simplification with multiple components

deconvolution/main/d2_reduction.py

@@ -13,6 +13,7 @@ def parse_arguments():
     parser.add_argument('barcode_graph', help='The barcode graph file. Must be a gefx formated file.')
     parser.add_argument('d2_graph', help='d2 graph to reduce. Must be a gefx formated file.')
     parser.add_argument('--output_d2_name', '-o', default="transitively_reduced_d2.gexf", help="Output file prefix.")
+    parser.add_argument('--component_min_size', '-c', type=int, default=10, help="Minimum size of a component to keep it in the d2-graph, after the edge simplifications.")
 
     args = parser.parse_args()
     return args
@@ -37,11 +38,14 @@ def main():
     d2a.transitive_reduction(d2g)
 
     # Take the principal component
-    largest_component_nodes = max(nx.connected_components(d2g), key=len)
-    largest_component = d2g.subgraph(largest_component_nodes)
-
-    # Write the simplificated graph
-    nx.write_gexf(largest_component, args.output_d2_name)
+    components = [c for c in nx.connected_components(d2g) if len(c) > args.component_min_size]
+    nodes = set()
+    for comp in components:
+        nodes.update(comp)
+    subgraph = d2g.subgraph(nodes)
+
+    # Write the simplified graph
+    nx.write_gexf(subgraph, args.output_d2_name)
 
 
 if __name__ == "__main__":