trab01.py

dataset = pandas.read_csv('epidemias.csv', skiprows=1, header=None, names=['nome', 'genero', 'data_nascimento', 'cidade', 'estado', 'doencax'])

cities = set(dataset['cidade'])
states = set(dataset['estado'])

def get_gender_value(raw_gender):
    gender = raw_gender.to_string()
    index_substring = gender.rfind(' ') + 1

    return 0 if gender[index_substring:] == 'Female' else 1

def get_city_value(raw_city):
    city_string = raw_city.to_string()

    city = (city_string[city_string.find(' '):])[4:]

    return list(cities).index(city)

def get_state_value(raw_state):
    state = raw_state.to_string()
    index_substring = state.rfind(' ') + 1

    return list(states).index(state[index_substring:])

def get_days_from_date(raw_birth_date):
    birth_date_string = raw_birth_date.to_string()
    index_substring = birth_date_string.rfind(' ') + 1

    month, day, year = birth_date_string[index_substring:].split('/')

    birth_date = datetime.date(int(year), int(month), int(day))
    current_date = datetime.datetime.now().date()

    date_value = str(current_date - birth_date)
    index_substring = date_value.find(' ')

    return int(date_value[0:index_substring])

def get_register_value(register):
    gender_value = get_gender_value(register['genero'])
    
    state_value = get_state_value(register['estado'])

    city_value = get_city_value(register['cidade'])

    date_value = get_days_from_date(register['data_nascimento'])

    return gender_value + state_value + city_value + date_value

def define_groups(dataset, k):
    elements = []
    groups = []
    
    for i in range(0, 1000):
        elements.append(new_dataset.iloc[[i]])

    for i in range(0, 1000):
        current_index = k * (i + 1)
        
        min_index = current_index - k
        max_index = current_index
        
        groups.append(elements[min_index:max_index])
        
    return groups

def anonymize_birth_date(group, k):
    print(list(group)[0]['data_nascimento'].to_string())

        
def anonymize_gender(group, k):
    group_copy = []
    genders = []
    
    for i in range(0, k):
        group_copy.append(list(group)[i]['genero'])
        
    for i in range(0, k):
        genders.append(group_copy[i].to_string()[group_copy[i].to_string().find(' '):][4:])
    
    if len(set(genders)) > 1:
        for i in range(0, k):
            print('---------------------------')
            print(group[i]['genero'])
            print('---------------------------')
        
            group_copy[i] = '*'
            
    
    print(group_copy)
    
def anonymize_state(group, k):
    group_copy = []
    states
   
                
def analyse(dataset, k):
    groups = define_groups(dataset, k)
    
    for i in range(0, 1000):
        anonymize_gender(groups[i], k)
    
register_value = []
for i in range(0, 1000):
    register_value.append(get_register_value(dataset.iloc[[i]]))

new_dataset = dataset

new_dataset['nome'] = '*'

new_dataset['register_value'] = register_value
new_dataset = new_dataset.sort_values(['register_value'])

analyse(dataset, 3)