Better solve statistics

Author: alexandrutomescu

examples/cycles_demo.py

@@ -18,6 +18,8 @@ def test_min_flow_decomp(filename: str):
             "pathwidth": 2,
         })
 
+    print(graph.graph["n"], graph.graph["m"], graph.graph["w"])
+
     mfd_model = fp.MinFlowDecompCycles(
         G=graph,
         flow_attr="flow",
@@ -137,9 +139,11 @@ def process_solution(model):
     print("solve_time:", solve_statistics['solve_time']) # time taken by the ILP for a given k, or by MFD to iterate through k and do small internal things
     print("number_of_nontrivial_SCCs:", solve_statistics['number_of_nontrivial_SCCs']) # trivial = at least one edge
     print("size_of_largest_SCC:", solve_statistics['size_of_largest_SCC']) # size = number of edges
+    print("avg_size_of_non_trivial_SCC:", solve_statistics['avg_size_of_non_trivial_SCC']) # size = number of edges
 
 def main():
-    test_min_flow_decomp(filename = "tests/cyclic_graphs/gt5.kmer27.(655000.660000).V18.E27.mincyc4.graph")
+    test_min_flow_decomp(filename = "tests/cyclic_graphs/gt3.kmer15.(130000.132000).V23.E32.cyc100.graph")
+    test_min_flow_decomp(filename = "tests/cyclic_graphs/gt5.kmer27.(655000.660000).V18.E27.mincyc4.e0.75.graph")
     test_least_abs_errors(filename = "tests/cyclic_graphs/gt5.kmer27.(655000.660000).V18.E27.mincyc4.e0.75.graph")
     test_min_path_error(filename = "tests/cyclic_graphs/gt5.kmer27.(655000.660000).V18.E27.mincyc4.e0.75.graph")
 

flowpaths/abstractwalkmodeldigraph.py

@@ -455,6 +455,7 @@ def solve(self) -> bool:
         self.solve_statistics[f"solve_time"] = time.perf_counter() - start_time
         self.solve_statistics[f"model_status"] = self.solver.get_model_status()
         self.solve_statistics[f"number_of_nontrivial_SCCs"] = self.G.get_number_of_nontrivial_SCCs()
+        self.solve_statistics[f"avg_size_of_non_trivial_SCC"] = self.G.get_avg_size_of_non_trivial_SCC()
         self.solve_statistics[f"size_of_largest_SCC"] = self.G.get_size_of_largest_SCC()
 
         if self.solver.get_model_status() == "kOptimal" or self.solver.get_model_status() == 2:

flowpaths/minflowdecompcycles.py

@@ -231,6 +231,7 @@ def solve(self) -> bool:
                     solver_options=fd_solver_options,
                 )
                 fd_model.solve()
+                self.solve_statistics = fd_model.solve_statistics
 
                 # If the previous run exceeded the time limit, 
                 # we still stop the search, even if we might have managed to solve it
@@ -251,8 +252,10 @@ def solve(self) -> bool:
                 self.fd_model = fd_model
                 return True
             elif fd_model.solver.get_model_status() == sw.SolverWrapper.infeasible_status:
+                self.solve_statistics = fd_model.solve_statistics
                 utils.logger.info(f"{__name__}: model is infeasible for k = {i}")
             else:
+                self.solve_statistics = fd_model.solve_statistics
                 # If the model is not solved and the status is not infeasible,
                 # it means that the solver stopped because of an unexpected termination,
                 # thus we cannot conclude that the model is infeasible.

flowpaths/stdigraph.py

@@ -309,6 +309,13 @@ def get_size_of_largest_SCC(self) -> int:
         Returns the size of the largest SCC (in terms of number of edges).
         """
         return max((len(self._condensation.graph['member_edges'][str(v)]) for v in self._condensation.nodes()), default=0)
+    
+    def get_avg_size_of_non_trivial_SCC(self) -> int:
+        """
+        Returns the average size (in terms of number of edges) of non-trivial SCCs (i.e. SCCs with at least one edge).
+        """
+        sizes = [len(self._condensation.graph['member_edges'][str(v)]) for v in self._condensation.nodes() if len(self._condensation.graph['member_edges'][str(v)]) > 0]
+        return sum(sizes) // len(sizes) if sizes else 0
 
     def get_longest_incompatible_sequences(self, sequences: list) -> list: