{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50\n",
      " - 0s - loss: 0.0588\n",
      "Epoch 2/50\n",
      " - 0s - loss: 0.0277\n",
      "Epoch 3/50\n",
      " - 0s - loss: 0.0247\n",
      "Epoch 4/50\n",
      " - 0s - loss: 0.0234\n",
      "Epoch 5/50\n",
      " - 0s - loss: 0.0227\n",
      "Epoch 6/50\n",
      " - 0s - loss: 0.0211\n",
      "Epoch 7/50\n",
      " - 0s - loss: 0.0191\n",
      "Epoch 8/50\n",
      " - 0s - loss: 0.0168\n",
      "Epoch 9/50\n",
      " - 0s - loss: 0.0139\n",
      "Epoch 10/50\n",
      " - 0s - loss: 0.0113\n",
      "Epoch 11/50\n",
      " - 0s - loss: 0.0088\n",
      "Epoch 12/50\n",
      " - 0s - loss: 0.0065\n",
      "Epoch 13/50\n",
      " - 0s - loss: 0.0048\n",
      "Epoch 14/50\n",
      " - 0s - loss: 0.0032\n",
      "Epoch 15/50\n",
      " - 0s - loss: 0.0024\n",
      "Epoch 16/50\n",
      " - 0s - loss: 0.0017\n",
      "Epoch 17/50\n",
      " - 0s - loss: 0.0014\n",
      "Epoch 18/50\n",
      " - 0s - loss: 0.0012\n",
      "Epoch 19/50\n",
      " - 0s - loss: 0.0010\n",
      "Epoch 20/50\n",
      " - 0s - loss: 8.8411e-04\n",
      "Epoch 21/50\n",
      " - 0s - loss: 8.2826e-04\n",
      "Epoch 22/50\n",
      " - 0s - loss: 7.6278e-04\n",
      "Epoch 23/50\n",
      " - 0s - loss: 6.5110e-04\n",
      "Epoch 24/50\n",
      " - 0s - loss: 6.3048e-04\n",
      "Epoch 25/50\n",
      " - 0s - loss: 5.7419e-04\n",
      "Epoch 26/50\n",
      " - 0s - loss: 5.7883e-04\n",
      "Epoch 27/50\n",
      " - 0s - loss: 5.1502e-04\n",
      "Epoch 28/50\n",
      " - 0s - loss: 4.3292e-04\n",
      "Epoch 29/50\n",
      " - 0s - loss: 4.5275e-04\n",
      "Epoch 30/50\n",
      " - 0s - loss: 3.9630e-04\n",
      "Epoch 31/50\n",
      " - 0s - loss: 3.7888e-04\n",
      "Epoch 32/50\n",
      " - 0s - loss: 3.9089e-04\n",
      "Epoch 33/50\n",
      " - 0s - loss: 3.2177e-04\n",
      "Epoch 34/50\n",
      " - 0s - loss: 3.0820e-04\n",
      "Epoch 35/50\n",
      " - 0s - loss: 2.7886e-04\n",
      "Epoch 36/50\n",
      " - 0s - loss: 2.6574e-04\n",
      "Epoch 37/50\n",
      " - 0s - loss: 2.6187e-04\n",
      "Epoch 38/50\n",
      " - 0s - loss: 2.3749e-04\n",
      "Epoch 39/50\n",
      " - 0s - loss: 2.4857e-04\n",
      "Epoch 40/50\n",
      " - 0s - loss: 2.4797e-04\n",
      "Epoch 41/50\n",
      " - 0s - loss: 2.0134e-04\n",
      "Epoch 42/50\n",
      " - 0s - loss: 2.0205e-04\n",
      "Epoch 43/50\n",
      " - 0s - loss: 2.0219e-04\n",
      "Epoch 44/50\n",
      " - 0s - loss: 1.9717e-04\n",
      "Epoch 45/50\n",
      " - 0s - loss: 1.7174e-04\n",
      "Epoch 46/50\n",
      " - 0s - loss: 1.7831e-04\n",
      "Epoch 47/50\n",
      " - 0s - loss: 1.9075e-04\n",
      "Epoch 48/50\n",
      " - 0s - loss: 1.6237e-04\n",
      "Epoch 49/50\n",
      " - 0s - loss: 1.7307e-04\n",
      "Epoch 50/50\n",
      " - 0s - loss: 1.6758e-04\n",
      "The mean squared error (MSE) for the test data set is: 0.00019516230269800872\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import keras\n",
    "from keras.models import Sequential\n",
    "from keras.layers import *\n",
    "\n",
    "RUN_NAME = \"run 2 with 5 nodes\"\n",
    "\n",
    "training_data_df = pd.read_csv(\"Exercise Files/06/sales_data_training_scaled.csv\")\n",
    "\n",
    "X = training_data_df.drop('total_earnings', axis=1).values\n",
    "Y = training_data_df[['total_earnings']].values\n",
    "\n",
    "# Define the model\n",
    "model = Sequential()\n",
    "model.add(Dense(5, input_dim=9, activation='relu', name='layer_1'))\n",
    "model.add(Dense(100, activation='relu', name='layer_2'))\n",
    "model.add(Dense(50, activation='relu', name='layer_3'))\n",
    "model.add(Dense(1, activation='linear', name='output_layer'))\n",
    "model.compile(loss='mean_squared_error', optimizer='adam')\n",
    "\n",
    "# Create a TensorBoard logger\n",
    "logger = keras.callbacks.TensorBoard(\n",
    "    log_dir='Exercise Files/06/logs/{}'.format(RUN_NAME),\n",
    "#     histogram_freq=5,\n",
    "    write_graph=True\n",
    ")\n",
    "\n",
    "# Train the model\n",
    "model.fit(\n",
    "    X,\n",
    "    Y,\n",
    "    epochs=50,\n",
    "    shuffle=True,\n",
    "    verbose=2,\n",
    "    callbacks=[logger]\n",
    ")\n",
    "\n",
    "# Load the separate test data set\n",
    "test_data_df = pd.read_csv(\"Exercise Files/06/sales_data_test_scaled.csv\")\n",
    "\n",
    "X_test = test_data_df.drop('total_earnings', axis=1).values\n",
    "Y_test = test_data_df[['total_earnings']].values\n",
    "\n",
    "test_error_rate = model.evaluate(X_test, Y_test, verbose=0)\n",
    "print(\"The mean squared error (MSE) for the test data set is: {}\".format(test_error_rate))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:keras]",
   "language": "python",
   "name": "conda-env-keras-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}