adjust DATA_PATH, use it in 02 and 04

Author: amueller

02-supervised-learning.ipynb

@@ -2290,8 +2290,8 @@
     }
    ],
    "source": [
-    "import pandas as pd\n",
-    "ram_prices = pd.read_csv(\"data/ram_price.csv\")\n",
+    "import os\n",
+    "ram_prices = pd.read_csv(os.path.join(mglearn.datasets.DATA_PATH, \"ram_price.csv\"))\n",
     "\n",
     "plt.semilogy(ram_prices.date, ram_prices.price)\n",
     "plt.xlabel(\"Year\")\n",
@@ -4622,9 +4622,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [Root]",
+   "display_name": "Python [conda root]",
    "language": "python",
-   "name": "Python [Root]"
+   "name": "conda-root-py"
   },
   "language_info": {
    "codemirror_mode": {

04-representing-data-feature-engineering.ipynb

@@ -27,14 +27,6 @@
     "### Categorical Variables"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\begin{align*}\n",
-    "\\end{align*}"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -142,11 +134,11 @@
     }
    ],
    "source": [
-    "import pandas as pd\n",
+    "import os\n",
     "# The file has no headers naming the columns, so we pass header=None\n",
     "# and provide the column names explicitly in \"names\"\n",
     "data = pd.read_csv(\n",
-    "    \"data/adult.data\", header=None, index_col=False,\n",
+    "    os.path.join(mglearn.datasets.DATA_FOLDER, \"adult.data\"), header=None, index_col=False,\n",
     "    names=['age', 'workclass', 'fnlwgt', 'education',  'education-num',\n",
     "           'marital-status', 'occupation', 'relationship', 'race', 'gender',\n",
     "           'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',\n",
@@ -2133,9 +2125,9 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python [Root]",
+   "display_name": "Python [conda root]",
    "language": "python",
-   "name": "Python [Root]"
+   "name": "conda-root-py"
   },
   "language_info": {
    "codemirror_mode": {

mglearn/datasets.py

@@ -6,7 +6,7 @@
 from sklearn.preprocessing import MinMaxScaler, PolynomialFeatures
 from .make_blobs import make_blobs
 
-DATA_FOLDER = os.path.join(os.path.dirname(__file__), "data")
+DATA_FOLDER = os.path.join(os.path.dirname(__file__), "..", "data")
 
 
 def make_forge():