PL2023/TPC1/tpc1.py

import matplotlib.pyplot as plt

# idade -> i, sexo -> s, tensao -> t, colesterol -> c, batimento -> b, doenca -> d
# estrutura de dados: [{"i": 1 , "s" : F | M}]
data = []

def readFile(filename):
    f = open(filename, 'r')
    lines = f.readlines()
    lines.pop(0)
    for line in lines:
        values = line.split(',')
        idade = int(values[0])
        sexo = values[1]
        tensao = int(values[2])
        colesterol = int(values[3])
        batimento = int(values[4])
        temDoenca = bool(values[5])
        data_entry = {
                      'i': idade,
                      's': sexo,
                      't': tensao,
                      'c': colesterol,
                      'b': batimento,
                      'd': temDoenca
                }
        data.append(data_entry)

def distrib_sexo():
    dist = {}
    size_of_data = len(data)
    for entry in data:
        if entry['d']:
            if dist.keys().__contains__(entry['s']):
                dist[entry['s']] += 1
            else:
                dist[entry['s']] = 1
    for (k,v) in dist.items():
        percentage = v/size_of_data 
        dist[k] = percentage 
    return dist


def distrib_etaria():
    dist = {}
    size_of_data = len(data)

    for entry in data:
        if entry['i'] >= 30 and entry['d']:
            lim_inf = (entry['i'] // 5) * 5
            lim_sup = lim_inf + 4
            position = str(lim_inf) + '-' + str(lim_sup)
            if dist.keys().__contains__(position):
                dist[position] += 1
            else:
                dist[position] = 1

    for (k,v) in dist.items():
        percentage = v/size_of_data 
        dist[k] = percentage 
    return dist


def distrib_colesterol():
    dist = {}
    size_of_data = len(data)
    
    for entry in data:
        lim_inf = (entry['c'] // 10) * 10
        lim_sup = lim_inf + 9
        position = str(lim_inf) + '-' + str(lim_sup)
        if dist.keys().__contains__(position):
            dist[position] += 1
        else:
            dist[position] = 1

    for (k,v) in dist.items():
        percentage = v/size_of_data 
        dist[k] = percentage 
    return dist


def show_distrib(type,dist):
    title_key = "Key"
    title_val = "Valor"
    match type:
        case 0:
            title_key = "Sexo"
        case 1:
            title_key = "Faixa Etaria"
        case 2:
            title_key = "Colesterol"
    max_key_len = max(max(len(str(k)) for k in dist.keys()),len(title_key))
    max_val_len = max(max(len(str(v)) for v in dist.values()),len(title_val))

    print('+' + '-'*(max_key_len+2) + '+' + '-'*(max_val_len+2) + '+')
    print('| {:{}} | {:{}} |'.format(title_key, max_key_len, title_val, max_val_len))
    print('+' + '-'*(max_key_len+2) + '+' + '-'*(max_val_len+2) + '+')
    for title_key, title_val in sorted(dist.items()):
        print('| {:{}} | {:{}} |'.format(title_key, max_key_len, title_val, max_val_len))
    print('+' + '-'*(max_key_len+2) + '+' + '-'*(max_val_len+2) + '+')
     

def main():
    readFile("myheart.csv")
    dist_sexo = distrib_sexo()
    dist_etaria = distrib_etaria()
    dist_colesterol = distrib_colesterol()
    show_distrib(1,dist_etaria)
     

if __name__ == "__main__":
    main()