(새 문서: <source lang="python3"> import csv import pickle with open("./NHIS_OPEN_GJ_2015.csv") as csvfile: reader = csv.reader(csvfile) header = next(reader, None) #header = {head...) |
|||
26번째 줄: | 26번째 줄: | ||
table.append(nrow) | table.append(nrow) | ||
− | + | with open("./preprocessing2015.pkl","wb+") as fw: | |
+ | pickle.dump(table, fw, protocol = pickle.HIGHEST_PROTOCOL) | ||
</source> | </source> |
2018년 11월 14일 (수) 17:20 판
import csv
import pickle
with open("./NHIS_OPEN_GJ_2015.csv") as csvfile:
reader = csv.reader(csvfile)
header = next(reader, None)
#header = {header[i]:i for i in range(0, len(header))}
table = list()
for row in reader:
row = {header[i] : row[i] for i in range(len(header))}
if row["신장(5Cm단위)"] == "" or row["체중(5Kg 단위)"] == "" or row["허리둘레"] == "":
continue
bmi = round(10000 * int(row["신장(5Cm단위)"]) / (int(row["체중(5Kg 단위)"]) ** 2), 2)
label = 1
if bmi > 40:label = 4
if bmi > 35:label = 3
if bmi > 30:label = 2
nrow = {
"height":int(row["신장(5Cm단위)"]),
"weight":int(row["체중(5Kg 단위)"]),
"waist":int(row["허리둘레"]),
"overweight":label
}
table.append(nrow)
with open("./preprocessing2015.pkl","wb+") as fw:
pickle.dump(table, fw, protocol = pickle.HIGHEST_PROTOCOL)