import pandas as pd
import os
import numpy as np


cutoff = 10

data = pd.read_csv('./data/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('data/barcelona_weekends.train.csv', index=False)
dev_set.to_csv('data/barcelona_weekends.dev.csv', index=False)
test_set.to_csv('data/barcelona_weekends.test.csv', index=False)


check = pd.read_csv('./train.csv')
print(check.head())