Thanks to visit codestin.com
Credit goes to github.com

Skip to content

CLN cluster/_hdbscan/_tree.pyx #25658

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 12 commits into from
Closed

CLN cluster/_hdbscan/_tree.pyx #25658

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
8a851fd
Updated np-->cnp for cimport
Micky774 Feb 13, 2023
101d2d3
First iter simplification for first few functions
Micky774 Feb 21, 2023
37dbcff
Updated typing and created private helper function
Micky774 Feb 22, 2023
6325790
Improved typing, and used memview where possible
Micky774 Feb 22, 2023
8a1bf88
Simplified iteration
Micky774 Feb 22, 2023
7fec479
Reverted function abstraction and improved naming
Micky774 Feb 24, 2023
ba80f0d
Continued refactor
Micky774 Feb 24, 2023
9af3c07
Continued refactor
Micky774 Feb 24, 2023
c8f190f
Propogated use of common dtype
Micky774 Feb 26, 2023
bb968e2
Renamed tree-->hierarchy
Micky774 Feb 26, 2023
201b47c
Added typing and updated documentation for dtype
Micky774 Feb 27, 2023
24a227d
Stylistic updates with removal of excess branches
Micky774 Mar 2, 2023
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
28 changes: 12 additions & 16 deletions sklearn/cluster/_hdbscan/_linkage.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@ from libc.float cimport DBL_MAX
import numpy as np
from ...metrics._dist_metrics cimport DistanceMetric
from ...cluster._hierarchical_fast cimport UnionFind
from ...cluster._hdbscan._tree cimport HIERARCHY_t
from ...cluster._hdbscan._tree import HIERARCHY_dtype
from ...utils._typedefs cimport ITYPE_t, DTYPE_t
from ...utils._typedefs import ITYPE, DTYPE

Expand Down Expand Up @@ -188,7 +190,7 @@ cpdef cnp.ndarray[MST_edge_t, ndim=1, mode='c'] mst_from_data_matrix(

return mst

cpdef cnp.ndarray[cnp.float64_t, ndim=2, mode='c'] make_single_linkage(const MST_edge_t[::1] mst):
cpdef cnp.ndarray[HIERARCHY_t, ndim=1] make_single_linkage(const MST_edge_t[::1] mst):
"""Construct a single-linkage tree from an MST.

Parameters
Expand All @@ -199,26 +201,20 @@ cpdef cnp.ndarray[cnp.float64_t, ndim=2, mode='c'] make_single_linkage(const MST

Returns
-------
single_linkage : ndarray of shape (n_samples - 1, 4)
The single-linkage tree tree (dendrogram) built from the MST. Each
of the array represents the following:

- left node/cluster
- right node/cluster
- distance
- new cluster size
single_linkage : ndarray of shape (n_samples - 1,), dtype=HIERARCHY_dtype
The single-linkage tree tree (dendrogram) built from the MST.
"""
cdef:
cnp.ndarray[cnp.float64_t, ndim=2, mode='c'] single_linkage
cnp.ndarray[HIERARCHY_t, ndim=1] single_linkage

# Note mst.shape[0] is one fewer than the number of samples
cnp.int64_t n_samples = mst.shape[0] + 1
cnp.int64_t current_node_cluster, next_node_cluster
cnp.intp_t current_node_cluster, next_node_cluster
cnp.int64_t current_node, next_node, index
cnp.float64_t distance
UnionFind U = UnionFind(n_samples)

single_linkage = np.zeros((n_samples - 1, 4), dtype=np.float64)
single_linkage = np.zeros(n_samples - 1, dtype=HIERARCHY_dtype)

for i in range(n_samples - 1):

Expand All @@ -231,10 +227,10 @@ cpdef cnp.ndarray[cnp.float64_t, ndim=2, mode='c'] make_single_linkage(const MST

# TODO: Update this to an array of structs (AoS).
# Should be done simultaneously in _tree.pyx to ensure compatability.
single_linkage[i][0] = <cnp.float64_t> current_node_cluster
single_linkage[i][1] = <cnp.float64_t> next_node_cluster
single_linkage[i][2] = distance
single_linkage[i][3] = U.size[current_node_cluster] + U.size[next_node_cluster]
single_linkage[i].left_node = current_node_cluster
single_linkage[i].right_node = next_node_cluster
single_linkage[i].value = distance
single_linkage[i].cluster_size = U.size[current_node_cluster] + U.size[next_node_cluster]

U.union(current_node_cluster, next_node_cluster)

Expand Down
9 changes: 9 additions & 0 deletions sklearn/cluster/_hdbscan/_tree.pxd
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
cimport numpy as cnp
import numpy as np


ctypedef packed struct HIERARCHY_t:
cnp.intp_t left_node
cnp.intp_t right_node
cnp.float64_t value
cnp.intp_t cluster_size
Loading