linkscluster 0.1.0__tar.gz

linkscluster-0.1.0/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

linkscluster-0.1.0/PKG-INFO

@@ -0,0 +1,256 @@
+Metadata-Version: 2.4
+Name: linkscluster
+Version: 0.1.0
+Summary: Links: A High-Dimensional Online Clustering Method
+Home-page: https://github.com/wq2012/LinksCluster
+Author: Quan Wang
+Author-email: quanw@google.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: summary
+
+# Links: A High-Dimensional Online Clustering Method
+[![Python application](https://github.com/wq2012/LinksCluster/workflows/Python%20application/badge.svg)](https://github.com/wq2012/LinksCluster/actions)
+[![PyPI Version](https://img.shields.io/pypi/v/linkscluster.svg)](https://pypi.python.org/pypi/linkscluster)
+[![Python Versions](https://img.shields.io/pypi/pyversions/linkscluster.svg)](https://pypi.org/project/linkscluster)
+[![Downloads](https://static.pepy.tech/badge/linkscluster)](https://www.pepy.tech/projects/linkscluster)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Python implementation of the **Links** high-dimensional online clustering algorithm, designed for unit vectors on the hypersphere S^(N-1).
+
+## Overview
+
+Links is an online clustering algorithm designed to cluster high-dimensional unit vectors efficiently in real time as data streams in. Unlike traditional batch clustering algorithms (such as [SpectralCluster](https://github.com/wq2012/SpectralCluster) or k-means) that require concurrent access to all data points, Links assigns each new datum to a cluster immediately upon arrival with no knowledge of future vectors and no backtracking.
+
+---
+
+## Disclaimer
+
+**This is not an official Google product.**
+
+---
+
+## Installation
+
+Install the package from PyPI:
+
+```bash
+pip3 install linkscluster
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/wq2012/LinksCluster.git
+cd LinksCluster
+pip3 install .
+```
+
+---
+
+## Quick Start
+
+### 1. Standard scikit-learn API
+
+`LinksClusterer` follows the standard scikit-learn estimator interface (`fit`, `predict`, `fit_predict`, `partial_fit`):
+
+```python
+import numpy as np
+from linkscluster import LinksClusterer
+
+# Create synthetic unit embeddings (n_samples, n_features)
+X = np.random.randn(500, 128)
+
+# Initialize the clusterer
+clusterer = LinksClusterer(
+    cluster_similarity_threshold=0.6,    # Tc
+    subcluster_similarity_threshold=0.85, # Ts
+    pair_similarity_maximum=0.95,        # Tp
+)
+
+# Fit and return cluster labels
+labels = clusterer.fit_predict(X)
+print(f"Number of clusters found: {clusterer.n_clusters_}")
+print(f"Cluster labels: {labels}")
+```
+
+### 2. Online Streaming API
+
+For real-time streaming applications (e.g. processing incoming audio frames or video embeddings datum-by-datum):
+
+```python
+from linkscluster import LinksClusterer
+
+clusterer = LinksClusterer(tc=0.6, ts=0.85, tp=0.95)
+
+# Process vectors as they arrive in real time
+for x in embedding_stream:
+  # Returns integer cluster ID immediately with zero backtracking
+  cluster_id = clusterer.predict_next(x)
+  print(f"Received vector assigned to cluster: {cluster_id}")
+```
+
+You can also use Python generators via `predict_stream`:
+
+```python
+for cluster_id in clusterer.predict_stream(embedding_stream):
+  handle_cluster_id(cluster_id)
+```
+
+Or batch incremental updates via `partial_fit`:
+
+```python
+clusterer.partial_fit(mini_batch)
+```
+
+### 3. Online Labels vs. Final Labels
+
+In Links, each vector is assigned a cluster ID upon arrival. Over time, as additional data reveals cluster topology, the internal graph representation can split or merge clusters:
+
+```python
+clusterer.fit(X)
+
+# Labels assigned at arrival time (online mode)
+online_labels = clusterer.online_labels_
+
+# Revised cluster assignments reflecting subsequent splits and merges
+final_labels = clusterer.final_labels_
+```
+
+### 4. Predefined Configurations
+
+The package provides pre-tuned presets for common embedding domains:
+
+```python
+from linkscluster import configs
+
+# General high-dimensional embeddings (Tc=0.5, Ts=0.8, Tp=1.0)
+clusterer = configs.default_links_clusterer
+
+# 128-dim FaceNet CNN face embeddings (Tc=0.6, Ts=0.85, Tp=0.95)
+clusterer = configs.facenet_clusterer
+
+# 256-dim LSTM GE2E voice embeddings (Tc=0.55, Ts=0.8, Tp=0.9)
+clusterer = configs.ge2e_voice_clusterer
+```
+
+---
+
+## How It Works
+
+### Two-Level Hierarchy
+
+Links represents data using a two-level hierarchy:
+- **Subclusters**: Indivisible nodes in a graph representing tight groups of vectors whose pairwise similarities exceed `Ts`.
+- **Clusters**: Connected components in the graph of subclusters joined by edges.
+
+This hierarchy scales with the number of *subclusters* rather than the number of vectors, enabling ultra-fast real-time operation.
+
+### Algorithm Steps
+
+1. **Cosine Similarity**: When a new vector `x` arrives, its cosine similarity to all active subcluster centroids is computed in a single vectorized matrix-vector multiplication:
+   ```
+   J = argmax_j (x · μ_j)
+   ```
+
+2. **Subcluster Addition vs. New Subcluster**:
+   - If `x · μ_J >= Ts`: `x` is added to subcluster `J`, and its centroid is updated.
+   - If `x · μ_J < Ts`: a new subcluster containing just `x` is created. It is linked to subcluster `J` if `x · μ_J >= s(kJ)` (or `s̃(kJ)` with anisotropy); otherwise, it starts a new cluster.
+
+3. **Subcluster Merging**: If updating subcluster `J` brings its centroid within `Ts` of an adjacent neighbor, the two subclusters merge recursively.
+
+4. **Edge Validity & Cluster Splitting**: Edges incident to affected nodes are checked against the threshold `s(ki, kj)` (or `s̃(ki, kj)`). If an edge falls below the threshold, it is removed. If the removal severs the cluster, Links attempts to re-join the two components via a valid partner node; if none exists, the cluster permanently splits.
+
+---
+
+## Hyperparameters & Tuning
+
+Links has three intuitive hyperparameters:
+
+| Parameter | Symbol | Range | Description |
+| :--- | :--- | :--- | :--- |
+| `cluster_similarity_threshold` (or `tc`) | `Tc = cos(θc)` | `(0, 1)` | Proximity threshold for vectors belonging to the same cluster. |
+| `subcluster_similarity_threshold` (or `ts`) | `Ts` | `(0, 1)` | Threshold for grouping vectors into tight subclusters (`Ts >= Tc`). |
+| `pair_similarity_maximum` (or `tp`) | `Tp` | `(Tc^2, 1]` | Asymptotic similarity ceiling accounting for intra-cluster correlation and anisotropy. Default is `1.0` (isotropic). |
+
+### Accuracy Evaluation
+
+Clustering accuracy can be computed using the Hungarian algorithm bijection as described in Section 3.6 of the paper:
+
+```python
+from linkscluster import compute_accuracy
+
+acc = compute_accuracy(ground_truth_labels, predicted_labels)
+print(f"Hungarian Clustering Accuracy: {acc * 100:.2f}%")
+```
+
+---
+
+## Performance & Efficiency
+
+Links is designed to be **ultra fast and efficient**:
+- **Vectorized Distance Calculations**: Subcluster centroids are kept in contiguous memory for BLAS level-2 matrix-vector dot products (`_centroids @ x`), bypassing Python loop overhead.
+- **O(1) Dynamic Subcluster Management**: Subcluster additions and deletions (merging) utilize swap-and-pop in the contiguous centroid matrix.
+- **High Throughput**: Capable of clustering **>50,000 - 100,000 vectors per second** on standard CPU hardware.
+
+---
+
+## Running Tests
+
+Run the test suite with coverage:
+
+```bash
+bash run_tests.sh
+```
+
+Or run directly with `unittest`:
+
+```bash
+python3 -m unittest discover -s tests -p "*_test.py"
+```
+
+Check code style:
+
+```bash
+flake8 --indent-size 2 --max-line-length 80 linkscluster tests
+```
+
+---
+
+## Citations
+
+If you use Links in your research, please cite:
+
+```bibtex
+@inproceedings{mansfield2018links,
+  title={Links: A high-dimensional online clustering method},
+  author={Mansfield, Philip Andrew and Wang, Quan and Downey, Carlton and Wan, Li and Moreno, Ignacio Lopez},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={2626--2630},
+  year={2018},
+  organization={IEEE}
+}
+
+@inproceedings{wang2018speaker,
+  title={Speaker diarization with LSTM},
+  author={Wang, Quan and Downey, Carlton and Wan, Li and Mansfield, Philip Andrew and Moreno, Ignacio Lopez},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={5239--5243},
+  year={2018},
+  organization={IEEE}
+}
+```

linkscluster-0.1.0/README.md

@@ -0,0 +1,231 @@
+# Links: A High-Dimensional Online Clustering Method
+[![Python application](https://github.com/wq2012/LinksCluster/workflows/Python%20application/badge.svg)](https://github.com/wq2012/LinksCluster/actions)
+[![PyPI Version](https://img.shields.io/pypi/v/linkscluster.svg)](https://pypi.python.org/pypi/linkscluster)
+[![Python Versions](https://img.shields.io/pypi/pyversions/linkscluster.svg)](https://pypi.org/project/linkscluster)
+[![Downloads](https://static.pepy.tech/badge/linkscluster)](https://www.pepy.tech/projects/linkscluster)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Python implementation of the **Links** high-dimensional online clustering algorithm, designed for unit vectors on the hypersphere S^(N-1).
+
+## Overview
+
+Links is an online clustering algorithm designed to cluster high-dimensional unit vectors efficiently in real time as data streams in. Unlike traditional batch clustering algorithms (such as [SpectralCluster](https://github.com/wq2012/SpectralCluster) or k-means) that require concurrent access to all data points, Links assigns each new datum to a cluster immediately upon arrival with no knowledge of future vectors and no backtracking.
+
+---
+
+## Disclaimer
+
+**This is not an official Google product.**
+
+---
+
+## Installation
+
+Install the package from PyPI:
+
+```bash
+pip3 install linkscluster
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/wq2012/LinksCluster.git
+cd LinksCluster
+pip3 install .
+```
+
+---
+
+## Quick Start
+
+### 1. Standard scikit-learn API
+
+`LinksClusterer` follows the standard scikit-learn estimator interface (`fit`, `predict`, `fit_predict`, `partial_fit`):
+
+```python
+import numpy as np
+from linkscluster import LinksClusterer
+
+# Create synthetic unit embeddings (n_samples, n_features)
+X = np.random.randn(500, 128)
+
+# Initialize the clusterer
+clusterer = LinksClusterer(
+    cluster_similarity_threshold=0.6,    # Tc
+    subcluster_similarity_threshold=0.85, # Ts
+    pair_similarity_maximum=0.95,        # Tp
+)
+
+# Fit and return cluster labels
+labels = clusterer.fit_predict(X)
+print(f"Number of clusters found: {clusterer.n_clusters_}")
+print(f"Cluster labels: {labels}")
+```
+
+### 2. Online Streaming API
+
+For real-time streaming applications (e.g. processing incoming audio frames or video embeddings datum-by-datum):
+
+```python
+from linkscluster import LinksClusterer
+
+clusterer = LinksClusterer(tc=0.6, ts=0.85, tp=0.95)
+
+# Process vectors as they arrive in real time
+for x in embedding_stream:
+  # Returns integer cluster ID immediately with zero backtracking
+  cluster_id = clusterer.predict_next(x)
+  print(f"Received vector assigned to cluster: {cluster_id}")
+```
+
+You can also use Python generators via `predict_stream`:
+
+```python
+for cluster_id in clusterer.predict_stream(embedding_stream):
+  handle_cluster_id(cluster_id)
+```
+
+Or batch incremental updates via `partial_fit`:
+
+```python
+clusterer.partial_fit(mini_batch)
+```
+
+### 3. Online Labels vs. Final Labels
+
+In Links, each vector is assigned a cluster ID upon arrival. Over time, as additional data reveals cluster topology, the internal graph representation can split or merge clusters:
+
+```python
+clusterer.fit(X)
+
+# Labels assigned at arrival time (online mode)
+online_labels = clusterer.online_labels_
+
+# Revised cluster assignments reflecting subsequent splits and merges
+final_labels = clusterer.final_labels_
+```
+
+### 4. Predefined Configurations
+
+The package provides pre-tuned presets for common embedding domains:
+
+```python
+from linkscluster import configs
+
+# General high-dimensional embeddings (Tc=0.5, Ts=0.8, Tp=1.0)
+clusterer = configs.default_links_clusterer
+
+# 128-dim FaceNet CNN face embeddings (Tc=0.6, Ts=0.85, Tp=0.95)
+clusterer = configs.facenet_clusterer
+
+# 256-dim LSTM GE2E voice embeddings (Tc=0.55, Ts=0.8, Tp=0.9)
+clusterer = configs.ge2e_voice_clusterer
+```
+
+---
+
+## How It Works
+
+### Two-Level Hierarchy
+
+Links represents data using a two-level hierarchy:
+- **Subclusters**: Indivisible nodes in a graph representing tight groups of vectors whose pairwise similarities exceed `Ts`.
+- **Clusters**: Connected components in the graph of subclusters joined by edges.
+
+This hierarchy scales with the number of *subclusters* rather than the number of vectors, enabling ultra-fast real-time operation.
+
+### Algorithm Steps
+
+1. **Cosine Similarity**: When a new vector `x` arrives, its cosine similarity to all active subcluster centroids is computed in a single vectorized matrix-vector multiplication:
+   ```
+   J = argmax_j (x · μ_j)
+   ```
+
+2. **Subcluster Addition vs. New Subcluster**:
+   - If `x · μ_J >= Ts`: `x` is added to subcluster `J`, and its centroid is updated.
+   - If `x · μ_J < Ts`: a new subcluster containing just `x` is created. It is linked to subcluster `J` if `x · μ_J >= s(kJ)` (or `s̃(kJ)` with anisotropy); otherwise, it starts a new cluster.
+
+3. **Subcluster Merging**: If updating subcluster `J` brings its centroid within `Ts` of an adjacent neighbor, the two subclusters merge recursively.
+
+4. **Edge Validity & Cluster Splitting**: Edges incident to affected nodes are checked against the threshold `s(ki, kj)` (or `s̃(ki, kj)`). If an edge falls below the threshold, it is removed. If the removal severs the cluster, Links attempts to re-join the two components via a valid partner node; if none exists, the cluster permanently splits.
+
+---
+
+## Hyperparameters & Tuning
+
+Links has three intuitive hyperparameters:
+
+| Parameter | Symbol | Range | Description |
+| :--- | :--- | :--- | :--- |
+| `cluster_similarity_threshold` (or `tc`) | `Tc = cos(θc)` | `(0, 1)` | Proximity threshold for vectors belonging to the same cluster. |
+| `subcluster_similarity_threshold` (or `ts`) | `Ts` | `(0, 1)` | Threshold for grouping vectors into tight subclusters (`Ts >= Tc`). |
+| `pair_similarity_maximum` (or `tp`) | `Tp` | `(Tc^2, 1]` | Asymptotic similarity ceiling accounting for intra-cluster correlation and anisotropy. Default is `1.0` (isotropic). |
+
+### Accuracy Evaluation
+
+Clustering accuracy can be computed using the Hungarian algorithm bijection as described in Section 3.6 of the paper:
+
+```python
+from linkscluster import compute_accuracy
+
+acc = compute_accuracy(ground_truth_labels, predicted_labels)
+print(f"Hungarian Clustering Accuracy: {acc * 100:.2f}%")
+```
+
+---
+
+## Performance & Efficiency
+
+Links is designed to be **ultra fast and efficient**:
+- **Vectorized Distance Calculations**: Subcluster centroids are kept in contiguous memory for BLAS level-2 matrix-vector dot products (`_centroids @ x`), bypassing Python loop overhead.
+- **O(1) Dynamic Subcluster Management**: Subcluster additions and deletions (merging) utilize swap-and-pop in the contiguous centroid matrix.
+- **High Throughput**: Capable of clustering **>50,000 - 100,000 vectors per second** on standard CPU hardware.
+
+---
+
+## Running Tests
+
+Run the test suite with coverage:
+
+```bash
+bash run_tests.sh
+```
+
+Or run directly with `unittest`:
+
+```bash
+python3 -m unittest discover -s tests -p "*_test.py"
+```
+
+Check code style:
+
+```bash
+flake8 --indent-size 2 --max-line-length 80 linkscluster tests
+```
+
+---
+
+## Citations
+
+If you use Links in your research, please cite:
+
+```bibtex
+@inproceedings{mansfield2018links,
+  title={Links: A high-dimensional online clustering method},
+  author={Mansfield, Philip Andrew and Wang, Quan and Downey, Carlton and Wan, Li and Moreno, Ignacio Lopez},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={2626--2630},
+  year={2018},
+  organization={IEEE}
+}
+
+@inproceedings{wang2018speaker,
+  title={Speaker diarization with LSTM},
+  author={Wang, Quan and Downey, Carlton and Wan, Li and Mansfield, Philip Andrew and Moreno, Ignacio Lopez},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={5239--5243},
+  year={2018},
+  organization={IEEE}
+}
+```

linkscluster-0.1.0/linkscluster/__init__.py

@@ -0,0 +1,26 @@
+"""__init__ file for linkscluster."""
+
+from linkscluster import configs
+from linkscluster import graph
+from linkscluster import links_clusterer
+from linkscluster import subcluster
+from linkscluster import utils
+
+__version__ = "0.1.0"
+
+LinksClusterer = links_clusterer.LinksClusterer
+Subcluster = subcluster.Subcluster
+SubclusterGraph = graph.SubclusterGraph
+
+single_threshold = utils.single_threshold
+multi_threshold = utils.multi_threshold
+anisotropic_threshold = utils.anisotropic_threshold
+s = utils.s
+s_tilde = utils.s_tilde
+compute_accuracy = utils.compute_accuracy
+enforce_ordered_labels = utils.enforce_ordered_labels
+l2_normalize = utils.l2_normalize
+
+default_links_clusterer = configs.default_links_clusterer
+facenet_clusterer = configs.facenet_clusterer
+ge2e_voice_clusterer = configs.ge2e_voice_clusterer