notebooks/week5_solutions.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Week 5 - An introduction to machine learning (PART1) - Solutions.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zMpGRu9kwiC3"
      },
      "source": [
        "# Week 6 - An introduction to machine learning (PART1) - Solutions"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kzVexm-twrWH"
      },
      "source": [
        "We will work with the built-in `sklearn.datasets` diabetes dataset.\n",
        "This dataset comprises 442 diabetes patients, each with ten baseline predictors: age, sex, body mass index, average blood pressure, and six blood serum measurements. The response variable is measure of disease progression one year after baseline. (Note that it is not neccessary to transform any of these variables prior to training the model - everything is all ready to go straight into `sklearn`.)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yikR55udOcqG"
      },
      "source": [
        "Details:\n",
        "\n",
        "https://scikit-learn.org/stable/datasets/toy_dataset.html#diabetes-dataset\n",
        "\n",
        "https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8SA91PY0wgJi"
      },
      "source": [
        "import pandas as pd\n",
        "import plotnine as p9\n",
        "from sklearn import datasets\n",
        "import sklearn.linear_model as linear"
      ],
      "execution_count": 108,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 205
        },
        "id": "SVdY9Cs9w4QW",
        "outputId": "51bc94e4-927c-475a-c7c9-593bec8f180c"
      },
      "source": [
        "diabetes_dataset = datasets.load_diabetes()\n",
        "predictors = pd.DataFrame(data=diabetes_dataset.data, columns=diabetes_dataset.feature_names)\n",
        "response = diabetes_dataset.target\n",
        "\n",
        "predictors.head()"
      ],
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>age</th>\n",
              "      <th>sex</th>\n",
              "      <th>bmi</th>\n",
              "      <th>bp</th>\n",
              "      <th>s1</th>\n",
              "      <th>s2</th>\n",
              "      <th>s3</th>\n",
              "      <th>s4</th>\n",
              "      <th>s5</th>\n",
              "      <th>s6</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.038076</td>\n",
              "      <td>0.050680</td>\n",
              "      <td>0.061696</td>\n",
              "      <td>0.021872</td>\n",
              "      <td>-0.044223</td>\n",
              "      <td>-0.034821</td>\n",
              "      <td>-0.043401</td>\n",
              "      <td>-0.002592</td>\n",
              "      <td>0.019908</td>\n",
              "      <td>-0.017646</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>-0.001882</td>\n",
              "      <td>-0.044642</td>\n",
              "      <td>-0.051474</td>\n",
              "      <td>-0.026328</td>\n",
              "      <td>-0.008449</td>\n",
              "      <td>-0.019163</td>\n",
              "      <td>0.074412</td>\n",
              "      <td>-0.039493</td>\n",
              "      <td>-0.068330</td>\n",
              "      <td>-0.092204</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.085299</td>\n",
              "      <td>0.050680</td>\n",
              "      <td>0.044451</td>\n",
              "      <td>-0.005671</td>\n",
              "      <td>-0.045599</td>\n",
              "      <td>-0.034194</td>\n",
              "      <td>-0.032356</td>\n",
              "      <td>-0.002592</td>\n",
              "      <td>0.002864</td>\n",
              "      <td>-0.025930</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>-0.089063</td>\n",
              "      <td>-0.044642</td>\n",
              "      <td>-0.011595</td>\n",
              "      <td>-0.036656</td>\n",
              "      <td>0.012191</td>\n",
              "      <td>0.024991</td>\n",
              "      <td>-0.036038</td>\n",
              "      <td>0.034309</td>\n",
              "      <td>0.022692</td>\n",
              "      <td>-0.009362</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.005383</td>\n",
              "      <td>-0.044642</td>\n",
              "      <td>-0.036385</td>\n",
              "      <td>0.021872</td>\n",
              "      <td>0.003935</td>\n",
              "      <td>0.015596</td>\n",
              "      <td>0.008142</td>\n",
              "      <td>-0.002592</td>\n",
              "      <td>-0.031991</td>\n",
              "      <td>-0.046641</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        age       sex       bmi  ...        s4        s5        s6\n",
              "0  0.038076  0.050680  0.061696  ... -0.002592  0.019908 -0.017646\n",
              "1 -0.001882 -0.044642 -0.051474  ... -0.039493 -0.068330 -0.092204\n",
              "2  0.085299  0.050680  0.044451  ... -0.002592  0.002864 -0.025930\n",
              "3 -0.089063 -0.044642 -0.011595  ...  0.034309  0.022692 -0.009362\n",
              "4  0.005383 -0.044642 -0.036385  ... -0.002592 -0.031991 -0.046641\n",
              "\n",
              "[5 rows x 10 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 299
        },
        "id": "j_pDx6BDP2M2",
        "outputId": "be1f50a2-2976-4ee2-8a1c-2c6abf180b93"
      },
      "source": [
        "response_dataframe = pd.DataFrame({\"response\": response})\n",
        "\n",
        "response_dataframe.describe()"
      ],
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>response</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>442.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>152.133484</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>77.093005</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>25.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>87.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>140.500000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>211.500000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>346.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         response\n",
              "count  442.000000\n",
              "mean   152.133484\n",
              "std     77.093005\n",
              "min     25.000000\n",
              "25%     87.000000\n",
              "50%    140.500000\n",
              "75%    211.500000\n",
              "max    346.000000"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 299
        },
        "id": "Z5soZEct602m",
        "outputId": "86c6f314-ab74-496e-b0e0-22b0f7caa623"
      },
      "source": [
        "predictors.describe()"
      ],
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>age</th>\n",
              "      <th>sex</th>\n",
              "      <th>bmi</th>\n",
              "      <th>bp</th>\n",
              "      <th>s1</th>\n",
              "      <th>s2</th>\n",
              "      <th>s3</th>\n",
              "      <th>s4</th>\n",
              "      <th>s5</th>\n",
              "      <th>s6</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "      <td>4.420000e+02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>-3.634285e-16</td>\n",
              "      <td>1.308343e-16</td>\n",
              "      <td>-8.045349e-16</td>\n",
              "      <td>1.281655e-16</td>\n",
              "      <td>-8.835316e-17</td>\n",
              "      <td>1.327024e-16</td>\n",
              "      <td>-4.574646e-16</td>\n",
              "      <td>3.777301e-16</td>\n",
              "      <td>-3.830854e-16</td>\n",
              "      <td>-3.412882e-16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "      <td>4.761905e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>-1.072256e-01</td>\n",
              "      <td>-4.464164e-02</td>\n",
              "      <td>-9.027530e-02</td>\n",
              "      <td>-1.123996e-01</td>\n",
              "      <td>-1.267807e-01</td>\n",
              "      <td>-1.156131e-01</td>\n",
              "      <td>-1.023071e-01</td>\n",
              "      <td>-7.639450e-02</td>\n",
              "      <td>-1.260974e-01</td>\n",
              "      <td>-1.377672e-01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>-3.729927e-02</td>\n",
              "      <td>-4.464164e-02</td>\n",
              "      <td>-3.422907e-02</td>\n",
              "      <td>-3.665645e-02</td>\n",
              "      <td>-3.424784e-02</td>\n",
              "      <td>-3.035840e-02</td>\n",
              "      <td>-3.511716e-02</td>\n",
              "      <td>-3.949338e-02</td>\n",
              "      <td>-3.324879e-02</td>\n",
              "      <td>-3.317903e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>5.383060e-03</td>\n",
              "      <td>-4.464164e-02</td>\n",
              "      <td>-7.283766e-03</td>\n",
              "      <td>-5.670611e-03</td>\n",
              "      <td>-4.320866e-03</td>\n",
              "      <td>-3.819065e-03</td>\n",
              "      <td>-6.584468e-03</td>\n",
              "      <td>-2.592262e-03</td>\n",
              "      <td>-1.947634e-03</td>\n",
              "      <td>-1.077698e-03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>3.807591e-02</td>\n",
              "      <td>5.068012e-02</td>\n",
              "      <td>3.124802e-02</td>\n",
              "      <td>3.564384e-02</td>\n",
              "      <td>2.835801e-02</td>\n",
              "      <td>2.984439e-02</td>\n",
              "      <td>2.931150e-02</td>\n",
              "      <td>3.430886e-02</td>\n",
              "      <td>3.243323e-02</td>\n",
              "      <td>2.791705e-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>1.107267e-01</td>\n",
              "      <td>5.068012e-02</td>\n",
              "      <td>1.705552e-01</td>\n",
              "      <td>1.320442e-01</td>\n",
              "      <td>1.539137e-01</td>\n",
              "      <td>1.987880e-01</td>\n",
              "      <td>1.811791e-01</td>\n",
              "      <td>1.852344e-01</td>\n",
              "      <td>1.335990e-01</td>\n",
              "      <td>1.356118e-01</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                age           sex  ...            s5            s6\n",
              "count  4.420000e+02  4.420000e+02  ...  4.420000e+02  4.420000e+02\n",
              "mean  -3.634285e-16  1.308343e-16  ... -3.830854e-16 -3.412882e-16\n",
              "std    4.761905e-02  4.761905e-02  ...  4.761905e-02  4.761905e-02\n",
              "min   -1.072256e-01 -4.464164e-02  ... -1.260974e-01 -1.377672e-01\n",
              "25%   -3.729927e-02 -4.464164e-02  ... -3.324879e-02 -3.317903e-02\n",
              "50%    5.383060e-03 -4.464164e-02  ... -1.947634e-03 -1.077698e-03\n",
              "75%    3.807591e-02  5.068012e-02  ...  3.243323e-02  2.791705e-02\n",
              "max    1.107267e-01  5.068012e-02  ...  1.335990e-01  1.356118e-01\n",
              "\n",
              "[8 rows x 10 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cMCeCcPLxCGm",
        "outputId": "d4371bb6-847f-4dc8-98fc-78f5ac90973e"
      },
      "source": [
        "print(diabetes_dataset.DESCR)"
      ],
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            ".. _diabetes_dataset:\n",
            "\n",
            "Diabetes dataset\n",
            "----------------\n",
            "\n",
            "Ten baseline variables, age, sex, body mass index, average blood\n",
            "pressure, and six blood serum measurements were obtained for each of n =\n",
            "442 diabetes patients, as well as the response of interest, a\n",
            "quantitative measure of disease progression one year after baseline.\n",
            "\n",
            "**Data Set Characteristics:**\n",
            "\n",
            "  :Number of Instances: 442\n",
            "\n",
            "  :Number of Attributes: First 10 columns are numeric predictive values\n",
            "\n",
            "  :Target: Column 11 is a quantitative measure of disease progression one year after baseline\n",
            "\n",
            "  :Attribute Information:\n",
            "      - Age\n",
            "      - Sex\n",
            "      - Body mass index\n",
            "      - Average blood pressure\n",
            "      - S1\n",
            "      - S2\n",
            "      - S3\n",
            "      - S4\n",
            "      - S5\n",
            "      - S6\n",
            "\n",
            "Note: Each of these 10 feature variables have been mean centered and scaled by the standard deviation times `n_samples` (i.e. the sum of squares of each column totals 1).\n",
            "\n",
            "Source URL:\n",
            "https://www4.stat.ncsu.edu/~boos/var.select/diabetes.html\n",
            "\n",
            "For more information see:\n",
            "Bradley Efron, Trevor Hastie, Iain Johnstone and Robert Tibshirani (2004) \"Least Angle Regression,\" Annals of Statistics (with discussion), 407-499.\n",
            "(https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 491
        },
        "id": "nMQbjes8xFU1",
        "outputId": "edbd2298-2054-47ae-f386-a38d8bf7c56c"
      },
      "source": [
        "p9.ggplot(response_dataframe, p9.aes('response')) + p9.geom_histogram(bins=20) + p9.ggtitle(\"Residuals\")"
      ],
      "execution_count": 109,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178532785)>"
            ]
          },
          "metadata": {},
          "execution_count": 109
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 542
        },
        "id": "iwvwjxb5xc-n",
        "outputId": "2628974e-509a-49a6-b546-6ad4b273ac75"
      },
      "source": [
        "import plotly.express as px\n",
        "fig = px.histogram(response_dataframe, \n",
        "                   x=\"response\", \n",
        "                   nbins=20,\n",
        "                   title=\"Residuals\")\n",
        "fig.show()"
      ],
      "execution_count": 110,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<html>\n",
              "<head><meta charset=\"utf-8\" /></head>\n",
              "<body>\n",
              "    <div>\n",
              "            <script src=\"https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js?config=TeX-AMS-MML_SVG\"></script><script type=\"text/javascript\">if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}</script>\n",
              "                <script type=\"text/javascript\">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>\n",
              "        <script src=\"https://cdn.plot.ly/plotly-latest.min.js\"></script>    \n",
              "            <div id=\"749ff94c-f5b2-4068-a018-259911012e53\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>\n",
              "            <script type=\"text/javascript\">\n",
              "                \n",
              "                    window.PLOTLYENV=window.PLOTLYENV || {};\n",
              "                    \n",
              "                if (document.getElementById(\"749ff94c-f5b2-4068-a018-259911012e53\")) {\n",
              "                    Plotly.newPlot(\n",
              "                        '749ff94c-f5b2-4068-a018-259911012e53',\n",
              "                        [{\"alignmentgroup\": \"True\", \"bingroup\": \"x\", \"hoverlabel\": {\"namelength\": 0}, \"hovertemplate\": \"response=%{x}<br>count=%{y}\", \"legendgroup\": \"\", \"marker\": {\"color\": \"#636efa\"}, \"name\": \"\", \"nbinsx\": 20, \"offsetgroup\": \"\", \"orientation\": \"v\", \"showlegend\": false, \"type\": \"histogram\", \"x\": [151.0, 75.0, 141.0, 206.0, 135.0, 97.0, 138.0, 63.0, 110.0, 310.0, 101.0, 69.0, 179.0, 185.0, 118.0, 171.0, 166.0, 144.0, 97.0, 168.0, 68.0, 49.0, 68.0, 245.0, 184.0, 202.0, 137.0, 85.0, 131.0, 283.0, 129.0, 59.0, 341.0, 87.0, 65.0, 102.0, 265.0, 276.0, 252.0, 90.0, 100.0, 55.0, 61.0, 92.0, 259.0, 53.0, 190.0, 142.0, 75.0, 142.0, 155.0, 225.0, 59.0, 104.0, 182.0, 128.0, 52.0, 37.0, 170.0, 170.0, 61.0, 144.0, 52.0, 128.0, 71.0, 163.0, 150.0, 97.0, 160.0, 178.0, 48.0, 270.0, 202.0, 111.0, 85.0, 42.0, 170.0, 200.0, 252.0, 113.0, 143.0, 51.0, 52.0, 210.0, 65.0, 141.0, 55.0, 134.0, 42.0, 111.0, 98.0, 164.0, 48.0, 96.0, 90.0, 162.0, 150.0, 279.0, 92.0, 83.0, 128.0, 102.0, 302.0, 198.0, 95.0, 53.0, 134.0, 144.0, 232.0, 81.0, 104.0, 59.0, 246.0, 297.0, 258.0, 229.0, 275.0, 281.0, 179.0, 200.0, 200.0, 173.0, 180.0, 84.0, 121.0, 161.0, 99.0, 109.0, 115.0, 268.0, 274.0, 158.0, 107.0, 83.0, 103.0, 272.0, 85.0, 280.0, 336.0, 281.0, 118.0, 317.0, 235.0, 60.0, 174.0, 259.0, 178.0, 128.0, 96.0, 126.0, 288.0, 88.0, 292.0, 71.0, 197.0, 186.0, 25.0, 84.0, 96.0, 195.0, 53.0, 217.0, 172.0, 131.0, 214.0, 59.0, 70.0, 220.0, 268.0, 152.0, 47.0, 74.0, 295.0, 101.0, 151.0, 127.0, 237.0, 225.0, 81.0, 151.0, 107.0, 64.0, 138.0, 185.0, 265.0, 101.0, 137.0, 143.0, 141.0, 79.0, 292.0, 178.0, 91.0, 116.0, 86.0, 122.0, 72.0, 129.0, 142.0, 90.0, 158.0, 39.0, 196.0, 222.0, 277.0, 99.0, 196.0, 202.0, 155.0, 77.0, 191.0, 70.0, 73.0, 49.0, 65.0, 263.0, 248.0, 296.0, 214.0, 185.0, 78.0, 93.0, 252.0, 150.0, 77.0, 208.0, 77.0, 108.0, 160.0, 53.0, 220.0, 154.0, 259.0, 90.0, 246.0, 124.0, 67.0, 72.0, 257.0, 262.0, 275.0, 177.0, 71.0, 47.0, 187.0, 125.0, 78.0, 51.0, 258.0, 215.0, 303.0, 243.0, 91.0, 150.0, 310.0, 153.0, 346.0, 63.0, 89.0, 50.0, 39.0, 103.0, 308.0, 116.0, 145.0, 74.0, 45.0, 115.0, 264.0, 87.0, 202.0, 127.0, 182.0, 241.0, 66.0, 94.0, 283.0, 64.0, 102.0, 200.0, 265.0, 94.0, 230.0, 181.0, 156.0, 233.0, 60.0, 219.0, 80.0, 68.0, 332.0, 248.0, 84.0, 200.0, 55.0, 85.0, 89.0, 31.0, 129.0, 83.0, 275.0, 65.0, 198.0, 236.0, 253.0, 124.0, 44.0, 172.0, 114.0, 142.0, 109.0, 180.0, 144.0, 163.0, 147.0, 97.0, 220.0, 190.0, 109.0, 191.0, 122.0, 230.0, 242.0, 248.0, 249.0, 192.0, 131.0, 237.0, 78.0, 135.0, 244.0, 199.0, 270.0, 164.0, 72.0, 96.0, 306.0, 91.0, 214.0, 95.0, 216.0, 263.0, 178.0, 113.0, 200.0, 139.0, 139.0, 88.0, 148.0, 88.0, 243.0, 71.0, 77.0, 109.0, 272.0, 60.0, 54.0, 221.0, 90.0, 311.0, 281.0, 182.0, 321.0, 58.0, 262.0, 206.0, 233.0, 242.0, 123.0, 167.0, 63.0, 197.0, 71.0, 168.0, 140.0, 217.0, 121.0, 235.0, 245.0, 40.0, 52.0, 104.0, 132.0, 88.0, 69.0, 219.0, 72.0, 201.0, 110.0, 51.0, 277.0, 63.0, 118.0, 69.0, 273.0, 258.0, 43.0, 198.0, 242.0, 232.0, 175.0, 93.0, 168.0, 275.0, 293.0, 281.0, 72.0, 140.0, 189.0, 181.0, 209.0, 136.0, 261.0, 113.0, 131.0, 174.0, 257.0, 55.0, 84.0, 42.0, 146.0, 212.0, 233.0, 91.0, 111.0, 152.0, 120.0, 67.0, 310.0, 94.0, 183.0, 66.0, 173.0, 72.0, 49.0, 64.0, 48.0, 178.0, 104.0, 132.0, 220.0, 57.0], \"xaxis\": \"x\", \"yaxis\": \"y\"}],\n",
              "                        {\"barmode\": \"relative\", \"legend\": {\"tracegroupgap\": 0}, \"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Residuals\"}, \"xaxis\": {\"anchor\": \"y\", \"domain\": [0.0, 1.0], \"title\": {\"text\": \"response\"}}, \"yaxis\": {\"anchor\": \"x\", \"domain\": [0.0, 1.0], \"title\": {\"text\": \"count\"}}},\n",
              "                        {\"responsive\": true}\n",
              "                    ).then(function(){\n",
              "                            \n",
              "var gd = document.getElementById('749ff94c-f5b2-4068-a018-259911012e53');\n",
              "var x = new MutationObserver(function (mutations, observer) {{\n",
              "        var display = window.getComputedStyle(gd).display;\n",
              "        if (!display || display === 'none') {{\n",
              "            console.log([gd, 'removed!']);\n",
              "            Plotly.purge(gd);\n",
              "            observer.disconnect();\n",
              "        }}\n",
              "}});\n",
              "\n",
              "// Listen for the removal of the full notebook cells\n",
              "var notebookContainer = gd.closest('#notebook-container');\n",
              "if (notebookContainer) {{\n",
              "    x.observe(notebookContainer, {childList: true});\n",
              "}}\n",
              "\n",
              "// Listen for the clearing of the current output cell\n",
              "var outputEl = gd.closest('.output');\n",
              "if (outputEl) {{\n",
              "    x.observe(outputEl, {childList: true});\n",
              "}}\n",
              "\n",
              "                        })\n",
              "                };\n",
              "                \n",
              "            </script>\n",
              "        </div>\n",
              "</body>\n",
              "</html>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "d6Si9f3LyDAO"
      },
      "source": [
        "## Exercise 1"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "88xHPwu0yFyL"
      },
      "source": [
        "Using `sklearn`, fit a multivariate linear regression using all 442 samples to predict the response variable. Use all 10 predictors, and also score your model using predictions on all 442 samples."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1qJkOPjjyKBh",
        "outputId": "ba97503b-8c04-455d-9b54-5b72b54d9ad8"
      },
      "source": [
        "# Instantiate the model\n",
        "model = linear.LinearRegression()\n",
        "# Fit the pipeline\n",
        "model.fit(X=predictors, y=response)\n",
        "\n",
        "# Inspect the fit regression coefficients and intercept\n",
        "model.intercept_, model.coef_"
      ],
      "execution_count": 111,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(152.1334841628965,\n",
              " array([ -10.01219782, -239.81908937,  519.83978679,  324.39042769,\n",
              "        -792.18416163,  476.74583782,  101.04457032,  177.06417623,\n",
              "         751.27932109,   67.62538639]))"
            ]
          },
          "metadata": {},
          "execution_count": 111
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qgTUr_dlyOBe"
      },
      "source": [
        "Now score our model using the same dataset we used to fit the model."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FC9TDK-OyQZt",
        "outputId": "9f4984a0-26df-43fc-93c1-e7ccce806a02"
      },
      "source": [
        "model.score(X=predictors, y=response)"
      ],
      "execution_count": 112,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.5177494254132934"
            ]
          },
          "metadata": {},
          "execution_count": 112
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "VT5bhS6Byja1",
        "outputId": "ae215a29-c572-4ad5-b1f3-ee16d7ec32ad"
      },
      "source": [
        "import numpy as np\n",
        "response_predicted = model.predict(X=predictors)\n",
        "residuals = pd.DataFrame({'residuals': np.abs(response - response_predicted)})\n",
        "\n",
        "# the aes object contains only the variable that will be plotted on the x axis i.e. the one for which we want to generate a distribution\n",
        "p9.ggplot(residuals, p9.aes('residuals')) + p9.geom_histogram(bins=20)"
      ],
      "execution_count": 113,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178706189)>"
            ]
          },
          "metadata": {},
          "execution_count": 113
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 491
        },
        "id": "EHo-AhM2RVds",
        "outputId": "86a959ed-2c2d-4c43-c310-4f5c927cd35a"
      },
      "source": [
        "p9.ggplot(response_dataframe, p9.aes('response')) + p9.geom_histogram(bins=20) + p9.ggtitle(\"Residuals\")"
      ],
      "execution_count": 114,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178455441)>"
            ]
          },
          "metadata": {},
          "execution_count": 114
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yVafaMoxysUX"
      },
      "source": [
        "## Exercise 2"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "H-M7ZbGNyudv"
      },
      "source": [
        "Do a test-train split, and run Exercise 1 again, this time fitting your model with the training set, and scoring it both with the test set and with the training set."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gbYQflyKcDyi"
      },
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dbIi6CHjyyEf"
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "predictors_train, predictors_test, response_train, response_test = train_test_split(predictors, \n",
        "                                                                                    response,\n",
        "                                                                                    test_size=0.3, \n",
        "                                                                                    random_state=42, \n",
        "                                                                                    shuffle=True)"
      ],
      "execution_count": 115,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "I18YYsDtzVHO",
        "outputId": "a99bdc16-9198-448b-998f-9687f753ff5b"
      },
      "source": [
        "# Instantiate the model\n",
        "model = linear.LinearRegression()\n",
        "# Fit the pipeline\n",
        "model.fit(X=predictors_train, y=response_train)\n",
        "# Inspect the fit regression coefficients and intercept\n",
        "model.intercept_, model.coef_"
      ],
      "execution_count": 116,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(151.00818273080338,\n",
              " array([  29.25034582, -261.70768053,  546.29737263,  388.40077257,\n",
              "        -901.95338706,  506.761149  ,  121.14845948,  288.02932495,\n",
              "         659.27133846,   41.37536901]))"
            ]
          },
          "metadata": {},
          "execution_count": 116
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tdnVexiSzjEz",
        "outputId": "6f2bdc12-f94a-49cb-a302-97320dca0ed8"
      },
      "source": [
        "model.score(X=predictors_test, y=response_test)"
      ],
      "execution_count": 117,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.4772920174157329"
            ]
          },
          "metadata": {},
          "execution_count": 117
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "q9nl7RP1zqXZ",
        "outputId": "d630cae7-ad09-44fb-843d-7b4828300959"
      },
      "source": [
        "response_predicted = model.predict(X=predictors_test)\n",
        "residuals = pd.DataFrame({'residuals': np.abs(response_test - response_predicted)})\n",
        "p9.ggplot(residuals, p9.aes('residuals')) + p9.geom_histogram(bins=20)"
      ],
      "execution_count": 118,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178297921)>"
            ]
          },
          "metadata": {},
          "execution_count": 118
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "Cu57STm4z37w",
        "outputId": "602a35e1-d204-4cdd-c8be-28e320a65149"
      },
      "source": [
        "# Display the results as a scatter plot\n",
        "predictions = pd.DataFrame({'y': response_test, 'y_hat': response_predicted}) # plotnine works with pd.DataFrame\n",
        "\n",
        "(\n",
        "p9.ggplot(predictions, p9.aes('y', 'y_hat'))\n",
        "    + p9.geom_point()\n",
        "    + p9.scales.xlim(0, 400)\n",
        "    + p9.scales.ylim(0, 400)\n",
        ") # plotnine will emit a `PlotnineWarning` indicating that we have cropped some points from our plot"
      ],
      "execution_count": 119,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178628313)>"
            ]
          },
          "metadata": {},
          "execution_count": 119
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0_QxVfX20A0B"
      },
      "source": [
        "## Exercise 3"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IHGRPN3w0DyW"
      },
      "source": [
        "As with Exercise 2, but this time try using the default RandomForestRegressor instead. How do your results compare? Try just using one or two predictors."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4fvTIt810Hfw",
        "outputId": "9d22138c-f1d3-4a8a-fb5f-fbbddad0dfdd"
      },
      "source": [
        "from sklearn import ensemble\n",
        "model = ensemble.RandomForestRegressor(n_estimators=100, max_depth=3)\n",
        "model.fit(X=predictors_train, y=response_train)"
      ],
      "execution_count": 120,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestRegressor(bootstrap=True, ccp_alpha=0.0, criterion='mse',\n",
              "                      max_depth=3, max_features='auto', max_leaf_nodes=None,\n",
              "                      max_samples=None, min_impurity_decrease=0.0,\n",
              "                      min_impurity_split=None, min_samples_leaf=1,\n",
              "                      min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
              "                      n_estimators=100, n_jobs=None, oob_score=False,\n",
              "                      random_state=None, verbose=0, warm_start=False)"
            ]
          },
          "metadata": {},
          "execution_count": 120
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "zu5kTHpf0Pml",
        "outputId": "e8946925-43b9-4ef4-b8b9-d2a834aed5bf"
      },
      "source": [
        "response_predicted = model.predict(X=predictors_test)\n",
        "residuals = pd.DataFrame({'residuals': np.abs(response_test - response_predicted)})\n",
        "p9.ggplot(residuals, p9.aes('residuals')) + p9.geom_histogram(bins=20)"
      ],
      "execution_count": 121,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178456861)>"
            ]
          },
          "metadata": {},
          "execution_count": 121
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 491
        },
        "id": "aUSR1XYbSV1j",
        "outputId": "9060397a-9079-4ea7-dde9-e01f4d9d02af"
      },
      "source": [
        "p9.ggplot(response_dataframe, p9.aes('response')) + p9.geom_histogram(bins=20) + p9.ggtitle(\"Residuals\")"
      ],
      "execution_count": 122,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178614149)>"
            ]
          },
          "metadata": {},
          "execution_count": 122
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lVC3ZBT30Xn-"
      },
      "source": [
        "A little bit of experimentation with C and gamma means we now beat the linear model - just!"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fU9Kev_O0ZTL",
        "outputId": "9076b394-6965-4bff-f8dd-e1d7fb3cecbc"
      },
      "source": [
        "model.score(X=predictors_test, y=response_test)"
      ],
      "execution_count": 123,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.48374522204294873"
            ]
          },
          "metadata": {},
          "execution_count": 123
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 538
        },
        "id": "YFFhAGQ90foa",
        "outputId": "613379e5-7b32-4eb4-9080-87f322139aae"
      },
      "source": [
        "predictions = pd.DataFrame({'y': response_test, 'y_hat': response_predicted}) # plotnine works with pd.DataFrame\n",
        "\n",
        "(\n",
        "p9.ggplot(predictions, p9.aes('y', 'y_hat'))\n",
        "    + p9.geom_point()\n",
        "    + p9.scales.xlim(0, 300)\n",
        "    + p9.scales.ylim(0, 300)\n",
        ")"
      ],
      "execution_count": 124,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/plotnine/layer.py:452: PlotnineWarning:\n",
            "\n",
            "geom_point : Removed 1 rows containing missing values.\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<ggplot: (8774178306541)>"
            ]
          },
          "metadata": {},
          "execution_count": 124
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hrEQeHmZ1OUY"
      },
      "source": [
        "## Exercise 4"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wJvPTjHW1QMv"
      },
      "source": [
        "Dive into the documentation of RandomForestRegressor and try tweaking some of the hyperparameters to see how this affects your model score on the training and test datasets ('n_estimators' and 'max_depth' are good places to start). If you want do delve deeper this blog post is a nice introduction to the concepts of cross-validation and hyperparameter tuning (more on this next week though!)."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MhjCkcZG1RUe"
      },
      "source": [
        "n_estimators_min, n_estimators_max = 2, 100\n",
        "max_depth_min, max_depth_max = 2, 10"
      ],
      "execution_count": 125,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FQD-YmOQ1U6l"
      },
      "source": [
        "grid_parameters = np.mgrid[n_estimators_min - 1:n_estimators_max + 1:20j,  max_depth_min - 1:max_depth_max + 1:9j]\n",
        "parameters = grid_parameters.reshape((2, -1)).T"
      ],
      "execution_count": 126,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2e8ySx411WoS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7db57de1-b230-41b9-d980-4f8d1cea896a"
      },
      "source": [
        "scores = np.empty(parameters.shape[0])\n",
        "for i, (n_estimators, max_depth) in enumerate(parameters):\n",
        "    print(\"i: \", i)\n",
        "    print(\"n_estimators: \", int(n_estimators))\n",
        "    print(\"max_depth: \", int(max_depth))\n",
        "    model = ensemble.RandomForestRegressor(n_estimators=int(n_estimators), max_depth=int(max_depth), random_state = np.random.seed(1234))\n",
        "    model.fit(X=predictors_train, y=response_train)\n",
        "    score = model.score(X=predictors_test, y=response_test)\n",
        "    print(\"score: \", score)\n",
        "    scores[i] = score"
      ],
      "execution_count": 127,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "i:  0\n",
            "n_estimators:  1\n",
            "max_depth:  1\n",
            "score:  0.39866465124442146\n",
            "i:  1\n",
            "n_estimators:  1\n",
            "max_depth:  2\n",
            "score:  0.306769087559461\n",
            "i:  2\n",
            "n_estimators:  1\n",
            "max_depth:  3\n",
            "score:  0.23537940596017193\n",
            "i:  3\n",
            "n_estimators:  1\n",
            "max_depth:  4\n",
            "score:  0.2551777542118129\n",
            "i:  4\n",
            "n_estimators:  1\n",
            "max_depth:  6\n",
            "score:  0.04294079199629808\n",
            "i:  5\n",
            "n_estimators:  1\n",
            "max_depth:  7\n",
            "score:  -0.058883156084337474\n",
            "i:  6\n",
            "n_estimators:  1\n",
            "max_depth:  8\n",
            "score:  -0.019560471309697514\n",
            "i:  7\n",
            "n_estimators:  1\n",
            "max_depth:  9\n",
            "score:  0.11860145113733146\n",
            "i:  8\n",
            "n_estimators:  1\n",
            "max_depth:  11\n",
            "score:  -0.08161897157565323\n",
            "i:  9\n",
            "n_estimators:  6\n",
            "max_depth:  1\n",
            "score:  0.3780196737636643\n",
            "i:  10\n",
            "n_estimators:  6\n",
            "max_depth:  2\n",
            "score:  0.44998274844942493\n",
            "i:  11\n",
            "n_estimators:  6\n",
            "max_depth:  3\n",
            "score:  0.4879548973404236\n",
            "i:  12\n",
            "n_estimators:  6\n",
            "max_depth:  4\n",
            "score:  0.51327702639602\n",
            "i:  13\n",
            "n_estimators:  6\n",
            "max_depth:  6\n",
            "score:  0.42190409090172387\n",
            "i:  14\n",
            "n_estimators:  6\n",
            "max_depth:  7\n",
            "score:  0.3819892642997613\n",
            "i:  15\n",
            "n_estimators:  6\n",
            "max_depth:  8\n",
            "score:  0.39211979339640607\n",
            "i:  16\n",
            "n_estimators:  6\n",
            "max_depth:  9\n",
            "score:  0.3640659759806115\n",
            "i:  17\n",
            "n_estimators:  6\n",
            "max_depth:  11\n",
            "score:  0.3572782412013584\n",
            "i:  18\n",
            "n_estimators:  11\n",
            "max_depth:  1\n",
            "score:  0.36984532171112483\n",
            "i:  19\n",
            "n_estimators:  11\n",
            "max_depth:  2\n",
            "score:  0.45076507505578123\n",
            "i:  20\n",
            "n_estimators:  11\n",
            "max_depth:  3\n",
            "score:  0.48365181150801756\n",
            "i:  21\n",
            "n_estimators:  11\n",
            "max_depth:  4\n",
            "score:  0.4863042325763615\n",
            "i:  22\n",
            "n_estimators:  11\n",
            "max_depth:  6\n",
            "score:  0.4301385579045668\n",
            "i:  23\n",
            "n_estimators:  11\n",
            "max_depth:  7\n",
            "score:  0.4107187698418814\n",
            "i:  24\n",
            "n_estimators:  11\n",
            "max_depth:  8\n",
            "score:  0.43352614165181724\n",
            "i:  25\n",
            "n_estimators:  11\n",
            "max_depth:  9\n",
            "score:  0.4036445148800875\n",
            "i:  26\n",
            "n_estimators:  11\n",
            "max_depth:  11\n",
            "score:  0.38814951028256467\n",
            "i:  27\n",
            "n_estimators:  16\n",
            "max_depth:  1\n",
            "score:  0.3553509209864816\n",
            "i:  28\n",
            "n_estimators:  16\n",
            "max_depth:  2\n",
            "score:  0.459641187457852\n",
            "i:  29\n",
            "n_estimators:  16\n",
            "max_depth:  3\n",
            "score:  0.4899720159660349\n",
            "i:  30\n",
            "n_estimators:  16\n",
            "max_depth:  4\n",
            "score:  0.47389304739278126\n",
            "i:  31\n",
            "n_estimators:  16\n",
            "max_depth:  6\n",
            "score:  0.442059439714538\n",
            "i:  32\n",
            "n_estimators:  16\n",
            "max_depth:  7\n",
            "score:  0.43364774756853436\n",
            "i:  33\n",
            "n_estimators:  16\n",
            "max_depth:  8\n",
            "score:  0.4407572133978949\n",
            "i:  34\n",
            "n_estimators:  16\n",
            "max_depth:  9\n",
            "score:  0.41579974432170963\n",
            "i:  35\n",
            "n_estimators:  16\n",
            "max_depth:  11\n",
            "score:  0.42272315925577775\n",
            "i:  36\n",
            "n_estimators:  22\n",
            "max_depth:  1\n",
            "score:  0.36088736381484277\n",
            "i:  37\n",
            "n_estimators:  22\n",
            "max_depth:  2\n",
            "score:  0.454309835415832\n",
            "i:  38\n",
            "n_estimators:  22\n",
            "max_depth:  3\n",
            "score:  0.4973073182822041\n",
            "i:  39\n",
            "n_estimators:  22\n",
            "max_depth:  4\n",
            "score:  0.47955023524324186\n",
            "i:  40\n",
            "n_estimators:  22\n",
            "max_depth:  6\n",
            "score:  0.4478773541393674\n",
            "i:  41\n",
            "n_estimators:  22\n",
            "max_depth:  7\n",
            "score:  0.44400255072919365\n",
            "i:  42\n",
            "n_estimators:  22\n",
            "max_depth:  8\n",
            "score:  0.44888583201637805\n",
            "i:  43\n",
            "n_estimators:  22\n",
            "max_depth:  9\n",
            "score:  0.4278521871154358\n",
            "i:  44\n",
            "n_estimators:  22\n",
            "max_depth:  11\n",
            "score:  0.42381029906654555\n",
            "i:  45\n",
            "n_estimators:  27\n",
            "max_depth:  1\n",
            "score:  0.3697333733150714\n",
            "i:  46\n",
            "n_estimators:  27\n",
            "max_depth:  2\n",
            "score:  0.4516110052148889\n",
            "i:  47\n",
            "n_estimators:  27\n",
            "max_depth:  3\n",
            "score:  0.49099906652302244\n",
            "i:  48\n",
            "n_estimators:  27\n",
            "max_depth:  4\n",
            "score:  0.47719431420346176\n",
            "i:  49\n",
            "n_estimators:  27\n",
            "max_depth:  6\n",
            "score:  0.44317470362130085\n",
            "i:  50\n",
            "n_estimators:  27\n",
            "max_depth:  7\n",
            "score:  0.43375324761219536\n",
            "i:  51\n",
            "n_estimators:  27\n",
            "max_depth:  8\n",
            "score:  0.4387848037542389\n",
            "i:  52\n",
            "n_estimators:  27\n",
            "max_depth:  9\n",
            "score:  0.4203286451458963\n",
            "i:  53\n",
            "n_estimators:  27\n",
            "max_depth:  11\n",
            "score:  0.41937248100677976\n",
            "i:  54\n",
            "n_estimators:  32\n",
            "max_depth:  1\n",
            "score:  0.37835466673608614\n",
            "i:  55\n",
            "n_estimators:  32\n",
            "max_depth:  2\n",
            "score:  0.46024726455937987\n",
            "i:  56\n",
            "n_estimators:  32\n",
            "max_depth:  3\n",
            "score:  0.4904854008421249\n",
            "i:  57\n",
            "n_estimators:  32\n",
            "max_depth:  4\n",
            "score:  0.4772007689972837\n",
            "i:  58\n",
            "n_estimators:  32\n",
            "max_depth:  6\n",
            "score:  0.4461003337668487\n",
            "i:  59\n",
            "n_estimators:  32\n",
            "max_depth:  7\n",
            "score:  0.4408892543015806\n",
            "i:  60\n",
            "n_estimators:  32\n",
            "max_depth:  8\n",
            "score:  0.4434423178295383\n",
            "i:  61\n",
            "n_estimators:  32\n",
            "max_depth:  9\n",
            "score:  0.4216032937208203\n",
            "i:  62\n",
            "n_estimators:  32\n",
            "max_depth:  11\n",
            "score:  0.4339338785531122\n",
            "i:  63\n",
            "n_estimators:  37\n",
            "max_depth:  1\n",
            "score:  0.3704470253302158\n",
            "i:  64\n",
            "n_estimators:  37\n",
            "max_depth:  2\n",
            "score:  0.46568257104950694\n",
            "i:  65\n",
            "n_estimators:  37\n",
            "max_depth:  3\n",
            "score:  0.49410494660481247\n",
            "i:  66\n",
            "n_estimators:  37\n",
            "max_depth:  4\n",
            "score:  0.481766402806162\n",
            "i:  67\n",
            "n_estimators:  37\n",
            "max_depth:  6\n",
            "score:  0.4504319341862699\n",
            "i:  68\n",
            "n_estimators:  37\n",
            "max_depth:  7\n",
            "score:  0.44709183450442636\n",
            "i:  69\n",
            "n_estimators:  37\n",
            "max_depth:  8\n",
            "score:  0.4505235143797127\n",
            "i:  70\n",
            "n_estimators:  37\n",
            "max_depth:  9\n",
            "score:  0.4290579938506274\n",
            "i:  71\n",
            "n_estimators:  37\n",
            "max_depth:  11\n",
            "score:  0.4421912093686601\n",
            "i:  72\n",
            "n_estimators:  43\n",
            "max_depth:  1\n",
            "score:  0.36336611425317533\n",
            "i:  73\n",
            "n_estimators:  43\n",
            "max_depth:  2\n",
            "score:  0.46182287043599657\n",
            "i:  74\n",
            "n_estimators:  43\n",
            "max_depth:  3\n",
            "score:  0.49126952356506987\n",
            "i:  75\n",
            "n_estimators:  43\n",
            "max_depth:  4\n",
            "score:  0.4817768438126981\n",
            "i:  76\n",
            "n_estimators:  43\n",
            "max_depth:  6\n",
            "score:  0.4502225463610848\n",
            "i:  77\n",
            "n_estimators:  43\n",
            "max_depth:  7\n",
            "score:  0.4476048907431434\n",
            "i:  78\n",
            "n_estimators:  43\n",
            "max_depth:  8\n",
            "score:  0.45870332062495156\n",
            "i:  79\n",
            "n_estimators:  43\n",
            "max_depth:  9\n",
            "score:  0.435989003163685\n",
            "i:  80\n",
            "n_estimators:  43\n",
            "max_depth:  11\n",
            "score:  0.44506649025547584\n",
            "i:  81\n",
            "n_estimators:  48\n",
            "max_depth:  1\n",
            "score:  0.3676061287951833\n",
            "i:  82\n",
            "n_estimators:  48\n",
            "max_depth:  2\n",
            "score:  0.46292409592096095\n",
            "i:  83\n",
            "n_estimators:  48\n",
            "max_depth:  3\n",
            "score:  0.4926656968806209\n",
            "i:  84\n",
            "n_estimators:  48\n",
            "max_depth:  4\n",
            "score:  0.48339787301404696\n",
            "i:  85\n",
            "n_estimators:  48\n",
            "max_depth:  6\n",
            "score:  0.45018229117843933\n",
            "i:  86\n",
            "n_estimators:  48\n",
            "max_depth:  7\n",
            "score:  0.4470335872888837\n",
            "i:  87\n",
            "n_estimators:  48\n",
            "max_depth:  8\n",
            "score:  0.4579477922654058\n",
            "i:  88\n",
            "n_estimators:  48\n",
            "max_depth:  9\n",
            "score:  0.4386013974570853\n",
            "i:  89\n",
            "n_estimators:  48\n",
            "max_depth:  11\n",
            "score:  0.4443718456335763\n",
            "i:  90\n",
            "n_estimators:  53\n",
            "max_depth:  1\n",
            "score:  0.357453277245141\n",
            "i:  91\n",
            "n_estimators:  53\n",
            "max_depth:  2\n",
            "score:  0.4606173500466777\n",
            "i:  92\n",
            "n_estimators:  53\n",
            "max_depth:  3\n",
            "score:  0.490201618079575\n",
            "i:  93\n",
            "n_estimators:  53\n",
            "max_depth:  4\n",
            "score:  0.4819000390085507\n",
            "i:  94\n",
            "n_estimators:  53\n",
            "max_depth:  6\n",
            "score:  0.4495386335622937\n",
            "i:  95\n",
            "n_estimators:  53\n",
            "max_depth:  7\n",
            "score:  0.4454651573975436\n",
            "i:  96\n",
            "n_estimators:  53\n",
            "max_depth:  8\n",
            "score:  0.4553205316033258\n",
            "i:  97\n",
            "n_estimators:  53\n",
            "max_depth:  9\n",
            "score:  0.4394801298476542\n",
            "i:  98\n",
            "n_estimators:  53\n",
            "max_depth:  11\n",
            "score:  0.4457274869646778\n",
            "i:  99\n",
            "n_estimators:  58\n",
            "max_depth:  1\n",
            "score:  0.35434530136425757\n",
            "i:  100\n",
            "n_estimators:  58\n",
            "max_depth:  2\n",
            "score:  0.4564795580977993\n",
            "i:  101\n",
            "n_estimators:  58\n",
            "max_depth:  3\n",
            "score:  0.4878843239181612\n",
            "i:  102\n",
            "n_estimators:  58\n",
            "max_depth:  4\n",
            "score:  0.4833780021339482\n",
            "i:  103\n",
            "n_estimators:  58\n",
            "max_depth:  6\n",
            "score:  0.45657363239191623\n",
            "i:  104\n",
            "n_estimators:  58\n",
            "max_depth:  7\n",
            "score:  0.45202722656298217\n",
            "i:  105\n",
            "n_estimators:  58\n",
            "max_depth:  8\n",
            "score:  0.4622280916400436\n",
            "i:  106\n",
            "n_estimators:  58\n",
            "max_depth:  9\n",
            "score:  0.44550456698070195\n",
            "i:  107\n",
            "n_estimators:  58\n",
            "max_depth:  11\n",
            "score:  0.4488414555964607\n",
            "i:  108\n",
            "n_estimators:  64\n",
            "max_depth:  1\n",
            "score:  0.34533879033416526\n",
            "i:  109\n",
            "n_estimators:  64\n",
            "max_depth:  2\n",
            "score:  0.4546528513370413\n",
            "i:  110\n",
            "n_estimators:  64\n",
            "max_depth:  3\n",
            "score:  0.4879607859735964\n",
            "i:  111\n",
            "n_estimators:  64\n",
            "max_depth:  4\n",
            "score:  0.4817812767692919\n",
            "i:  112\n",
            "n_estimators:  64\n",
            "max_depth:  6\n",
            "score:  0.45954288111324376\n",
            "i:  113\n",
            "n_estimators:  64\n",
            "max_depth:  7\n",
            "score:  0.4566875313251756\n",
            "i:  114\n",
            "n_estimators:  64\n",
            "max_depth:  8\n",
            "score:  0.4631279516984359\n",
            "i:  115\n",
            "n_estimators:  64\n",
            "max_depth:  9\n",
            "score:  0.45024271384240455\n",
            "i:  116\n",
            "n_estimators:  64\n",
            "max_depth:  11\n",
            "score:  0.45254393817018335\n",
            "i:  117\n",
            "n_estimators:  69\n",
            "max_depth:  1\n",
            "score:  0.3432749677935766\n",
            "i:  118\n",
            "n_estimators:  69\n",
            "max_depth:  2\n",
            "score:  0.4557019217890939\n",
            "i:  119\n",
            "n_estimators:  69\n",
            "max_depth:  3\n",
            "score:  0.4894122110783089\n",
            "i:  120\n",
            "n_estimators:  69\n",
            "max_depth:  4\n",
            "score:  0.4854409184985056\n",
            "i:  121\n",
            "n_estimators:  69\n",
            "max_depth:  6\n",
            "score:  0.46314464999879834\n",
            "i:  122\n",
            "n_estimators:  69\n",
            "max_depth:  7\n",
            "score:  0.4600981044925765\n",
            "i:  123\n",
            "n_estimators:  69\n",
            "max_depth:  8\n",
            "score:  0.4663533411733295\n",
            "i:  124\n",
            "n_estimators:  69\n",
            "max_depth:  9\n",
            "score:  0.45576383435498996\n",
            "i:  125\n",
            "n_estimators:  69\n",
            "max_depth:  11\n",
            "score:  0.45565125335263945\n",
            "i:  126\n",
            "n_estimators:  74\n",
            "max_depth:  1\n",
            "score:  0.3359303987327086\n",
            "i:  127\n",
            "n_estimators:  74\n",
            "max_depth:  2\n",
            "score:  0.45406329232398374\n",
            "i:  128\n",
            "n_estimators:  74\n",
            "max_depth:  3\n",
            "score:  0.48854588776650487\n",
            "i:  129\n",
            "n_estimators:  74\n",
            "max_depth:  4\n",
            "score:  0.485748529268879\n",
            "i:  130\n",
            "n_estimators:  74\n",
            "max_depth:  6\n",
            "score:  0.46411412689626297\n",
            "i:  131\n",
            "n_estimators:  74\n",
            "max_depth:  7\n",
            "score:  0.45992822203679734\n",
            "i:  132\n",
            "n_estimators:  74\n",
            "max_depth:  8\n",
            "score:  0.4677948258313755\n",
            "i:  133\n",
            "n_estimators:  74\n",
            "max_depth:  9\n",
            "score:  0.45934708549787445\n",
            "i:  134\n",
            "n_estimators:  74\n",
            "max_depth:  11\n",
            "score:  0.4586575612867\n",
            "i:  135\n",
            "n_estimators:  79\n",
            "max_depth:  1\n",
            "score:  0.33602376031413483\n",
            "i:  136\n",
            "n_estimators:  79\n",
            "max_depth:  2\n",
            "score:  0.45520074223004103\n",
            "i:  137\n",
            "n_estimators:  79\n",
            "max_depth:  3\n",
            "score:  0.4874398530305569\n",
            "i:  138\n",
            "n_estimators:  79\n",
            "max_depth:  4\n",
            "score:  0.48571336623465394\n",
            "i:  139\n",
            "n_estimators:  79\n",
            "max_depth:  6\n",
            "score:  0.46560079377502106\n",
            "i:  140\n",
            "n_estimators:  79\n",
            "max_depth:  7\n",
            "score:  0.4618081382623014\n",
            "i:  141\n",
            "n_estimators:  79\n",
            "max_depth:  8\n",
            "score:  0.46703050248877487\n",
            "i:  142\n",
            "n_estimators:  79\n",
            "max_depth:  9\n",
            "score:  0.4624315280612192\n",
            "i:  143\n",
            "n_estimators:  79\n",
            "max_depth:  11\n",
            "score:  0.45959261010225455\n",
            "i:  144\n",
            "n_estimators:  85\n",
            "max_depth:  1\n",
            "score:  0.3292239996195545\n",
            "i:  145\n",
            "n_estimators:  85\n",
            "max_depth:  2\n",
            "score:  0.455418535196766\n",
            "i:  146\n",
            "n_estimators:  85\n",
            "max_depth:  3\n",
            "score:  0.48891609584982165\n",
            "i:  147\n",
            "n_estimators:  85\n",
            "max_depth:  4\n",
            "score:  0.48794846786212215\n",
            "i:  148\n",
            "n_estimators:  85\n",
            "max_depth:  6\n",
            "score:  0.4687901576906246\n",
            "i:  149\n",
            "n_estimators:  85\n",
            "max_depth:  7\n",
            "score:  0.4603867897930324\n",
            "i:  150\n",
            "n_estimators:  85\n",
            "max_depth:  8\n",
            "score:  0.46606314481445776\n",
            "i:  151\n",
            "n_estimators:  85\n",
            "max_depth:  9\n",
            "score:  0.46160721571596236\n",
            "i:  152\n",
            "n_estimators:  85\n",
            "max_depth:  11\n",
            "score:  0.4613462845228423\n",
            "i:  153\n",
            "n_estimators:  90\n",
            "max_depth:  1\n",
            "score:  0.33304343472338727\n",
            "i:  154\n",
            "n_estimators:  90\n",
            "max_depth:  2\n",
            "score:  0.45374495473999055\n",
            "i:  155\n",
            "n_estimators:  90\n",
            "max_depth:  3\n",
            "score:  0.4868934926282202\n",
            "i:  156\n",
            "n_estimators:  90\n",
            "max_depth:  4\n",
            "score:  0.4860933933135499\n",
            "i:  157\n",
            "n_estimators:  90\n",
            "max_depth:  6\n",
            "score:  0.46636287926398\n",
            "i:  158\n",
            "n_estimators:  90\n",
            "max_depth:  7\n",
            "score:  0.45639136558667914\n",
            "i:  159\n",
            "n_estimators:  90\n",
            "max_depth:  8\n",
            "score:  0.4629846596728272\n",
            "i:  160\n",
            "n_estimators:  90\n",
            "max_depth:  9\n",
            "score:  0.45820420585596977\n",
            "i:  161\n",
            "n_estimators:  90\n",
            "max_depth:  11\n",
            "score:  0.4573177428213588\n",
            "i:  162\n",
            "n_estimators:  95\n",
            "max_depth:  1\n",
            "score:  0.33234132555916907\n",
            "i:  163\n",
            "n_estimators:  95\n",
            "max_depth:  2\n",
            "score:  0.4539648442507722\n",
            "i:  164\n",
            "n_estimators:  95\n",
            "max_depth:  3\n",
            "score:  0.4858605786307656\n",
            "i:  165\n",
            "n_estimators:  95\n",
            "max_depth:  4\n",
            "score:  0.48598074035077016\n",
            "i:  166\n",
            "n_estimators:  95\n",
            "max_depth:  6\n",
            "score:  0.46555706923315743\n",
            "i:  167\n",
            "n_estimators:  95\n",
            "max_depth:  7\n",
            "score:  0.45686073502816277\n",
            "i:  168\n",
            "n_estimators:  95\n",
            "max_depth:  8\n",
            "score:  0.46265549835428155\n",
            "i:  169\n",
            "n_estimators:  95\n",
            "max_depth:  9\n",
            "score:  0.4584366344820383\n",
            "i:  170\n",
            "n_estimators:  95\n",
            "max_depth:  11\n",
            "score:  0.4559414511135862\n",
            "i:  171\n",
            "n_estimators:  101\n",
            "max_depth:  1\n",
            "score:  0.3317501676378305\n",
            "i:  172\n",
            "n_estimators:  101\n",
            "max_depth:  2\n",
            "score:  0.4551637184761236\n",
            "i:  173\n",
            "n_estimators:  101\n",
            "max_depth:  3\n",
            "score:  0.48594862542932993\n",
            "i:  174\n",
            "n_estimators:  101\n",
            "max_depth:  4\n",
            "score:  0.4857952558252941\n",
            "i:  175\n",
            "n_estimators:  101\n",
            "max_depth:  6\n",
            "score:  0.4631861077827467\n",
            "i:  176\n",
            "n_estimators:  101\n",
            "max_depth:  7\n",
            "score:  0.4564377541092188\n",
            "i:  177\n",
            "n_estimators:  101\n",
            "max_depth:  8\n",
            "score:  0.4612055970394475\n",
            "i:  178\n",
            "n_estimators:  101\n",
            "max_depth:  9\n",
            "score:  0.45635418423968593\n",
            "i:  179\n",
            "n_estimators:  101\n",
            "max_depth:  11\n",
            "score:  0.45392129681712595\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6b_UGMv8Tntu",
        "outputId": "83cfabda-4a2f-49e1-afd6-e2c3ac273417"
      },
      "source": [
        "scores.max()"
      ],
      "execution_count": 128,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.51327702639602"
            ]
          },
          "metadata": {},
          "execution_count": 128
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BmiQH-cPV-uM",
        "outputId": "2b6f6826-118b-46d3-bebe-15e49f1abf96"
      },
      "source": [
        "scores"
      ],
      "execution_count": 129,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ 0.39866465,  0.30676909,  0.23537941,  0.25517775,  0.04294079,\n",
              "       -0.05888316, -0.01956047,  0.11860145, -0.08161897,  0.37801967,\n",
              "        0.44998275,  0.4879549 ,  0.51327703,  0.42190409,  0.38198926,\n",
              "        0.39211979,  0.36406598,  0.35727824,  0.36984532,  0.45076508,\n",
              "        0.48365181,  0.48630423,  0.43013856,  0.41071877,  0.43352614,\n",
              "        0.40364451,  0.38814951,  0.35535092,  0.45964119,  0.48997202,\n",
              "        0.47389305,  0.44205944,  0.43364775,  0.44075721,  0.41579974,\n",
              "        0.42272316,  0.36088736,  0.45430984,  0.49730732,  0.47955024,\n",
              "        0.44787735,  0.44400255,  0.44888583,  0.42785219,  0.4238103 ,\n",
              "        0.36973337,  0.45161101,  0.49099907,  0.47719431,  0.4431747 ,\n",
              "        0.43375325,  0.4387848 ,  0.42032865,  0.41937248,  0.37835467,\n",
              "        0.46024726,  0.4904854 ,  0.47720077,  0.44610033,  0.44088925,\n",
              "        0.44344232,  0.42160329,  0.43393388,  0.37044703,  0.46568257,\n",
              "        0.49410495,  0.4817664 ,  0.45043193,  0.44709183,  0.45052351,\n",
              "        0.42905799,  0.44219121,  0.36336611,  0.46182287,  0.49126952,\n",
              "        0.48177684,  0.45022255,  0.44760489,  0.45870332,  0.435989  ,\n",
              "        0.44506649,  0.36760613,  0.4629241 ,  0.4926657 ,  0.48339787,\n",
              "        0.45018229,  0.44703359,  0.45794779,  0.4386014 ,  0.44437185,\n",
              "        0.35745328,  0.46061735,  0.49020162,  0.48190004,  0.44953863,\n",
              "        0.44546516,  0.45532053,  0.43948013,  0.44572749,  0.3543453 ,\n",
              "        0.45647956,  0.48788432,  0.483378  ,  0.45657363,  0.45202723,\n",
              "        0.46222809,  0.44550457,  0.44884146,  0.34533879,  0.45465285,\n",
              "        0.48796079,  0.48178128,  0.45954288,  0.45668753,  0.46312795,\n",
              "        0.45024271,  0.45254394,  0.34327497,  0.45570192,  0.48941221,\n",
              "        0.48544092,  0.46314465,  0.4600981 ,  0.46635334,  0.45576383,\n",
              "        0.45565125,  0.3359304 ,  0.45406329,  0.48854589,  0.48574853,\n",
              "        0.46411413,  0.45992822,  0.46779483,  0.45934709,  0.45865756,\n",
              "        0.33602376,  0.45520074,  0.48743985,  0.48571337,  0.46560079,\n",
              "        0.46180814,  0.4670305 ,  0.46243153,  0.45959261,  0.329224  ,\n",
              "        0.45541854,  0.4889161 ,  0.48794847,  0.46879016,  0.46038679,\n",
              "        0.46606314,  0.46160722,  0.46134628,  0.33304343,  0.45374495,\n",
              "        0.48689349,  0.48609339,  0.46636288,  0.45639137,  0.46298466,\n",
              "        0.45820421,  0.45731774,  0.33234133,  0.45396484,  0.48586058,\n",
              "        0.48598074,  0.46555707,  0.45686074,  0.4626555 ,  0.45843663,\n",
              "        0.45594145,  0.33175017,  0.45516372,  0.48594863,  0.48579526,\n",
              "        0.46318611,  0.45643775,  0.4612056 ,  0.45635418,  0.4539213 ])"
            ]
          },
          "metadata": {},
          "execution_count": 129
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pR27CucITzYL",
        "outputId": "4dd20cd1-7ebe-4204-ed77-db69a54e32ae"
      },
      "source": [
        "np.where(scores == scores.max())"
      ],
      "execution_count": 130,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(array([12]),)"
            ]
          },
          "metadata": {},
          "execution_count": 130
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gYEfBMtf1YXF"
      },
      "source": [
        "scores = np.reshape(scores, (20, 9))"
      ],
      "execution_count": 131,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 329
        },
        "id": "zyVsPTgN1aKS",
        "outputId": "853661ed-4182-4174-ff8f-e54f95dc5757"
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "fig = plt.figure(figsize=(6, 4.5))\n",
        "ax = fig.add_subplot()\n",
        "ax.set_ylabel('max_depth')\n",
        "ax.set_xlabel('n_estimators')\n",
        "score_min, score_max = scores.min(), scores.max()\n",
        "plot = ax.imshow(\n",
        "    np.rot90(scores),\n",
        "    vmin=score_min,\n",
        "    vmax=score_max,\n",
        "    aspect='auto',\n",
        "    extent=(n_estimators_min - 1, n_estimators_max, max_depth_min - 1, max_depth_max),\n",
        "    cmap=plt.cm.viridis)\n",
        "\n",
        "fig.colorbar(plot, ax=ax)"
      ],
      "execution_count": 132,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.colorbar.Colorbar at 0x7fae5c8c9e90>"
            ]
          },
          "metadata": {},
          "execution_count": 132
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x324 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "m3n28zkb1wQb",
        "outputId": "d3038f71-cc56-4b25-8cf2-babe45ebfaaf"
      },
      "source": [
        "model = ensemble.RandomForestRegressor(n_estimators=6, max_depth=4, random_state = np.random.seed(1234))\n",
        "model.fit(X=predictors_train, y=response_train)"
      ],
      "execution_count": 133,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestRegressor(bootstrap=True, ccp_alpha=0.0, criterion='mse',\n",
              "                      max_depth=4, max_features='auto', max_leaf_nodes=None,\n",
              "                      max_samples=None, min_impurity_decrease=0.0,\n",
              "                      min_impurity_split=None, min_samples_leaf=1,\n",
              "                      min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
              "                      n_estimators=6, n_jobs=None, oob_score=False,\n",
              "                      random_state=None, verbose=0, warm_start=False)"
            ]
          },
          "metadata": {},
          "execution_count": 133
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MDxEO8lY11nX",
        "outputId": "1b258dc9-c738-4ee3-d1c6-53839a6eb2a6"
      },
      "source": [
        "model.score(X=predictors_test, y=response_test)"
      ],
      "execution_count": 134,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.51327702639602"
            ]
          },
          "metadata": {},
          "execution_count": 134
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3iOF-QDZ31Tz",
        "outputId": "093a9201-880b-4f22-a40d-7a96eb1e9958"
      },
      "source": [
        "from scipy import stats\n",
        "\n",
        "df = predictors_train\n",
        "z_scores = stats.zscore(df)\n",
        "abs_z_scores = np.abs(z_scores)\n",
        "filtered_entries = (abs_z_scores < 3).all(axis=1)\n",
        "new_predictors_train = df[filtered_entries]\n",
        "\n",
        "new_response_train = response_train[filtered_entries]\n",
        "\n",
        "new_predictors_train.shape"
      ],
      "execution_count": 135,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(300, 10)"
            ]
          },
          "metadata": {},
          "execution_count": 135
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hX1UQv1Q4gco",
        "outputId": "bd7e317c-d478-4e6c-8aee-293888d57d91"
      },
      "source": [
        "predictors_train.shape"
      ],
      "execution_count": 136,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(309, 10)"
            ]
          },
          "metadata": {},
          "execution_count": 136
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aN1TE0404sKB",
        "outputId": "9de4e32e-3362-46aa-a3fc-6b9ab38f01ca"
      },
      "source": [
        "model = ensemble.RandomForestRegressor(n_estimators=5, max_depth=3)\n",
        "model.fit(X=new_predictors_train, y=new_response_train)\n",
        "model.score(X=predictors_test, y=response_test)"
      ],
      "execution_count": 137,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.49035009812322566"
            ]
          },
          "metadata": {},
          "execution_count": 137
        }
      ]
    }
  ]
}