def prepare_dataset(data_dir):
# download dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/00229/Skin_NonSkin.txt"
save_path = os.path.join(data_dir, url.split("/")[-1])
try:
download_url(url, save_path)
except Exception as e:
print('Error downloading dataset: %s' % str(e))
sys.exit(1)
# read the dataset
data = list()
for line in open(save_path, "r").readlines():
data.append(line.strip("\n").split("\t"))
data = np.asarray(data).astype(float)
n_samples = len(data)
random_idx = np.arange(0, n_samples)
np.random.shuffle(random_idx)
data = data[random_idx]
x, y = data[:, :3], data[:, 3:]
y = (y - 1).astype(int)
train_split = int(n_samples * 0.7)
valid_split = int(n_samples * 0.85)
train_set = [x[:train_split, :], y[:train_split]]
valid_set = [x[train_split:valid_split, :], y[train_split:valid_split]]
test_set = [x[valid_split:, :], y[valid_split:]]
return [train_set, valid_set, test_set]
def prepare_dataset(data_dir):
url = "http://deeplearning.net/data/mnist/mnist.pkl.gz"
save_path = os.path.join(data_dir, url.split("/")[-1])
print("Preparing MNIST dataset ...")
try:
download_url(url, save_path)
except Exception as e:
print('Error downloading dataset: %s' % str(e))
sys.exit(1)
# load the dataset
with gzip.open(save_path, "rb") as f:
return pickle.load(f, encoding="latin1")
def prepare_dataset(data_dir):
url = "https://raw.githubusercontent.com/mnielsen/neural-networks-and-deep-learning/master/data/mnist.pkl.gz"
save_path = os.path.join(data_dir, url.split("/")[-1])
print("Preparing MNIST dataset ...")
try:
download_url(url, save_path)
except Exception as e:
print('Error downloading dataset: %s' % str(e))
sys.exit(1)
# load the dataset
with gzip.open(save_path, "rb") as f:
return pickle.load(f, encoding="latin1")
def prepare_dataset(data_dir):
url = "http://deeplearning.net/data/mnist/mnist.pkl.gz"
save_path = os.path.join(data_dir, url.split("/")[-1])
print("Preparing MNIST dataset ...")
try:
download_url(url, save_path)
except Exception as e:
print("Error downloading dataset: %s" % str(e))
sys.exit(1)
# load the dataset
with gzip.open(save_path, "rb") as f:
train, valid, test = pickle.load(f, encoding="latin1")
# return all X from train/valid/test
X = np.concatenate([train[0], valid[0], test[0]])
y = np.concatenate([train[1], valid[1], test[1]])
return X, y
