simplify d2 snakemake interface and remove parasit prints

README.md

@@ -42,3 +42,11 @@ Config parameters:
     export PYTHONPATH=deconvolution/
     pytest tests
     export PYTHONPATH=
+
+
+## Tests for Cedric
+
+```bash
+    snakemake -s Snakefile_data_simu --config n=10000 m=[4,6,8,10,12] m_dev=[0,0.5,1,2,3]
+    snakemake -s Snakefile_d2 --config input=[snakemake -s Snakefile_d2 --config input=[snake_exec/simu_bar_n10000_d5_m10-dev0.5.gexf,snake_exec/simu_bar_n10000_d5_m10-dev0.gexf,snake_exec/simu_bar_n10000_d5_m10-dev1.gexf,snake_exec/simu_bar_n10000_d5_m10-dev2.gexf,snake_exec/simu_bar_n10000_d5_m10-dev3.gexf,snake_exec/simu_bar_n10000_d5_m12-dev0.5.gexf,snake_exec/simu_bar_n10000_d5_m12-dev0.gexf,snake_exec/simu_bar_n10000_d5_m12-dev1.gexf,snake_exec/simu_bar_n10000_d5_m12-dev2.gexf,snake_exec/simu_bar_n10000_d5_m12-dev3.gexf,snake_exec/simu_bar_n10000_d5_m4-dev0.5.gexf,snake_exec/simu_bar_n10000_d5_m4-dev0.gexf,snake_exec/simu_bar_n10000_d5_m4-dev1.gexf,snake_exec/simu_bar_n10000_d5_m4-dev2.gexf,snake_exec/simu_bar_n10000_d5_m4-dev3.gexf,snake_exec/simu_bar_n10000_d5_m6-dev0.5.gexf,snake_exec/simu_bar_n10000_d5_m6-dev0.gexf,snake_exec/simu_bar_n10000_d5_m6-dev1.gexf,snake_exec/simu_bar_n10000_d5_m6-dev2.gexf,snake_exec/simu_bar_n10000_d5_m6-dev3.gexf,snake_exec/simu_bar_n10000_d5_m8-dev0.5.gexf,snake_exec/simu_bar_n10000_d5_m8-dev0.gexf,snake_exec/simu_bar_n10000_d5_m8-dev1.gexf,snake_exec/simu_bar_n10000_d5_m8-dev2.gexf,snake_exec/simu_bar_n10000_d5_m8-dev3.gexf]]
+```

Snakefile_d2

 import glob
 
 WORKDIR = "snake_exec" if "workdir" not in config else config["workdir"]
-INPUT = "snake_tests/simu_bar_n1000_d5_m2-dev0.gexf" if "input" not in config else config["input"]
-SAMPLE_NAME = INPUT[INPUT.rfind('/')+1:INPUT.rfind('.')]
+INPUT = ["snake_tests/simu_bar_n1000_d5_m2-dev0.gexf"] if "input" not in config else config["input"]
+INPUT = INPUT if isinstance(INPUT, list) else [INPUT]
+SAMPLE_NAME = [name[name.rfind('/')+1:name.rfind('.')] for name in INPUT]
 
 rule all:
     input:
-        f"{WORKDIR}/{SAMPLE_NAME}.tar.gz"
+        expand(f"{WORKDIR}/{{name}}.tar.gz", name=SAMPLE_NAME)
 
 rule compress_data:
     input:

deconvolution/d_graph.py

@@ -237,7 +237,7 @@ def compute_all_max_d_graphs(graph, debug=False, clique_mode=None):
 
     for idx, node in enumerate(list(graph.nodes())):
         #if "MI" not in str(node): continue    # for debugging; only look at deconvolved nodes
-        print(f"\r{idx+1}/{len(graph.nodes())}")
+        #print(f"\r{idx+1}/{len(graph.nodes())}")
         neighbors = list(graph.neighbors(node))
         neighbors_graph = nx.Graph(graph.subgraph(neighbors))
 
@@ -278,7 +278,7 @@ def compute_all_max_d_graphs(graph, debug=False, clique_mode=None):
             cliques = list(cliques_dict2.values())
             mode_str += "(testing)"
 
-        print("cliques", len(cliques))
+        #print("cliques", len(cliques))
         if debug: print("node",node,"has",len(cliques),"cliques in neighborhood (of size",len(neighbors),")")
         
         cliques_debugging = True
@@ -289,7 +289,7 @@ def compute_all_max_d_graphs(graph, debug=False, clique_mode=None):
 
             from collections import Counter
             len_cliques = Counter(map(len,cliques))
-            print("sizes of found cliques%s:" % mode_str, len_cliques)
+            #print("sizes of found cliques%s:" % mode_str, len_cliques)
 
         # Pair halves to create d-graphes
         for idx, clq1 in enumerate(cliques):
@@ -306,9 +306,9 @@ def compute_all_max_d_graphs(graph, debug=False, clique_mode=None):
                 if d_graph.get_link_divergence() <= d_graph.get_optimal_score() * factor:
                     node_d_graphs.add(d_graph)
 
-        print("d-graphs", len(node_d_graphs))
+        #print("d-graphs", len(node_d_graphs))
         d_graphs[node] = brutal_list_domination_filter(sorted(node_d_graphs))
-        print("filtered", len(d_graphs[node]))
+        #print("filtered", len(d_graphs[node]))
 
     return d_graphs