ium_z434743/z434743-create-dataset.py

import pandas
import os
from sklearn.model_selection import train_test_split


CUTOFF = int(os.environ['CUTOFF'])

movies = pandas.read_csv('./ium_z434743/rotten_tomatoes_movies.csv',
                              engine='python',
                              encoding='ISO-8859-1',
                              sep=',')

movies = movies.dropna()
movies = movies.drop(movies.columns[[0, 1, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15]], axis=1)


movies = movies.sample(CUTOFF)

X = movies.copy()
Y = pandas.DataFrame(movies.pop('audienceScore'))


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)
Y_test.to_csv('Y_test.csv', index=False)
Y_train.to_csv('Y_train.csv', index=False)
Y_dev.to_csv('Y_dev.csv', index=False)