Merge ab932e8899 into d0d0ea2b2d

2-Regression/1-Tools/notebook.ipynb

@@ -0,0 +1,128 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ccd1edc5",
+   "metadata": {},
+   "source": [
+    "### In order to create a regression model using the Linnerud dataset, you first load the data, then select one of the exercise variables (for example, sit-ups) as the input feature and one of the physiological variables (for example, waistline) as the output variable, fit a regression model such as LinearRegression, and then assess it and, if desired, plot the relationship; you carry out this procedure for each combination of exercise and physiological variables that you are interested in.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4fc227b7",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import load_linnerud\n",
+    "\n",
+    "data = load_linnerud(as_frame=True)\n",
+    "X = data.data        # exercises\n",
+    "y = data.target      # physiological measures"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fad548fe",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "X_situps = X[[\"Situps\"]]   # 2D DataFrame\n",
+    "y_waist = y[\"Waist\"]       # Series"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "325f344e",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(\n",
+    "    X_situps, y_waist, test_size=0.25, random_state=42\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "930b8b74",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71cee5ee",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "y_pred = model.predict(X_test)\n",
+    "mse = mean_squared_error(y_test, y_pred)\n",
+    "r2 = r2_score(y_test, y_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2533995",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "plt.scatter(X_situps, y_waist, label=\"Data\")\n",
+    "x_vals = np.linspace(X_situps.min(), X_situps.max(), 100).reshape(-1, 1)\n",
+    "plt.plot(x_vals, model.predict(x_vals), color=\"red\", label=\"Fit\")\n",
+    "plt.xlabel(\"Situps\")\n",
+    "plt.ylabel(\"Waist\")\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}