Classif + regression

TP/TP2_mardi/main.ipynb

@@ -2,21 +2,64 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import numpy as np"
+    "import numpy as np\n",
+    "# Des datasets comme discuté au téléhphone @Théophile"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 14,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((569, 30), (569,))"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Boston dataset (Régression)\n",
+    "# https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html\n",
+    "# Prix des maisons à Boston (cf le site pour les variables)\n",
+    "from sklearn.datasets import load_boston\n",
+    "boston = load_boston()\n",
+    "X, y = boston[\"data\"], boston[\"target\"]\n",
+    "X.shape, y.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((569, 30), (569,))"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "# Des datasets comme discuté au téléhphone @Théophile\n",
-    "\n"
+    "# Breast cancer dataset (classification)\n",
+    "# https://scikit-learn.org/stable/datasets/index.html#breast-cancer-wisconsin-diagnostic-dataset\n",
+    "# Données sur les tumeurs : cette tumeur est-elle cancéreuse ?\n",
+    "from sklearn.datasets import load_breast_cancer\n",
+    "breast = load_breast_cancer()\n",
+    "X, y = breast[\"data\"], breast[\"target\"]\n",
+    "X.shape, y.shape"
    ]
   },
   {