Large change: replace os.path with pathlib, move to Python 3.7

02_end_to_end_machine_learning_project.ipynb

@@ -4,8 +4,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Chapter 2 – End-to-end Machine Learning project**\n",
-    "\n",
+    "**Chapter 2 – End-to-end Machine Learning project**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "*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.*"
@@ -36,7 +41,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "First, let's import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures. We also check that Python 3.5 or later is installed (although Python 2.x may work, it is deprecated so we strongly recommend you use Python 3 instead), as well as Scikit-Learn ≥0.20."
+    "First, let's import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures."
    ]
   },
   {
@@ -45,17 +50,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Python ≥3.5 is required\n",
+    "# Python ≥3.7 is required\n",
     "import sys\n",
-    "assert sys.version_info >= (3, 5)\n",
+    "assert sys.version_info >= (3, 7)\n",
     "\n",
-    "# Scikit-Learn ≥0.20 is required\n",
+    "# Scikit-Learn ≥1.0 is required\n",
     "import sklearn\n",
-    "assert sklearn.__version__ >= \"0.20\"\n",
+    "assert sklearn.__version__ >= \"1.0\"\n",
     "\n",
     "# Common imports\n",
     "import numpy as np\n",
-    "import os\n",
+    "from pathlib import Path\n",
     "\n",
     "# To plot pretty figures\n",
     "%matplotlib inline\n",
@@ -66,14 +71,11 @@
     "mpl.rc('ytick', labelsize=12)\n",
     "\n",
     "# Where to save the figures\n",
-    "PROJECT_ROOT_DIR = \".\"\n",
-    "CHAPTER_ID = \"end_to_end_project\"\n",
-    "IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID)\n",
-    "os.makedirs(IMAGES_PATH, exist_ok=True)\n",
+    "IMAGES_PATH = Path() / \"images\" / \"end_to_end_project\"\n",
+    "IMAGES_PATH.mkdir(parents=True, exist_ok=True)\n",
     "\n",
     "def save_fig(fig_id, tight_layout=True, fig_extension=\"png\", resolution=300):\n",
-    "    path = os.path.join(IMAGES_PATH, fig_id + \".\" + fig_extension)\n",
-    "    print(\"Saving figure\", fig_id)\n",
+    "    path = IMAGES_PATH / f\"{fig_id}.{fig_extension}\"\n",
     "    if tight_layout:\n",
     "        plt.tight_layout()\n",
     "    plt.savefig(path, format=fig_extension, dpi=resolution)"
@@ -95,48 +97,36 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from pathlib import Path\n",
     "import tarfile\n",
     "import urllib.request\n",
-    "\n",
-    "DOWNLOAD_ROOT = \"https://raw.githubusercontent.com/ageron/handson-ml2/master/\"\n",
-    "HOUSING_PATH = os.path.join(\"datasets\", \"housing\")\n",
-    "HOUSING_URL = DOWNLOAD_ROOT + \"datasets/housing/housing.tgz\"\n",
-    "\n",
-    "def fetch_housing_data(housing_url=HOUSING_URL, housing_path=HOUSING_PATH):\n",
-    "    if not os.path.isdir(housing_path):\n",
-    "        os.makedirs(housing_path)\n",
-    "    tgz_path = os.path.join(housing_path, \"housing.tgz\")\n",
-    "    urllib.request.urlretrieve(housing_url, tgz_path)\n",
-    "    housing_tgz = tarfile.open(tgz_path)\n",
-    "    housing_tgz.extractall(path=housing_path)\n",
-    "    housing_tgz.close()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "fetch_housing_data()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "import pandas as pd\n",
     "\n",
-    "def load_housing_data(housing_path=HOUSING_PATH):\n",
-    "    csv_path = os.path.join(housing_path, \"housing.csv\")\n",
-    "    return pd.read_csv(csv_path)"
+    "def load_housing_data():\n",
+    "    housing_path = Path() / \"datasets\" / \"housing\"\n",
+    "    if not (housing_path / \"housing.csv\").is_file():\n",
+    "        housing_path.mkdir(parents=True, exist_ok=True)\n",
+    "        root = \"https://raw.githubusercontent.com/ageron/handson-ml2/master/\"\n",
+    "        url = root + \"datasets/housing/housing.tgz\"\n",
+    "        tgz_path = housing_path / \"housing.tgz\"\n",
+    "        urllib.request.urlretrieve(url, tgz_path)\n",
+    "        housing_tgz = tarfile.open(tgz_path)\n",
+    "        housing_tgz.extractall(path=housing_path)\n",
+    "        housing_tgz.close()\n",
+    "    return pd.read_csv(housing_path / \"housing.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "housing = load_housing_data()"
    ]
   },
   {
@@ -526,18 +516,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Download the California image\n",
-    "images_path = os.path.join(PROJECT_ROOT_DIR, \"images\", \"end_to_end_project\")\n",
-    "os.makedirs(images_path, exist_ok=True)\n",
-    "DOWNLOAD_ROOT = \"https://raw.githubusercontent.com/ageron/handson-ml2/master/\"\n",
+    "images_path = Path() / \"images\" / \"end_to_end_project\"\n",
     "filename = \"california.png\"\n",
-    "print(\"Downloading\", filename)\n",
-    "url = DOWNLOAD_ROOT + \"images/end_to_end_project/\" + filename\n",
-    "urllib.request.urlretrieve(url, os.path.join(images_path, filename))"
+    "if not (images_path / filename).is_file():\n",
+    "    images_path.mkdir(parents=True, exist_ok=True)\n",
+    "    root = \"https://raw.githubusercontent.com/ageron/handson-ml2/master/\"\n",
+    "    url = root + \"images/end_to_end_project/\" + filename\n",
+    "    print(\"Downloading\", filename)\n",
+    "    urllib.request.urlretrieve(url, images_path / filename)"
    ]
   },
   {
@@ -547,7 +538,8 @@
    "outputs": [],
    "source": [
     "import matplotlib.image as mpimg\n",
-    "california_img=mpimg.imread(os.path.join(images_path, filename))\n",
+    "\n",
+    "california_img=mpimg.imread(images_path / filename)\n",
     "ax = housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", figsize=(10,7),\n",
     "                  s=housing['population']/100, label=\"Population\",\n",
     "                  c=\"median_house_value\", cmap=plt.get_cmap(\"jet\"),\n",
@@ -2342,7 +2334,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },