deltric 0.1.0__tar.gz

deltric-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

deltric-0.1.0/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: deltric
+Version: 0.1.0
+Summary: A clustering algorithm implementation with sklearn-like API
+Author-email: Your Name <your@email.com>
+License: MIT
+Project-URL: Homepage, https://github.com/TomasJavurek/deltric
+Project-URL: Issues, https://github.com/TomasJavurek/deltric/issues
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: networkx
+Requires-Dist: umap-learn
+Requires-Dist: pandas
+Requires-Dist: statsmodels
+Dynamic: license-file
+
+dt = DelTriC(prune_param=1.497, merge_param=-0.773, dim_reduction='umap', back_proj=True, anomaly_sensitivity=0.9)
+labels = dt.fit_predict(X)

deltric-0.1.0/README.md

@@ -0,0 +1,2 @@
+dt = DelTriC(prune_param=1.497, merge_param=-0.773, dim_reduction='umap', back_proj=True, anomaly_sensitivity=0.9)
+labels = dt.fit_predict(X)

deltric-0.1.0/deltric/deltric.py

@@ -0,0 +1,80 @@
+import numpy as np
+from sklearn.base import BaseEstimator, ClusterMixin
+from sklearn.utils.validation import check_array
+from .utils import cluster_tri
+
+# import your existing functions here
+# from .deltric_core import cluster_tri   # keep your implementation intact
+
+class DelTriC(BaseEstimator, ClusterMixin):
+    """
+    DelTriC clustering algorithm.
+    Compatible with scikit-learn estimator API.
+    """
+
+    def __init__(
+        self,
+        prune_param=-0.8,
+        merge_param=0.0,
+        min_cluster_size=10,
+        dim_reduction="umap",
+        back_proj=True,
+        anomaly_sensitivity=0.99,
+        random_state=42,
+    ):
+        self.prune_param = prune_param
+        self.merge_param = merge_param
+        self.min_cluster_size = min_cluster_size
+        self.dim_reduction = dim_reduction
+        self.back_proj = back_proj
+        self.anomaly_sensitivity = anomaly_sensitivity
+        self.random_state = random_state
+
+    def fit(self, X, y=None):
+        """
+        Fit the DelTriC model to data X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data.
+        y : Ignored
+            Not used, present for API consistency by convention.
+        """
+        X = check_array(X)
+
+        # keep original DelTriC core untouched
+        self.labels_ = cluster_tri(
+            X,
+            prune_param=self.prune_param,
+            merge_param=self.merge_param,
+            min_cluster_size=self.min_cluster_size,
+            dim_reduction=self.dim_reduction,
+            back_proj=self.back_proj,
+            anomaly_sensitivity=self.anomaly_sensitivity,
+        )
+
+        return self
+
+    def fit_predict(self, X, y=None):
+        """
+        Fit to data X and return cluster labels.
+        """
+        self.fit(X, y)
+        return self.labels_
+
+    def get_params(self, deep=True):
+        return {
+            "prune_param": self.prune_param,
+            "merge_param": self.merge_param,
+            "min_cluster_size": self.min_cluster_size,
+            "dim_reduction": self.dim_reduction,
+            "back_proj": self.back_proj,
+            "anomaly_sensitivity": self.anomaly_sensitivity,
+            "random_state": self.random_state,
+        }
+
+    def set_params(self, **params):
+        for k, v in params.items():
+            setattr(self, k, v)
+        return self

deltric-0.1.0/deltric/utils.py

@@ -0,0 +1,295 @@
+import numpy as np
+
+from sklearn.decomposition import PCA
+from scipy.spatial import Delaunay
+import networkx as nx
+from sklearn.manifold import TSNE
+from umap import UMAP
+import pandas as pd
+
+from statsmodels import robust
+
+ANOMALY_THRESH = 3
+
+def get_triangles_with_edges(X, project_dim=2, method='umap', back_proj=True):
+    # Project if needed
+    if method == 'pca' and X.shape[1] > project_dim:
+        projector = PCA(n_components=project_dim, random_state=42)
+        X_proj = projector.fit_transform(X)
+    elif method == 'umap' and X.shape[1] > project_dim:
+        projector = UMAP(n_components=project_dim, random_state=42)
+        X_proj = projector.fit_transform(X)
+    elif method == 'none' or X.shape[1] <= project_dim:
+        X_proj = X
+    else:
+        raise ValueError("Invalid projection method. Choose from 'pca', 'umap', or 'none'.")
+
+    tri = Delaunay(X_proj)
+    triangles = tri.simplices  # shape (num_triangles, 3)
+
+    # Calculate triangle sizes (max edge length)
+    triangle_sizes = []
+    triangle_sizes_proj = []
+    for simplex in triangles:
+        pts = X[list(simplex)]  # original space points for accurate edge lengths
+        pts_proj = X_proj[list(simplex)]
+        if back_proj==False:
+            pts = pts_proj
+        edges = [np.linalg.norm(pts[i] - pts[(i+1)%3]) for i in range(3)]
+        edges_proj = [np.linalg.norm(pts_proj[i] - pts_proj[(i+1)%3]) for i in range(3)]
+        max_edge = max(edges)
+        max_edge_proj = max(edges_proj)
+        triangle_sizes.append(max_edge)
+        triangle_sizes_proj.append(max_edge_proj)
+
+    return triangles, np.array(triangle_sizes), np.array(triangle_sizes_proj), X_proj
+
+
+# 4️⃣ Get clusters from remaining edges
+def get_clusters(edges, n_points):
+    G = nx.Graph()
+    G.add_nodes_from(range(n_points))
+    G.add_edges_from(edges)
+    clusters = [list(c) for c in nx.connected_components(G)]
+    return clusters
+
+def cluster_umap_representative(X, X_proj, clusters):
+    reps = []
+    for cluster in clusters:
+        pts_proj = X_proj[cluster]
+        center = pts_proj.mean(axis=0)
+        # find the index in the original dataset
+        idx = cluster[np.argmin(np.linalg.norm(pts_proj - center, axis=1))]
+        reps.append(X_proj[idx])  # X would be actual point, if X_proj used, the merging effectively runs only in umap space. There is only few points after creating centroids, thus umap would create manifolds wrongly.
+    return np.array(reps)
+
+def merge_anomalies_triangles(X, X_proj, clusters, triangles, sizes, proj_sizes, dist_thresh=0.15,
+                              anomaly_thresh=1, max_iter=1, debug=True):
+
+    scaling_factor = (np.median(proj_sizes) / np.median(sizes))
+
+    # Map point -> cluster
+    point_to_cluster = {}
+    for ci, cluster in enumerate(clusters):
+        for p in cluster:
+            point_to_cluster[p] = ci
+
+    merged_clusters = [list(c) for c in clusters]  # deep copy
+
+    for it in range(max_iter):
+        if debug:
+            print(f"\nIteration {it+1}/{max_iter}")
+
+        merged_any = False
+        anomaly_count = 0
+        merged_count = 0
+
+        for ci, cluster in enumerate(list(merged_clusters)):
+            if len(cluster) > anomaly_thresh:
+                continue  # only anomalies
+            if len(cluster) == 0:
+                continue
+
+            anomaly_count += 1
+            # p = cluster[0]
+
+            dists = {}
+            for p in cluster:
+                
+                # Find triangles containing this anomaly
+                tri_mask = np.any(triangles == p, axis=1)
+                tri_candidates = triangles[tri_mask]
+                size_candidates = sizes[tri_mask]
+
+                if tri_candidates.size == 0:
+                    continue
+
+                # Collect neighbors from all triangles
+                neighbor_points = set()
+                for tri in tri_candidates:
+                    for q in tri:
+                        if q != p and q in point_to_cluster and point_to_cluster[q] != ci:
+                            neighbor_points.add(q)
+
+                neighbor_points = list(neighbor_points)
+
+                # Distances to anomaly in both spaces
+                for q in neighbor_points:
+                    d_X = scaling_factor * np.linalg.norm(X[p] - X[q])
+                    d_Xproj = np.linalg.norm(X_proj[p] - X_proj[q])
+                    _d = max(d_X, d_Xproj)
+                    dists[q] = _d if _d < dists.get(q, float('inf')) else dists.get(q, float('inf'))
+
+            n = len(dists)
+            if n == 0:
+                continue
+
+            # Aggregate scores per cluster
+            cluster_scores = {}
+            mean_size = scaling_factor * np.mean(sizes)  # could also use np.mean(size_candidates)
+            for q, dist in dists.items():
+                if dist == 0:
+                    continue
+                neigh_cluster = point_to_cluster[q]
+                contrib = 1.0 / dist
+                cluster_scores[neigh_cluster] = cluster_scores.get(neigh_cluster, 0.0) + contrib
+
+            if not cluster_scores:
+                continue
+
+            # Normalize by n and multiply by mean_size
+            for k in cluster_scores:
+                cluster_scores[k] = (1.0 / n) * mean_size * cluster_scores[k]
+
+            # Pick cluster with max score
+            target_cluster, best_score = max(cluster_scores.items(), key=lambda x: x[1])
+
+            if best_score > dist_thresh:
+                continue
+
+            # Merge anomaly
+            merged_clusters[target_cluster].extend(cluster)
+            merged_clusters[ci] = []
+            merged_any = True
+            merged_count += 1
+
+        if debug:
+            print(f" - Anomalies processed: {anomaly_count}")
+            print(f" - Merged this round: {merged_count}")
+
+        # Update mapping if we merged
+        if merged_any:
+            point_to_cluster = {}
+            for ci, cluster in enumerate(merged_clusters):
+                for p in cluster:
+                    point_to_cluster[p] = ci
+        else:
+            break  # no more merges → stop early
+
+    # Remove empty clusters
+    merged_clusters = [sorted(c) for c in merged_clusters if len(c) > 0]
+    return merged_clusters
+
+
+def sigma_prune_triangles(triangles, sizes, proj_sizes, sigma_factor):
+    # Normalize sizes to have comparable scales
+    #scaling_factor = (np.median(proj_sizes) / np.median(sizes))
+    #sizes_z = sizes * scaling_factor
+    #proj_sizes_z = proj_sizes
+
+    # sizes_z = (sizes - sizes.mean()) / sizes.std()
+    # proj_sizes_z = (proj_sizes - proj_sizes.mean()) / proj_sizes.std()
+    # mean_size = np.mean(sizes_z)
+    # sigma = np.std(sizes_z)
+    # threshold = mean_size + sigma_factor * sigma
+
+    # sizes_z = dominant_bump_normalization(sizes, sigma_factor)
+    # proj_sizes_z = dominant_bump_normalization(proj_sizes, sigma_factor)
+    # threshold = sigma_factor  # since sizes_z are already in z-score form
+
+    mu = np.median(sizes)
+    sigma = robust.mad(sizes)  # robust std
+    sizes_z = (sizes - mu) / sigma
+    mu = np.median(proj_sizes)
+    sigma = robust.mad(proj_sizes)  # robust std
+    proj_sizes_z = (proj_sizes - mu) / sigma
+
+    mean_size = np.mean(sizes_z)
+    sigma = np.std(sizes_z)
+    threshold = mean_size + sigma_factor * sigma
+
+
+    kept_triangles = triangles[np.maximum(sizes_z, proj_sizes_z) <= threshold]   # we trust umap to create a distinct clusters
+    rm_triangles = triangles[np.maximum(sizes_z, proj_sizes_z) > threshold]
+    edges = set()
+    rm_edges = set()
+    for tri in rm_triangles:
+        for i in range(3):
+            a, b = sorted((tri[i], tri[(i+1)%3]))
+            rm_edges.add((a, b))
+    for tri in kept_triangles:
+        for i in range(3):
+            a, b = sorted((tri[i], tri[(i+1)%3]))
+            edges.add((a, b))
+    return list(edges), list(rm_edges), threshold
+
+def merge_clusters(X, X_proj, clusters, method, merge_param, back_proj=True, anomaly_thresh=2, min_centroids=5):
+    # Compute centroids of clusters in original high-dimensional space
+    # centroids = np.array([np.mean(X[cluster], axis=0) for cluster in clusters])
+    anomalies = [cl for cl in clusters if len(cl) <= anomaly_thresh]
+    rich_clusters = [cl for cl in clusters if len(cl) > anomaly_thresh]
+    centroids = cluster_umap_representative(X, X_proj, rich_clusters)
+    if len(centroids) < min_centroids:
+        return clusters
+
+    try:
+        # Triangulate on centroids
+        triangles, sizes, proj_sizes, _ = get_triangles_with_edges(centroids, project_dim=2, method=method, back_proj=back_proj)
+
+        # Merge clusters if triangle size <= mean + merge_param*sigma
+        edges_between_clusters, _, _ = sigma_prune_triangles(triangles, sizes, proj_sizes, sigma_factor=merge_param)
+
+        # Build graph where nodes are clusters and edges mean merge
+        G = nx.Graph()
+        G.add_nodes_from(range(len(rich_clusters)))
+        G.add_edges_from(edges_between_clusters)
+
+        merged_clusters = []
+        for comp in nx.connected_components(G):
+            merged_points = []
+            for cluster_idx in comp:
+                merged_points.extend(rich_clusters[cluster_idx])
+            merged_clusters.append(sorted(merged_points))
+
+        return merged_clusters + anomalies  # add back anomalies as separate clusters
+    except:
+        print('!!! Cluster Merging Failed !!!')
+        return clusters
+
+
+def tri_cluster_sigma_merge(X, prune_param=0.15, merge_param=-0.2, method='umap', anomaly_sensitivity=0.5, back_proj=True, debug=False):
+    # Step 1: Triangles & sigma pruning
+    triangles, sizes, proj_sizes, X_proj = get_triangles_with_edges(X, project_dim=2, method=method, back_proj=back_proj)
+    pruned_edges, rm_edges, threshold = sigma_prune_triangles(triangles, sizes, proj_sizes, sigma_factor=prune_param)
+    clusters = get_clusters(pruned_edges, len(X))
+    if debug:
+        print(f"After pruning: {len(clusters)} clusters")
+        print(f"Anomalies: {len([cl for cl in clusters if len(cl) <= ANOMALY_THRESH])}")
+
+    # Step 2: Merge pass on centroids
+    merged_clusters = merge_clusters(X, X_proj, clusters, method, merge_param, back_proj=back_proj, anomaly_thresh=ANOMALY_THRESH)
+    if debug:
+        print(f"After merging clusters: {len(merged_clusters)} clusters")
+
+    if anomaly_sensitivity < 1.00:
+        # threshold = np.mean(sizes) + np.std(sizes) * prune_param
+        # dist_thresh = threshold / anomaly_sensitivity  # fix this completely to the projected space
+        dist_thresh = 1.0 - anomaly_sensitivity
+        # merged_clusters = merge_anomalies(X, X_proj, merged_clusters, dist_thresh=dist_thresh, anomaly_thresh=ANOMALY_THRESH)
+        _X = X
+        if back_proj==False:
+            _X = X_proj
+        merged_clusters = merge_anomalies_triangles(_X, X_proj, merged_clusters, triangles, sizes, proj_sizes, dist_thresh=dist_thresh, anomaly_thresh=ANOMALY_THRESH, max_iter=3, debug=True)
+
+    if debug:
+        print(f"After merging anomalies: {len(merged_clusters)} clusters")
+
+    # Keeping same output structure, but adding merged_clusters as extra
+    return triangles, sizes, pruned_edges, rm_edges, merged_clusters
+
+
+def cluster_tri(X, prune_param=-0.8, merge_param=0.0, min_cluster_size=10, dim_reduction='umap', back_proj=True, anomaly_sensitivity=0.99):
+    _, _, pruned_edges, _, clusters = tri_cluster_sigma_merge(X, prune_param=prune_param, merge_param=merge_param, method=dim_reduction, back_proj=back_proj, anomaly_sensitivity=anomaly_sensitivity)
+
+    # Start with all points as noise
+    labels = np.full(len(X), -1, dtype=int)
+
+    label_id = 0
+    for cluster in clusters:
+        if len(cluster) > ANOMALY_THRESH:
+            for idx in cluster:
+                labels[idx] = label_id
+            label_id += 1
+        # else: keep as -1 (noise)
+
+    return labels

deltric-0.1.0/deltric.egg-info/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: deltric
+Version: 0.1.0
+Summary: A clustering algorithm implementation with sklearn-like API
+Author-email: Your Name <your@email.com>
+License: MIT
+Project-URL: Homepage, https://github.com/TomasJavurek/deltric
+Project-URL: Issues, https://github.com/TomasJavurek/deltric/issues
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: networkx
+Requires-Dist: umap-learn
+Requires-Dist: pandas
+Requires-Dist: statsmodels
+Dynamic: license-file
+
+dt = DelTriC(prune_param=1.497, merge_param=-0.773, dim_reduction='umap', back_proj=True, anomaly_sensitivity=0.9)
+labels = dt.fit_predict(X)

deltric-0.1.0/deltric.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+deltric/__init__.py
+deltric/deltric.py
+deltric/utils.py
+deltric.egg-info/PKG-INFO
+deltric.egg-info/SOURCES.txt
+deltric.egg-info/dependency_links.txt
+deltric.egg-info/requires.txt
+deltric.egg-info/top_level.txt

deltric-0.1.0/deltric.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

deltric-0.1.0/deltric.egg-info/requires.txt

@@ -0,0 +1,7 @@
+numpy
+scikit-learn
+scipy
+networkx
+umap-learn
+pandas
+statsmodels

deltric-0.1.0/deltric.egg-info/top_level.txt

@@ -0,0 +1 @@
+deltric

deltric-0.1.0/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "deltric"
+version = "0.1.0"
+authors = [
+  { name="Your Name", email="your@email.com" },
+]
+description = "A clustering algorithm implementation with sklearn-like API"
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.8"
+
+dependencies = [
+  "numpy",
+  "scikit-learn",
+  "scipy",
+  "networkx",
+  "umap-learn",
+  "pandas",
+  "statsmodels"
+]
+
+[project.urls]
+Homepage = "https://github.com/TomasJavurek/deltric"
+Issues = "https://github.com/TomasJavurek/deltric/issues"

deltric-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+