import os, shutil
original_dataset_dir = '/Users/arnec/OneDrive - Karel de Grote Hogeschool/School/2019-2020/Crysco/Week 1/kaggle_original_data/train'

# Location to store smaller dataset
base_dir = '/Users/arnec/OneDrive - Karel de Grote Hogeschool/School/2019-2020/Crysco/Week 1/cats_and_dogs_small'
os.mkdir(base_dir)

train_dir = os.path.join(base_dir, 'train') # training directory
os.mkdir(train_dir)
validation_dir = os.path.join(base_dir, 'validation') # validation directory
os.mkdir(validation_dir)
test_dir = os.path.join(base_dir, 'test') # test directory
os.mkdir(test_dir)

train_cats_dir = os.path.join(train_dir, 'cats') # directory with trainging cat pictures
os.mkdir(train_cats_dir)

train_dogs_dir = os.path.join(train_dir, 'dogs') # directory with training dog pictures
os.mkdir(train_dogs_dir)

validation_cats_dir = os.path.join(validation_dir, 'cats') # directory with validation cat pictures
os.mkdir(validation_cats_dir)

validation_dogs_dir = os.path.join(validation_dir, 'dogs') # directory with validation dog pictures
os.mkdir(validation_dogs_dir)
test_cats_dir = os.path.join(test_dir, 'cats') # directory with test cat pictures
os.mkdir(test_cats_dir)

test_dogs_dir = os.path.join(test_dir, 'dogs') # directory with test dog pictures
os.mkdir(test_dogs_dir)

fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(train_cats_dir, fname)
  shutil.copyfile(src, dst)
  fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]

for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(validation_cats_dir, fname)
  shutil.copyfile(src, dst)
  fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]

for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(test_cats_dir, fname)
  shutil.copyfile(src, dst)

fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(train_dogs_dir, fname)
  shutil.copyfile(src, dst)
  fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]

for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(validation_dogs_dir, fname)
  shutil.copyfile(src, dst)
  fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]

for fname in fnames:
  src = os.path.join(original_dataset_dir, fname)
  dst = os.path.join(test_dogs_dir, fname)
  shutil.copyfile(src, dst)

print('total training cat images:', len(os.listdir(train_cats_dir)))
# total training cat images: 1000
print('total training dog images:', len(os.listdir(train_dogs_dir)))
# total training dog images: 1000
print('total validation cat images:', len(os.listdir(validation_cats_dir)))
# total validation cat images: 500
print('total validation dog images:', len(os.listdir(validation_dogs_dir)))
# total validation dog images: 500
print('total test cat images:', len(os.listdir(test_cats_dir)))
# total test cat images: 500
print('total test dog images:', len(os.listdir(test_dogs_dir)))
# total test dog images: 500