{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Linear Regression for Diabetes dataset - Lesson 1"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Import needed libraries"
]
},
{
"cell_type": "code",
"execution_count": 12,
"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": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"from sklearn import datasets, linear_model, model_selection\n",
"\n",
"# Load the diabetes dataset\n",
"X, y= datasets.load_diabetes(return_X_y=True)\n",
"# Print the shape of the data and the first row\n",
"print(X.shape)\n",
"print(X[0])"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(442,)\n",
"(442, 1)\n"
]
}
],
"source": [
"# Extract the column at index 2 bmi\n",
"X = X[:,2]\n",
"print(X.shape)\n",
"\n",
"# Shape to a 2D array\n",
"X = X.reshape(-1,1)\n",
"print(X.shape)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"# split the data into training and testing data\n",
"X_train, X_test,y_train, y_test = model_selection.train_test_split(X,y, test_size=0.33)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"LinearRegression() In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. \n",
"
\n",
"
\n",
" Parameters \n",
" \n",
" \n",
" \n",
" \n",
" fit_intercept \n",
" True \n",
" \n",
" \n",
"\n",
" \n",
" copy_X \n",
" True \n",
" \n",
" \n",
"\n",
" \n",
" tol \n",
" 1e-06 \n",
" \n",
" \n",
"\n",
" \n",
" n_jobs \n",
" None \n",
" \n",
" \n",
"\n",
" \n",
" positive \n",
" False \n",
" \n",
" \n",
" \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# create a scatter plot\n",
"plt.scatter(X_test, y_test, color='black')\n",
"\n",
"# Plot the prediction\n",
"plt.plot(X_test, y_pred, color='blue', linewidth=3)\n",
"\n",
"# Add labels and a title\n",
"plt.xlabel('Scale BMIs')\n",
"plt.ylabel('Disease Progression')\n",
"plt.title('A Graph plot Showing Diabetes Progression Against BMI')\n",
"\n",
"# Draw the plot\n",
"plt.show()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
},
"metadata": {
"interpreter": {
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
}
},
"orig_nbformat": 2
},
"nbformat": 4,
"nbformat_minor": 2
}