Update chapters 1, 2 and 4

end_to_end_project.ipynb

@@ -6,7 +6,9 @@
    "source": [
     "**Chapter 2 – End to end Machine Learning project**\n",
     "\n",
-    "*Welcome to Machine Learning Housing Corp.! Your task is to predict median house values in Californian districts, given a number of features from these districts.*"
+    "*Welcome to Machine Learning Housing Corp.! Your task is to predict median house values in Californian districts, given a number of features from these districts.*\n",
+    "\n",
+    "*This notebook contains all the sample code and solutions to the exercices in chapter 2.*"
    ]
   },
   {
@@ -20,7 +22,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "First, let's make sure this notebook works well in both python 2 and 3:"
+    "First, let's make sure this notebook works well in both python 2 and 3, import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures:"
    ]
   },
   {
@@ -31,23 +33,34 @@
    },
    "outputs": [],
    "source": [
+    "# To support both python 2 and python 3\n",
     "from __future__ import division, print_function, unicode_literals\n",
     "\n",
+    "# Common imports\n",
+    "import numpy as np\n",
+    "import numpy.random as rnd\n",
     "import os\n",
     "\n",
+    "# to make this notebook's output stable across runs\n",
+    "rnd.seed(42)\n",
+    "\n",
+    "# To plot pretty figures\n",
     "%matplotlib inline\n",
+    "import matplotlib\n",
     "import matplotlib.pyplot as plt\n",
     "plt.rcParams['axes.labelsize'] = 14\n",
     "plt.rcParams['xtick.labelsize'] = 12\n",
     "plt.rcParams['ytick.labelsize'] = 12\n",
     "\n",
+    "# Where to save the figures\n",
     "PROJECT_ROOT_DIR = \".\"\n",
     "CHAPTER_ID = \"end_to_end_project\"\n",
     "\n",
-    "def save_fig(fig_id):\n",
+    "def save_fig(fig_id, tight_layout=True):\n",
     "    path = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID, fig_id + \".png\")\n",
     "    print(\"Saving figure\", fig_id)\n",
-    "    plt.tight_layout()\n",
+    "    if tight_layout:\n",
+    "        plt.tight_layout()\n",
     "    plt.savefig(path, format='png', dpi=300)"
    ]
   },
@@ -66,7 +79,7 @@
    },
    "outputs": [],
    "source": [
-    "DATASETS_URL = \"https://github.com/ageron/ml-notebooks/raw/master/datasets\""
+    "DATASETS_URL = \"https://github.com/ageron/handson-ml/raw/master/datasets\""
    ]
   },
   {
@@ -951,7 +964,7 @@
    ],
    "source": [
     "housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\")\n",
-    "save_fig(\"bad_visualization\")"
+    "save_fig(\"bad_visualization_plot\")"
    ]
   },
   {
@@ -981,7 +994,7 @@
    ],
    "source": [
     "housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", alpha=0.1)\n",
-    "save_fig(\"better_visualization\")"
+    "save_fig(\"better_visualization_plot\")"
    ]
   },
   {
@@ -1065,7 +1078,7 @@
     "cbar.set_label('Median House Value', fontsize=16)\n",
     "\n",
     "plt.legend(fontsize=16)\n",
-    "save_fig(\"california_housing_prices\")\n",
+    "save_fig(\"california_housing_prices_plot\")\n",
     "plt.show()"
    ]
   },
@@ -3384,6 +3397,29 @@
     "plt.hist(expon_distrib, bins=50)\n",
     "plt.show()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Exercise solutions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Coming soon**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -3404,10 +3440,17 @@
    "pygments_lexer": "ipython3",
    "version": "3.5.1"
   },
+  "nav_menu": {
+   "height": "279px",
+   "width": "309px"
+  },
   "toc": {
+   "navigate_menu": true,
+   "number_sections": true,
+   "sideBar": true,
+   "threshold": 6,
    "toc_cell": false,
-   "toc_number_sections": true,
-   "toc_threshold": 6,
+   "toc_section_display": "block",
    "toc_window_display": false
   }
  },