#pairwise sequence alignment results
results = main_algorithm(df_encoded, gap, T, s, 0)
#reset indexes
df_encoded = df_encoded.reset_index()
#convert similarity matrix into distance matrix
results['score'] = convert_to_distance_matrix(results['score'])
#exception when all the scores are the same, in this case we continue with the next value of gap
if ((results['score'] == 0).all()):
print('entrei')
continue
else:
#hierarchical clustering
Z = hierarchical_clustering(results['score'], method, gap)
#validation
chosen = validation(M, df_encoded, results, Z, method, min_K,
max_K + 1)
chosen_k = chosen[2]
df_avgs = chosen[0]
df_stds = chosen[1]
chosen_results = df_avgs.loc[chosen_k]
chosen_results['gap'] = gap
concat_for_final_decision.append(chosen_results)
df_final_decision = pd.concat(concat_for_final_decision, axis=1).T
final_k_results = final_decision(df_final_decision)
#reset indexes
df_encoded = df_encoded.reset_index()
#convert similarity matrix into distance matrix
results['score'] = convert_to_distance_matrix(results['score'])
#exception when all the scores are the same, in this case we continue with the next value of gap
if((results['score']== 0).all()):
#print('entrei')
continue
else:
#hierarchical clustering
Z = hierarchical_clustering(results['score'],method,gap,T,args.automatic,pp)
#validation
chosen = validation(M,df_encoded,results,Z,method,min_K,max_K+1,args.automatic,pp,gap,T)
chosen_k = chosen[2]
df_avgs = chosen[0]
df_stds = chosen[1]
chosen_results = df_avgs.loc[chosen_k]
chosen_results['gap'] = gap
concat_for_final_decision.append(chosen_results)
############################################################################
# RESULTS
############################################################################
#close pdf
pp.close()
if(args.automatic==1):
df_final_decision = pd.concat(concat_for_final_decision,axis=1).T