{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Graphes en machine learning - correction\n", "\n", "Correction (en cours de r\u00e9daction) des exercices autour des graphes courants en machine learning."]}, {"cell_type": "code", "execution_count": 1, "metadata": {"collapsed": true}, "outputs": [], "source": ["%matplotlib inline\n", "%load_ext pyensae"]}, {"cell_type": "code", "execution_count": 2, "metadata": {"collapsed": true}, "outputs": [], "source": ["import matplotlib.pyplot as plt\n", "plt.style.use('ggplot')"]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [{"data": {"text/html": ["<div id=\"my_id_menu_nb\">run previous cell, wait for 2 seconds</div>\n", "<script>\n", "function repeat_indent_string(n){\n", "    var a = \"\" ;\n", "    for ( ; n > 0 ; --n)\n", "        a += \"    \";\n", "    return a;\n", "}\n", "var update_menu_string = function(begin, lfirst, llast, sformat, send, keep_item, begin_format, end_format) {\n", "    var anchors = document.getElementsByClassName(\"section\");\n", "    if (anchors.length == 0) {\n", "        anchors = document.getElementsByClassName(\"text_cell_render rendered_html\");\n", "    }\n", "    var i,t;\n", "    var text_menu = begin;\n", "    var text_memo = \"<pre>\\nlength:\" + anchors.length + \"\\n\";\n", "    var ind = \"\";\n", "    var memo_level = 1;\n", "    var href;\n", "    var tags = [];\n", "    var main_item = 0;\n", "    var format_open = 0;\n", "    for (i = 0; i <= llast; i++)\n", "        tags.push(\"h\" + i);\n", "\n", "    for (i = 0; i < anchors.length; i++) {\n", "        text_memo += \"**\" + anchors[i].id + \"--\\n\";\n", "\n", "        var child = null;\n", "        for(t = 0; t < tags.length; t++) {\n", "            var r = anchors[i].getElementsByTagName(tags[t]);\n", "            if (r.length > 0) {\n", "child = r[0];\n", "break;\n", "            }\n", "        }\n", "        if (child == null) {\n", "            text_memo += \"null\\n\";\n", "            continue;\n", "        }\n", "        if (anchors[i].hasAttribute(\"id\")) {\n", "            // when converted in RST\n", "            href = anchors[i].id;\n", "            text_memo += \"#1-\" + href;\n", "            // passer \u00e0 child suivant (le chercher)\n", "        }\n", "        else if (child.hasAttribute(\"id\")) {\n", "            // in a notebook\n", "            href = child.id;\n", "            text_memo += \"#2-\" + href;\n", "        }\n", "        else {\n", "            text_memo += \"#3-\" + \"*\" + \"\\n\";\n", "            continue;\n", "        }\n", "        var title = child.textContent;\n", "        var level = parseInt(child.tagName.substring(1,2));\n", "\n", "        text_memo += \"--\" + level + \"?\" + lfirst + \"--\" + title + \"\\n\";\n", "\n", "        if ((level < lfirst) || (level > llast)) {\n", "            continue ;\n", "        }\n", "        if (title.endsWith('\u00b6')) {\n", "            title = title.substring(0,title.length-1).replace(\"<\", \"&lt;\")\n", "         .replace(\">\", \"&gt;\").replace(\"&\", \"&amp;\");\n", "        }\n", "        if (title.length == 0) {\n", "            continue;\n", "        }\n", "\n", "        while (level < memo_level) {\n", "            text_menu += end_format + \"</ul>\\n\";\n", "            format_open -= 1;\n", "            memo_level -= 1;\n", "        }\n", "        if (level == lfirst) {\n", "            main_item += 1;\n", "        }\n", "        if (keep_item != -1 && main_item != keep_item + 1) {\n", "            // alert(main_item + \" - \" + level + \" - \" + keep_item);\n", "            continue;\n", "        }\n", "        while (level > memo_level) {\n", "            text_menu += \"<ul>\\n\";\n", "            memo_level += 1;\n", "        }\n", "        text_menu += repeat_indent_string(level-2);\n", "        text_menu += begin_format + sformat.replace(\"__HREF__\", href).replace(\"__TITLE__\", title);\n", "        format_open += 1;\n", "    }\n", "    while (1 < memo_level) {\n", "        text_menu += end_format + \"</ul>\\n\";\n", "        memo_level -= 1;\n", "        format_open -= 1;\n", "    }\n", "    text_menu += send;\n", "    //text_menu += \"\\n\" + text_memo;\n", "\n", "    while (format_open > 0) {\n", "        text_menu += end_format;\n", "        format_open -= 1;\n", "    }\n", "    return text_menu;\n", "};\n", "var update_menu = function() {\n", "    var sbegin = \"\";\n", "    var sformat = '<a href=\"#__HREF__\">__TITLE__</a>';\n", "    var send = \"\";\n", "    var begin_format = '<li>';\n", "    var end_format = '</li>';\n", "    var keep_item = -1;\n", "    var text_menu = update_menu_string(sbegin, 2, 4, sformat, send, keep_item,\n", "       begin_format, end_format);\n", "    var menu = document.getElementById(\"my_id_menu_nb\");\n", "    menu.innerHTML=text_menu;\n", "};\n", "window.setTimeout(update_menu,2000);\n", "            </script>"], "text/plain": ["<IPython.core.display.HTML object>"]}, "execution_count": 4, "metadata": {}, "output_type": "execute_result"}], "source": ["from jyquickhelper import add_notebook_menu\n", "add_notebook_menu()"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Le module utilise des donn\u00e9es issue de [Wine Quality Data Set](https://archive.ics.uci.edu/ml/datasets/Wine+Quality) pour lequel on essaye de pr\u00e9dire la qualit\u00e9 du vin en fonction de ses caract\u00e9ristiques chimiques."]}, {"cell_type": "code", "execution_count": 4, "metadata": {"collapsed": true}, "outputs": [], "source": ["from pyensae.datasource import download_data, DownloadDataException\n", "uci = \"https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/\"\n", "try:\n", "    download_data(\"winequality-red.csv\", url=uci)\n", "    download_data(\"winequality-white.csv\", url=uci)\n", "except DownloadDataException:\n", "    print(\"backup\")\n", "    download_data(\"winequality-red.csv\", website=\"xd\")\n", "    download_data(\"winequality-white.csv\", website=\"xd\")"]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [{"data": {"text/html": ["<pre>\n", "\"fixed acidity\";\"volatile acidity\";\"citric acid\";\"residual sugar\";\"chlorides\";\"free sulfur dioxide\";\"total sulfur dioxide\";\"density\";\"pH\";\"sulphates\";\"alcohol\";\"quality\"\n", "7.4;0.7;0;1.9;0.076;11;34;0.9978;3.51;0.56;9.4;5\n", "7.8;0.88;0;2.6;0.098;25;67;0.9968;3.2;0.68;9.8;5\n", "7.8;0.76;0.04;2.3;0.092;15;54;0.997;3.26;0.65;9.8;5\n", "11.2;0.28;0.56;1.9;0.075;17;60;0.998;3.16;0.58;9.8;6\n", "7.4;0.7;0;1.9;0.076;11;34;0.9978;3.51;0.56;9.4;5\n", "7.4;0.66;0;1.8;0.075;13;40;0.9978;3.51;0.56;9.4;5\n", "7.9;0.6;0.06;1.6;0.069;15;59;0.9964;3.3;0.46;9.4;5\n", "7.3;0.65;0;1.2;0.065;15;21;0.9946;3.39;0.47;10;7\n", "7.8;0.58;0.02;2;0.073;9;18;0.9968;3.36;0.57;9.5;7\n", "\n", "</pre>"], "text/plain": ["<IPython.core.display.HTML object>"]}, "execution_count": 6, "metadata": {}, "output_type": "execute_result"}], "source": ["%head winequality-red.csv"]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style>\n", "    .dataframe thead tr:only-child th {\n", "        text-align: right;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: left;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>fixed acidity</th>\n", "      <th>volatile acidity</th>\n", "      <th>citric acid</th>\n", "      <th>residual sugar</th>\n", "      <th>chlorides</th>\n", "      <th>free sulfur dioxide</th>\n", "      <th>total sulfur dioxide</th>\n", "      <th>density</th>\n", "      <th>pH</th>\n", "      <th>sulphates</th>\n", "      <th>alcohol</th>\n", "      <th>quality</th>\n", "      <th>red</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>7.4</td>\n", "      <td>0.70</td>\n", "      <td>0.00</td>\n", "      <td>1.9</td>\n", "      <td>0.076</td>\n", "      <td>11.0</td>\n", "      <td>34.0</td>\n", "      <td>0.9978</td>\n", "      <td>3.51</td>\n", "      <td>0.56</td>\n", "      <td>9.4</td>\n", "      <td>5</td>\n", "      <td>1</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>7.8</td>\n", "      <td>0.88</td>\n", "      <td>0.00</td>\n", "      <td>2.6</td>\n", "      <td>0.098</td>\n", "      <td>25.0</td>\n", "      <td>67.0</td>\n", "      <td>0.9968</td>\n", "      <td>3.20</td>\n", "      <td>0.68</td>\n", "      <td>9.8</td>\n", "      <td>5</td>\n", "      <td>1</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2</th>\n", "      <td>7.8</td>\n", "      <td>0.76</td>\n", "      <td>0.04</td>\n", "      <td>2.3</td>\n", "      <td>0.092</td>\n", "      <td>15.0</td>\n", "      <td>54.0</td>\n", "      <td>0.9970</td>\n", "      <td>3.26</td>\n", "      <td>0.65</td>\n", "      <td>9.8</td>\n", "      <td>5</td>\n", "      <td>1</td>\n", "    </tr>\n", "    <tr>\n", "      <th>3</th>\n", "      <td>11.2</td>\n", "      <td>0.28</td>\n", "      <td>0.56</td>\n", "      <td>1.9</td>\n", "      <td>0.075</td>\n", "      <td>17.0</td>\n", "      <td>60.0</td>\n", "      <td>0.9980</td>\n", "      <td>3.16</td>\n", "      <td>0.58</td>\n", "      <td>9.8</td>\n", "      <td>6</td>\n", "      <td>1</td>\n", "    </tr>\n", "    <tr>\n", "      <th>4</th>\n", "      <td>7.4</td>\n", "      <td>0.70</td>\n", "      <td>0.00</td>\n", "      <td>1.9</td>\n", "      <td>0.076</td>\n", "      <td>11.0</td>\n", "      <td>34.0</td>\n", "      <td>0.9978</td>\n", "      <td>3.51</td>\n", "      <td>0.56</td>\n", "      <td>9.4</td>\n", "      <td>5</td>\n", "      <td>1</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n", "0            7.4              0.70         0.00             1.9      0.076   \n", "1            7.8              0.88         0.00             2.6      0.098   \n", "2            7.8              0.76         0.04             2.3      0.092   \n", "3           11.2              0.28         0.56             1.9      0.075   \n", "4            7.4              0.70         0.00             1.9      0.076   \n", "\n", "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n", "0                 11.0                  34.0   0.9978  3.51       0.56   \n", "1                 25.0                  67.0   0.9968  3.20       0.68   \n", "2                 15.0                  54.0   0.9970  3.26       0.65   \n", "3                 17.0                  60.0   0.9980  3.16       0.58   \n", "4                 11.0                  34.0   0.9978  3.51       0.56   \n", "\n", "   alcohol  quality  red  \n", "0      9.4        5    1  \n", "1      9.8        5    1  \n", "2      9.8        5    1  \n", "3      9.8        6    1  \n", "4      9.4        5    1  "]}, "execution_count": 7, "metadata": {}, "output_type": "execute_result"}], "source": ["import pandas\n", "red_wine = pandas.read_csv(\"winequality-red.csv\", sep=\";\")\n", "red_wine[\"red\"] = 1\n", "white_wine = pandas.read_csv(\"winequality-white.csv\", sep=\";\")\n", "white_wine[\"red\"] = 0\n", "wines = pandas.concat([red_wine, white_wine])\n", "wines.head()"]}, {"cell_type": "markdown", "metadata": {}, "source": ["On d\u00e9coupe en base d'apprentissage, base de test :"]}, {"cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [{"data": {"text/plain": ["(pandas.core.frame.DataFrame, pandas.core.series.Series)"]}, "execution_count": 8, "metadata": {}, "output_type": "execute_result"}], "source": ["from sklearn.model_selection import train_test_split\n", "X = wines[[c for c in wines.columns if c != \"quality\"]]\n", "Y = wines[\"quality\"]\n", "x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)\n", "type(x_train), type(y_train)"]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [{"data": {"text/plain": ["((6497, 13), (4352, 12), (4352,))"]}, "execution_count": 9, "metadata": {}, "output_type": "execute_result"}], "source": ["wines.shape, x_train.shape, y_train.shape"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["## Exercice 1 : cr\u00e9er une fonction pour automatiser la cr\u00e9ation de ce graphe"]}, {"cell_type": "code", "execution_count": 9, "metadata": {"collapsed": true}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["## Exercice 2 : simplifier l'apprentissage  de chaque mod\u00e8le"]}, {"cell_type": "code", "execution_count": 10, "metadata": {"collapsed": true}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["## Exercice 3 : grid_search\n", "\n", "Consid\u00e9rer un mod\u00e8le et estimer au mieux ses param\u00e8tres."]}, {"cell_type": "code", "execution_count": 11, "metadata": {"collapsed": true}, "outputs": [], "source": []}], "metadata": {"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.1"}}, "nbformat": 4, "nbformat_minor": 2}