if( edge_value_dict[edge] == True ): tuple_dict_true[edge] += 1 ;
for i in range(1, 11):
temp = int(target_num*i/10.0) ;
mytuple = (edge, temp) ;
if( res_effect_list[i-1] == True ):
if( edge_value_dict[edge] == True ): flag_dict_true[mytuple] += 1 ;
else: flag_dict_false[mytuple] += 1 ;
mc_num = mc_num * 2 ;
res_dict = {} ;
for edge in tuplelist:
for i in range(1, 11):
temp = int(target_num*i/10.0) ;
mytuple = (edge, temp) ;
res_dict[mytuple] = flag_dict_true[mytuple]/float(tuple_dict_true[edge]) - flag_dict_false[mytuple]/(mc_num-float(tuple_dict_true[edge])) ;
return res_dict ;
if __name__ == "__main__":
filename = "provenance_dataset/karate_provenance.txt";
targetnodelist = get_targets_karate() ;
targetlist = readProvenance(filename, targetnodelist) ;
start = timeit.default_timer() ;
res_dict = run_mc(targetlist, mc_num=100, k=5) ;
stop = timeit.default_timer() ;
print stop-start ;
lines = get_mc_result_list(res_dict, targetlist, get_tuple_list(targetlist)) ;
for line in lines:
print line ;
def causal_test(pro_file_name, mc_num, k):
targetnodelist = get_targets_karate() ;
targetlist = readProvenance(filename, targetnodelist) ;
res_dict = run_mc(targetlist, mc_num, k) ;
return get_mc_result_list(res_dict, targetlist, get_tuple_list(targetlist)) ;
