'''Functions for downloading and reading MNIST data.'''

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

import os

import gzip

import collections

import numpy

from six.moves import xrange

SOURCE_URL = 'http://yann./exdb/mnist/'

Datasets = collections.namedtuple('Datasets', ['train', 'validation', 'test'])

def _read32(bytestream):

  dt = numpy.dtype(numpy.uint32).newbyteorder('>')

  return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]

def extract_images(f):

  '''Extract the images into a 4D uint8 numpy array [index, y, x, depth].

  Args:

    f: A file object that can be passed into a gzip reader.

  Returns:

    data: A 4D uint8 numpy array [index, y, x, depth].

  Raises:

    ValueError: If the bytestream does not start with 2051.

  '''

  print('Extracting', f.name)

  with gzip.GzipFile(fileobj=f) as bytestream:

    magic = _read32(bytestream)

    if magic != 2051:

      raise ValueError('Invalid magic number %d in MNIST image file: %s' %

                       (magic, f.name))

    num_images = _read32(bytestream)

    rows = _read32(bytestream)

    cols = _read32(bytestream)

    buf = bytestream.read(rows * cols * num_images)

    data = numpy.frombuffer(buf, dtype=numpy.uint8)

    data = data.reshape(num_images, rows, cols, 1)

    return data

def dense_to_one_hot(labels_dense, num_classes):

  '''Convert class labels from scalars to one-hot vectors.'''

  num_labels = labels_dense.shape[0]

  index_offset = numpy.arange(num_labels) * num_classes

  labels_one_hot = numpy.zeros((num_labels, num_classes))

  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1

  return labels_one_hot

def extract_labels(f, one_hot=False, num_classes=10):

  '''Extract the labels into a 1D uint8 numpy array [index].

  Args:

    f: A file object that can be passed into a gzip reader.

    one_hot: Does one hot encoding for the result.

    num_classes: Number of classes for the one hot encoding.

  Returns:

    labels: a 1D uint8 numpy array.

  Raises:

    ValueError: If the bystream doesn't start with 2049.

  '''

  print('Extracting', f.name)

  with gzip.GzipFile(fileobj=f) as bytestream:

    magic = _read32(bytestream)

    if magic != 2049:

      raise ValueError('Invalid magic number %d in MNIST label file: %s' %

                       (magic, f.name))

    num_items = _read32(bytestream)

    buf = bytestream.read(num_items)

    labels = numpy.frombuffer(buf, dtype=numpy.uint8)

    if one_hot:

      return dense_to_one_hot(labels, num_classes)

    return labels

class DataSet(object):

  def __init__(self,

               images,

               labels,

               fake_data=False,

               one_hot=False,

               dtype=numpy.float32,

               reshape=True):

    '''Construct a DataSet.

    one_hot arg is used only if fake_data is true.  `dtype` can be either

    `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into

    `[0, 1]`.

    '''

    #dtype = dtypes.as_dtype(dtype).base_dtype

    if dtype not in (numpy.uint8, numpy.float32):

      raise TypeError('Invalid image dtype %r, expected uint8 or float32' %

                      dtype)

    if fake_data:

      self._num_examples = 10000

      self.one_hot = one_hot

    else:

      assert images.shape[0] == labels.shape[0], (

          'images.shape: %s labels.shape: %s' % (images.shape, labels.shape))

      self._num_examples = images.shape[0]

      # Convert shape from [num examples, rows, columns, depth]

      # to [num examples, rows*columns] (assuming depth == 1)

      if reshape:

        assert images.shape[3] == 1

        images = images.reshape(images.shape[0],

                                images.shape[1] * images.shape[2])

      if dtype == numpy.float32:

        # Convert from [0, 255] -> [0.0, 1.0].

        images = images.astype(numpy.float32)

        images = numpy.multiply(images, 1.0 / 255.0)

    self._images = images

    self._labels = labels

    self._epochs_completed = 0

    self._index_in_epoch = 0

  @property

  def images(self):

    return self._images

  @property

  def labels(self):

    return self._labels

  @property

  def num_examples(self):

    return self._num_examples

  @property

  def epochs_completed(self):

    return self._epochs_completed

  def next_batch(self, batch_size, fake_data=False):

    '''Return the next `batch_size` examples from this data set.'''

    if fake_data:

      fake_image = [1] * 784

      if self.one_hot:

        fake_label = [1] + [0] * 9

      else:

        fake_label = 0

      return [fake_image for _ in xrange(batch_size)], [

          fake_label for _ in xrange(batch_size)

      ]

    start = self._index_in_epoch

    self._index_in_epoch += batch_size

    if self._index_in_epoch > self._num_examples:

      # Finished epoch

      self._epochs_completed += 1

      # Shuffle the data

      perm = numpy.arange(self._num_examples)

      numpy.random.shuffle(perm)

      self._images = self._images[perm]

      self._labels = self._labels[perm]

      # Start next epoch

      start = 0

      self._index_in_epoch = batch_size

      assert batch_size <=>

    end = self._index_in_epoch

    return self._images[start:end], self._labels[start:end]

def maybe_download(filename, work_directory, source_url):

  '''Download the data from source url, unless it's already here.

  Args:

      filename: string, name of the file in the directory.

      work_directory: string, path to working directory.

      source_url: url to download from if file doesn't exist.

  Returns:

      Path to resulting file.

  '''

  filepath = os.path.join(work_directory, filename)

  print('filepath:%s' % filepath)

  return filepath

def read_data_sets(train_dir,

                   fake_data=False,

                   one_hot=False,

                   dtype=numpy.float32,

                   reshape=True,

                   validation_size=5000):

  if fake_data:

    def fake():

      return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)

    train = fake()

    validation = fake()

    test = fake()

    return Datasets(train=train, validation=validation, test=test)

  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'

  TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'

  TEST_IMAGES = 't10k-images-idx3-ubyte.gz'

  TEST_LABELS = 't10k-labels-idx1-ubyte.gz'

  local_file = maybe_download(TRAIN_IMAGES, train_dir,

                                   SOURCE_URL + TRAIN_IMAGES)

  with open(local_file, 'rb') as f:

    train_images = extract_images(f)

  local_file = maybe_download(TRAIN_LABELS, train_dir,

                                   SOURCE_URL + TRAIN_LABELS)

  with open(local_file, 'rb') as f:

    train_labels = extract_labels(f, one_hot=one_hot)

  local_file = maybe_download(TEST_IMAGES, train_dir,

                                   SOURCE_URL + TEST_IMAGES)

  with open(local_file, 'rb') as f:

    test_images = extract_images(f)

  local_file = maybe_download(TEST_LABELS, train_dir,

                                   SOURCE_URL + TEST_LABELS)

  with open(local_file, 'rb') as f:

    test_labels = extract_labels(f, one_hot=one_hot)

  if not 0 <= validation_size=""><=>

    raise ValueError(

        'Validation size should be between 0 and {}. Received: {}.'

        .format(len(train_images), validation_size))

  validation_images = train_images[:validation_size]

  validation_labels = train_labels[:validation_size]

  train_images = train_images[validation_size:]

  train_labels = train_labels[validation_size:]

  train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)

  validation = DataSet(validation_images,

                       validation_labels,

                       dtype=dtype,

                       reshape=reshape)

  test = DataSet(test_images, test_labels, dtype=dtype, reshape=reshape)

  return Datasets(train=train, validation=validation, test=test)

def load_mnist(train_dir='MNIST-data'):

  return read_data_sets(train_dir)

# -*- coding: utf-8 -*-

import tensorflow as tf

from mnist import read_data_sets

input_data = read_data_sets('/home/gdw/PycharmProjects/projectOne/data', one_hot=True)

x = tf.placeholder('float',[None, 784])

W = tf.Variable(tf.zeros([784,10]))

b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W)+b)

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ *tf.log(y), reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.initialize_all_variables()

sess = tf.Session()

sess.run(init)

for i in range(10000):

    batch_xs, batch_ys = input_data.train.next_batch(100)

    sess.run(train_step, feed_dict={x:batch_xs, y_:batch_ys})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print sess.run(accuracy, feed_dict={x:input_data.test.images, y_:input_data.test.labels})