add create-dataset python file

This commit is contained in:
piotrwrzodak 2023-04-20 21:03:45 +02:00
parent 8eb731b53f
commit 1afa0cf50e

17
create-dataset.py Normal file
View File

@ -0,0 +1,17 @@
import pandas as pd
import os
import numpy as np
cutoff = int(os.environ['CUTOFF'])
data = pd.read_csv('./ium_z444510/barcelona_weekends.csv')
data = data.sample(cutoff)
data = data.iloc[:, 1:]
train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
[int(.6 * len(data)), int(.8 * len(data))])
train_set.to_csv('train.csv', index=False)
dev_set.to_csv('dev.csv', index=False)
test_set.to_csv('test.csv', index=False)