Merge remote-tracking branch 'wangyi/dataset' into feature/clean_mnist_v2

python/paddle/v2/dataset/cifar.py

+"""
+CIFAR Dataset.
+
+URL: https://www.cs.toronto.edu/~kriz/cifar.html
+
+the default train_creator, test_creator used for CIFAR-10 dataset.
+"""
+import cPickle
+import itertools
+import tarfile
+
+import numpy
+
+from common import download
+
+__all__ = [
+    'cifar_100_train_creator', 'cifar_100_test_creator', 'train_creator',
+    'test_creator'
+]
+
+CIFAR10_URL = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
+CIFAR10_MD5 = 'c58f30108f718f92721af3b95e74349a'
+CIFAR100_URL = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
+CIFAR100_MD5 = 'eb9058c3a382ffc7106e4002c42a8d85'
+
+
+def __read_batch__(filename, sub_name):
+    def reader():
+        def __read_one_batch_impl__(batch):
+            data = batch['data']
+            labels = batch.get('labels', batch.get('fine_labels', None))
+            assert labels is not None
+            for sample, label in itertools.izip(data, labels):
+                yield (sample / 255.0).astype(numpy.float32), int(label)
+
+        with tarfile.open(filename, mode='r') as f:
+            names = (each_item.name for each_item in f
+                     if sub_name in each_item.name)
+
+            for name in names:
+                batch = cPickle.load(f.extractfile(name))
+                for item in __read_one_batch_impl__(batch):
+                    yield item
+
+    return reader
+
+
+def cifar_100_train_creator():
+    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
+    return __read_batch__(fn, 'train')
+
+
+def cifar_100_test_creator():
+    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
+    return __read_batch__(fn, 'test')
+
+
+def train_creator():
+    """
+    Default train reader creator. Use CIFAR-10 dataset.
+    """
+    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
+    return __read_batch__(fn, 'data_batch')
+
+
+def test_creator():
+    """
+    Default test reader creator. Use CIFAR-10 dataset.
+    """
+    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
+    return __read_batch__(fn, 'test_batch')
+
+
+def unittest():
+    for _ in train_creator()():
+        pass
+    for _ in test_creator()():
+        pass
+
+
+if __name__ == '__main__':
+    unittest()

python/paddle/v2/dataset/common.py

+import requests
+import hashlib
+import os
+import shutil
+
+__all__ = ['DATA_HOME', 'download', 'md5file']
+
+DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset')
+
+if not os.path.exists(DATA_HOME):
+    os.makedirs(DATA_HOME)
+
+
+def md5file(fname):
+    hash_md5 = hashlib.md5()
+    f = open(fname, "rb")
+    for chunk in iter(lambda: f.read(4096), b""):
+        hash_md5.update(chunk)
+    f.close()
+    return hash_md5.hexdigest()
+
+
+def download(url, module_name, md5sum):
+    dirname = os.path.join(DATA_HOME, module_name)
+    if not os.path.exists(dirname):
+        os.makedirs(dirname)
+
+    filename = os.path.join(dirname, url.split('/')[-1])
+    if not (os.path.exists(filename) and md5file(filename) == md5sum):
+        # If file doesn't exist or MD5 doesn't match, then download.
+        r = requests.get(url, stream=True)
+        with open(filename, 'w') as f:
+            shutil.copyfileobj(r.raw, f)
+
+    return filename

python/paddle/v2/dataset/config.py

-import os
-
-__all__ = ['DATA_HOME']
-
-DATA_HOME = os.path.expanduser('~/.cache/paddle_data_set')
-
-if not os.path.exists(DATA_HOME):
-    os.makedirs(DATA_HOME)

python/paddle/v2/dataset/mnist.py

-import sklearn.datasets.mldata
-import sklearn.model_selection
+import paddle.v2.dataset.common
+import subprocess
 import numpy
-from config import DATA_HOME
 
-__all__ = ['train_creator', 'test_creator']
+__all__ = ['train', 'test']
 
+URL_PREFIX = 'http://yann.lecun.com/exdb/mnist/'
+
+TEST_IMAGE_URL = URL_PREFIX + 't10k-images-idx3-ubyte.gz'
+TEST_IMAGE_MD5 = '25e3cc63507ef6e98d5dc541e8672bb6'
+TEST_LABEL_URL = URL_PREFIX + 't10k-labels-idx1-ubyte.gz'
+TEST_LABEL_MD5 = '4e9511fe019b2189026bd0421ba7b688'
+TRAIN_IMAGE_URL = URL_PREFIX + 'train-images-idx3-ubyte.gz'
+TRAIN_IMAGE_MD5 = 'f68b3c2dcbeaaa9fbdd348bbdeb94873'
+TRAIN_LABEL_URL = URL_PREFIX + 'train-labels-idx1-ubyte.gz'
+TRAIN_LABEL_MD5 = 'd53e105ee54ea40749a09fcbcd1e9432'
 
-def __mnist_reader_creator__(data, target):
-    def reader():
-        n_samples = data.shape[0]
-        for i in xrange(n_samples):
-            yield (data[i] / 255.0).astype(numpy.float32), int(target[i])
 
-    return reader
+def reader_creator(image_filename, label_filename, buffer_size):
+    def reader():
+        # According to http://stackoverflow.com/a/38061619/724872, we
+        # cannot use standard package gzip here.
+        m = subprocess.Popen(["zcat", image_filename], stdout=subprocess.PIPE)
+        m.stdout.read(16)  # skip some magic bytes
 
+        l = subprocess.Popen(["zcat", label_filename], stdout=subprocess.PIPE)
+        l.stdout.read(8)  # skip some magic bytes
 
-TEST_SIZE = 10000
-X_train = None
-X_test = None
-y_train = None
-y_test = None
+        while True:
+            labels = numpy.fromfile(
+                l.stdout, 'ubyte', count=buffer_size).astype("int")
 
+            if labels.size != buffer_size:
+                break  # numpy.fromfile returns empty slice after EOF.
 
-def __initialize_dataset__():
-    global X_train, X_test, y_train, y_test
-    if X_train is not None:
-        return
-    data = sklearn.datasets.mldata.fetch_mldata(
-        "MNIST original", data_home=DATA_HOME)
-    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
-        data.data, data.target, test_size=TEST_SIZE, random_state=0)
+            images = numpy.fromfile(
+                m.stdout, 'ubyte', count=buffer_size * 28 * 28).reshape(
+                    (buffer_size, 28 * 28)).astype('float32')
 
+            images = images / 255.0 * 2.0 - 1.0
 
-def train_creator():
-    __initialize_dataset__()
-    return __mnist_reader_creator__(X_train, y_train)
+            for i in xrange(buffer_size):
+                yield images[i, :], labels[i]
 
+        m.terminate()
+        l.terminate()
 
-def test_creator():
-    __initialize_dataset__()
-    return __mnist_reader_creator__(X_test, y_test)
+    return reader()
 
 
-def unittest():
-    assert len(list(test_creator()())) == TEST_SIZE
+def train():
+    return reader_creator(
+        paddle.v2.dataset.common.download(TRAIN_IMAGE_URL, 'mnist',
+                                          TRAIN_IMAGE_MD5),
+        paddle.v2.dataset.common.download(TRAIN_LABEL_URL, 'mnist',
+                                          TRAIN_LABEL_MD5), 100)
 
 
-if __name__ == '__main__':
-    unittest()
+def test():
+    return reader_creator(
+        paddle.v2.dataset.common.download(TEST_IMAGE_URL, 'mnist',
+                                          TEST_IMAGE_MD5),
+        paddle.v2.dataset.common.download(TEST_LABEL_URL, 'mnist',
+                                          TEST_LABEL_MD5), 100)

python/paddle/v2/dataset/movielens.py

+import zipfile
+from common import download
+import re
+import random
+import functools
+
+__all__ = ['train_creator', 'test_creator']
+
+
+class MovieInfo(object):
+    def __init__(self, index, categories, title):
+        self.index = int(index)
+        self.categories = categories
+        self.title = title
+
+    def value(self):
+        return [
+            self.index, [CATEGORIES_DICT[c] for c in self.categories],
+            [MOVIE_TITLE_DICT[w.lower()] for w in self.title.split()]
+        ]
+
+
+class UserInfo(object):
+    def __init__(self, index, gender, age, job_id):
+        self.index = int(index)
+        self.is_male = gender == 'M'
+        self.age = [1, 18, 25, 35, 45, 50, 56].index(int(age))
+        self.job_id = int(job_id)
+
+    def value(self):
+        return [self.index, 0 if self.is_male else 1, self.age, self.job_id]
+
+
+MOVIE_INFO = None
+MOVIE_TITLE_DICT = None
+CATEGORIES_DICT = None
+USER_INFO = None
+
+
+def __initialize_meta_info__():
+    fn = download(
+        url='http://files.grouplens.org/datasets/movielens/ml-1m.zip',
+        md5='c4d9eecfca2ab87c1945afe126590906')
+    global MOVIE_INFO
+    if MOVIE_INFO is None:
+        pattern = re.compile(r'^(.*)\((\d+)\)$')
+        with zipfile.ZipFile(file=fn) as package:
+            for info in package.infolist():
+                assert isinstance(info, zipfile.ZipInfo)
+                MOVIE_INFO = dict()
+                title_word_set = set()
+                categories_set = set()
+                with package.open('ml-1m/movies.dat') as movie_file:
+                    for i, line in enumerate(movie_file):
+                        movie_id, title, categories = line.strip().split('::')
+                        categories = categories.split('|')
+                        for c in categories:
+                            categories_set.add(c)
+                        title = pattern.match(title).group(1)
+                        MOVIE_INFO[int(movie_id)] = MovieInfo(
+                            index=movie_id, categories=categories, title=title)
+                        for w in title.split():
+                            title_word_set.add(w.lower())
+
+                global MOVIE_TITLE_DICT
+                MOVIE_TITLE_DICT = dict()
+                for i, w in enumerate(title_word_set):
+                    MOVIE_TITLE_DICT[w] = i
+
+                global CATEGORIES_DICT
+                CATEGORIES_DICT = dict()
+                for i, c in enumerate(categories_set):
+                    CATEGORIES_DICT[c] = i
+
+                global USER_INFO
+                USER_INFO = dict()
+                with package.open('ml-1m/users.dat') as user_file:
+                    for line in user_file:
+                        uid, gender, age, job, _ = line.strip().split("::")
+                        USER_INFO[int(uid)] = UserInfo(
+                            index=uid, gender=gender, age=age, job_id=job)
+    return fn
+
+
+def __reader__(rand_seed=0, test_ratio=0.1, is_test=False):
+    fn = __initialize_meta_info__()
+    rand = random.Random(x=rand_seed)
+    with zipfile.ZipFile(file=fn) as package:
+        with package.open('ml-1m/ratings.dat') as rating:
+            for line in rating:
+                if (rand.random() < test_ratio) == is_test:
+                    uid, mov_id, rating, _ = line.strip().split("::")
+                    uid = int(uid)
+                    mov_id = int(mov_id)
+                    rating = float(rating) * 2 - 5.0
+
+                    mov = MOVIE_INFO[mov_id]
+                    usr = USER_INFO[uid]
+                    yield usr.value() + mov.value() + [[rating]]
+
+
+def __reader_creator__(**kwargs):
+    return lambda: __reader__(**kwargs)
+
+
+train_creator = functools.partial(__reader_creator__, is_test=False)
+test_creator = functools.partial(__reader_creator__, is_test=True)
+
+
+def unittest():
+    for train_count, _ in enumerate(train_creator()()):
+        pass
+    for test_count, _ in enumerate(test_creator()()):
+        pass
+
+    print train_count, test_count
+
+
+if __name__ == '__main__':
+    unittest()

python/paddle/v2/dataset/tests/common_test.py

+import paddle.v2.dataset.common
+import unittest
+import tempfile
+
+
+class TestCommon(unittest.TestCase):
+    def test_md5file(self):
+        _, temp_path = tempfile.mkstemp()
+        with open(temp_path, 'w') as f:
+            f.write("Hello\n")
+        self.assertEqual('09f7e02f1290be211da707a266f153b3',
+                         paddle.v2.dataset.common.md5file(temp_path))
+
+    def test_download(self):
+        yi_avatar = 'https://avatars0.githubusercontent.com/u/1548775?v=3&s=460'
+        self.assertEqual(
+            paddle.v2.dataset.common.DATA_HOME + '/test/1548775?v=3&s=460',
+            paddle.v2.dataset.common.download(
+                yi_avatar, 'test', 'f75287202d6622414c706c36c16f8e0d'))
+
+
+if __name__ == '__main__':
+    unittest.main()

python/paddle/v2/dataset/tests/mnist_test.py

+import paddle.v2.dataset.mnist
+import unittest
+
+
+class TestMNIST(unittest.TestCase):
+    def check_reader(self, reader):
+        sum = 0
+        for l in reader:
+            self.assertEqual(l[0].size, 784)
+            self.assertEqual(l[1].size, 1)
+            self.assertLess(l[1], 10)
+            self.assertGreaterEqual(l[1], 0)
+            sum += 1
+        return sum
+
+    def test_train(self):
+        self.assertEqual(
+            self.check_reader(paddle.v2.dataset.mnist.train()), 60000)
+
+    def test_test(self):
+        self.assertEqual(
+            self.check_reader(paddle.v2.dataset.mnist.test()), 10000)
+
+
+if __name__ == '__main__':
+    unittest.main()