diff --git a/2-Regression/1-Tools/notebook.ipynb b/2-Regression/1-Tools/notebook.ipynb
index 6e92813b9..184e20bfd 100644
--- a/2-Regression/1-Tools/notebook.ipynb
+++ b/2-Regression/1-Tools/notebook.ipynb
@@ -9,7 +9,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 118,
"metadata": {},
"outputs": [
{
@@ -26,45 +26,562 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 119,
"metadata": {},
"outputs": [
{
- "ename": "ModuleNotFoundError",
- "evalue": "No module named 'numpy'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[1;32mIn[10], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mnumpy\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mnp\u001b[39;00m\n\u001b[0;32m 3\u001b[0m a \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray([\u001b[38;5;241m1\u001b[39m,\u001b[38;5;241m2\u001b[39m,\u001b[38;5;241m3\u001b[39m,\u001b[38;5;241m4\u001b[39m],[\u001b[38;5;241m5\u001b[39m,\u001b[38;5;241m6\u001b[39m,\u001b[38;5;241m7\u001b[39m,\u001b[38;5;241m8\u001b[39m],[\u001b[38;5;241m9\u001b[39m,\u001b[38;5;241m10\u001b[39m,\u001b[38;5;241m11\u001b[39m,\u001b[38;5;241m12\u001b[39m])\n\u001b[0;32m 5\u001b[0m \u001b[38;5;28mprint\u001b[39m(a[\u001b[38;5;241m0\u001b[39m])\n",
- "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'numpy'"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[1 2 3 4]\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
- "a = np.array([1,2,3,4],[5,6,7,8],[9,10,11,12])\n",
+ "a = np.array([[1,2,3,4],[5,6,7,8],[9,10,11,12]])\n",
"\n",
"print(a[0])"
]
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 120,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import matplotlib.pyplot as plt\n",
+ "import numpy as np\n",
+ "from sklearn import datasets, linear_model, model_selection"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 121,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(442, 10)\n",
+ "[ 0.03807591 0.05068012 0.06169621 0.02187239 -0.0442235 -0.03482076\n",
+ " -0.04340085 -0.00259226 0.01990749 -0.01764613]\n"
+ ]
+ }
+ ],
+ "source": [
+ "X,y = datasets.load_diabetes(return_X_y=True)\n",
+ "columns = [\"age age in years\", \"sex\", \"bmi body mass index\",\"bp average blood pressure\",\"s1 tc, total serum cholesterol\",\"s2 ldl, low-density lipoproteins\",\"s3 hdl, high-density lipoproteins\",\"s4 tch, total cholesterol / HDL\",\"s5 ltg, possibly log of serum triglycerides level\",\"s6 glu, blood sugar level\"]\n",
+ "print(X.shape)\n",
+ "print(X[0])\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 122,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "3.12.5 (tags/v3.12.5:ff3bc82, Aug 6 2024, 20:45:27) [MSC v.1940 64 bit (AMD64)]\n"
+ "(442,)\n",
+ "(442, 1)\n"
]
}
],
"source": [
- "import sys\n",
- "print(sys.version)"
+ "columnNumber = 2\n",
+ "X = X[:,columnNumber]\n",
+ "print(X.shape)\n",
+ "X = X.reshape((-1,1))\n",
+ "print(X.shape)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Splitting between training and testing data and training"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 123,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "LinearRegression() In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "plt.scatter(X_test, y_test, color='red')\n",
+ "plt.plot(X_test, y_pred, color='green', linewidth=3)\n",
+ "plt.xlabel(f\"{columns[columnNumber]}\")\n",
+ "plt.ylabel(\"Disease Progression\")\n",
+ "plt.title(f\"A Graph Plot Showing Diabetes Progression Against {columns[columnNumber]}\")\n",
+ "plt.show()"
]
}
],