19 lines
603 B
Python
19 lines
603 B
Python
|
import pandas
|
||
|
|
import os
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
|
||
|
|
CUTOFF = int(os.environ['CUTOFF'])
|
||
|
|
adults = pandas.read_csv('./ium_z444439/adult.csv', engine='python', encoding='ISO-8859-1', sep=',')
|
||
|
|
adults = adults.dropna()
|
||
|
|
|
||
|
|
adults = adults.sample(CUTOFF)
|
||
|
|
|
||
|
|
X, Y = adults, adults
|
||
|
|
|
||
|
|
X_train, X_temp, Y_train, Y_temp = train_test_split(X, Y, test_size=0.3, random_state=1)
|
||
|
|
X_dev, X_test, Y_dev, Y_test = train_test_split(X_temp, Y_temp, test_size=0.3, random_state=1)
|
||
|
|
|
||
|
|
X_train.to_csv('X_train.csv', index=False)
|
||
|
|
X_dev.to_csv('X_dev.csv', index=False)
|
||
|
|
X_test.to_csv('X_test.csv', index=False)
|