df_encoded = pd.concat(concat, ignore_index=True)
#numerate patients from 0 to N-1, where N is the number patients
df_encoded['id_patient'] = df_encoded.index.tolist()
df_encoded.to_csv('patient_temporal_sequences_experiment1.csv')
print(df_encoded)
################################################################################
## SEQUENCE ALIGNMENT, HIERARCHICAL CLUSTERING & VALIDATION
################################################################################
concat_for_final_decision = []
for gap in gap_values:
print('GAP PENALTY:', gap)
#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)
print('number of experiment:', i)
#initialize list that will contain the auxliary dataframes to be concataneted
concat = []
#generate sequences
df_encoded = generate_dataset(n_sequences, dataset)
###########################################################################
## SEQUENCE ALIGNMENT, HIERARCHICAL CLUSTERING & VALIDATION
###########################################################################
concat_for_final_decision = []
for gap in gap_values:
#print(gap)
#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()):
continue
else:
#hierarchical clustering
Z = hierarchical_clustering(results['score'], method, gap)
#validation