important bugfix in clustering

Author: derohde

Fred/__pycache__/__init__.cpython-39.pyc

@@ -38,6 +38,8 @@ By default, Fred will automatically determine the number of threads to use. If y
 
 ### Curve Simplification
 
+All simplifications are vertex-restricted!
+
 #### weak minimum error simplification
 - graph approach from [**Polygonal Approximations of a Curve — Formulations and Algorithms**](https://www.sciencedirect.com/science/article/pii/B9780444704672500114)
 - signature: `fred.weak_minimum_error_simplification(fred.Curve, int complexity)`
@@ -65,8 +67,8 @@ A `fred.Distance_Matrix()` can be used to speed up consecutive calls of `fred.di
     - `k`: number of centers
     - `l`: maximum complexity of the centers, only used when center_domain is default value
     - `distances`: `fred.Distance_Matrix`, defaults to empty `fred.Distance_Matrix`
-    - `center_domain`: possible centers, defaults to empty `fred.Curves()`, in this case the input is simplified and used as center domain
     - `random_first_center`: determines if first center is chosen uniformly at random or first curve is used as first center, optional, defaults to true
+    - `fast_simplification`: determines whether to use the weak minimum error simplification or the faster approximate weak minimum error simplification, defaults to false
 - returns: `fred.Clustering_Result` with mebers 
     - `value`: objective value 
     - `time`: running-time 
@@ -78,7 +80,7 @@ A `fred.Distance_Matrix()` can be used to speed up consecutive calls of `fred.di
     - `k`: number of centers
     - `l`: maximum complexity of the centers, only used when center_domain is default value
     - `distances`: `fred.Distance_Matrix`, defaults to empty `fred.Distance_Matrix`
-    - `center_domain`: possible centers, optional parameter, if not given the input is simplified and used as center domain
+    - `fast_simplification`: determines whether to use the weak minimum error simplification or the faster approximate weak minimum error simplification, defaults to false
 - returns: `fred.Clustering_Result` with mebers 
     - `value`: objective value 
     - `time`: running-time 

README.md

@@ -128,41 +128,35 @@ struct Clustering_Result {
     }
 };
 
-Clustering_Result kl_center(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Distance_Matrix &distances, const bool local_search = false, const Curves &center_domain = Curves(), const bool random_start_center = true) {
-    
+Clustering_Result kl_cluster(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Distance_Matrix &distances, const bool local_search = false, const bool random_start_center = true, const bool fast_simplification = false) {
     const auto start = std::chrono::high_resolution_clock::now();
     Clustering_Result result;
 
     if (in.empty()) return result;
 
     std::vector<curve_number_t> centers;
-    Curves &simplified_in = const_cast<Curves&>(center_domain);
-    bool self_simplify = false;
+    Curves simplified_in(in.number(), ell, in.dimensions());
 
-    if (center_domain.empty()) {
-        self_simplify = true;
-        Curves simplified_in_self(in.number(), ell, in.dimensions());
-        simplified_in = simplified_in_self;
-    }
-        
+    auto simplify = [&](const curve_number_t i) {
+        if (fast_simplification) {
+            auto simplified_curve = Simplification::approximate_weak_minimum_error_simplification(const_cast<Curve&>(in[i]), ell);
+            simplified_curve.set_name("Simplification of " + in[i].get_name());
+            return simplified_curve;
+        } else {
+            Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(in[i]));
+            auto simplified_curve = graph.weak_minimum_error_simplification(ell);
+            simplified_curve.set_name("Simplification of " + in[i].get_name());
+            return simplified_curve;
+        }
+    };
+
     if (random_start_center) {
         Random::Uniform_Random_Generator<double> ugen;
         const curve_number_t r =  std::floor(simplified_in.size() * ugen.get());
-        if (self_simplify) {
-            Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(in[r]));
-            auto simplified_curve = graph.weak_minimum_error_simplification(ell);
-            simplified_curve.set_name("Simplification of " + in[r].get_name());
-            simplified_in[r] = simplified_curve;
-        }
+        simplified_in[r] = simplify(r);
         centers.push_back(r);
-        
     } else {
-        if (self_simplify) {
-            Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(in[0]));
-            auto simplified_curve = graph.weak_minimum_error_simplification(ell);
-            simplified_curve.set_name("Simplification of " + in[0].get_name());
-            simplified_in[0] = simplified_curve;
-        }
+        simplified_in[0] = simplify(0);
         centers.push_back(0);
     }
 
@@ -195,11 +189,8 @@ Clustering_Result kl_center(const curve_number_t num_centers, const curve_size_t
                 std::cout << "found center no. " << i+1 << std::endl;
                 #endif
 
-                if (self_simplify and simplified_in[curr_maxcurve].empty()) {
-                    Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(in[curr_maxcurve]));
-                    auto simplified_curve = graph.weak_minimum_error_simplification(ell);
-                    simplified_curve.set_name("Simplification of " + in[curr_maxcurve].get_name());
-                    simplified_in[curr_maxcurve] = simplified_curve;
+                if (simplified_in[curr_maxcurve].empty()) {
+                    simplified_in[curr_maxcurve] = simplify(curr_maxcurve);
                 }
                 centers.push_back(curr_maxcurve);
             }   
@@ -229,11 +220,8 @@ Clustering_Result kl_center(const curve_number_t num_centers, const curve_size_t
                     if (std::find(curr_centers.begin(), curr_centers.end(), j) != curr_centers.end()) continue;
 
                     // swap
-                    if (self_simplify and simplified_in[j].empty()) {
-                        Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(in[j]));
-                        auto simplified_curve = graph.weak_minimum_error_simplification(ell);
-                        simplified_curve.set_name("Simplification of " + in[j].get_name());
-                        simplified_in[j] = simplified_curve;
+                    if (simplified_in[j].empty()) {
+                        simplified_in[j] = simplify(j);
                     }
                     curr_centers[i] = j;
                     // new cost
@@ -260,8 +248,12 @@ Clustering_Result kl_center(const curve_number_t num_centers, const curve_size_t
     return result;
 }
 
-Clustering_Result kl_median(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Distance_Matrix &distances, const Curves &center_domain = Curves()) {
-    return kl_center(num_centers, ell, in, distances, true, center_domain, false);
+Clustering_Result kl_center(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Distance_Matrix &distances, const bool random_start_center = true, const bool fast_simplification = false) {
+    return kl_cluster(num_centers, ell, in, distances, false, random_start_center, fast_simplification);
+}
+
+Clustering_Result kl_median(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Distance_Matrix &distances, const bool fast_simplification = false) {
+    return kl_cluster(num_centers, ell, in, distances, true, fast_simplification);
 }
 
 Clustering_Result one_median_sampling(const curve_size_t ell, const Curves &in, const double epsilon, const Curves &center_domain = Curves()) {

include/clustering.hpp

@@ -74,7 +74,7 @@ def build_extension(self, ext):
 
 setup(
     name='Fred-Frechet',
-    version='1.7.4',
+    version='1.7.5',
     author='Dennis Rohde',
     author_email='[email protected]',
     description='A fast, scalable and light-weight C++ Fréchet distance library, exposed to python and focused on (k,l)-clustering of polygonal curves.',

setup.py

@@ -45,38 +45,6 @@ bool get_frechet_rounding() {
     return fc::round;
 }
 
-Clustering::Clustering_Result klcenter(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Clustering::Distance_Matrix &distances, const Curves &center_domain = Curves(), const bool random_start_center = true) {
-    auto result = Clustering::kl_center(num_centers, ell, in, distances, false, center_domain, random_start_center);
-    return result;
-}
-
-Clustering::Clustering_Result klmedian(const curve_number_t num_centers, const curve_size_t ell, const Curves &in, Clustering::Distance_Matrix distances, const Curves &center_domain = Curves()) {
-
-    auto result = Clustering::kl_median(num_centers, ell, in, distances, center_domain);
-    
-    return result;
-}
-
-// Clustering::Clustering_Result onemedian_sampling(const curve_size_t ell,  Curves &in, const double epsilon, const bool with_assignment = false, const Curves &center_domain = Curves()) {
-//     
-//     auto result = Clustering::one_median_sampling(ell, in, epsilon, with_assignment);
-//     
-//     return result;
-// }
-// 
-// Clustering::Clustering_Result onemedian_exhaustive(const curve_size_t ell,  Curves &in, const bool with_assignment = false, const Curves &center_domain = Curves()) {
-// 
-//     auto result = Clustering::one_median_exhaustive(ell, in, with_assignment);
-//     
-//     return result;
-// }
-// 
-// 
-// Coreset::Onemedian_Coreset onemedian_coreset(const Curves &in, const curve_size_t ell, const double epsilon, const double constant = 1) {
-//     return Coreset::Onemedian_Coreset(ell, in, epsilon, constant);
-// }
-// 
-
 Curve weak_minimum_error_simplification(const Curve &curve, const curve_size_t l) {
     Simplification::Subcurve_Shortcut_Graph graph(const_cast<Curve&>(curve));
     auto scurve = graph.weak_minimum_error_simplification(l);
@@ -224,8 +192,8 @@ PYBIND11_MODULE(backend, m) {
 
     m.def("dimension_reduction", &JLTransform::transform_naive, py::arg("in") = Curves(), py::arg("epsilon") = 0.5, py::arg("empirical_constant") = true);
 
-    m.def("discrete_klcenter", &klcenter, py::arg("num_centers") = 1, py::arg("ell") = 2, py::arg("in") = Curves(), py::arg("distances") = Clustering::Distance_Matrix(), py::arg("center_domain") = Curves(), py::arg("random_start_center") = true);
-    m.def("discrete_klmedian", &klmedian, py::arg("num_centers") = 1, py::arg("ell") = 2, py::arg("in") = Curves(), py::arg("distances") = Clustering::Distance_Matrix(), py::arg("center_domain") = Curves());
+    m.def("discrete_klcenter", &Clustering::kl_center, py::arg("num_centers") = 1, py::arg("ell") = 2, py::arg("in") = Curves(), py::arg("distances") = Clustering::Distance_Matrix(), py::arg("random_start_center") = true, py::arg("fast_simplification") = false);
+    m.def("discrete_klmedian", &Clustering::kl_median, py::arg("num_centers") = 1, py::arg("ell") = 2, py::arg("in") = Curves(), py::arg("distances") = Clustering::Distance_Matrix(), py::arg("fast_simplification") = false);
 
     // these are experimental
     //m.def("two_two_dtw_one_two_median", &Clustering::two_two_dtw_one_two_median);