 +158,7 @@ def optics(X, min_samples=5, max_eps=np.inf, metric='euclidean',
clust = OPTICS(min_samples, max_eps, metric, p, metric_params,
maxima_ratio, rejection_ratio,
similarity_threshold, significant_min,
min_cluster_size, min_maxima_ratio,
min_cluster_size, min_maxima_ratio, xi,
algorithm, leaf_size, n_jobs)
clust.fit(X)
return clust.core_sample_indices_, clust.labels_
Expand Down Expand Up @@ -233,6 +238,11 @@ class OPTICS(BaseEstimator, ClusterMixin):
Each local maxima should be a largest value in a neighborhood
of the `size min_maxima_ratio * len(X)` from left and right.

xi : float between 0 and 1, optional (default=.9)
Defines the steepness used to include/explude a split point and
the last point of a split in that cluster. Setting `xi` to 1
would always exclude those split points.

algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
Algorithm used to compute the nearest neighbors:

Expand Down Expand Up @@ -294,7 +304,7 @@ def __init__(self, min_samples=5, max_eps=np.inf, metric='euclidean',
p=2, metric_params=None, maxima_ratio=.75,
rejection_ratio=.7, similarity_threshold=0.4,
significant_min=.003, min_cluster_size=.005,
min_maxima_ratio=0.001, algorithm='ball_tree',
min_maxima_ratio=0.001, xi=.9, algorithm='ball_tree',
leaf_size=30, n_jobs=None):

self.max_eps = max_eps
Expand All @@ -305,6 +315,7 @@ def __init__(self, min_samples=5, max_eps=np.inf, metric='euclidean',
self.significant_min = significant_min
self.min_cluster_size = min_cluster_size
self.min_maxima_ratio = min_maxima_ratio
self.xi = xi
self.algorithm = algorithm
self.metric = metric
self.metric_params = metric_params
Expand Down Expand Up @@ -379,7 +390,8 @@ def fit(self, X, y=None):
self.similarity_threshold,
self.significant_min,
self.min_cluster_size,
self.min_maxima_ratio)
self.min_maxima_ratio,
self.xi)
self.core_sample_indices_ = indices_
return self

Expand Down Expand Up @@ -508,7 +520,7 @@ def _extract_dbscan(ordering, core_distances, reachability, eps):
def _extract_optics(ordering, reachability, maxima_ratio=.75,
rejection_ratio=.7, similarity_threshold=0.4,
significant_min=.003, min_cluster_size=.005,
min_maxima_ratio=0.001):
min_maxima_ratio=0.001, xi=0.9):
"""Performs automatic cluster extraction for variable density data.

Parameters
Expand Down Expand Up @@ -568,7 +580,7 @@ def _extract_optics(ordering, reachability, maxima_ratio=.75,
root_node = _automatic_cluster(reachability_plot, ordering,
maxima_ratio, rejection_ratio,
similarity_threshold, significant_min,
min_cluster_size, min_maxima_ratio)
min_cluster_size, min_maxima_ratio, xi)
leaves = _get_leaves(root_node, [])
# Start cluster id's at 0
clustid = 0
Expand All @@ -581,13 +593,14 @@ def _extract_optics(ordering, reachability, maxima_ratio=.75,
labels[index] = clustid
is_core[index] = 1
clustid += 1

return np.arange(n_samples)[is_core], labels


def _automatic_cluster(reachability_plot, ordering,
maxima_ratio, rejection_ratio,
similarity_threshold, significant_min,
min_cluster_size, min_maxima_ratio):
min_cluster_size, min_maxima_ratio, xi):
"""Converts reachability plot to cluster tree and returns root node.

Parameters
Expand All @@ -613,7 +626,7 @@ def _automatic_cluster(reachability_plot, ordering,
_cluster_tree(root_node, None, local_maxima_points,
reachability_plot, ordering, min_cluster_size,
maxima_ratio, rejection_ratio,
similarity_threshold, significant_min)
similarity_threshold, significant_min, xi)

return root_node

Expand Down Expand Up @@ -657,7 +670,7 @@ def _find_local_maxima(reachability_plot, neighborhood_size):
def _cluster_tree(node, parent_node, local_maxima_points,
reachability_plot, reachability_ordering,
min_cluster_size, maxima_ratio, rejection_ratio,
similarity_threshold, significant_min):
similarity_threshold, significant_min, xi):
"""Recursively builds cluster tree to hold hierarchical cluster structure

node is a node or the root of the tree in the first call
Expand All @@ -677,15 +690,28 @@ def _cluster_tree(node, parent_node, local_maxima_points,
# create two new nodes and add to list of nodes
node_1 = _TreeNode(reachability_ordering[node.start:s],
node.start, s, node)
node_2 = _TreeNode(reachability_ordering[s + 1:node.end],
s + 1, node.end, node)

# check if s is xi-steep downward
if reachability_plot[s] * (1 - xi) >= reachability_plot[s + 1]:
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use proper _steep_upward and/or _steep_downward instead.

node_2_start = s
else:
node_2_start = s + 1

# check if the last point is xi-steep upward
node_2_end = node.end
if (reachability_plot[node.end - 1] * (1 - xi)
>= reachability_plot[node.end - 2]):
node_2_end = node.end - 1

node_2 = _TreeNode(reachability_ordering[node_2_start:node_2_end],
node_2_start, node_2_end, node)
local_max_1 = []
local_max_2 = []

for i in local_maxima_points:
if i < s:
local_max_1.append(i)
if i > s:
if i >= node_2_start:
local_max_2.append(i)

node_list = []
Expand Down Expand Up @@ -725,7 +751,7 @@ def _cluster_tree(node, parent_node, local_maxima_points,
_cluster_tree(node, parent_node, local_maxima_points,
reachability_plot, reachability_ordering,
min_cluster_size, maxima_ratio, rejection_ratio,
similarity_threshold, significant_min)
similarity_threshold, significant_min, xi)
return

# remove clusters that are too small
Expand Down Expand Up @@ -758,13 +784,13 @@ def _cluster_tree(node, parent_node, local_maxima_points,
_cluster_tree(nl[0], parent_node, nl[1],
reachability_plot, reachability_ordering,
min_cluster_size, maxima_ratio, rejection_ratio,
similarity_threshold, significant_min)
similarity_threshold, significant_min, xi)
else:
node.children.append(nl[0])
_cluster_tree(nl[0], node, nl[1], reachability_plot,
reachability_ordering, min_cluster_size,
maxima_ratio, rejection_ratio,
similarity_threshold, significant_min)
similarity_threshold, significant_min, xi)


def _get_leaves(node, arr):
Expand Down
22 changes: 21 additions & 1 deletion sklearn/cluster/tests/test_optics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,26 @@ def test_min_cluster_size_invalid2():
clust.fit(X)


def test_auto_extract_outlier():
np.random.seed(0)

n_points_per_cluster = 4

C1 = [-5, -2] + .8 * np.random.randn(n_points_per_cluster, 2)
C2 = [4, -1] + .1 * np.random.randn(n_points_per_cluster, 2)
X = np.vstack((C1, C2, np.array([[100, 200]])))
clust = OPTICS(min_samples=3).fit(X)

assert_array_equal(clust.labels_, np.r_[[0] * 4, [1] * 4, -1])

C1 = [-5, -2] + .8 * np.random.randn(n_points_per_cluster, 2)
C2 = [4, -1] + .1 * np.random.randn(n_points_per_cluster, 2)
X = np.vstack((C1, np.array([[100, 200], [200, 300]]), C2))
clust = OPTICS(min_samples=3).fit(X)

assert_array_equal(clust.labels_, np.r_[[0] * 4, -1, -1, [1] * 4])


@pytest.mark.parametrize("reach, n_child, members", [
(np.array([np.inf, 0.9, 0.9, 1.0, 0.89, 0.88, 10, .9, .9, .9, 10, 0.9,
0.9, 0.89, 0.88, 10, .9, .9, .9, .9]), 2, np.r_[0:6]),
Expand All @@ -199,7 +219,7 @@ def test_cluster_sigmin_pruning(reach, n_child, members):

# Build cluster tree inplace on root node
_cluster_tree(root, None, cluster_boundaries, reach, ordering,
5, .75, .7, .4, .3)
5, .75, .7, .4, .3, 1)
assert_equal(root.split_point, cluster_boundaries[0])
assert_equal(n_child, len(root.children))
assert_array_equal(members, root.children[0].points)
Expand Down
0