notebook.community

Edit and run

MA





In [1]:



    


import menpo.io as mio
import numpy as np
import tensorflow as tf
from sklearn import svm
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

%matplotlib inline

data preparation





In [2]:



    


stock_slices = mio.import_pickle('/homes/yz4009/wd/gitdev/MarketAnalysor/DataAnalysis/data/090_030_slices.pkl')



    











In [3]:



    


len(stock_slices)



    


















    
Out[3]:








1490

















In [4]:



    


data = []
for s in stock_slices:
    for k in s.keys():
        data += s[k]



    











In [5]:



    


def label_y(trend):
    cl = [0, 0, 1]
    if trend > 0.3:
        cl = [1, 0, 0]
    elif trend < -0.3:
        cl = [0, 1, 0]
        
    return cl



data_X = [d['data'] for d in data]
data_Y = [label_y(d['trend']) for d in data]



    











In [6]:



    


data_X = np.array(data_X)
data_Y = np.array(data_Y)

data_X[np.isnan(data_X)] = 0



    











In [7]:



    


n_data = len(data)
n_train = int(n_data * 0.8)
n_valid = int(n_data * 0.1)



    











In [8]:



    


train_X = data_X[:n_train]
train_Y = data_Y[:n_train]
valid_X = data_X[n_train:n_train+n_valid]
valid_Y = data_Y[n_train:n_train+n_valid]
test_X = data_X[n_train+n_valid:]
test_Y = data_Y[n_train+n_valid:]

SVM Prediction

acc2 = [] for C in range(90000, 900000, 10000): print C clf = svm.SVC(C=C, tol=0.0001) clf.fit(train_X, train_Y) predict_Y = clf.predict(valid_X) acc2.append(float(np.sum(predict_Y == valid_Y) ) / len(valid_Y))
plt.plot(acc2)

Tensor Flow Prediction





In [9]:



    


train_X.shape



    


















    
Out[9]:








(2650423, 89)

















In [10]:



    


np.isnan(train_Y).any()



    


















    
Out[10]:








False

















In [11]:



    


train_Y.shape



    


















    
Out[11]:








(2650423, 3)

















In [12]:



    


batch_size = 100

sess = tf.InteractiveSession()

x = tf.placeholder(tf.float32, [None, 89])
y_ = tf.placeholder(tf.float32, [None, 3])

W1 = tf.Variable(tf.random_uniform([89, 3], -1.0, 1.0))
b1 = tf.Variable(tf.random_uniform([3], -1.0, 1.0))

pred = tf.nn.softmax(tf.matmul(x, W1) + b1)

keep_prob = tf.placeholder(tf.float32)
y = tf.nn.dropout(pred, keep_prob)

cross_entropy = -tf.reduce_sum(y_*tf.log(tf.clip_by_value(y,1e-10,1.0)))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


sess.run(tf.initialize_all_variables())

for i in xrange(train_X.shape[0] / batch_size):
    batch_xs = train_X[i * batch_size: i * batch_size + batch_size]
    batch_ys = train_Y[i * batch_size: i * batch_size + batch_size]
    
    if i % batch_size == 0:
        train_accuracy = accuracy.eval(feed_dict={
        x:batch_xs, y_: batch_ys, keep_prob: 1.0})
        print("step %d, training accuracy %g"%(i, train_accuracy))

    train_step.run(feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 0.5})



print(sess.run(accuracy, feed_dict={x: test_X, y_: test_Y, keep_prob: 1.0}))



    


















    






step 0, training accuracy 0.46
step 100, training accuracy 0.95
step 200, training accuracy 1
step 300, training accuracy 1
step 400, training accuracy 1
step 500, training accuracy 0.98
step 600, training accuracy 1
step 700, training accuracy 1
step 800, training accuracy 1
step 900, training accuracy 1
step 1000, training accuracy 1
step 1100, training accuracy 1
step 1200, training accuracy 0.94
step 1300, training accuracy 1
step 1400, training accuracy 1
step 1500, training accuracy 1
step 1600, training accuracy 1
step 1700, training accuracy 0.42
step 1800, training accuracy 1
step 1900, training accuracy 1
step 2000, training accuracy 0.43
step 2100, training accuracy 1
step 2200, training accuracy 1
step 2300, training accuracy 1
step 2400, training accuracy 1
step 2500, training accuracy 1
step 2600, training accuracy 1
step 2700, training accuracy 1
step 2800, training accuracy 1
step 2900, training accuracy 1
step 3000, training accuracy 0.99
step 3100, training accuracy 1
step 3200, training accuracy 1
step 3300, training accuracy 1
step 3400, training accuracy 1
step 3500, training accuracy 1
step 3600, training accuracy 1
step 3700, training accuracy 1
step 3800, training accuracy 1
step 3900, training accuracy 0.97
step 4000, training accuracy 1
step 4100, training accuracy 1
step 4200, training accuracy 1
step 4300, training accuracy 1
step 4400, training accuracy 0.94
step 4500, training accuracy 0.73
step 4600, training accuracy 1
step 4700, training accuracy 0.65
step 4800, training accuracy 1
step 4900, training accuracy 1
step 5000, training accuracy 1
step 5100, training accuracy 1
step 5200, training accuracy 1
step 5300, training accuracy 1
step 5400, training accuracy 1
step 5500, training accuracy 0.79
step 5600, training accuracy 1
step 5700, training accuracy 1
step 5800, training accuracy 1
step 5900, training accuracy 1
step 6000, training accuracy 1
step 6100, training accuracy 1
step 6200, training accuracy 0.82
step 6300, training accuracy 0.87
step 6400, training accuracy 1
step 6500, training accuracy 1
step 6600, training accuracy 1
step 6700, training accuracy 1
step 6800, training accuracy 0.52
step 6900, training accuracy 0.96
step 7000, training accuracy 1
step 7100, training accuracy 1
step 7200, training accuracy 1
step 7300, training accuracy 1
step 7400, training accuracy 1
step 7500, training accuracy 0.82
step 7600, training accuracy 1
step 7700, training accuracy 1
step 7800, training accuracy 1
step 7900, training accuracy 1
step 8000, training accuracy 0.8
step 8100, training accuracy 0.97
step 8200, training accuracy 1
step 8300, training accuracy 1
step 8400, training accuracy 1
step 8500, training accuracy 1
step 8600, training accuracy 1
step 8700, training accuracy 1
step 8800, training accuracy 0.69
step 8900, training accuracy 1
step 9000, training accuracy 0.31
step 9100, training accuracy 1
step 9200, training accuracy 0.64
step 9300, training accuracy 1
step 9400, training accuracy 0.98
step 9500, training accuracy 1
step 9600, training accuracy 0.83
step 9700, training accuracy 1
step 9800, training accuracy 1
step 9900, training accuracy 1
step 10000, training accuracy 0.89
step 10100, training accuracy 1
step 10200, training accuracy 0.8
step 10300, training accuracy 1
step 10400, training accuracy 1
step 10500, training accuracy 1
step 10600, training accuracy 1
step 10700, training accuracy 1
step 10800, training accuracy 1
step 10900, training accuracy 0.78
step 11000, training accuracy 0.69
step 11100, training accuracy 0.77
step 11200, training accuracy 0.73
step 11300, training accuracy 0.85
step 11400, training accuracy 0.92
step 11500, training accuracy 1
step 11600, training accuracy 0.99
step 11700, training accuracy 0.72
step 11800, training accuracy 0.98
step 11900, training accuracy 0.83
step 12000, training accuracy 0.83
step 12100, training accuracy 1
step 12200, training accuracy 1
step 12300, training accuracy 0.55
step 12400, training accuracy 1
step 12500, training accuracy 1
step 12600, training accuracy 0.84
step 12700, training accuracy 1
step 12800, training accuracy 0.9
step 12900, training accuracy 0.95
step 13000, training accuracy 1
step 13100, training accuracy 0.76
step 13200, training accuracy 0.98
step 13300, training accuracy 1
step 13400, training accuracy 0.99
step 13500, training accuracy 1
step 13600, training accuracy 0.72
step 13700, training accuracy 0.91
step 13800, training accuracy 1
step 13900, training accuracy 0.99
step 14000, training accuracy 0.71
step 14100, training accuracy 0.74
step 14200, training accuracy 0.83
step 14300, training accuracy 1
step 14400, training accuracy 0.75
step 14500, training accuracy 1
step 14600, training accuracy 1
step 14700, training accuracy 0.43
step 14800, training accuracy 0.7
step 14900, training accuracy 0.64
step 15000, training accuracy 0.84
step 15100, training accuracy 0.89
step 15200, training accuracy 0.69
step 15300, training accuracy 0.64
step 15400, training accuracy 0.89
step 15500, training accuracy 0.52
step 15600, training accuracy 1
step 15700, training accuracy 1
step 15800, training accuracy 0.75
step 15900, training accuracy 0.5
step 16000, training accuracy 0.71
step 16100, training accuracy 0.58
step 16200, training accuracy 0.58
step 16300, training accuracy 0.75
step 16400, training accuracy 1
step 16500, training accuracy 0.66
step 16600, training accuracy 0.79
step 16700, training accuracy 0.86
step 16800, training accuracy 0.99
step 16900, training accuracy 0.99
step 17000, training accuracy 0.72
step 17100, training accuracy 0.43
step 17200, training accuracy 0.47
step 17300, training accuracy 0.75
step 17400, training accuracy 0.95
step 17500, training accuracy 0.99
step 17600, training accuracy 0.98
step 17700, training accuracy 0.85
step 17800, training accuracy 0.57
step 17900, training accuracy 0.97
step 18000, training accuracy 0.87
step 18100, training accuracy 0.66
step 18200, training accuracy 0.5
step 18300, training accuracy 0.54
step 18400, training accuracy 0.97
step 18500, training accuracy 0.97
step 18600, training accuracy 0.53
step 18700, training accuracy 1
step 18800, training accuracy 0.87
step 18900, training accuracy 0.82
step 19000, training accuracy 0.4
step 19100, training accuracy 1
step 19200, training accuracy 0.93
step 19300, training accuracy 1
step 19400, training accuracy 0.95
step 19500, training accuracy 0.7
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 0.91
step 19900, training accuracy 1
step 20000, training accuracy 0.67
step 20100, training accuracy 0.86
step 20200, training accuracy 1
step 20300, training accuracy 1
step 20400, training accuracy 0.79
step 20500, training accuracy 0.98
step 20600, training accuracy 0.98
step 20700, training accuracy 0.95
step 20800, training accuracy 0.94
step 20900, training accuracy 0.57
step 21000, training accuracy 1
step 21100, training accuracy 1
step 21200, training accuracy 0.73
step 21300, training accuracy 0.76
step 21400, training accuracy 1
step 21500, training accuracy 1
step 21600, training accuracy 1
step 21700, training accuracy 0.99
step 21800, training accuracy 1
step 21900, training accuracy 0.37
step 22000, training accuracy 1
step 22100, training accuracy 1
step 22200, training accuracy 1
step 22300, training accuracy 0.93
step 22400, training accuracy 1
step 22500, training accuracy 0.96
step 22600, training accuracy 1
step 22700, training accuracy 0.99
step 22800, training accuracy 0.96
step 22900, training accuracy 1
step 23000, training accuracy 1
step 23100, training accuracy 0.78
step 23200, training accuracy 1
step 23300, training accuracy 1
step 23400, training accuracy 0.98
step 23500, training accuracy 1
step 23600, training accuracy 1
step 23700, training accuracy 1
step 23800, training accuracy 1
step 23900, training accuracy 0.61
step 24000, training accuracy 0.91
step 24100, training accuracy 0.91
step 24200, training accuracy 0.96
step 24300, training accuracy 0.99
step 24400, training accuracy 1
step 24500, training accuracy 1
step 24600, training accuracy 1
step 24700, training accuracy 1
step 24800, training accuracy 1
step 24900, training accuracy 1
step 25000, training accuracy 0.44
step 25100, training accuracy 1
step 25200, training accuracy 1
step 25300, training accuracy 0.99
step 25400, training accuracy 1
step 25500, training accuracy 0.8
step 25600, training accuracy 1
step 25700, training accuracy 0.81
step 25800, training accuracy 1
step 25900, training accuracy 0.99
step 26000, training accuracy 0.98
step 26100, training accuracy 1
step 26200, training accuracy 1
step 26300, training accuracy 1
step 26400, training accuracy 0.48
step 26500, training accuracy 0.87
0.913321

















In [13]:



    


ret = y.eval(feed_dict={x: test_X})



    


















    






---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-13-a2793eb74f77> in <module>()
----> 1 ret = y.eval(feed_dict={x: test_X})

/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/framework/ops.pyc in eval(self, feed_dict, session)
    458 
    459     """
--> 460     return _eval_using_default_session(self, feed_dict, self.graph, session)
    461 
    462 

/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/framework/ops.pyc in _eval_using_default_session(tensors, feed_dict, graph, session)
   2908                        "the tensor's graph is different from the session's "
   2909                        "graph.")
-> 2910   return session.run(tensors, feed_dict)
   2911 
   2912 

/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict)
    366 
    367     # Run request and get response.
--> 368     results = self._do_run(target_list, unique_fetch_targets, feed_dict_string)
    369 
    370     # User may have fetched the same tensor multiple times, but we

/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, target_list, fetch_list, feed_dict)
    442         # pylint: disable=protected-access
    443         raise errors._make_specific_exception(node_def, op, error_message,
--> 444                                               e.code)
    445         # pylint: enable=protected-access
    446       six.reraise(e_type, e_value, e_traceback)

InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder_2' with dtype float
	 [[Node: Placeholder_2 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'Placeholder_2', defined at:
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/runpy.py", line 162, in _run_module_as_main
    "__main__", fname, loader, pkg_name)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/runpy.py", line 72, in _run_code
    exec code in run_globals
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/__main__.py", line 3, in <module>
    app.launch_new_instance()
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/traitlets/config/application.py", line 596, in launch_instance
    app.start()
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/kernelapp.py", line 442, in start
    ioloop.IOLoop.instance().start()
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/zmq/eventloop/ioloop.py", line 162, in start
    super(ZMQIOLoop, self).start()
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tornado/ioloop.py", line 883, in start
    handler_func(fd_obj, events)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tornado/stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tornado/stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 276, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
    handler(stream, idents, msg)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 391, in execute_request
    user_expressions, allow_stdin)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/ipykernel/ipkernel.py", line 199, in do_execute
    shell.run_cell(code, store_history=store_history, silent=silent)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2723, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2825, in run_ast_nodes
    if self.run_code(code, result):
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2885, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-12-618f423a6465>", line 13, in <module>
    keep_prob = tf.placeholder(tf.float32)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 673, in placeholder
    name=name)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 463, in _placeholder
    name=name)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/ops/op_def_library.py", line 664, in apply_op
    op_def=op_def)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1834, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/vol/atlas/homes/yz4009/miniconda/envs/gitdev/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1043, in __init__
    self._traceback = _extract_stack()

















In [ ]:



    


np.sum((ret[:,0] - ret[:,1]) < 0)

demo





In [11]:



    


import tensorflow as tf
import numpy as np

# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data * 0.1 + 0.3

# Try to find values for W and b that compute y_data = W * x_data + b
# (We know that W should be 0.1 and b 0.3, but Tensorflow will
# figure that out for us.)
W = tf.Variable(tf.zeros([1]))
b = tf.Variable(tf.zeros([1]))

y = W * x_data + b

# Minimize the mean squared errors.
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)

# Before starting, initialize the variables.  We will 'run' this first.
init = tf.initialize_all_variables()

# Launch the graph.
sess = tf.Session()
sess.run(init)

# Fit the line.
for step in xrange(401):
    sess.run(train)
    if step % 20 == 0:
        print(step, sess.run(W), sess.run(b))

# Learns best fit is W: [0.1], b: [0.3]



    


















    






(0, array([ 0.19459628], dtype=float32), array([ 0.35310328], dtype=float32))
(20, array([ 0.11602166], dtype=float32), array([ 0.29100075], dtype=float32))
(40, array([ 0.10521366], dtype=float32), array([ 0.29707155], dtype=float32))
(60, array([ 0.10169658], dtype=float32), array([ 0.29904705], dtype=float32))
(80, array([ 0.1005521], dtype=float32), array([ 0.29968989], dtype=float32))
(100, array([ 0.10017967], dtype=float32), array([ 0.2998991], dtype=float32))
(120, array([ 0.10005846], dtype=float32), array([ 0.29996717], dtype=float32))
(140, array([ 0.10001902], dtype=float32), array([ 0.29998934], dtype=float32))
(160, array([ 0.10000618], dtype=float32), array([ 0.29999655], dtype=float32))
(180, array([ 0.10000201], dtype=float32), array([ 0.29999888], dtype=float32))
(200, array([ 0.10000065], dtype=float32), array([ 0.29999965], dtype=float32))
(220, array([ 0.10000022], dtype=float32), array([ 0.29999989], dtype=float32))
(240, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(260, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(280, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(300, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(320, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(340, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(360, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(380, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))
(400, array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32))

mnist





In [34]:



    


from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)



    


















    






Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

















In [66]:



    


sess = tf.InteractiveSession()

x = tf.placeholder(tf.float32, [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_sum(y_*tf.log(y))

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

init = tf.initialize_all_variables()

sess.run(init)

for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  train_step.run(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: mnist.test.images, y_: mnist.test.labels}))



    


















    






Exception AssertionError: AssertionError() in <bound method InteractiveSession.__del__ of <tensorflow.python.client.session.InteractiveSession object at 0x7f9cdcf47dd0>> ignored










    






0.9168

deep mnist





In [24]:



    


def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')



    











In [25]:



    


mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)



    


















    






Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

















In [26]:



    


sess = tf.InteractiveSession()



    


















    






Exception AssertionError: AssertionError() in <bound method InteractiveSession.__del__ of <tensorflow.python.client.session.InteractiveSession object at 0x7f9f3aab0690>> ignored

















In [27]:



    


x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])



    











In [28]:



    


W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])



    











In [29]:



    


x_image = tf.reshape(x, [-1,28,28,1])



    











In [30]:



    


h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)



    











In [31]:



    


W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)



    











In [32]:



    


W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)



    











In [33]:



    


keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)



    











In [34]:



    


W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)



    











In [35]:



    


cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))



    


















    






step 0, training accuracy 0.08
step 100, training accuracy 0.82
step 200, training accuracy 0.92
step 300, training accuracy 0.84
step 400, training accuracy 0.98
step 500, training accuracy 0.9
step 600, training accuracy 0.96
step 700, training accuracy 0.96
step 800, training accuracy 0.88
step 900, training accuracy 1
step 1000, training accuracy 0.96
step 1100, training accuracy 0.92
step 1200, training accuracy 0.94
step 1300, training accuracy 0.92
step 1400, training accuracy 0.94
step 1500, training accuracy 0.94
step 1600, training accuracy 1
step 1700, training accuracy 0.96
step 1800, training accuracy 0.98
step 1900, training accuracy 0.96
step 2000, training accuracy 0.96
step 2100, training accuracy 1
step 2200, training accuracy 0.98
step 2300, training accuracy 0.96
step 2400, training accuracy 0.96
step 2500, training accuracy 0.96
step 2600, training accuracy 0.96
step 2700, training accuracy 1
step 2800, training accuracy 1
step 2900, training accuracy 1
step 3000, training accuracy 0.98
step 3100, training accuracy 0.96
step 3200, training accuracy 0.98
step 3300, training accuracy 0.98
step 3400, training accuracy 1
step 3500, training accuracy 1
step 3600, training accuracy 0.96
step 3700, training accuracy 0.98
step 3800, training accuracy 0.96
step 3900, training accuracy 0.98
step 4000, training accuracy 1
step 4100, training accuracy 0.96
step 4200, training accuracy 0.98
step 4300, training accuracy 0.98
step 4400, training accuracy 0.98
step 4500, training accuracy 0.96
step 4600, training accuracy 0.98
step 4700, training accuracy 0.98
step 4800, training accuracy 1
step 4900, training accuracy 1
step 5000, training accuracy 0.98
step 5100, training accuracy 0.98
step 5200, training accuracy 1
step 5300, training accuracy 1
step 5400, training accuracy 1
step 5500, training accuracy 0.98
step 5600, training accuracy 0.98
step 5700, training accuracy 1
step 5800, training accuracy 1
step 5900, training accuracy 1
step 6000, training accuracy 1
step 6100, training accuracy 1
step 6200, training accuracy 1
step 6300, training accuracy 1
step 6400, training accuracy 1
step 6500, training accuracy 1
step 6600, training accuracy 1
step 6700, training accuracy 1
step 6800, training accuracy 0.98
step 6900, training accuracy 1
step 7000, training accuracy 1
step 7100, training accuracy 0.98
step 7200, training accuracy 1
step 7300, training accuracy 1
step 7400, training accuracy 0.98
step 7500, training accuracy 1
step 7600, training accuracy 1
step 7700, training accuracy 1
step 7800, training accuracy 0.98
step 7900, training accuracy 1
step 8000, training accuracy 1
step 8100, training accuracy 1
step 8200, training accuracy 0.98
step 8300, training accuracy 1
step 8400, training accuracy 1
step 8500, training accuracy 1
step 8600, training accuracy 1
step 8700, training accuracy 1
step 8800, training accuracy 1
step 8900, training accuracy 1
step 9000, training accuracy 1
step 9100, training accuracy 0.98
step 9200, training accuracy 1
step 9300, training accuracy 1
step 9400, training accuracy 1
step 9500, training accuracy 1
step 9600, training accuracy 1
step 9700, training accuracy 1
step 9800, training accuracy 1
step 9900, training accuracy 1
step 10000, training accuracy 1
step 10100, training accuracy 1
step 10200, training accuracy 1
step 10300, training accuracy 1
step 10400, training accuracy 1
step 10500, training accuracy 1
step 10600, training accuracy 1
step 10700, training accuracy 0.96
step 10800, training accuracy 0.96
step 10900, training accuracy 1
step 11000, training accuracy 1
step 11100, training accuracy 1
step 11200, training accuracy 1
step 11300, training accuracy 1
step 11400, training accuracy 1
step 11500, training accuracy 1
step 11600, training accuracy 1
step 11700, training accuracy 1
step 11800, training accuracy 1
step 11900, training accuracy 1
step 12000, training accuracy 1
step 12100, training accuracy 1
step 12200, training accuracy 1
step 12300, training accuracy 1
step 12400, training accuracy 1
step 12500, training accuracy 1
step 12600, training accuracy 1
step 12700, training accuracy 1
step 12800, training accuracy 1
step 12900, training accuracy 0.98
step 13000, training accuracy 1
step 13100, training accuracy 1
step 13200, training accuracy 1
step 13300, training accuracy 1
step 13400, training accuracy 1
step 13500, training accuracy 1
step 13600, training accuracy 1
step 13700, training accuracy 1
step 13800, training accuracy 0.98
step 13900, training accuracy 0.98
step 14000, training accuracy 1
step 14100, training accuracy 1
step 14200, training accuracy 1
step 14300, training accuracy 1
step 14400, training accuracy 1
step 14500, training accuracy 1
step 14600, training accuracy 1
step 14700, training accuracy 1
step 14800, training accuracy 1
step 14900, training accuracy 1
step 15000, training accuracy 1
step 15100, training accuracy 1
step 15200, training accuracy 0.98
step 15300, training accuracy 1
step 15400, training accuracy 1
step 15500, training accuracy 1
step 15600, training accuracy 1
step 15700, training accuracy 1
step 15800, training accuracy 1
step 15900, training accuracy 1
step 16000, training accuracy 1
step 16100, training accuracy 1
step 16200, training accuracy 1
step 16300, training accuracy 1
step 16400, training accuracy 1
step 16500, training accuracy 1
step 16600, training accuracy 1
step 16700, training accuracy 1
step 16800, training accuracy 1
step 16900, training accuracy 1
step 17000, training accuracy 1
step 17100, training accuracy 1
step 17200, training accuracy 1
step 17300, training accuracy 1
step 17400, training accuracy 1
step 17500, training accuracy 1
step 17600, training accuracy 1
step 17700, training accuracy 1
step 17800, training accuracy 1
step 17900, training accuracy 1
step 18000, training accuracy 1
step 18100, training accuracy 1
step 18200, training accuracy 1
step 18300, training accuracy 1
step 18400, training accuracy 1
step 18500, training accuracy 1
step 18600, training accuracy 1
step 18700, training accuracy 1
step 18800, training accuracy 1
step 18900, training accuracy 1
step 19000, training accuracy 1
step 19100, training accuracy 1
step 19200, training accuracy 1
step 19300, training accuracy 1
step 19400, training accuracy 1
step 19500, training accuracy 1
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 1
step 19900, training accuracy 1
test accuracy 0.9924

















In [52]:



    


result = y_conv.eval(feed_dict={
    x: mnist.test.images[:1], y_: range(10), keep_prob: 1.0})



    











In [49]:



    


result[0]



    


















    
Out[49]:








array([  1.39344040e-11,   6.08332940e-10,   3.15340254e-10,
         4.88835361e-10,   5.84304870e-12,   2.30223094e-13,
         8.29810597e-16,   1.00000000e+00,   4.27762253e-12,
         2.36218245e-09], dtype=float32)

















In [ ]:

Content source: yuxiang-zhou/MarketAnalysor

Similar notebooks:

notebook.community | gallery | about