ML-For-Beginners/2-Regression/1-Tools/solution/notebook.ipynb

{
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3-final"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3",
   "language": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "source": [
    "## Linear Regression for North American Pumpkins - Lesson 1"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "source": [
    "Import needed libraries"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn import datasets, linear_model, model_selection\n"
   ]
  },
  {
   "source": [
    "Load the diabetes dataset, divided into `X` data and `y` features"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "(442, 10)\n[ 0.03807591  0.05068012  0.06169621  0.02187235 -0.0442235  -0.03482076\n -0.04340085 -0.00259226  0.01990842 -0.01764613]\n"
     ]
    }
   ],
   "source": [
    "X, y = datasets.load_diabetes(return_X_y=True)\n",
    "print(X.shape)\n",
    "print(X[0])"
   ]
  },
  {
   "source": [
    "Select just one feature to target for this exercise"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X[:, np.newaxis, 2]\n"
   ]
  },
  {
   "source": [
    "Split the training and test data for both `X` and `y`"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.33)\n"
   ]
  },
  {
   "source": [
    "Select the model and fit it with the training data"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "metadata": {},
     "execution_count": 5
    }
   ],
   "source": [
    "model = linear_model.LinearRegression()\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "source": [
    "Use test data to predict a line"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model.predict(X_test)\n"
   ]
  },
  {
   "source": [
    "Display the results in a plot"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"248.518125pt\" version=\"1.1\" viewBox=\"0 0 375.2875 248.518125\" width=\"375.2875pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n  <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 248.518125 \nL 375.2875 248.518125 \nL 375.2875 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n  </g>\n  <g id=\"axes_1\">\n   <g id=\"patch_2\">\n    <path d=\"M 33.2875 224.64 \nL 368.0875 224.64 \nL 368.0875 7.2 \nL 33.2875 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n   </g>\n   <g id=\"PathCollection_1\">\n    <defs>\n     <path d=\"M 0 3 \nC 0.795609 3 1.55874 2.683901 2.12132 2.12132 \nC 2.683901 1.55874 3 0.795609 3 0 \nC 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \nC 1.55874 -2.683901 0.795609 -3 0 -3 \nC -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \nC -2.683901 -1.55874 -3 -0.795609 -3 0 \nC -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \nC -1.55874 2.683901 -0.795609 3 0 3 \nz\n\" id=\"m24aebb984e\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#p966a7f7ee7)\">\n     <use style=\"stroke:#000000;\" x=\"137.939547\" xlink:href=\"#m24aebb984e\" y=\"196.520872\"/>\n     <use style=\"stroke:#000000;\" x=\"163.904217\" xlink:href=\"#m24aebb984e\" y=\"95.860959\"/>\n     <use style=\"stroke:#000000;\" x=\"217.276039\" xlink:href=\"#m24aebb984e\" y=\"108.990513\"/>\n     <use style=\"stroke:#000000;\" x=\"197.081296\" xlink:href=\"#m24aebb984e\" y=\"38.236806\"/>\n     <use style=\"stroke:#000000;\" x=\"100.435023\" xlink:href=\"#m24aebb984e\" y=\"188.497256\"/>\n     <use style=\"stroke:#000000;\" x=\"81.682761\" xlink:href=\"#m24aebb984e\" y=\"173.179443\"/>\n     <use style=\"stroke:#000000;\" x=\"135.054583\" xlink:href=\"#m24aebb984e\" y=\"171.720604\"/>\n     <use style=\"stroke:#000000;\" x=\"107.647431\" xlink:href=\"#m24aebb984e\" y=\"190.685515\"/>\n     <use style=\"stroke:#000000;\" x=\"244.683192\" xlink:href=\"#m24aebb984e\" y=\"44.801583\"/>\n     <use style=\"stroke:#000000;\" x=\"207.178668\" xlink:href=\"#m24aebb984e\" y=\"137.43788\"/>\n     <use style=\"stroke:#000000;\" x=\"166.78918\" xlink:href=\"#m24aebb984e\" y=\"108.261094\"/>\n     <use style=\"stroke:#000000;\" x=\"250.453118\" xlink:href=\"#m24aebb984e\" y=\"65.954753\"/>\n     <use style=\"stroke:#000000;\" x=\"113.417358\" xlink:href=\"#m24aebb984e\" y=\"168.073506\"/>\n     <use style=\"stroke:#000000;\" x=\"250.453118\" xlink:href=\"#m24aebb984e\" y=\"64.495914\"/>\n     <use style=\"stroke:#000000;\" x=\"241.798228\" xlink:href=\"#m24aebb984e\" y=\"106.802254\"/>\n     <use style=\"stroke:#000000;\" x=\"161.019254\" xlink:href=\"#m24aebb984e\" y=\"145.461496\"/>\n     <use style=\"stroke:#000000;\" x=\"117.744803\" xlink:href=\"#m24aebb984e\" y=\"92.943281\"/>\n     <use style=\"stroke:#000000;\" x=\"166.78918\" xlink:href=\"#m24aebb984e\" y=\"163.696988\"/>\n     <use style=\"stroke:#000000;\" x=\"126.399693\" xlink:href=\"#m24aebb984e\" y=\"179.74422\"/>\n     <use style=\"stroke:#000000;\" x=\"70.142907\" xlink:href=\"#m24aebb984e\" y=\"208.191587\"/>\n     <use style=\"stroke:#000000;\" x=\"287.957642\" xlink:href=\"#m24aebb984e\" y=\"39.695646\"/>\n     <use style=\"stroke:#000000;\" x=\"220.161003\" xlink:href=\"#m24aebb984e\" y=\"121.390647\"/>\n     <use style=\"stroke:#000000;\" x=\"181.213997\" xlink:href=\"#m24aebb984e\" y=\"150.567434\"/>\n     <use style=\"stroke:#000000;\" x=\"71.585389\" xlink:href=\"#m24aebb984e\" y=\"139.626139\"/>\n     <use style=\"stroke:#000000;\" x=\"175.44407\" xlink:href=\"#m24aebb984e\" y=\"208.191587\"/>\n     <use style=\"stroke:#000000;\" x=\"78.797797\" xlink:href=\"#m24aebb984e\" y=\"203.085649\"/>\n     <use style=\"stroke:#000000;\" x=\"122.072248\" xlink:href=\"#m24aebb9
      "image/png": "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
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "plt.scatter(X_test, y_test,  color='black')\n",
    "plt.plot(X_test, y_pred, color='blue', linewidth=3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ]
}