{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# Logistic Regression in TensorFlow\n",
    "\n",
    "### Updated for Python 3.6+\n",
    "\n",
    "Credits: Forked from [TensorFlow-Examples](https://github.com/aymericdamien/TensorFlow-Examples) by Aymeric Damien\n",
    "\n",
    "## Setup\n",
    "\n",
    "Refer to the [setup instructions](http://nbviewer.ipython.org/github/donnemartin/data-science-ipython-notebooks/blob/master/deep-learning/tensor-flow-examples/Setup_TensorFlow.md)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting /tmp/data/train-images-idx3-ubyte.gz\n",
      "Extracting /tmp/data/train-labels-idx1-ubyte.gz\n",
      "Extracting /tmp/data/t10k-images-idx3-ubyte.gz\n",
      "Extracting /tmp/data/t10k-labels-idx1-ubyte.gz\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.examples.tutorials.mnist import input_data\n",
    "mnist = input_data.read_data_sets(\"/tmp/data/\", one_hot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Parameters\n",
    "learning_rate = 0.01\n",
    "training_epochs = 25\n",
    "batch_size = 100\n",
    "display_step = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# tf Graph Input\n",
    "x = tf.placeholder(\"float\", [None, 784]) # mnist data image of shape 28*28=784\n",
    "y = tf.placeholder(\"float\", [None, 10]) # 0-9 digits recognition => 10 classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Create model\n",
    "\n",
    "# Set model weights\n",
    "W = tf.Variable(tf.zeros([784, 10]))\n",
    "b = tf.Variable(tf.zeros([10]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Construct model\n",
    "activation = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Minimize error using cross entropy\n",
    "# Cross entropy\n",
    "cost = -tf.reduce_sum(y*tf.log(activation)) \n",
    "# Gradient Descent\n",
    "optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initializing the variables\n",
    "init = tf.global_variables_initializer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch: 0001 cost= 30.201449143\n",
      "Epoch: 0002 cost= 22.036444135\n",
      "Epoch: 0003 cost= 21.054862718\n",
      "Epoch: 0004 cost= 20.597353284\n",
      "Epoch: 0005 cost= 20.190342429\n",
      "Epoch: 0006 cost= 19.786361580\n",
      "Epoch: 0007 cost= 19.593195786\n",
      "Epoch: 0008 cost= 19.423822853\n",
      "Epoch: 0009 cost= 19.390960660\n",
      "Epoch: 0010 cost= 19.237225328\n",
      "Epoch: 0011 cost= 19.129154354\n",
      "Epoch: 0012 cost= 19.068082945\n",
      "Epoch: 0013 cost= 18.961399286\n",
      "Epoch: 0014 cost= 18.836373898\n",
      "Epoch: 0015 cost= 18.799891092\n",
      "Epoch: 0016 cost= 18.727478255\n",
      "Epoch: 0017 cost= 18.591258308\n",
      "Epoch: 0018 cost= 18.676952642\n",
      "Epoch: 0019 cost= 18.548722290\n",
      "Epoch: 0020 cost= 18.484304102\n",
      "Epoch: 0021 cost= 18.437379690\n",
      "Epoch: 0022 cost= 18.387524192\n",
      "Epoch: 0023 cost= 18.353106305\n",
      "Epoch: 0024 cost= 18.252915604\n",
      "Epoch: 0025 cost= 18.257536320\n",
      "Optimization Finished!\n",
      "Accuracy: 0.9233\n"
     ]
    }
   ],
   "source": [
    "# Launch the graph\n",
    "with tf.Session() as sess:\n",
    "    sess.run(init)\n",
    "\n",
    "    # Training cycle\n",
    "    for epoch in range(training_epochs):\n",
    "        avg_cost = 0.\n",
    "        total_batch = int(mnist.train.num_examples/batch_size)\n",
    "        # Loop over all batches\n",
    "        for i in range(total_batch):\n",
    "            batch_xs, batch_ys = mnist.train.next_batch(batch_size)\n",
    "            # Fit training using batch data\n",
    "            sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})\n",
    "            # Compute average loss\n",
    "            avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys})/total_batch\n",
    "        # Display logs per epoch step\n",
    "        if epoch % display_step == 0:\n",
    "            print (\"Epoch:\", '%04d' % (epoch+1), \"cost=\", \"{:.9f}\".format(avg_cost))\n",
    "\n",
    "    print (\"Optimization Finished!\")\n",
    "\n",
    "    # Test model\n",
    "    correct_prediction = tf.equal(tf.argmax(activation, 1), tf.argmax(y, 1))\n",
    "    # Calculate accuracy\n",
    "    accuracy = tf.reduce_mean(tf.cast(correct_prediction, \"float\"))\n",
    "    print (\"Accuracy:\", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}