Merge branch 'main' into memory-cleanup

# Conflicts:
#	radius_clustering/utils/main-emos.c

Author: quentinhaenn

.github/workflows/build_wheels.yml

@@ -0,0 +1,71 @@
+name: Build and upload to PyPI
+
+on:
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+
+jobs:
+  build_wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      #fail-fast: false #commented until windows support is added
+      matrix:
+        # macos-13 is an intel runner, macos-14 is apple silicon
+        os: [ubuntu-latest, windows-latest, macos-13, macos-14]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Build wheels
+        uses: pypa/[email protected]
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: cibw-wheels-${{ matrix.os }}-${{ strategy.job-index }}
+          path: ./wheelhouse/*.whl
+
+  build_sdist:
+    name: Build source distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Build sdist
+        run: pipx run build --sdist
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: cibw-sdist
+          path: dist/*.tar.gz
+
+  upload_pypi:
+    needs: [build_wheels, build_sdist]
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    if: github.event_name == 'release' && github.event.action == 'published'
+    # or, alternatively, upload to PyPI on every tag starting with 'v' (remove on: release above to use this)
+    #if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          # unpacks all CIBW artifacts into dist/
+          pattern: cibw-*
+          path: dist
+          merge-multiple: true
+
+      - name: Generate artifact attestations
+        uses: actions/[email protected]
+        with:
+          subject-path: "dist/*"
+
+      - uses: pypa/gh-action-pypi-publish@release/v1
+        #with:
+          # To test: repository-url: https://test.pypi.org/legacy/

CITATION.cff

@@ -0,0 +1,34 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: Radius Clustering
+message: >-
+  If you use this software, please cite it using the
+  metadata from this file.
+type: software
+authors:
+  - given-names: Quentin
+    family-names: Haenn
+    email: [email protected]
+    affiliation: LIAS Lab
+    orcid: 'https://orcid.org/0009-0009-1663-0107'
+  - given-names: Brice
+    family-names: Chardin
+    email: [email protected]
+    affiliation: LIAS Lab
+    orcid: 'https://orcid.org/0000-0002-9298-9447'
+  - given-names: Mickael
+    family-names: Baron
+    email: [email protected]
+    affiliation: LIAS Lab
+    orcid: 'https://orcid.org/0000-0002-3356-0835'
+  - name: LIAS Laboratory
+    address: 1 Avenue Clément Ader
+    city: Chasseneuil du Poitou
+    post-code: '86360'
+    website: 'https://www.lias-lab.fr'
+identifiers:
+  - type: swh
+    value: 'swh:1:rev:66f8d295cc5fbc80f356d11be46571bfbb190609'
+license: GPL-3.0

pyproject.toml

@@ -9,6 +9,7 @@ description = "A Clustering under radius constraints algorithm using minimum dom
 readme = "README.md"
 authors = [
     {name = "Quentin Haenn"},
+    {name = "Lias Laboratory"}
 ]
 
 dependencies = [
@@ -37,6 +38,7 @@ classifiers=[
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: Implementation :: CPython",
 ]
 keywords = ["Unsupervised learning","clustering", "minimum dominating sets","clustering under radius constraint"]
@@ -137,3 +139,8 @@ docstring-code-format = true
 # Set the line length limit used when formatting code snippets in
 # docstrings.
 docstring-code-line-length = "dynamic"
+
+
+[tool.cibuildwheel]
+# Skip building for PyPy, python 3.6/7/8 and 13t, and 32-bit platforms.
+skip = ["pp*", "cp36-*", "cp37-*", "cp38-*", "*-win32", "*linux_i686", "*musllinux*"]

radius_clustering/radius_clustering.py

@@ -10,7 +10,7 @@
 
 import os
 import numpy as np
-import scipy.spatial as sp_spatial
+from sklearn.metrics import pairwise_distances
 from sklearn.base import BaseEstimator, ClusterMixin
 from sklearn.utils.validation import check_array
 
@@ -38,7 +38,7 @@ class RadiusClustering(BaseEstimator, ClusterMixin):
     -----------
     X : array-like, shape (n_samples, n_features)
         The input data.
-    centers : list
+    centers\_ : list
         The indices of the cluster centers.
     labels\_ : array-like, shape (n_samples,)
         The cluster labels for each point in the input data.
@@ -50,6 +50,9 @@ def __init__(self, manner="approx", threshold=0.5):
         self.manner = manner
         self.threshold = threshold
 
+    def _check_symmetric(self, a, tol=1e-8):
+        return np.allclose(a, a.T, atol=tol)
+
     def fit(self, X, y=None):
         """
         Fit the MDS clustering model to the input data.
@@ -87,10 +90,19 @@ def fit(self, X, y=None):
         self.X = check_array(X)
 
         # Create dist and adj matrices
-        dist_mat = sp_spatial.distance_matrix(self.X, self.X)
+        if not self._check_symmetric(self.X):
+            dist_mat = pairwise_distances(self.X, metric="euclidean")
+        else:
+            dist_mat = self.X
         adj_mask = np.triu((dist_mat <= self.threshold), k=1)
         self.nb_edges = np.sum(adj_mask)
-        self.edges = np.argwhere(adj_mask).astype(np.int32)
+        if self.nb_edges == 0:
+            self.centers_ = list(range(self.X.shape[0]))
+            self.labels_ = self.centers_
+            self.effective_radius = 0
+            self._mds_exec_time = 0
+            return self
+        self.edges = np.argwhere(adj_mask).astype(np.uint32) #TODO: changer en uint32
         self.dist_mat = dist_mat
 
         self._clustering()

radius_clustering/utils/emos.pyx

@@ -17,7 +17,7 @@ cdef extern from "mds3-util.h":
         int set_size
         double exec_time
 
-    Result* emos_main(int* edges, int nb_edge, int n)
+    Result* emos_main(unsigned int* edges, int nb_edge, int n)
 
     void cleanup()
 
@@ -26,7 +26,7 @@ cdef extern from "mds3-util.h":
 import numpy as np
 cimport numpy as np
 
-def py_emos_main(np.ndarray[int, ndim=1] edges, int n, int nb_edge):
+def py_emos_main(np.ndarray[unsigned int, ndim=1] edges, int n, int nb_edge):
     cdef Result* result = emos_main(&edges[0], n, nb_edge)
 
     dominating_set = [result.dominating_set[i] - 1 for i in range(result.set_size)]

radius_clustering/utils/main-emos.c

@@ -10,15 +10,27 @@ Copyright (C) 2024, Haenn Quentin.
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <signal.h>
 #include <time.h>
-#include <sys/times.h>
-#include <sys/types.h>
-#include <limits.h>
-#include <unistd.h>
-#include <sys/resource.h>
-#include <math.h>
 #include <assert.h>
+#include <math.h>
+
+#ifdef _WIN32
+    #include <windows.h>
+    #include <process.h>
+    #include <direct.h>
+    #define SIGINT 2
+    typedef void (*SignalHandlerFn)(int);
+#elif defined(__APPLE__) || defined(__linux__)
+    #include <sys/time.h>
+    #include <sys/resource.h>
+    #include <sys/types.h>
+    #include <unistd.h>
+    #include <signal.h>
+#else
+    #error "Unsupported platform"
+#endif
+
+
 #include "mds3-util.h"
 #include "util_heap.h"
 
@@ -1462,7 +1474,7 @@ void check_consistance(){
     assert(!domed(CFG[i]));
   }
   int level=-1;
-  for(int idx=0;idx<USED(BRA_STK);idx++){
+  for(size_t idx=0;idx<USED(BRA_STK);idx++){
     if(ITEM(BRA_STK,idx)==NONE){
       level++;
     }else if(idx<=BRAIDX[level])
@@ -1487,7 +1499,7 @@ void check_consistance(){
 
 
 void cleanup(){
-  
+
   // Free all allocated memory
   if (CFG != NULL) {
     free(CFG);
@@ -1554,15 +1566,35 @@ void cleanup(){
   instance[0] = '\0';
 }
 
+
 void handler(int sig) {
   cleanup();
   exit(sig);
 }
 
-struct Result* emos_main(int* edges, int n, int nb_edge) {
+#ifdef _WIN32
+static BOOL WINAPI win32_handler(DWORD signal) {
+    if (signal == CTRL_C_EVENT) {
+        handler(SIGINT);
+        return TRUE;
+    }
+    return FALSE;
+}
+
+static void setup_signal_handler(SignalHandlerFn handler_fn) {
+    SetConsoleCtrlHandler(win32_handler, TRUE);
+}
+#else
+static void setup_signal_handler(void (*handler_fn)(int)) {
+    signal(SIGINT, handler_fn);
+}
+#endif
+
+
+struct Result* emos_main(unsigned int* edges, int n, int nb_edge) {
 
     // Set the signal handler
-  signal(SIGINT, handler);
+  setup_signal_handler(handler);
 
   _read_graph_from_edge_list(edges, n, nb_edge);
   NB_NODE_O = NB_NODE;
@@ -1584,7 +1616,7 @@ struct Result* emos_main(int* edges, int n, int nb_edge) {
 
   // Get the results
   int* dominating_set = (int*)malloc(USED(VEC_SOLUTION) * sizeof(int));
-  for (int i= 0; i<USED(VEC_SOLUTION); i++) {
+  for (size_t i= 0; i<USED(VEC_SOLUTION); i++) {
     dominating_set[i] = ITEM(VEC_SOLUTION, i);
   }
 
@@ -1615,22 +1647,4 @@ void free_results(struct Result* result) {
         free(result);
     }
 }
-
-/** int main(int argc, char *argv[]) {
-
-  print_compile_options();
-  parse_parmerters(argc,argv);
-  if(read_instance(argv[1])) {
-    initialize();
-    #ifndef NOR
-    reduce_graph();
-    #endif
-    partition_oneproblem();    
-    solve_subproblems();
-    check_final_solution();
-    print_final_solution(getInstanceName(argv[1]));
-    printf("### %s pruning rate %0.2lf total %llu pruned %llu\n",getInstanceName(argv[1]), (total_branches-pruned_branches)/((double)total_branches),total_branches,total_branches-pruned_branches);
-  }	   
-  return 0;
-} */