#%%

"""
Credits: This code is adapted from the textbook "Deep Learning with Python", 
2nd Edition, by François Chollet. 
"""

#%% This code should be run only once, to set aside 20% of the training set
#   for use as a validation set.
#   If this code is run multiple times, it will keep removing from the 
#   training set and adding to the validation set.
#
#   If your data comes from the aclImdb.zip file posted on the class website, 
#   DO NOT use this code, as it has already been applied to this data.

import os, pathlib, shutil, random
base_dir = pathlib.Path("../../../../../home/cse4392_data/20_text/aclImdb")
val_dir = base_dir / "val"
train_dir = base_dir / "train"

for category in ("neg", "pos"):
    os.makedirs(val_dir / category)
    files = os.listdir(train_dir / category)
    random.Random(1337).shuffle(files)
    num_val_samples = int(0.2 * len(files))
    val_files = files[-num_val_samples:]

    for fname in val_files:
        shutil.move(train_dir / category / fname, val_dir / category / fname)