def get_quartets(filepath): f = open(filepath,'r') q_set=set() for line in f: q_set.add(unique_quartet(line)) f.close() return q_set
def update(dict_list,filepath): f=open(filepath,'r') for line in f: q=unique_quartet(line) for i in range(len(dict_list)): if q in dict_list[i]: dict_list[i][q]+=1 else: dict_list[i][q]=1 f.close()
def adjust_quartet_weight_similarity(file_dir,gene,numtaxa,n): nlist=neighbors(file_dir+'//gene_'+str(gene)+'_similarity.txt', n, gene) wlist=[2,10,25] q_dict=[{},{},{}] for i in range(numtaxa-3): for j in range(len(wlist)): q_dict[j][format(i, i+1, i+2, i+3)]=0 f = open(file_dir+'//gene_'+str(gene)+'_quartets.txt','r') for line in f: q=unique_quartet(line) for i in range(len(wlist)): q_dict[i][q]=wlist[i] f.close() for i in nlist: print 'neighbor ',i update(q_dict, file_dir+'//gene_'+str(i)+'_quartets.txt') for i in range(len(wlist)): write(q_dict[i],file_dir+'//gene_'+str(gene)+'_neighbor_'+str(n)+'_w_'+str(wlist[i])+'_quartets.txt')