{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from IPython.display import Image\n",
    "\n",
    "import numpy as np\n",
    "np.random.seed(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABC8AAALcCAYAAADHZ5qwAAAABmJLR0QA/wD/AP+gvaeTAAAACXBI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\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Image(filename='and-or.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "or_input = np.array([[0,0], [0,1], [1,0], [1,1]])\n",
    "or_output = np.array([[0,1,1,1]]).T\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0],\n",
       "       [0, 1],\n",
       "       [1, 0],\n",
       "       [1, 1]])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "or_input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1]])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "or_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def sigmoid(x): # Returns values that range between -1 and 1\n",
    "    # BTW, this is pretty fun stuff: https://www.google.com.sg/#q=1/(1%2Bexp(-x))\n",
    "    return 1/(1+np.exp(-x))\n",
    "\n",
    "def sigmoid_derivative(x): # We don't really care what it outputs, lolz...\n",
    "    return x*(1-x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0.92414182,  0.57932425,  0.19466158])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sigmoid(np.array([2.5, 0.32, -1.42]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'sigmoid_derivaive' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-8-64f3aed90076>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0msigmoid_derivaive\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m2.5\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0.32\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m-\u001b[0m\u001b[1;36m1.42\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m: name 'sigmoid_derivaive' is not defined"
     ]
    }
   ],
   "source": [
    "sigmoid_derivaive(np.array([2.5, 0.32, -1.42]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-3.75  ,  0.2176, -8.2764])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sigmoid_derivative(np.array([2.5, 0.32, -2.42]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def cost(predicted, truth):\n",
    "    return truth - predicted\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.1,  0.2, -0.2])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gold = np.array([0.5, 1.2, 9.8])\n",
    "pred = np.array([0.6, 1.0, 10.0])\n",
    "cost(pred, gold)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ -8.8,  -2.8, -89.2])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gold = np.array([0.5, 1.2, 9.8])\n",
    "pred = np.array([9.3, 4.0, 99.0])\n",
    "cost(pred, gold)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "num_data, input_dim = or_input.shape\n",
    "output_dim = len(or_output.T)\n",
    "\n",
    "# Initialize weights for the input layer, aka \"syn0\", syn is short for synapse. \n",
    "syn0 = np.random.random((input_dim, output_dim)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "num_epochs = 10000\n",
    "learning_rate = 1.0\n",
    "\n",
    "X = or_input\n",
    "y = or_output\n",
    "\n",
    "for _ in range(num_epochs):\n",
    "    # forward propagation.\n",
    "    l0 = X\n",
    "    l1 = sigmoid(np.dot(l0, syn0))\n",
    "\n",
    "    # how much did we miss?\n",
    "    l1_error = cost(l1, y)\n",
    "\n",
    "    # back propagation.\n",
    "    # multiply how much we missed by the \n",
    "    # slope of the sigmoid at the values in l1\n",
    "    l1_delta = l1_error * sigmoid_derivative(l1)\n",
    "\n",
    "    # update weights\n",
    "    syn0 +=  learning_rate * np.dot(l0.T, l1_delta)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.5       ],\n",
       "       [ 0.99283162],\n",
       "       [ 0.99282994],\n",
       "       [ 0.99994786]])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 1, 1]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[int(l > 0.5) for l in l1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1]])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "or_output"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Do the same but with 1 more hidden layer\n",
    "===="
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def sigmoid(x): # Returns values that range between -1 and 1\n",
    "    # BTW, this is pretty fun stuff: https://www.google.com.sg/#q=1/(1%2Bexp(-x))\n",
    "    return 1/(1+np.exp(-x)) # ... # YOUR CODE HERE\n",
    "\n",
    "def sigmoid_derivative(x): # We don't really care what it outputs, lolz...\n",
    "    return x*(1-x) # ... # YOUR CODE HERE\n",
    "\n",
    "# Cost functions.\n",
    "def cost(predicted, truth):\n",
    "    return truth - predicted\n",
    "\n",
    "\n",
    "X = or_input = np.array([[0,0], [0,1], [1,0], [1,1]])\n",
    "y = or_output = np.array([[0,1,1,1]]).T\n",
    "\n",
    "# Initialize weights for the input layer, aka \"syn0\", syn is short for synapse. \n",
    "num_data, input_dim = or_input.shape\n",
    "hidden_dim = 5 #... # YOUR CODE HERE\n",
    "syn0 = np.random.random((input_dim, hidden_dim))#... # YOUR CODE HERE\n",
    "\n",
    "# Initialize weights for the first hidden layer, aka \"syn1\".\n",
    "output_dim = len(or_output.T) #... # YOUR CODE HERE\n",
    "syn1 = np.random.random((hidden_dim, output_dim)) #... # YOUR CODE HERE\n",
    "\n",
    "\n",
    "num_epochs = 10000\n",
    "learning_rate = 1.0\n",
    "cost = cost\n",
    "\n",
    "for _ in range(num_epochs):\n",
    "    # forward propagation.\n",
    "    l0 = X\n",
    "    l1 = sigmoid(np.dot(l0, syn0))\n",
    "    l2 = sigmoid(np.dot(l1, syn1))\n",
    "\n",
    "    # how much did we miss?\n",
    "    l2_error = cost(l2, y)\n",
    "\n",
    "    # Now we back propagate...\n",
    "    \n",
    "    # in what direction is the target value?\n",
    "    # were we really sure? if so, don't change too much.\n",
    "    l2_delta = l2_error * sigmoid_derivative(l2)\n",
    "\n",
    "    # how much did each l1 value contribute to the l2 error (according to the weights)?\n",
    "    l1_error = l2_delta.dot(syn1.T)\n",
    "    \n",
    "    # in what direction is the target l1?\n",
    "    # were we really sure? if so, don't change too much.\n",
    "    l1_delta = l1_error * sigmoid_derivative(l1)\n",
    "\n",
    "    syn1 += l1.T.dot(l2_delta)\n",
    "    syn0 += l0.T.dot(l1_delta)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.01286598],\n",
       "       [ 0.99285218],\n",
       "       [ 0.99266375],\n",
       "       [ 0.99797014]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l2 # output layer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.5       ,  0.5       ,  0.5       ,  0.5       ,  0.5       ],\n",
       "       [ 0.05030027,  0.9370088 ,  0.06046283,  0.88587697,  0.87996499],\n",
       "       [ 0.0475292 ,  0.93480791,  0.05574036,  0.86846293,  0.84798218],\n",
       "       [ 0.00263601,  0.99533365,  0.00378448,  0.98086165,  0.9761297 ]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l1 # hidden layer."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's make it even more challenging, \n",
    "====\n",
    "we'll drop one data point and use 3 layers \n",
    "===="
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def sigmoid(x): # Returns values that range between -1 and 1\n",
    "    # BTW, this is pretty fun stuff: https://www.google.com.sg/#q=1/(1%2Bexp(-x))\n",
    "    return 1/(1+np.exp(-x)) # ... # YOUR CODE HERE\n",
    "\n",
    "def sigmoid_derivative(x): # We don't really care what it outputs, lolz...\n",
    "    return x*(1-x) # ... # YOUR CODE HERE\n",
    "\n",
    "# Cost functions.\n",
    "def cost(predicted, truth):\n",
    "    return truth - predicted\n",
    "\n",
    "\n",
    "X = or_input = np.array([[0,0], [0,1], [1,0]])\n",
    "y = or_output = np.array([[0,1,1]]).T\n",
    "\n",
    "# Initialize weights for the input layer, aka \"syn0\", syn is short for synapse. \n",
    "num_data, input_dim = or_input.shape\n",
    "hidden_dim_1 = 5 #... # YOUR CODE HERE\n",
    "syn0 = np.random.random((input_dim, hidden_dim_1))#... # YOUR CODE HERE\n",
    "\n",
    "# Initialize weights for the first hidden layer, aka \"syn1\".\n",
    "hidden_dim_2 = 3 #... # YOUR CODE HERE\n",
    "syn1 = np.random.random((hidden_dim_1, hidden_dim_2)) #... # YOUR CODE HERE\n",
    "\n",
    "# Initialize weights for the first hidden layer, aka \"syn2\".\n",
    "output_dim = len(or_output.T) #... # YOUR CODE HERE\n",
    "syn2 = np.random.random((hidden_dim_2, output_dim)) #... # YOUR CODE HERE\n",
    "\n",
    "                       \n",
    "num_epochs = 10000\n",
    "learning_rate = 1.0\n",
    "cost = cost\n",
    "\n",
    "for _ in range(num_epochs):\n",
    "    # forward propagation.\n",
    "    l0 = X\n",
    "    l1 = sigmoid(np.dot(l0, syn0))\n",
    "    l2 = sigmoid(np.dot(l1, syn1))\n",
    "    l3 = sigmoid(np.dot(l2, syn2))\n",
    "\n",
    "    # how much did we miss?\n",
    "    l3_error = cost(l3, y)                         \n",
    "\n",
    "    # Now we back propagate...\n",
    "    \n",
    "    # in what direction is the target value?\n",
    "    # were we really sure? if so, don't change too much.\n",
    "    l3_delta = l3_error * sigmoid_derivative(l3)\n",
    "                         \n",
    "    # how much did each l2 value contribute to the l3 error (according to the weights)?\n",
    "    l2_error = l3_delta.dot(syn2.T)                     \n",
    "\n",
    "    # in what direction is the l2 weights changing?\n",
    "    l2_delta = l2_error * sigmoid_derivative(l2)\n",
    "\n",
    "    # how much did each l1 value contribute to the l2 error (according to the weights)?\n",
    "    l1_error = l2_delta.dot(syn1.T)\n",
    "    \n",
    "    # in what direction is the target l1?\n",
    "    # were we really sure? if so, don't change too much.\n",
    "    l1_delta = l1_error * sigmoid_derivative(l1)\n",
    "                         \n",
    "    syn2 += l2.T.dot(l3_delta)\n",
    "    syn1 += l1.T.dot(l2_delta)\n",
    "    syn0 += l0.T.dot(l1_delta)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.00798033],\n",
       "       [ 0.99521575],\n",
       "       [ 0.99523938]])"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.99821909]])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_input = np.array([[1,1]])\n",
    "# apply l1 to new input\n",
    "_l1 = sigmoid(np.dot(new_input, syn0))\n",
    "# apply l2 to new input\n",
    "_l2 = sigmoid(np.dot(_l1, syn1))\n",
    "# apply l3 (output layer) to new input\n",
    "prediction = _l3 = sigmoid(np.dot(_l2, syn2))\n",
    "\n",
    "prediction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's do the same in tensorflow!!!\n",
    "===="
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Parameters\n",
    "learning_rate = 1.0\n",
    "num_epochs = 10000\n",
    "\n",
    "# Network Parameters\n",
    "hidden_dim_1 = 5 # 1st layer number of features\n",
    "hidden_dim_2 = 3 # 2nd layer number of features\n",
    "input_dim = 2 # Input dimensions.\n",
    "output_dim = 1 # Output dimensions.\n",
    "\n",
    "# tf Graph input\n",
    "x = tf.placeholder(\"float\", [None, input_dim])\n",
    "y = tf.placeholder(\"float\", [hidden_dim_2, output_dim])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Without biases.\n",
    "\n",
    "weights = {\n",
    "    'syn0': tf.Variable(tf.random_normal([input_dim, hidden_dim_1])),\n",
    "    'syn1': tf.Variable(tf.random_normal([hidden_dim_1, hidden_dim_2])),\n",
    "    'syn2': tf.Variable(tf.random_normal([hidden_dim_2, output_dim]))\n",
    "}\n",
    "\n",
    "# Create a model\n",
    "def multilayer_perceptron(X, weights, biases):\n",
    "    # Hidden layer 1\n",
    "    layer_1 = tf.matmul(X, weights['syn0'])\n",
    "    # Hidden layer 2\n",
    "    layer_2 = tf.matmul(layer_1, weights['syn1'])\n",
    "    # Output layer\n",
    "    out_layer = tf.matmul(layer_2, weights['syn2'])\n",
    "    return out_layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# With biases.\n",
    "weights = {\n",
    "    'syn0': tf.Variable(tf.random_normal([input_dim, hidden_dim_1])),\n",
    "    'syn1': tf.Variable(tf.random_normal([hidden_dim_1, hidden_dim_2])),\n",
    "    'syn2': tf.Variable(tf.random_normal([hidden_dim_2, output_dim]))\n",
    "}\n",
    "\n",
    "\n",
    "biases = {\n",
    "    'b0': tf.Variable(tf.random_normal([hidden_dim_1])),\n",
    "    'b1': tf.Variable(tf.random_normal([hidden_dim_2])),\n",
    "    'b2': tf.Variable(tf.random_normal([output_dim]))\n",
    "}\n",
    "\n",
    "\n",
    "# Create a model\n",
    "def multilayer_perceptron(X, weights, biases):\n",
    "    # Hidden layer 1\n",
    "    layer_1 = tf.add(tf.matmul(X, weights['syn0']), biases['b0'])\n",
    "    # Hidden layer 2\n",
    "    layer_2 = tf.add(tf.matmul(layer_1, weights['syn1']), biases['b1'])\n",
    "    # Output layer\n",
    "    out_layer = tf.matmul(layer_2, weights['syn2']) + biases['b2']\n",
    "    return out_layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# With biases.\n",
    "weights = {\n",
    "    'syn0': tf.Variable(tf.random_normal([input_dim, hidden_dim_1])),\n",
    "    'syn1': tf.Variable(tf.random_normal([hidden_dim_1, hidden_dim_2])),\n",
    "    'syn2': tf.Variable(tf.random_normal([hidden_dim_2, output_dim]))\n",
    "}\n",
    "\n",
    "\n",
    "biases = {\n",
    "    'b0': tf.Variable(tf.random_normal([hidden_dim_1])),\n",
    "    'b1': tf.Variable(tf.random_normal([hidden_dim_2])),\n",
    "    'b2': tf.Variable(tf.random_normal([output_dim]))\n",
    "}\n",
    "\n",
    "\n",
    "# Create a model\n",
    "def multilayer_perceptron(X, weights, biases):\n",
    "    # Hidden layer 1  + sigmoid activation function\n",
    "    layer_1 = tf.add(tf.matmul(X, weights['syn0']), biases['b0'])\n",
    "    layer_1 = tf.nn.sigmoid(layer_1)\n",
    "    # Hidden layer 2 + sigmoid activation function\n",
    "    layer_2 = tf.add(tf.matmul(layer_1, weights['syn1']), biases['b1'])\n",
    "    layer_2 = tf.nn.sigmoid(layer_2)\n",
    "    # Output layer\n",
    "    out_layer = tf.matmul(layer_2, weights['syn2']) + biases['b2']\n",
    "    out_layer = tf.nn.sigmoid(out_layer)\n",
    "    return out_layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Construct model\n",
    "pred = multilayer_perceptron(x, weights, biases)\n",
    "\n",
    "# Define loss and optimizer\n",
    "cost = tf.sub(y, pred) \n",
    "# Or you can use fancy cost like:\n",
    "##tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))\n",
    "optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)\n",
    "init = tf.initialize_all_variables()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0],\n",
       "       [1],\n",
       "       [1]])"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array([[0,1,1]]).T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 0.99999201]\n",
      " [ 0.99999034]]\n"
     ]
    }
   ],
   "source": [
    "or_input = np.array([[0.,0.], [0.,1.], [1.,0.]])\n",
    "or_output = np.array([[0.,1.,1.]]).T\n",
    "\n",
    "# Launch the graph\n",
    "with tf.Session() as sess:\n",
    "    sess.run(init)\n",
    "    # Training cycle\n",
    "    for epoch in range(num_epochs):\n",
    "        batch_x, batch_y = or_input, or_output # Loop over all data points.\n",
    "        # Run optimization op (backprop) and cost op (to get loss value)\n",
    "        _, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})\n",
    "        #print (c)\n",
    "        \n",
    "    # Now let's test it on the unknown dataset.\n",
    "    new_inputs = np.array([[1.,1.], [1.,0.]])\n",
    "    feed_dict = {x: new_inputs}\n",
    "    predictions = sess.run(pred, feed_dict)\n",
    "    print (predictions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's do the same in tensorflow learn (aka skflow)!!!\n",
    "===="
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from tensorflow.contrib import learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "classifier = learn.DNNClassifier(hidden_units=[5, 3], n_classes=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py:1197: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future\n",
      "  result_shape.insert(dim, 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "DNNClassifier()"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "or_input = np.array([[0.,0.], [0.,1.], [1.,0.]])\n",
    "or_output = np.array([[0,1,1]]).T\n",
    "\n",
    "classifier.fit(or_input, or_output, steps=0.05, batch_size=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 0])"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier.predict(np.array([ [1., 1.], [1., 0.] , [0., 0.] , [0., 1.]]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py:1197: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future\n",
      "  result_shape.insert(dim, 1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([1, 1, 0, 1])"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from tensorflow.contrib import learn\n",
    "classifier = learn.DNNClassifier(hidden_units=[5, 3], n_classes=2)\n",
    "\n",
    "or_input = np.array([[0.,0.], [0.,1.], [1.,0.]])\n",
    "or_output = np.array([[0,1,1]]).T\n",
    "\n",
    "classifier.fit(or_input, or_output, steps=10000, batch_size=3)\n",
    "classifier.predict(np.array([ [1., 1.], [1., 0.] , [0., 0.] , [0., 1.]]))"
   ]
  },
  {
   "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": "3.5.1+"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}