ium_z434686/create-dataset.py

import pandas
import os
from sklearn.model_selection import train_test_split


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

# READ DATA
video_games = pandas.read_csv('./ium_z434686/Video_Games_Sales_as_at_22_Dec_2016.csv',
                              engine='python',
                              encoding='ISO-8859-1',
                              sep=',')
# DROP NA FIELDS
video_games = video_games.dropna()

# CUT OFF DATASET TO X LINES
video_games = video_games.sample(CUTOFF)

X, Y = video_games, video_games

# SPLIT BETWEEN DEV, TRAINS, AND TEST
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)