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": "3.7.0"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7",
   "display_name": "Python 3.7.0 64-bit ('3.7')"
  },
  "metadata": {
   "interpreter": {
    "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
   }
  }
 },
 "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(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
      ]
     },
     "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;white-space:pre;}\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=\"m789fb0d015\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#pba36295171)\">\n     <use style=\"stroke:#000000;\" x=\"127.932027\" xlink:href=\"#m789fb0d015\" y=\"148.433275\"/>\n     <use style=\"stroke:#000000;\" x=\"139.018575\" xlink:href=\"#m789fb0d015\" y=\"174.186365\"/>\n     <use style=\"stroke:#000000;\" x=\"262.356425\" xlink:href=\"#m789fb0d015\" y=\"180.624637\"/>\n     <use style=\"stroke:#000000;\" x=\"152.876761\" xlink:href=\"#m789fb0d015\" y=\"181.268465\"/>\n     <use style=\"stroke:#000000;\" x=\"295.616069\" xlink:href=\"#m789fb0d015\" y=\"140.707349\"/>\n     <use style=\"stroke:#000000;\" x=\"240.183328\" xlink:href=\"#m789fb0d015\" y=\"88.557342\"/>\n     <use style=\"stroke:#000000;\" x=\"233.254235\" xlink:href=\"#m789fb0d015\" y=\"147.789448\"/>\n     <use style=\"stroke:#000000;\" x=\"139.018575\" xlink:href=\"#m789fb0d015\" y=\"115.598086\"/>\n     <use style=\"stroke:#000000;\" x=\"111.302205\" xlink:href=\"#m789fb0d015\" y=\"174.830192\"/>\n     <use style=\"stroke:#000000;\" x=\"96.058201\" xlink:href=\"#m789fb0d015\" y=\"196.720318\"/>\n     <use style=\"stroke:#000000;\" x=\"137.632757\" xlink:href=\"#m789fb0d015\" y=\"174.186365\"/>\n     <use style=\"stroke:#000000;\" x=\"104.373112\" xlink:href=\"#m789fb0d015\" y=\"143.926485\"/>\n     <use style=\"stroke:#000000;\" x=\"161.191672\" xlink:href=\"#m789fb0d015\" y=\"108.515987\"/>\n     <use style=\"stroke:#000000;\" x=\"101.601475\" xlink:href=\"#m789fb0d015\" y=\"190.282046\"/>\n     <use style=\"stroke:#000000;\" x=\"144.56185\" xlink:href=\"#m789fb0d015\" y=\"188.994391\"/>\n     <use style=\"stroke:#000000;\" x=\"147.333487\" xlink:href=\"#m789fb0d015\" y=\"130.406113\"/>\n     <use style=\"stroke:#000000;\" x=\"158.420035\" xlink:href=\"#m789fb0d015\" y=\"91.776479\"/>\n     <use style=\"stroke:#000000;\" x=\"165.349127\" xlink:href=\"#m789fb0d015\" y=\"210.884517\"/>\n     <use style=\"stroke:#000000;\" x=\"137.632757\" xlink:href=\"#m789fb0d015\" y=\"186.419082\"/>\n     <use style=\"stroke:#000000;\" x=\"145.947668\" xlink:href=\"#m789fb0d015\" y=\"134.269076\"/>\n     <use style=\"stroke:#000000;\" x=\"115.45966\" xlink:href=\"#m789fb0d015\" y=\"141.995003\"/>\n     <use style=\"stroke:#000000;\" x=\"145.947668\" xlink:href=\"#m789fb0d015\" y=\"185.131428\"/>\n     <use style=\"stroke:#000000;\" x=\"199.994591\" xlink:href=\"#m789fb0d015\" y=\"158.090684\"/>\n     <use style=\"stroke:#000000;\" x=\"274.828791\" xlink:href=\"#m789fb0d015\" y=\"17.092519\"/>\n     <use style=\"stroke:#000000;\" x=\"105.758931\" xlink:href=\"#m789fb0d015\" y=\"192.213528\"/>\n     <use style=\"stroke:#000000;\" x=\"169.506583\" xlink:href=\"#m789fb0d015\" y=\"156.159202\"/>\n     <use style=\"stroke:#000000;\" x=\"80.814197
      "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": []
  }
 ]
}