fix start_nodes and eq_scc bug

main.py

@@ -18,25 +18,41 @@ args = {
     'threshold3': 3, # gene flow merge threshold 
     'bidirectional': True, # calculate the reversed gene flow
     'calculate_pd': True, # calculate the gene flow confidence
-    'data_path': 'data/test.log',
+    'data_path': 'data/D_AI_230710.log',
     'save_path': 'pictures/tree.png',
     'draw_gene_flow': True,
     'gene_flow_display_confidence': 0.7,
-    'target_block_list': ['Tianyuan'],
-    's1_block_list': ['Boshan'],
+    'target_block_list': ['AR14K'],
+    's1_block_list': ['AR14K'],
     # 'target_block_list': [],
     # 's1_block_list': [],
 }
+populations = ['Tianyuan',
+    'Boshan',
+    'Qihe',
+    'Longlin',
+    'Dushan',
+    'Baojianshan',
+    'La368',
+    'Bianbian',
+    'Xiaojingshan',
+    'BQGroup',
+    'YJCGroup',
+    'LJZGroup',
+    'YR_MN_WGM',
+    'WLR_MN',
+    'DevilsCave_N',
+    'AR14K']
 
-populations = ['Kostenki14',
-               'Tianyuan',
-               'AR19K',
-               'AR14K',
-               'Zongri5_1k',
-               'Boshan',
-               'Qihe3',
-               'Donghulin',
-               ]
+# populations = ['Kostenki14',
+#                'Tianyuan',
+#                'AR19K',
+#                'AR14K',
+#                'Zongri5_1k',
+#                'Boshan',
+#                'Qihe3',
+#                'Donghulin',
+#                ]
 
 #args = {
 #    'change_greenstar': True,
@@ -114,6 +130,7 @@ print('Analyzing the minimum Z...')
 bottom_threshold = 0
 D_statistics, adjusted_D_values, triangles, redstar_indices, min_redstar, s2_record \
     = read_data(data_path, bottom_threshold, populations)
+print(s2_record)
 builder = TreeBuilder(populations, triangles, s2_record)
 builder.D2graph(D_statistics)
 g = builder.g
@@ -203,7 +220,10 @@ for scc_idx, s in enumerate(scc0):
         del g.graph[idx]
         g.graph[represent]['in'].discard(idx)
         g.graph[represent]['out'].discard(idx)
-        g.start_nodes.discard(idx) 
+        if idx in g.start_nodes:
+            g.start_nodes.discard(idx)
+        else:
+            g.start_nodes.discard(represent)
     # note that, the eq set of the node may contain duplicated nodes with different values!!!!!!!
     # tmp_node_record is used to duplicate them.
 #    tmp_node_record = []
@@ -420,7 +440,10 @@ for scc_idx, s in enumerate(scc):
             g.graph[node]['in'].add(represent)
             g.graph[node]['in'].remove(idx)
         del g.graph[idx]
-        g.start_nodes.discard(idx)
+        if idx in g.start_nodes:
+            g.start_nodes.discard(idx)
+        else:
+            g.start_nodes.discard(represent)
     g.graph[represent]['in'].remove(represent)
     g.graph[represent]['out'].remove(represent)
     if represent in eq_scc: