{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Analyse de survie"]}, {"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": "markdown", "metadata": {}, "source": ["## Quelques donn\u00e9es\n", "\n", "On r\u00e9cup\u00e8re les donn\u00e9es disponibles sur *open.data.gouv.fr* [Donn\u00e9es hospitali\u00e8res relatives \u00e0 l'\u00e9pid\u00e9mie de COVID-19](https://www.data.gouv.fr/fr/datasets/donnees-hospitalieres-relatives-a-lepidemie-de-covid-19/). Ces donn\u00e9es ne permettent pas de construire la courbe de [Kaplan-Meier](https://fr.wikipedia.org/wiki/Estimateur_de_Kaplan-Meier). On sait combien de personnes rentrent et sortent chaque jour mais on ne sait pas quand une personne qui sort un 1er avril est entr\u00e9e."]}, {"cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [{"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>jour</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>2020-03-18</td>\n", "      <td>NaN</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>2020-03-19</td>\n", "      <td>695.0</td>\n", "      <td>207.0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2</th>\n", "      <td>2020-03-20</td>\n", "      <td>806.0</td>\n", "      <td>248.0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>3</th>\n", "      <td>2020-03-21</td>\n", "      <td>452.0</td>\n", "      <td>151.0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>4</th>\n", "      <td>2020-03-22</td>\n", "      <td>608.0</td>\n", "      <td>210.0</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["         jour    rad     dc\n", "0  2020-03-18    NaN    NaN\n", "1  2020-03-19  695.0  207.0\n", "2  2020-03-20  806.0  248.0\n", "3  2020-03-21  452.0  151.0\n", "4  2020-03-22  608.0  210.0"]}, "execution_count": 3, "metadata": {}, "output_type": "execute_result"}], "source": ["import numpy.random as rnd\n", "\n", "import pandas\n", "df = pandas.read_csv(\"https://www.data.gouv.fr/en/datasets/r/63352e38-d353-4b54-bfd1-f1b3ee1cabd7\", sep=\";\")\n", "gr = df[[\"jour\", \"rad\", \"dc\"]].groupby([\"jour\"]).sum()\n", "diff = gr.diff().reset_index(drop=False)\n", "diff.head()"]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [{"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>entree</th>\n", "      <th>sortie</th>\n", "      <th>issue</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>518488</th>\n", "      <td>-200</td>\n", "      <td>19</td>\n", "      <td>0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>541408</th>\n", "      <td>-192</td>\n", "      <td>27</td>\n", "      <td>0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>476735</th>\n", "      <td>-187</td>\n", "      <td>2</td>\n", "      <td>0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>587013</th>\n", "      <td>-185</td>\n", "      <td>42</td>\n", "      <td>0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>476057</th>\n", "      <td>-180</td>\n", "      <td>1</td>\n", "      <td>0</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        entree  sortie  issue\n", "518488    -200      19      0\n", "541408    -192      27      0\n", "476735    -187       2      0\n", "587013    -185      42      0\n", "476057    -180       1      0"]}, "execution_count": 4, "metadata": {}, "output_type": "execute_result"}], "source": ["\n", "def donnees_artificielles(hosp, mu=14, nu=21):\n", "    dt = pandas.to_datetime(hosp['jour'])\n", "    res = []\n", "    for i in range(hosp.shape[0]):\n", "        date = dt[i].dayofyear\n", "        h = hosp.iloc[i, 1]\n", "        delay = rnd.exponential(mu, int(h))\n", "        for j in range(delay.shape[0]):\n", "            res.append([date - int(delay[j]), date, 1])\n", "        h = hosp.iloc[i, 2]\n", "        delay = rnd.exponential(nu, int(h))\n", "        for j in range(delay.shape[0]):\n", "            res.append([date - int(delay[j]), date , 0])\n", "    return pandas.DataFrame(res, columns=[\"entree\", \"sortie\", \"issue\"])\n", "\n", "\n", "data = donnees_artificielles(diff[1:].reset_index(drop=True)).sort_values('entree')\n", "data.head()"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Chaque ligne est une personne, `entree` est le jour d'entr\u00e9e \u00e0 l'h\u00f4pital, `sortie` celui de la sortie, `issue`, 0 pour d\u00e9c\u00e8s, 1 pour en vie."]}, {"cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [{"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>entree</th>\n", "      <th>sortie</th>\n", "      <th>issue</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>count</th>\n", "      <td>624130.000000</td>\n", "      <td>624130.000000</td>\n", "      <td>624130.000000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>mean</th>\n", "      <td>169.704510</td>\n", "      <td>184.532815</td>\n", "      <td>0.806729</td>\n", "    </tr>\n", "    <tr>\n", "      <th>std</th>\n", "      <td>125.420957</td>\n", "      <td>124.343186</td>\n", "      <td>0.394864</td>\n", "    </tr>\n", "    <tr>\n", "      <th>min</th>\n", "      <td>-200.000000</td>\n", "      <td>1.000000</td>\n", "      <td>0.000000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>25%</th>\n", "      <td>53.000000</td>\n", "      <td>84.000000</td>\n", "      <td>1.000000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>50%</th>\n", "      <td>133.000000</td>\n", "      <td>144.000000</td>\n", "      <td>1.000000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>75%</th>\n", "      <td>301.000000</td>\n", "      <td>315.000000</td>\n", "      <td>1.000000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>max</th>\n", "      <td>366.000000</td>\n", "      <td>366.000000</td>\n", "      <td>1.000000</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["              entree         sortie          issue\n", "count  624130.000000  624130.000000  624130.000000\n", "mean      169.704510     184.532815       0.806729\n", "std       125.420957     124.343186       0.394864\n", "min      -200.000000       1.000000       0.000000\n", "25%        53.000000      84.000000       1.000000\n", "50%       133.000000     144.000000       1.000000\n", "75%       301.000000     315.000000       1.000000\n", "max       366.000000     366.000000       1.000000"]}, "execution_count": 5, "metadata": {}, "output_type": "execute_result"}], "source": ["data.describe()"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Il y a environ 80% de survie dans ces donn\u00e9es."]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": ["import numpy\n", "duree = data.sortie - data.entree\n", "deces = (data.issue == 0).astype(numpy.int32)"]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 720x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["import numpy\n", "import matplotlib.pyplot as plt\n", "from lifelines import KaplanMeierFitter\n", "fig, ax = plt.subplots(1, 1, figsize=(10, 4))\n", "kmf = KaplanMeierFitter()\n", "kmf.fit(duree, deces)\n", "kmf.plot(ax=ax)\n", "ax.legend();"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## R\u00e9gression de Cox\n", "\n", "On reprend les donn\u00e9es artificiellement g\u00e9n\u00e9r\u00e9es et on ajoute une variable identique \u00e0 la dur\u00e9e plus un bruit mais quasi nul "]}, {"cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [{"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>duree</th>\n", "      <th>deces</th>\n", "      <th>X1</th>\n", "      <th>X2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>518488</th>\n", "      <td>219</td>\n", "      <td>1</td>\n", "      <td>125.653230</td>\n", "      <td>-125.666662</td>\n", "    </tr>\n", "    <tr>\n", "      <th>541408</th>\n", "      <td>219</td>\n", "      <td>1</td>\n", "      <td>126.006024</td>\n", "      <td>-125.327549</td>\n", "    </tr>\n", "    <tr>\n", "      <th>476735</th>\n", "      <td>189</td>\n", "      <td>1</td>\n", "      <td>107.920779</td>\n", "      <td>-108.358230</td>\n", "    </tr>\n", "    <tr>\n", "      <th>587013</th>\n", "      <td>227</td>\n", "      <td>1</td>\n", "      <td>129.788930</td>\n", "      <td>-130.045019</td>\n", "    </tr>\n", "    <tr>\n", "      <th>476057</th>\n", "      <td>181</td>\n", "      <td>1</td>\n", "      <td>103.642440</td>\n", "      <td>-103.793008</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        duree  deces          X1          X2\n", "518488    219      1  125.653230 -125.666662\n", "541408    219      1  126.006024 -125.327549\n", "476735    189      1  107.920779 -108.358230\n", "587013    227      1  129.788930 -130.045019\n", "476057    181      1  103.642440 -103.793008"]}, "execution_count": 8, "metadata": {}, "output_type": "execute_result"}], "source": ["import pandas\n", "data_simple = pandas.DataFrame({'duree': duree, 'deces': deces,\n", "                                'X1': duree * 0.57 * deces + numpy.random.randn(duree.shape[0]),\n", "                                'X2': duree * (-0.57) * deces + numpy.random.randn(duree.shape[0])})\n", "data_simple.head()"]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": ["from sklearn.model_selection import train_test_split\n", "data_train, data_test = train_test_split(data_simple, test_size=0.8)"]}, {"cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["\r", "Iteration 1: norm_delta = 0.13943, step_size = 0.9000, log_lik = -250658.36250, newton_decrement = 889.93933, seconds_since_start = 0.0\n", "\r", "Iteration 2: norm_delta = 0.00660, step_size = 0.9000, log_lik = -249862.37270, newton_decrement = 2.81312, seconds_since_start = 0.0\n", "\r", "Iteration 3: norm_delta = 0.00073, step_size = 0.9000, log_lik = -249859.57376, newton_decrement = 0.03357, seconds_since_start = 0.1\n", "\r", "Iteration 4: norm_delta = 0.00000, step_size = 1.0000, log_lik = -249859.54017, newton_decrement = 0.00000, seconds_since_start = 0.1\n", "Convergence success after 4 iterations.\n"]}, {"data": {"text/plain": ["<lifelines.CoxPHFitter: fitted with 124826 total observations, 100754 right-censored observations>"]}, "execution_count": 10, "metadata": {}, "output_type": "execute_result"}], "source": ["from lifelines.fitters.coxph_fitter import CoxPHFitter\n", "cox = CoxPHFitter()\n", "cox.fit(data_train[['duree', 'deces', 'X1']], duration_col=\"duree\", event_col=\"deces\",\n", "        show_progress=True)"]}, {"cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [{"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", "  <tbody>\n", "    <tr>\n", "      <th>model</th>\n", "      <td>lifelines.CoxPHFitter</td>\n", "    </tr>\n", "    <tr>\n", "      <th>duration col</th>\n", "      <td>'duree'</td>\n", "    </tr>\n", "    <tr>\n", "      <th>event col</th>\n", "      <td>'deces'</td>\n", "    </tr>\n", "    <tr>\n", "      <th>baseline estimation</th>\n", "      <td>breslow</td>\n", "    </tr>\n", "    <tr>\n", "      <th>number of observations</th>\n", "      <td>124826</td>\n", "    </tr>\n", "    <tr>\n", "      <th>number of events observed</th>\n", "      <td>24072</td>\n", "    </tr>\n", "    <tr>\n", "      <th>partial log-likelihood</th>\n", "      <td>-249859.54</td>\n", "    </tr>\n", "    <tr>\n", "      <th>time fit was run</th>\n", "      <td>2021-02-24 23:48:57 UTC</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div><table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th style=\"min-width: 12px;\"></th>\n", "      <th style=\"min-width: 12px;\">coef</th>\n", "      <th style=\"min-width: 12px;\">exp(coef)</th>\n", "      <th style=\"min-width: 12px;\">se(coef)</th>\n", "      <th style=\"min-width: 12px;\">coef lower 95%</th>\n", "      <th style=\"min-width: 12px;\">coef upper 95%</th>\n", "      <th style=\"min-width: 12px;\">exp(coef) lower 95%</th>\n", "      <th style=\"min-width: 12px;\">exp(coef) upper 95%</th>\n", "      <th style=\"min-width: 12px;\">z</th>\n", "      <th style=\"min-width: 12px;\">p</th>\n", "      <th style=\"min-width: 12px;\">-log2(p)</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>X1</th>\n", "      <td>0.02</td>\n", "      <td>1.02</td>\n", "      <td>0.00</td>\n", "      <td>0.02</td>\n", "      <td>0.02</td>\n", "      <td>1.02</td>\n", "      <td>1.02</td>\n", "      <td>42.23</td>\n", "      <td>&lt;0.005</td>\n", "      <td>inf</td>\n", "    </tr>\n", "  </tbody>\n", "</table><br><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", "  <tbody>\n", "    <tr>\n", "      <th>Concordance</th>\n", "      <td>0.69</td>\n", "    </tr>\n", "    <tr>\n", "      <th>Partial AIC</th>\n", "      <td>499721.08</td>\n", "    </tr>\n", "    <tr>\n", "      <th>log-likelihood ratio test</th>\n", "      <td>1597.64 on 1 df</td>\n", "    </tr>\n", "    <tr>\n", "      <th>-log2(p) of ll-ratio test</th>\n", "      <td>inf</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/latex": ["\\begin{tabular}{lrrrrrrrrrr}\n", "\\toprule\n", "{} &  coef &  exp(coef) &  se(coef) &  coef lower 95\\% &  coef upper 95\\% &  exp(coef) lower 95\\% &  exp(coef) upper 95\\% &     z &    p &  -log2(p) \\\\\n", "covariate &       &            &           &                 &                 &                      &                      &       &      &           \\\\\n", "\\midrule\n", "X1        &  0.02 &       1.02 &      0.00 &            0.02 &            0.02 &                 1.02 &                 1.02 & 42.23 & 0.00 &       inf \\\\\n", "\\bottomrule\n", "\\end{tabular}\n"], "text/plain": ["<lifelines.CoxPHFitter: fitted with 124826 total observations, 100754 right-censored observations>\n", "             duration col = 'duree'\n", "                event col = 'deces'\n", "      baseline estimation = breslow\n", "   number of observations = 124826\n", "number of events observed = 24072\n", "   partial log-likelihood = -249859.54\n", "         time fit was run = 2021-02-24 23:48:57 UTC\n", "\n", "---\n", "            coef  exp(coef)   se(coef)   coef lower 95%   coef upper 95%  exp(coef) lower 95%  exp(coef) upper 95%\n", "covariate                                                                                                         \n", "X1          0.02       1.02       0.00             0.02             0.02                 1.02                 1.02\n", "\n", "              z      p   -log2(p)\n", "covariate                        \n", "X1        42.23 <0.005        inf\n", "---\n", "Concordance = 0.69\n", "Partial AIC = 499721.08\n", "log-likelihood ratio test = 1597.64 on 1 df\n", "-log2(p) of ll-ratio test = inf"]}, "metadata": {}, "output_type": "display_data"}], "source": ["cox.print_summary()"]}, {"cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["\r", "Iteration 1: norm_delta = 0.13946, step_size = 0.9000, log_lik = -250658.36250, newton_decrement = 888.92089, seconds_since_start = 0.0\n", "\r", "Iteration 2: norm_delta = 0.00667, step_size = 0.9000, log_lik = -249863.61089, newton_decrement = 2.86434, seconds_since_start = 0.0\n", "\r", "Iteration 3: norm_delta = 0.00074, step_size = 0.9000, log_lik = -249860.76079, newton_decrement = 0.03426, seconds_since_start = 0.1\n", "\r", "Iteration 4: norm_delta = 0.00000, step_size = 1.0000, log_lik = -249860.72650, newton_decrement = 0.00000, seconds_since_start = 0.1\n", "Convergence success after 4 iterations.\n"]}, {"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", "  <tbody>\n", "    <tr>\n", "      <th>model</th>\n", "      <td>lifelines.CoxPHFitter</td>\n", "    </tr>\n", "    <tr>\n", "      <th>duration col</th>\n", "      <td>'duree'</td>\n", "    </tr>\n", "    <tr>\n", "      <th>event col</th>\n", "      <td>'deces'</td>\n", "    </tr>\n", "    <tr>\n", "      <th>baseline estimation</th>\n", "      <td>breslow</td>\n", "    </tr>\n", "    <tr>\n", "      <th>number of observations</th>\n", "      <td>124826</td>\n", "    </tr>\n", "    <tr>\n", "      <th>number of events observed</th>\n", "      <td>24072</td>\n", "    </tr>\n", "    <tr>\n", "      <th>partial log-likelihood</th>\n", "      <td>-249860.73</td>\n", "    </tr>\n", "    <tr>\n", "      <th>time fit was run</th>\n", "      <td>2021-02-24 23:48:59 UTC</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div><table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th style=\"min-width: 12px;\"></th>\n", "      <th style=\"min-width: 12px;\">coef</th>\n", "      <th style=\"min-width: 12px;\">exp(coef)</th>\n", "      <th style=\"min-width: 12px;\">se(coef)</th>\n", "      <th style=\"min-width: 12px;\">coef lower 95%</th>\n", "      <th style=\"min-width: 12px;\">coef upper 95%</th>\n", "      <th style=\"min-width: 12px;\">exp(coef) lower 95%</th>\n", "      <th style=\"min-width: 12px;\">exp(coef) upper 95%</th>\n", "      <th style=\"min-width: 12px;\">z</th>\n", "      <th style=\"min-width: 12px;\">p</th>\n", "      <th style=\"min-width: 12px;\">-log2(p)</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>X2</th>\n", "      <td>-0.02</td>\n", "      <td>0.98</td>\n", "      <td>0.00</td>\n", "      <td>-0.02</td>\n", "      <td>-0.02</td>\n", "      <td>0.98</td>\n", "      <td>0.98</td>\n", "      <td>-42.21</td>\n", "      <td>&lt;0.005</td>\n", "      <td>inf</td>\n", "    </tr>\n", "  </tbody>\n", "</table><br><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", "  <tbody>\n", "    <tr>\n", "      <th>Concordance</th>\n", "      <td>0.69</td>\n", "    </tr>\n", "    <tr>\n", "      <th>Partial AIC</th>\n", "      <td>499723.45</td>\n", "    </tr>\n", "    <tr>\n", "      <th>log-likelihood ratio test</th>\n", "      <td>1595.27 on 1 df</td>\n", "    </tr>\n", "    <tr>\n", "      <th>-log2(p) of ll-ratio test</th>\n", "      <td>inf</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/latex": ["\\begin{tabular}{lrrrrrrrrrr}\n", "\\toprule\n", "{} &  coef &  exp(coef) &  se(coef) &  coef lower 95\\% &  coef upper 95\\% &  exp(coef) lower 95\\% &  exp(coef) upper 95\\% &      z &    p &  -log2(p) \\\\\n", "covariate &       &            &           &                 &                 &                      &                      &        &      &           \\\\\n", "\\midrule\n", "X2        & -0.02 &       0.98 &      0.00 &           -0.02 &           -0.02 &                 0.98 &                 0.98 & -42.21 & 0.00 &       inf \\\\\n", "\\bottomrule\n", "\\end{tabular}\n"], "text/plain": ["<lifelines.CoxPHFitter: fitted with 124826 total observations, 100754 right-censored observations>\n", "             duration col = 'duree'\n", "                event col = 'deces'\n", "      baseline estimation = breslow\n", "   number of observations = 124826\n", "number of events observed = 24072\n", "   partial log-likelihood = -249860.73\n", "         time fit was run = 2021-02-24 23:48:59 UTC\n", "\n", "---\n", "            coef  exp(coef)   se(coef)   coef lower 95%   coef upper 95%  exp(coef) lower 95%  exp(coef) upper 95%\n", "covariate                                                                                                         \n", "X2         -0.02       0.98       0.00            -0.02            -0.02                 0.98                 0.98\n", "\n", "               z      p   -log2(p)\n", "covariate                         \n", "X2        -42.21 <0.005        inf\n", "---\n", "Concordance = 0.69\n", "Partial AIC = 499723.45\n", "log-likelihood ratio test = 1595.27 on 1 df\n", "-log2(p) of ll-ratio test = inf"]}, "metadata": {}, "output_type": "display_data"}], "source": ["cox2 = CoxPHFitter()\n", "cox2.fit(data_train[['duree', 'deces', 'X2']], duration_col=\"duree\", event_col=\"deces\",\n", "        show_progress=True)\n", "cox2.print_summary()"]}, {"cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [{"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>621725</th>\n", "      <th>110352</th>\n", "      <th>139986</th>\n", "      <th>72623</th>\n", "      <th>248121</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0.0</th>\n", "      <td>0.008806</td>\n", "      <td>0.008673</td>\n", "      <td>0.008543</td>\n", "      <td>0.008717</td>\n", "      <td>0.008661</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1.0</th>\n", "      <td>0.018218</td>\n", "      <td>0.017942</td>\n", "      <td>0.017673</td>\n", "      <td>0.018035</td>\n", "      <td>0.017918</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2.0</th>\n", "      <td>0.026735</td>\n", "      <td>0.026330</td>\n", "      <td>0.025936</td>\n", "      <td>0.026466</td>\n", "      <td>0.026295</td>\n", "    </tr>\n", "    <tr>\n", "      <th>3.0</th>\n", "      <td>0.036002</td>\n", "      <td>0.035457</td>\n", "      <td>0.034926</td>\n", "      <td>0.035640</td>\n", "      <td>0.035409</td>\n", "    </tr>\n", "    <tr>\n", "      <th>4.0</th>\n", "      <td>0.045543</td>\n", "      <td>0.044854</td>\n", "      <td>0.044182</td>\n", "      <td>0.045085</td>\n", "      <td>0.044793</td>\n", "    </tr>\n", "    <tr>\n", "      <th>...</th>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "    </tr>\n", "    <tr>\n", "      <th>184.0</th>\n", "      <td>2.055736</td>\n", "      <td>2.024623</td>\n", "      <td>1.994277</td>\n", "      <td>2.035070</td>\n", "      <td>2.021872</td>\n", "    </tr>\n", "    <tr>\n", "      <th>189.0</th>\n", "      <td>2.092002</td>\n", "      <td>2.060340</td>\n", "      <td>2.029459</td>\n", "      <td>2.070971</td>\n", "      <td>2.057541</td>\n", "    </tr>\n", "    <tr>\n", "      <th>197.0</th>\n", "      <td>2.138687</td>\n", "      <td>2.106318</td>\n", "      <td>2.074747</td>\n", "      <td>2.117186</td>\n", "      <td>2.103457</td>\n", "    </tr>\n", "    <tr>\n", "      <th>201.0</th>\n", "      <td>2.205513</td>\n", "      <td>2.172133</td>\n", "      <td>2.139576</td>\n", "      <td>2.183341</td>\n", "      <td>2.169182</td>\n", "    </tr>\n", "    <tr>\n", "      <th>217.0</th>\n", "      <td>2.330629</td>\n", "      <td>2.295356</td>\n", "      <td>2.260952</td>\n", "      <td>2.307199</td>\n", "      <td>2.292237</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "<p>165 rows \u00d7 5 columns</p>\n", "</div>"], "text/plain": ["         621725    110352    139986    72623     248121\n", "0.0    0.008806  0.008673  0.008543  0.008717  0.008661\n", "1.0    0.018218  0.017942  0.017673  0.018035  0.017918\n", "2.0    0.026735  0.026330  0.025936  0.026466  0.026295\n", "3.0    0.036002  0.035457  0.034926  0.035640  0.035409\n", "4.0    0.045543  0.044854  0.044182  0.045085  0.044793\n", "...         ...       ...       ...       ...       ...\n", "184.0  2.055736  2.024623  1.994277  2.035070  2.021872\n", "189.0  2.092002  2.060340  2.029459  2.070971  2.057541\n", "197.0  2.138687  2.106318  2.074747  2.117186  2.103457\n", "201.0  2.205513  2.172133  2.139576  2.183341  2.169182\n", "217.0  2.330629  2.295356  2.260952  2.307199  2.292237\n", "\n", "[165 rows x 5 columns]"]}, "execution_count": 13, "metadata": {}, "output_type": "execute_result"}], "source": ["cox.predict_cumulative_hazard(data_test[:5])"]}, {"cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [{"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>621725</th>\n", "      <th>110352</th>\n", "      <th>139986</th>\n", "      <th>72623</th>\n", "      <th>248121</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0.0</th>\n", "      <td>0.991233</td>\n", "      <td>0.991365</td>\n", "      <td>0.991494</td>\n", "      <td>0.991321</td>\n", "      <td>0.991377</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1.0</th>\n", "      <td>0.981947</td>\n", "      <td>0.982218</td>\n", "      <td>0.982482</td>\n", "      <td>0.982127</td>\n", "      <td>0.982242</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2.0</th>\n", "      <td>0.973619</td>\n", "      <td>0.974013</td>\n", "      <td>0.974398</td>\n", "      <td>0.973881</td>\n", "      <td>0.974048</td>\n", "    </tr>\n", "    <tr>\n", "      <th>3.0</th>\n", "      <td>0.964638</td>\n", "      <td>0.965164</td>\n", "      <td>0.965677</td>\n", "      <td>0.964988</td>\n", "      <td>0.965211</td>\n", "    </tr>\n", "    <tr>\n", "      <th>4.0</th>\n", "      <td>0.955478</td>\n", "      <td>0.956137</td>\n", "      <td>0.956780</td>\n", "      <td>0.955916</td>\n", "      <td>0.956196</td>\n", "    </tr>\n", "    <tr>\n", "      <th>...</th>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "    </tr>\n", "    <tr>\n", "      <th>184.0</th>\n", "      <td>0.127999</td>\n", "      <td>0.132044</td>\n", "      <td>0.136112</td>\n", "      <td>0.130671</td>\n", "      <td>0.132407</td>\n", "    </tr>\n", "    <tr>\n", "      <th>189.0</th>\n", "      <td>0.123440</td>\n", "      <td>0.127411</td>\n", "      <td>0.131407</td>\n", "      <td>0.126063</td>\n", "      <td>0.127768</td>\n", "    </tr>\n", "    <tr>\n", "      <th>197.0</th>\n", "      <td>0.117809</td>\n", "      <td>0.121685</td>\n", "      <td>0.125588</td>\n", "      <td>0.120370</td>\n", "      <td>0.122034</td>\n", "    </tr>\n", "    <tr>\n", "      <th>201.0</th>\n", "      <td>0.110194</td>\n", "      <td>0.113934</td>\n", "      <td>0.117705</td>\n", "      <td>0.112664</td>\n", "      <td>0.114271</td>\n", "    </tr>\n", "    <tr>\n", "      <th>217.0</th>\n", "      <td>0.097235</td>\n", "      <td>0.100726</td>\n", "      <td>0.104251</td>\n", "      <td>0.099540</td>\n", "      <td>0.101040</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "<p>165 rows \u00d7 5 columns</p>\n", "</div>"], "text/plain": ["         621725    110352    139986    72623     248121\n", "0.0    0.991233  0.991365  0.991494  0.991321  0.991377\n", "1.0    0.981947  0.982218  0.982482  0.982127  0.982242\n", "2.0    0.973619  0.974013  0.974398  0.973881  0.974048\n", "3.0    0.964638  0.965164  0.965677  0.964988  0.965211\n", "4.0    0.955478  0.956137  0.956780  0.955916  0.956196\n", "...         ...       ...       ...       ...       ...\n", "184.0  0.127999  0.132044  0.136112  0.130671  0.132407\n", "189.0  0.123440  0.127411  0.131407  0.126063  0.127768\n", "197.0  0.117809  0.121685  0.125588  0.120370  0.122034\n", "201.0  0.110194  0.113934  0.117705  0.112664  0.114271\n", "217.0  0.097235  0.100726  0.104251  0.099540  0.101040\n", "\n", "[165 rows x 5 columns]"]}, "execution_count": 14, "metadata": {}, "output_type": "execute_result"}], "source": ["cox.predict_survival_function(data_test[:5])"]}, {"cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "code", "execution_count": 15, "metadata": {}, "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": "3.8.7"}}, "nbformat": 4, "nbformat_minor": 4}