summary of subproblem_size_summary.json as a .tsv

table_from_subproblem_size_summary.py

#!/bin/env python
import json
import sys
import subprocess
import itertools


inpjson = 'subproblem_size_summary.json'
with open(inpjson, 'r', encoding='utf-8') as inp:
    summary_blob = json.load(inp)
subprobs = summary_blob["subproblems"]
tree_ids = summary_blob["tree_ids"]

print('\t'.join(["ID",
                 "num_scaff_leaves",
                 "num_synth_leaves",
                 "num_splits",
                 "num_informative_input_trees",
                 "num_noninformative_overlapping_input_trees",
                 "inf_tree_ids",
                 "noninf_tree_ids"]))
for ott_id, summary_blob in subprobs.items():
    num_scaff_leaves, num_synth_leaves, by_input = summary_blob
    inf_by_inp, non_inf = [], []
    num_splits = 0
    for el in by_input:
        tid = tree_ids[el[2]]
        if el[1] > 0:
            num_splits += el[1]
            inf_by_inp.append(tid)
        else:
            non_inf.append(tid)    
    data = [ott_id, num_scaff_leaves, num_synth_leaves, num_splits, len(inf_by_inp), len(non_inf), ','.join(inf_by_inp), ','.join(non_inf)]
    print('\t'.join([str(i) for i in data]))