{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Hyperparam\u00e8tres, LassoRandomForestRregressor et grid_search (correction)\n", "\n", "Le notebook explore l'optimisation des hyper parama\u00e8tres du mod\u00e8le [LassoRandomForestRegressor](http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/ensae_teaching_cs/ml/lasso_random_forest_regressor.html), et fait varier le nombre d'arbre et le param\u00e8tres alpha."]}, {"cell_type": "code", "execution_count": 1, "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", "// look up into all sections and builds an automated menu //\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": 2, "metadata": {}, "output_type": "execute_result"}], "source": ["from jyquickhelper import add_notebook_menu\n", "add_notebook_menu()"]}, {"cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": ["%matplotlib inline"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Donn\u00e9es"]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": ["from sklearn.datasets import load_diabetes\n", "from sklearn.model_selection import train_test_split\n", "data = load_diabetes()\n", "X, y = data.data, data.target\n", "X_train, X_test, y_train, y_test = train_test_split(X, y)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Premiers mod\u00e8les"]}, {"cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.3166064611454491"]}, "execution_count": 5, "metadata": {}, "output_type": "execute_result"}], "source": ["from sklearn.ensemble import RandomForestRegressor\n", "from sklearn.metrics import r2_score\n", "\n", "rf = RandomForestRegressor()\n", "rf.fit(X_train, y_train)\n", "r2_score(y_test, rf.predict(X_test))"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Pour le mod\u00e8le, il suffit de copier coller le code \u00e9crit dans ce fichier [lasso_random_forest_regressor.py](https://github.com/sdpython/ensae_teaching_cs/blob/master/src/ensae_teaching_cs/ml/lasso_random_forest_regressor.py)."]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.20558896981102492"]}, "execution_count": 6, "metadata": {}, "output_type": "execute_result"}], "source": ["from ensae_teaching_cs.ml.lasso_random_forest_regressor import LassoRandomForestRegressor\n", "lrf = LassoRandomForestRegressor()\n", "lrf.fit(X_train, y_train)\n", "r2_score(y_test, lrf.predict(X_test))"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Le mod\u00e8le a r\u00e9duit le nombre d'arbres."]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"text/plain": ["97"]}, "execution_count": 7, "metadata": {}, "output_type": "execute_result"}], "source": ["len(lrf.estimators_)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Grid Search\n", "\n", "On veut trouver la meilleure paire de param\u00e8tres (``n_estimators``, ``alpha``). *scikit-learn* impl\u00e9mente l'objet [GridSearchCV](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html) qui effectue de nombreux apprentissage avec toutes les valeurs de param\u00e8tres qu'il re\u00e7oit. Voici tous les param\u00e8tres qu'on peut changer :"]}, {"cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [{"data": {"text/plain": ["{'lasso_estimator__alpha': 1.0,\n", " 'lasso_estimator__copy_X': True,\n", " 'lasso_estimator__fit_intercept': True,\n", " 'lasso_estimator__max_iter': 1000,\n", " 'lasso_estimator__positive': False,\n", " 'lasso_estimator__precompute': False,\n", " 'lasso_estimator__random_state': None,\n", " 'lasso_estimator__selection': 'cyclic',\n", " 'lasso_estimator__tol': 0.0001,\n", " 'lasso_estimator__warm_start': False,\n", " 'lasso_estimator': Lasso(),\n", " 'rf_estimator__bootstrap': True,\n", " 'rf_estimator__ccp_alpha': 0.0,\n", " 'rf_estimator__criterion': 'squared_error',\n", " 'rf_estimator__max_depth': None,\n", " 'rf_estimator__max_features': 1.0,\n", " 'rf_estimator__max_leaf_nodes': None,\n", " 'rf_estimator__max_samples': None,\n", " 'rf_estimator__min_impurity_decrease': 0.0,\n", " 'rf_estimator__min_samples_leaf': 1,\n", " 'rf_estimator__min_samples_split': 2,\n", " 'rf_estimator__min_weight_fraction_leaf': 0.0,\n", " 'rf_estimator__n_estimators': 100,\n", " 'rf_estimator__n_jobs': None,\n", " 'rf_estimator__oob_score': False,\n", " 'rf_estimator__random_state': None,\n", " 'rf_estimator__verbose': 0,\n", " 'rf_estimator__warm_start': False,\n", " 'rf_estimator': RandomForestRegressor()}"]}, "execution_count": 8, "metadata": {}, "output_type": "execute_result"}], "source": ["lrf.get_params()"]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": ["params = {\n", "    'lasso_estimator__alpha': [0.25, 0.5, 0.75, 1., 1.25, 1.5],\n", "    'rf_estimator__n_estimators': [20, 40, 60, 80, 100, 120]\n", "}"]}, {"cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Fitting 5 folds for each of 36 candidates, totalling 180 fits\n"]}, {"data": {"text/html": ["<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"\u25b8\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"\u25be\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(estimator=LassoRandomForestRegressor(lasso_estimator=Lasso(),\n", "                                                  rf_estimator=RandomForestRegressor()),\n", "             param_grid={&#x27;lasso_estimator__alpha&#x27;: [0.25, 0.5, 0.75, 1.0, 1.25,\n", "                                                    1.5],\n", "                         &#x27;rf_estimator__n_estimators&#x27;: [20, 40, 60, 80, 100,\n", "                                                        120]},\n", "             verbose=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(estimator=LassoRandomForestRegressor(lasso_estimator=Lasso(),\n", "                                                  rf_estimator=RandomForestRegressor()),\n", "             param_grid={&#x27;lasso_estimator__alpha&#x27;: [0.25, 0.5, 0.75, 1.0, 1.25,\n", "                                                    1.5],\n", "                         &#x27;rf_estimator__n_estimators&#x27;: [20, 40, 60, 80, 100,\n", "                                                        120]},\n", "             verbose=1)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: LassoRandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>LassoRandomForestRegressor(lasso_estimator=Lasso(),\n", "                           rf_estimator=RandomForestRegressor())</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">lasso_estimator: Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso()</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rf_estimator: RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</pre></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>"], "text/plain": ["GridSearchCV(estimator=LassoRandomForestRegressor(lasso_estimator=Lasso(),\n", "                                                  rf_estimator=RandomForestRegressor()),\n", "             param_grid={'lasso_estimator__alpha': [0.25, 0.5, 0.75, 1.0, 1.25,\n", "                                                    1.5],\n", "                         'rf_estimator__n_estimators': [20, 40, 60, 80, 100,\n", "                                                        120]},\n", "             verbose=1)"]}, "execution_count": 10, "metadata": {}, "output_type": "execute_result"}], "source": ["from sklearn.exceptions import ConvergenceWarning\n", "from sklearn.model_selection import GridSearchCV\n", "\n", "import warnings\n", "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n", "\n", "grid = GridSearchCV(estimator=LassoRandomForestRegressor(),\n", "                    param_grid=params, verbose=1)\n", "grid.fit(X_train, y_train)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Les meilleurs param\u00e8tres sont les suivants :"]}, {"cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [{"data": {"text/plain": ["{'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 20}"]}, "execution_count": 11, "metadata": {}, "output_type": "execute_result"}], "source": ["grid.best_params_"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Et le mod\u00e8le a gard\u00e9 un nombre r\u00e9duit d'arbres :"]}, {"cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [{"data": {"text/plain": ["20"]}, "execution_count": 12, "metadata": {}, "output_type": "execute_result"}], "source": ["len(grid.best_estimator_.estimators_)"]}, {"cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.23768343413832094"]}, "execution_count": 13, "metadata": {}, "output_type": "execute_result"}], "source": ["r2_score(y_test, grid.predict(X_test))"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Evolution de la performance en fonction des param\u00e8tres"]}, {"cell_type": "code", "execution_count": 13, "metadata": {"scrolled": false}, "outputs": [{"data": {"text/plain": ["{'mean_fit_time': array([0.051863  , 0.11151867, 0.16286798, 0.20638132, 0.24587946,\n", "        0.30230732, 0.04886923, 0.10883999, 0.1585783 , 0.21171408,\n", "        0.25670881, 0.30813308, 0.04687281, 0.10599108, 0.16779151,\n", "        0.21490512, 0.24286323, 0.37416844, 0.04798951, 0.10375576,\n", "        0.13916297, 0.19486108, 0.23168812, 0.35405369, 0.04832931,\n", "        0.10837116, 0.17046494, 0.21563282, 0.250454  , 0.30722728,\n", "        0.0500711 , 0.10197167, 0.14489303, 0.19933763, 0.31132407,\n", "        0.69930143]),\n", " 'std_fit_time': array([0.00362419, 0.01626225, 0.00804797, 0.01572331, 0.00662523,\n", "        0.01574959, 0.00169066, 0.0097691 , 0.0132841 , 0.0106317 ,\n", "        0.01988724, 0.02359756, 0.00126011, 0.00448715, 0.00627981,\n", "        0.02519122, 0.02605425, 0.09337497, 0.01102544, 0.00824485,\n", "        0.00715579, 0.01587819, 0.006515  , 0.04939259, 0.00602516,\n", "        0.00652839, 0.01898743, 0.01727985, 0.01794094, 0.02079929,\n", "        0.00562965, 0.00345422, 0.00807745, 0.00482911, 0.09500837,\n", "        0.11143193]),\n", " 'mean_score_time': array([0.00239778, 0.00359111, 0.00518904, 0.00718164, 0.00817652,\n", "        0.01257362, 0.0021884 , 0.00339103, 0.00539336, 0.00738797,\n", "        0.00917087, 0.00998683, 0.00199485, 0.00379586, 0.00599022,\n", "        0.0103807 , 0.01236439, 0.00837784, 0.00431471, 0.00392194,\n", "        0.00887637, 0.00752082, 0.00937295, 0.01437345, 0.00079789,\n", "        0.00312424, 0.00479422, 0.00718193, 0.00958648, 0.01098609,\n", "        0.00199614, 0.0039938 , 0.0049974 , 0.00697622, 0.01322117,\n", "        0.02559528]),\n", " 'std_score_time': array([8.11351379e-04, 4.87586231e-04, 3.98946617e-04, 3.98891227e-04,\n", "        4.01356881e-04, 4.68445598e-03, 3.86144056e-04, 4.75930831e-04,\n", "        4.96522489e-04, 1.36387385e-03, 1.15770100e-03, 1.41214662e-05,\n", "        1.39020727e-06, 4.03363736e-04, 6.28333254e-04, 9.76193348e-03,\n", "        6.18748536e-03, 4.21257447e-03, 5.70546749e-03, 6.04969222e-03,\n", "        6.08895072e-03, 4.95836569e-03, 7.65298131e-03, 2.73983497e-03,\n", "        9.77213669e-04, 6.24847412e-03, 2.48103089e-03, 3.95754917e-04,\n", "        2.06222335e-03, 1.41556299e-03, 1.58579723e-06, 1.09920549e-03,\n", "        1.70908708e-05, 6.18028043e-04, 2.94616536e-03, 1.07247410e-02]),\n", " 'param_lasso_estimator__alpha': masked_array(data=[0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.5, 0.5, 0.5, 0.5,\n", "                    0.5, 0.5, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 1.0, 1.0,\n", "                    1.0, 1.0, 1.0, 1.0, 1.25, 1.25, 1.25, 1.25, 1.25, 1.25,\n", "                    1.5, 1.5, 1.5, 1.5, 1.5, 1.5],\n", "              mask=[False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False],\n", "        fill_value='?',\n", "             dtype=object),\n", " 'param_rf_estimator__n_estimators': masked_array(data=[20, 40, 60, 80, 100, 120, 20, 40, 60, 80, 100, 120, 20,\n", "                    40, 60, 80, 100, 120, 20, 40, 60, 80, 100, 120, 20, 40,\n", "                    60, 80, 100, 120, 20, 40, 60, 80, 100, 120],\n", "              mask=[False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False, False, False, False, False,\n", "                    False, False, False, False],\n", "        fill_value='?',\n", "             dtype=object),\n", " 'params': [{'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 0.25, 'rf_estimator__n_estimators': 120},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 0.5, 'rf_estimator__n_estimators': 120},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 0.75, 'rf_estimator__n_estimators': 120},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 1.0, 'rf_estimator__n_estimators': 120},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 1.25, 'rf_estimator__n_estimators': 120},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 20},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 40},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 60},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 80},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 100},\n", "  {'lasso_estimator__alpha': 1.5, 'rf_estimator__n_estimators': 120}],\n", " 'split0_test_score': array([0.48765423, 0.47007607, 0.41456128, 0.34332073, 0.36888898,\n", "        0.370369  , 0.50945042, 0.52478666, 0.45136636, 0.38160909,\n", "        0.46464615, 0.52426278, 0.33309356, 0.50165501, 0.5023884 ,\n", "        0.47159884, 0.40443694, 0.42850669, 0.35280764, 0.41274937,\n", "        0.41530415, 0.35325067, 0.461381  , 0.40458056, 0.45063697,\n", "        0.47402597, 0.39203225, 0.58405673, 0.43074069, 0.36958539,\n", "        0.35946403, 0.46811327, 0.43129582, 0.47471034, 0.31616108,\n", "        0.43820558]),\n", " 'split1_test_score': array([0.31748269, 0.32402775, 0.31309735, 0.36776797, 0.36291097,\n", "        0.25860886, 0.32332546, 0.28310914, 0.34370404, 0.29429633,\n", "        0.32531769, 0.30070425, 0.32083858, 0.31018103, 0.28147265,\n", "        0.36096592, 0.33612201, 0.34993859, 0.31710402, 0.34449814,\n", "        0.32729745, 0.29203103, 0.3028285 , 0.40849055, 0.35384028,\n", "        0.35159579, 0.30777994, 0.34548216, 0.29892216, 0.32126091,\n", "        0.30904616, 0.30511572, 0.30571425, 0.356684  , 0.32693294,\n", "        0.33647908]),\n", " 'split2_test_score': array([0.36714477, 0.28075098, 0.27797057, 0.28236282, 0.30276893,\n", "        0.21700352, 0.38350757, 0.3370075 , 0.31649401, 0.20121556,\n", "        0.30713851, 0.28664918, 0.33362753, 0.30618393, 0.36897318,\n", "        0.24307011, 0.33060169, 0.32188143, 0.35355399, 0.32021347,\n", "        0.35526908, 0.25476369, 0.26570208, 0.16455204, 0.4154126 ,\n", "        0.30368747, 0.27953113, 0.32737498, 0.23057391, 0.31069444,\n", "        0.36235946, 0.2807269 , 0.33147417, 0.2414187 , 0.2822582 ,\n", "        0.24876048]),\n", " 'split3_test_score': array([0.4043803 , 0.31910819, 0.23721216, 0.30117822, 0.24160984,\n", "        0.29643875, 0.29444929, 0.36670958, 0.29294625, 0.35849669,\n", "        0.28732813, 0.06164115, 0.27354921, 0.30412114, 0.31082146,\n", "        0.23641828, 0.29371034, 0.34239524, 0.39866027, 0.36307616,\n", "        0.2895736 , 0.31561043, 0.41537819, 0.25744729, 0.39204788,\n", "        0.35827202, 0.3558286 , 0.25123577, 0.22871596, 0.36031404,\n", "        0.33534641, 0.31542919, 0.29505816, 0.30829603, 0.27520299,\n", "        0.20069686]),\n", " 'split4_test_score': array([0.37299925, 0.29360033, 0.35534609, 0.34508877, 0.3955746 ,\n", "        0.24485609, 0.32355244, 0.40128887, 0.25337656, 0.26202744,\n", "        0.2442764 , 0.12475539, 0.36143398, 0.25855855, 0.27470568,\n", "        0.37247721, 0.26957179, 0.28886332, 0.34711816, 0.35216452,\n", "        0.30793447, 0.26319255, 0.22076315, 0.197187  , 0.29571515,\n", "        0.30295817, 0.27574516, 0.32196883, 0.32617658, 0.23406369,\n", "        0.30742707, 0.37246999, 0.1981131 , 0.35704234, 0.26689645,\n", "        0.29602189]),\n", " 'mean_test_score': array([0.38993225, 0.33751266, 0.31963749, 0.3279437 , 0.33435067,\n", "        0.27745524, 0.36685703, 0.38258035, 0.33157744, 0.29952902,\n", "        0.32574138, 0.25960255, 0.32450857, 0.33613993, 0.34767227,\n", "        0.33690607, 0.32688855, 0.34631705, 0.35384882, 0.35854033,\n", "        0.33907575, 0.29576967, 0.33321058, 0.28645149, 0.38153057,\n", "        0.35810788, 0.32218342, 0.3660237 , 0.30302586, 0.31918369,\n", "        0.33472862, 0.34837101, 0.3123311 , 0.34763028, 0.29349033,\n", "        0.30403278]),\n", " 'std_test_score': array([0.05623747, 0.06818182, 0.06141412, 0.03133811, 0.05541701,\n", "        0.05303893, 0.07697179, 0.0809888 , 0.06683068, 0.06528952,\n", "        0.07450222, 0.16114489, 0.02874254, 0.08486524, 0.08420844,\n", "        0.08819219, 0.04582314, 0.04622048, 0.0260949 , 0.03054825,\n", "        0.04389069, 0.03592898, 0.09088902, 0.10248598, 0.05322657,\n", "        0.06242197, 0.04515318, 0.11364082, 0.07434396, 0.04807043,\n", "        0.0235824 , 0.06700877, 0.0747087 , 0.07635179, 0.02366514,\n", "        0.08105877]),\n", " 'rank_test_score': array([ 1, 14, 26, 21, 18, 35,  4,  2, 20, 31, 23, 36, 24, 16, 10, 15, 22,\n", "        12,  8,  6, 13, 32, 19, 34,  3,  7, 25,  5, 30, 27, 17,  9, 28, 11,\n", "        33, 29])}"]}, "execution_count": 14, "metadata": {}, "output_type": "execute_result"}], "source": ["grid.cv_results_"]}, {"cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x432 with 3 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["import numpy\n", "from mpl_toolkits.mplot3d import Axes3D\n", "import matplotlib.pyplot as plt\n", "\n", "fig = plt.figure(figsize=(14, 6))\n", "ax = fig.add_subplot(131, projection='3d')\n", "xs = numpy.array([el['lasso_estimator__alpha'] for el in grid.cv_results_['params']])\n", "ys = numpy.array([el['rf_estimator__n_estimators'] for el in grid.cv_results_['params']])\n", "zs = numpy.array(grid.cv_results_['mean_test_score'])\n", "ax.scatter(xs, ys, zs)\n", "ax.set_title(\"3D...\")\n", "\n", "ax = fig.add_subplot(132)\n", "for x in sorted(set(xs)):\n", "    y2 = ys[xs == x]\n", "    z2 = zs[xs == x]\n", "    ax.plot(y2, z2, label=\"alpha=%1.2f\" % x, lw=x*2)\n", "ax.legend();\n", "\n", "ax = fig.add_subplot(133)\n", "for y in sorted(set(ys)):\n", "    x2 = xs[ys == y]\n", "    z2 = zs[ys == y]\n", "    ax.plot(x2, z2, label=\"n_estimators=%d\" % y, lw=y/40)\n", "ax.legend();"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Il semble que la valeur de alpha importe peu mais qu'un grand nombre d'arbres a un impact positif. Cela dit, il faut ne pas oublier l'\u00e9cart-type de ces variations qui n'est pas n\u00e9gligeable."]}, {"cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": []}], "metadata": {"kernelspec": {"display_name": "Python 3 (ipykernel)", "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": "3.10.5"}}, "nbformat": 4, "nbformat_minor": 2}