'''
A logistic regression learning algorithm example using TensorFlow library.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''

from __future__ import print_function

import tensorflow as tf

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 10
batch_size = 100
display_step = 1

# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28*28=784
y = tf.placeholder(tf.float32, [None, 10]) # 0-9 digits recognition => 10 classes

# Set model weights
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# Construct model
pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

# Minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:

    # Run the initializer
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs,
                                                          y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

    # predict
    # results = sess.run(pred, feed_dict={x: batch_xs[:1]})

    # save model
    saver = tf.train.Saver()
    save_path = saver.save(sess, "logistic_regression/model.ckpt")
    tf.train.write_graph(sess.graph.as_graph_def(),'logistic_regression','model.pbtxt', as_text=True)

    freeze_graph.freeze_graph(input_graph = 'logistic_regression/model.pbtxt', 
                              input_saver = "", 
                              input_binary = False, 
                              input_checkpoint = 'logistic_regression/model.ckpt', 
                              output_node_names = "Softmax",
                              restore_op_name = "save/restore_all", 
                              filename_tensor_name = "save/Const:0",
                              output_graph = 'logistic_regression/model.pb', 
                              clear_devices = True, 
                              initializer_nodes = "")

    # restoring the model
    saver = tf.train.import_meta_graph('logistic_regression/tensorflowModel.ckpt.meta')
    saver.restore(sess,tf.train.latest_checkpoint('logistic_regression'))

    # predict
    # pred = graph._nodes_by_name["Softmax"]
    # output = pred.outputs[0]
    # x = graph._nodes_by_name["Placeholder"]
    # input = x.outputs[0]
    # results = sess.run(output, feed_dict={input: batch_xs[:1]})