from sklearn.naive_bayes import GaussianNB
# 0：晴 1：阴 2：降水 3：多云
data_table =[["date", "weather"],[1, 0],[2, 1],[3, 2],
             [4, 1],[5, 2],[6, 0],[7, 0],[8, 3],[9, 1],[10, 1]]
#当天的天气
X = [[0], [1], [2], [1], [2], [0], [0], [3], [1]]
#当天的天气对应后一天的天气
y = [1, 2, 1, 2, 0, 0, 3, 1, 1]
#现在把训练数据和对应的分类放入分类器中进行训练
clf = GaussianNB().fit(X, y)
p = [[1]]
print(clf.predict(p))

import tensorflow as tf
hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()
print(sess.run(hello))
a = tf.constant(10)
b = tf.constant(32)
print(sess.run(a + b))

# ex-01.py
import tensorflow as tf
import numpy as np

#create some training data
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*1 + 3

print ("x_data:")
print (x_data)

print ("y_data:")
print( y_data)

#create the weights and bias variables
weights = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
print ("weights before initializing:")
print (weights)

biases = tf.Variable(tf.zeros([1]))
print ("bias before initializing:")
print (biases)

#predict (fit) value
y = weights*x_data + biases

#loss function
loss = tf.reduce_mean(tf.square(y - y_data))

#optimizer definition
optimizer = tf.train.GradientDescentOptimizer(0.1)

#train definition
train = optimizer.minimize(loss)

#initialiing the variables
init = tf.initialize_all_variables()

#session definition and active
sess = tf.Session()
sess.run(init)

#train the model
for step in range(501):
    sess.run(train)
    if step % 10 == 0:
        print (step,sess.run(weights),sess.run(biases))

# ex-02.py
import tensorflow as tf

matrix1 = tf.constant([[3,3]])

matrix2 = tf.constant([[1],
                        [2]])

#matrix multiply
product = tf.matmul(matrix1, matrix2)

#method1
#sess = tf.Session()
#result = sess.run(product)
#print "result:",result
#sess.close()

#method2
with tf.Session() as sess:
    result2 = sess.run(product)
    print ("result2:",result2)

# ex-03.py
import tensorflow as tf

state = tf.Variable(10, name='counter')

print( state.name)

one = tf.constant(1)

new_value = tf.add(state, one)

update = tf.assign(state, new_value)

#this initializing is very important
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for x in range(10):
        sess.run(update)
    # must do sess.run to operate the variables
        print(sess.run(state))

# ex-04.py
import tensorflow as tf

input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)

output = input1 * input2

with tf.Session() as sess:
    print(sess.run(output, feed_dict={input1: 4, input2: 2}))
    print(sess.run(output, feed_dict={input1: [4,2], input2: [2,7]}))

# ex-05.py
import tensorflow as tf
import numpy as np

def add_layer(inputs, in_size, out_size, activation_function=None):
    weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1,out_size]))
    wx_b = tf.matmul(inputs, weights) + biases
    if activation_function is None:
        outputs = wx_b
    else:
        outputs = activation_function(wx_b)
    return outputs

#make some input value
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) + noise

xs = tf.placeholder(tf.float32, [None,1])
ys = tf.placeholder(tf.float32, [None,1])

layer1 = add_layer(xs, 1, 10, activation_function=tf.nn.sigmoid)
prediction = add_layer(layer1, 10, 1, activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

train = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

init = tf.global_variables_initializer()

sess = tf.Session()
sess.run(init)

for x in range(1000):
    sess.run(train, feed_dict = { xs: x_data, ys: y_data})
    if x % 10==0:
        print (sess.run(loss, feed_dict={xs:x_data, ys: y_data}))

import time
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

def add_layer(inputs, in_size, out_size, activation_function=None):
    weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1,out_size]))
    wx_b = tf.matmul(inputs, weights) + biases
    if activation_function is None:
        outputs = wx_b
    else:
        outputs = activation_function(wx_b)
    return outputs

#make some input value
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) + noise

xs = tf.placeholder(tf.float32, [None,1])
ys = tf.placeholder(tf.float32, [None,1])

layer1 = add_layer(xs, 1, 10, activation_function=tf.nn.sigmoid)
prediction = add_layer(layer1, 10, 1, activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

train = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.global_variables_initializer()

sess = tf.Session()
sess.run(init)

#added coding
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data, y_data)
plt.ion()
plt.show()

for x in range(1000):
    sess.run(train, feed_dict = { xs: x_data, ys: y_data})
    if x % 10==0:
        # print (sess.run(loss, feed_dict={xs:x_data, ys: y_data}))
        
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction, feed_dict={xs:x_data})
        lines = ax.plot(x_data, prediction_value, 'r-', lw=5)
        plt.pause(0.1)

import time
for i in [1,2,34,5]:
    print(i)
    time.sleep(0.1)

import tensorflow as tf

a = tf.constant(5, name="input_a")
b = tf.constant(3, name="input_b")
c = tf.multiply(a, b, name="mul_c")
d = tf.add(a, b, name="add_d")
e = tf.add(c, d, name="add_e")

sess = tf.Session()
sess.run(e)

writer = tf.summary.FileWriter("E:/tensorflow/graph", tf.get_default_graph())
writer.close()

import tensorflow as tf
import gzip
import numpy
import collections
from tensorflow.python.framework import random_seed
from tensorflow.python.framework import dtypes
#from tensorflow.examples.tutorials.mnist import input_data

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 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_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 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

def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=tf.float32,
                   reshape=True,
                   validation_size=5000,
                   seed=None):
  '''
  if fake_data:
    def fake():
      return DataSet(
          [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)
  
    train = fake()
    validation = fake()
    test = fake()
    return base.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 = '/home/gao/dl_learning/py-example/MNIST_data/' + TRAIN_IMAGES
  with open(local_file, 'rb') as f:
    train_images = extract_images(f)

                                   
  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TRAIN_LABELS
  with open(local_file, 'rb') as f:
    train_labels = extract_labels(f, one_hot=one_hot)

  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TEST_IMAGES
  with open(local_file, 'rb') as f:
    test_images = extract_images(f)

  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TEST_LABELS
     
  with open(local_file, 'rb') as f:
    test_labels = extract_labels(f, one_hot=one_hot)

  if not 0 <= validation_size <= len(train_images):
    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:]

  options = dict(dtype=dtype, reshape=reshape, seed=seed)
  
  train = DataSet(train_images, train_labels, **options)
  validation = DataSet(validation_images, validation_labels, **options)
  test = DataSet(test_images, test_labels, **options)
  
  return Datasets(train=train, validation=validation, test=test)

class DataSet(object):

  def __init__(self,
               images,
               labels,
               fake_data=False,
               one_hot=False,
               dtype=tf.float32,
               reshape=True,
               seed=None):
    """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]`.  Seed arg provides for convenient deterministic testing.
    """
    seed1, seed2 = random_seed.get_seed(seed)
    # If op level seed is not set, use whatever graph level seed is returned
    numpy.random.seed(seed1 if seed is None else seed2)
    dtype = dtypes.as_dtype(dtype).base_dtype
    if dtype not in (dtypes.uint8, dtypes.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 == dtypes.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, shuffle=True):
    """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
    # Shuffle for the first epoch
    if self._epochs_completed == 0 and start == 0 and shuffle:
      perm0 = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm0)
      self._images = self.images[perm0]
      self._labels = self.labels[perm0]
    # Go to the next epoch
    if start + batch_size > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Get the rest examples in this epoch
      rest_num_examples = self._num_examples - start
      images_rest_part = self._images[start:self._num_examples]
      labels_rest_part = self._labels[start:self._num_examples]
      # Shuffle the data
      if shuffle:
        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 - rest_num_examples
      end = self._index_in_epoch
      images_new_part = self._images[start:end]
      labels_new_part = self._labels[start:end]
      return numpy.concatenate((images_rest_part, images_new_part), axis=0) , numpy.concatenate((labels_rest_part, labels_new_part), axis=0)
    else:
      self._index_in_epoch += batch_size
      end = self._index_in_epoch
      return self._images[start:end], self._labels[start:end]

################################################################
#from here to operate the network

mnist = read_data_sets('MNIST_data', one_hot=True)

def add_layer(inputs, in_size, out_size, activation_function=None):
  weights = tf.Variable(tf.random_normal([in_size, out_size]))
  biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
  wx_b = tf.matmul(inputs, weights) + biases
  if activation_function is None:
    outputs = wx_b
  else:
    outputs = activation_function(wx_b,)
  return outputs

xs = tf.placeholder(tf.float32, [None, 28*28])
ys = tf.placeholder(tf.float32, [None, 10])

def compute_accuracy(v_xs, v_ys):
  global prediction
  y_pre = sess.run(prediction, feed_dict={xs: v_xs})
  correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  result = sess.run(accuracy, feed_dict={xs:v_xs, ys:v_ys})
  return result

prediction = add_layer(xs, 784, 10, activation_function = tf.nn.softmax)

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

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)

sess = tf.Session()

sess.run(tf.initialize_all_variables())

for i in range(10000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict = {xs: batch_xs, ys: batch_ys})
  if i % 50 ==0:
    print "step:",i,", ",compute_accuracy(mnist.test.images, mnist.test.labels)

# ex-10-ml.py

# import tensorflow as tf
import gzip
import numpy
import collections
from tensorflow.python.framework import random_seed
from tensorflow.python.framework import dtypes
#from tensorflow.examples.tutorials.mnist import input_data

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 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_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 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

def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=tf.float32,
                   reshape=True,
                   validation_size=5000,
                   seed=None):
  '''
  if fake_data:
    def fake():
      return DataSet(
          [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)
  
    train = fake()
    validation = fake()
    test = fake()
    return base.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 = '/home/gao/dl_learning/py-example/MNIST_data/' + TRAIN_IMAGES
  with open(local_file, 'rb') as f:
    train_images = extract_images(f)

                                   
  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TRAIN_LABELS
  with open(local_file, 'rb') as f:
    train_labels = extract_labels(f, one_hot=one_hot)

  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TEST_IMAGES
  with open(local_file, 'rb') as f:
    test_images = extract_images(f)

  local_file = '/home/gao/dl_learning/py-example/MNIST_data/' + TEST_LABELS
     
  with open(local_file, 'rb') as f:
    test_labels = extract_labels(f, one_hot=one_hot)

  if not 0 <= validation_size <= len(train_images):
    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:]

  options = dict(dtype=dtype, reshape=reshape, seed=seed)
  
  train = DataSet(train_images, train_labels, **options)
  validation = DataSet(validation_images, validation_labels, **options)
  test = DataSet(test_images, test_labels, **options)
  
  return Datasets(train=train, validation=validation, test=test)

class DataSet(object):

  def __init__(self,
               images,
               labels,
               fake_data=False,
               one_hot=False,
               dtype=tf.float32,
               reshape=True,
               seed=None):
    """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]`.  Seed arg provides for convenient deterministic testing.
    """
    seed1, seed2 = random_seed.get_seed(seed)
    # If op level seed is not set, use whatever graph level seed is returned
    numpy.random.seed(seed1 if seed is None else seed2)
    dtype = dtypes.as_dtype(dtype).base_dtype
    if dtype not in (dtypes.uint8, dtypes.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 == dtypes.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, shuffle=True):
    """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
    # Shuffle for the first epoch
    if self._epochs_completed == 0 and start == 0 and shuffle:
      perm0 = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm0)
      self._images = self.images[perm0]
      self._labels = self.labels[perm0]
    # Go to the next epoch
    if start + batch_size > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Get the rest examples in this epoch
      rest_num_examples = self._num_examples - start
      images_rest_part = self._images[start:self._num_examples]
      labels_rest_part = self._labels[start:self._num_examples]
      # Shuffle the data
      if shuffle:
        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 - rest_num_examples
      end = self._index_in_epoch
      images_new_part = self._images[start:end]
      labels_new_part = self._labels[start:end]
      return numpy.concatenate((images_rest_part, images_new_part), axis=0) , numpy.concatenate((labels_rest_part, labels_new_part), axis=0)
    else:
      self._index_in_epoch += batch_size
      end = self._index_in_epoch
      return self._images[start:end], self._labels[start:end]

################################################################


mnist = read_data_sets('MNIST_data', one_hot=True)

def add_layer(inputs, in_size, out_size, activation_function=None):
  weights = tf.Variable(tf.random_normal([in_size, out_size]))
  #biases = tf.Variable(tf.zeros([1, out_size]) + 100)
  biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
  wx_b = tf.matmul(inputs, weights) + biases
  if activation_function is None:
    outputs = wx_b
  else:
    outputs = activation_function(wx_b,)
  return outputs

xs = tf.placeholder(tf.float32, [None, 28*28])
ys = tf.placeholder(tf.float32, [None, 10])

def compute_accuracy(v_xs, v_ys):
  global prediction
  y_pre = sess.run(prediction, feed_dict={xs: v_xs})
  correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  result = sess.run(accuracy, feed_dict={xs:v_xs, ys:v_ys})
  return result

#layer1 = add_layer(xs, 784, 50, activation_function = tf.nn.tanh)
#layer1 = add_layer(xs, 784, 30, activation_function = tf.nn.sigmoid)
layer1 = add_layer(xs, 784, 50, activation_function = tf.nn.relu)
layer2 = add_layer(layer1, 50, 50, activation_function = tf.nn.tanh)
layer3 = add_layer(layer2, 50, 50, activation_function = tf.nn.tanh)
layer4 = add_layer(layer3, 50, 50, activation_function = tf.nn.tanh)

prediction = add_layer(layer4, 50, 10, activation_function = tf.nn.softmax)

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

train_step = tf.train.GradientDescentOptimizer(0.05).minimize(cross_entropy)

sess = tf.Session()

sess.run(tf.initialize_all_variables())

for i in range(100000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(layer1,  feed_dict = {xs: batch_xs, ys: batch_ys})
  sess.run(train_step, feed_dict = {xs: batch_xs, ys:batch_ys})
  if i % 100 ==0:
    print "step:",i,", ",compute_accuracy(mnist.test.images, mnist.test.labels)

# ex-11.py
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer

digits = load_digits()
x = digits.data
y = digits.target
#one-hot transform
y = LabelBinarizer().fit_transform(y)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3)

def add_layer(inputs, in_size, out_size, layer_name, activation_function = None):
  weights = tf.Variable(tf.random_normal([in_size, out_size]))
  biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
  wx_b = tf.matmul(inputs, weights) + biases

  if activation_function is None:
    outputs = wx_b
  else:
    outputs = activation_function(wx_b)
  tf.summary.histogram(layer_name + '/outputs', outputs)
  return outputs

xs = tf.placeholder(tf.float32, [None, 8*8])
ys = tf.placeholder(tf.float32, [None, 10])

layer1 = add_layer(xs, 64, 100, 'layer1', activation_function = tf.nn.tanh)
prediction = add_layer(layer1, 100, 10, 'layer2', activation_function = tf.nn.softmax)

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

tf.summary.scalar('loss', cross_entropy)

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)

sess = tf.Session()
merged = tf.summary.merge_all()

train_writer = tf.train.SummaryWriter("logs/train", sess.graph)
test_writer = tf.train.SummaryWriter("logs/test", sess.graph)

sess.run(tf.initialize_all_variables())

for i in range(1000):
  sess.run(train_step, feed_dict = {xs: x_train, ys:y_train})
  if i % 100==0:
    train_result = sess.run(merged, feed_dict={xs:x_train, ys:y_train})
    test_result = sess.run(merged, feed_dict={xs:x_test, ys:y_test})
    train_writer.add_summary(train_result, i)
    test_writer.add_summary(test_result, i)

# ex-11-dropout.py
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer

digits = load_digits()
x = digits.data
y = digits.target
#one-hot transform
y = LabelBinarizer().fit_transform(y)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3)

def add_layer(inputs, in_size, out_size, layer_name, activation_function = None):
  weights = tf.Variable(tf.random_normal([in_size, out_size]))
  biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
  wx_b = tf.matmul(inputs, weights) + biases
  #drop out and keep a proportion
  wx_b = tf.nn.dropout(wx_b, keep_prob)

  if activation_function is None:
    outputs = wx_b
  else:
    outputs = activation_function(wx_b)
  tf.histogram_summary(layer_name + '/outputs', outputs)
  return outputs

keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 8*8])
ys = tf.placeholder(tf.float32, [None, 10])

layer1 = add_layer(xs, 64, 100, 'layer1', activation_function = tf.nn.tanh)
prediction = add_layer(layer1, 100, 10, 'layer2', activation_function = tf.nn.softmax)

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

tf.scalar_summary('loss', cross_entropy)

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)

sess = tf.Session()
merged = tf.merge_all_summaries()

train_writer = tf.train.SummaryWriter("logs/train", sess.graph)
test_writer = tf.train.SummaryWriter("logs/test", sess.graph)

sess.run(tf.initialize_all_variables())

for i in range(1000):
  sess.run(train_step, feed_dict = {xs: x_train, ys:y_train, keep_prob:0.7})
  if i % 100==0:
    train_result = sess.run(merged, feed_dict={xs:x_train, ys:y_train, keep_prob: 0.7})
    test_result = sess.run(merged, feed_dict={xs:x_test, ys:y_test, keep_prob: 0.7})
    train_writer.add_summary(train_result, i)
    test_writer.add_summary(test_result, i)

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os
import tempfile

import numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

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

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip

import numpy
from six.moves import xrange  # pylint: disable=redefined-builtin

from tensorflow.contrib.learn.python.learn.datasets import base
from tensorflow.python.framework import dtypes
from tensorflow.python.framework import random_seed

# CVDF mirror of http://yann.lecun.com/exdb/mnist/
SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/'


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=dtypes.float32,
               reshape=True,
               seed=None):
    """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]`.  Seed arg provides for convenient deterministic testing.
    """
    seed1, seed2 = random_seed.get_seed(seed)
    # If op level seed is not set, use whatever graph level seed is returned
    numpy.random.seed(seed1 if seed is None else seed2)
    dtype = dtypes.as_dtype(dtype).base_dtype
    if dtype not in (dtypes.uint8, dtypes.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 == dtypes.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, shuffle=True):
    """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
    # Shuffle for the first epoch
    if self._epochs_completed == 0 and start == 0 and shuffle:
      perm0 = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm0)
      self._images = self.images[perm0]
      self._labels = self.labels[perm0]
    # Go to the next epoch
    if start + batch_size > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Get the rest examples in this epoch
      rest_num_examples = self._num_examples - start
      images_rest_part = self._images[start:self._num_examples]
      labels_rest_part = self._labels[start:self._num_examples]
      # Shuffle the data
      if shuffle:
        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 - rest_num_examples
      end = self._index_in_epoch
      images_new_part = self._images[start:end]
      labels_new_part = self._labels[start:end]
      return numpy.concatenate((images_rest_part, images_new_part), axis=0) , numpy.concatenate((labels_rest_part, labels_new_part), axis=0)
    else:
      self._index_in_epoch += batch_size
      end = self._index_in_epoch
      return self._images[start:end], self._labels[start:end]


def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=dtypes.float32,
                   reshape=True,
                   validation_size=5000,
                   seed=None):
  if fake_data:

    def fake():
      return DataSet(
          [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)

    train = fake()
    validation = fake()
    test = fake()
    return base.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 = base.maybe_download(TRAIN_IMAGES, train_dir,
                                   SOURCE_URL + TRAIN_IMAGES)
  with open(local_file, 'rb') as f:
    train_images = extract_images(f)

  local_file = base.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 = base.maybe_download(TEST_IMAGES, train_dir,
                                   SOURCE_URL + TEST_IMAGES)
  with open(local_file, 'rb') as f:
    test_images = extract_images(f)

  local_file = base.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 <= len(train_images):
    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:]

  
  options = dict(dtype=dtype, reshape=reshape, seed=seed)
  
  train = DataSet(train_images, train_labels, **options)
  validation = DataSet(validation_images, validation_labels, **options)
  test = DataSet(test_images, test_labels, **options)
  
  return base.Datasets(train=train, validation=validation, test=test)


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