"""A very simple MNIST classifier.
See extensive documentation at
http://tensorflow.org/tutorials/mnist/beginners/index.md
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def main(_):
  # Import data
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
  
  #28x28 = 784
  #mnist.train.images -> shape=[55000, 784]
  #mnist.train.labels -> shape=[55000, 10]

  # Create the model -> satu fully-connected layer doang, input 784 unit, output 10 unit
  x = tf.placeholder(tf.float32, [None, 784]) #-> 2D, None artinya bisa berapapun, jadi shape [55000, 784] juga cocok di-feed
  W = tf.Variable(tf.zeros([784, 10])) #-> artinya, output unit = 10
  b = tf.Variable(tf.zeros([10]))
  y = tf.matmul(x, W) + b

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 10])

  # The raw formulation of cross-entropy,
  #
  #   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
  #                                 reduction_indices=[1]))
  #
  # can be numerically unstable.
  #
  # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
  # outputs of 'y', and then average across the batch.
  cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y, y_))
  train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

  sess = tf.InteractiveSession()
  tf.global_variables_initializer().run()
  # Train
  for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

  # Test trained model
  # argmax(y,1) -> y = [[0,1,0],[0,0,1],...] -> [1,2,...]
  # equal(y,_y) -> y = [1,2,...]; _y = [1,3,...] -> [True, False, ...]
  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  # casting list of booleans ke list of integer 1,0
  # akurasi adalah rata-ratanya
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  print(sess.run(accuracy, feed_dict={x: mnist.test.images, \
                                      y_: mnist.test.labels}))

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
                      help='Directory for storing input data')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)