Joint Modeling of Longitudinal and Survival Outcomes in PyMC

joint-long-surv.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e15a67fc-ab90-45d5-9685-c98b3d70717d",
   "metadata": {},
   "source": [
    "It should be clear from the back posts on this blog ([1](https://austinrochford.com/posts/2015-10-05-bayes-survival.html) [2](https://austinrochford.com/posts/2017-10-02-bayes-param-survival.html) [3](https://austinrochford.com/posts/revisit-survival-pymc.html)) that I have a long-standing interesting in [survival analysis](https://en.wikipedia.org/wiki/Survival_analysis).  Over the last few years, I have been sporadically learning about joint models for longitudinal and time-to-event data.  These models augment survival models by incorporating information from other (non-survival) outcomes repeatedly measured from the subjects over time.  The resulting models can provide better survival estimates by incorporating this information.  Recently I succeeded in wrapping my head around the theory of one class of such models, and wanted to record that understanding for my future self here, along with any one else this may help.  This post contains a crash course in the basics of these joint models, along with a worked example in Python using [PyMC](https://www.pymc.io/welcome.html).\n",
    "\n",
    "My present understanding of this topic is largely based on [Dimitris Rizopoulos's](https://www.drizopoulos.com/) excellent presentation [_Joint Modeling of Longitudinal and Time-to-Event Data\n",
    "with Applications in R_](https://www.drizopoulos.com/courses/EMC/ESP72.pdf) and the [documentation](https://drizopoulos.github.io/JMbayes2/) for his R package, `JMBayes2`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd24e306-7f92-4dc6-bed2-99f980d634be",
   "metadata": {},
   "source": [
    "## Theory"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88ee121f-93da-44fc-a765-84476d598a62",
   "metadata": {},
   "source": [
    "### Surival analysis\n",
    "\n",
    "For the survival component of our models, we will use the [proportional hazards model](https://en.wikipedia.org/wiki/Proportional_hazards_model#The_Cox_model) that I have written about in two previous posts ([2023](https://austinrochford.com/posts/revisit-survival-pymc.html), [2015](https://austinrochford.com/posts/2015-10-05-bayes-survival.html)).  In this model, we represent the [hazard function](https://en.wikipedia.org/wiki/Survival_analysis#Hazard_function_and_cumulative_hazard_function) of the $i$-th subject associated with covariates $\\mathbf{x}_i$ as\n",
    "\n",
    "$$\\lambda(t\\ |\\ \\mathbf{x}_i) = \\lambda_0(t) \\cdot \\exp(\\alpha \\cdot \\mathbf{x}_i),$$\n",
    "\n",
    "where $\\lambda_0(t)$ is the baseline hazard at time $t$ and $\\alpha$ is a vector of regression coefficients.\n",
    "\n",
    "In this post, we will use the equivalent Poisson model discussed in the past posts to perform inference on these survival models."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0cfdc122-48a3-42bb-a95e-08b43887d888",
   "metadata": {},
   "source": [
    "### Joint model\n",
    "\n",
    "The goal of this post is to show how we can improve our models by incorporating information from longitudinal outcomes into our survival models.  We denote the value of the longitudinal outcome for the $i$-th subject at time $t$ by $y_{i, t}$.  There are many ways to incorporate this information into our survival model (entire [books](https://www.routledge.com/Joint-Modeling-of-Longitudinal-and-Time-to-Event-Data/Elashoff-li-Li/p/book/9780367570576) have been written on the subject); in this post we take the approach of assuming independence of the survival and longitudinal outcomes conditional on random effects.  Specifically, we posit a random effects model for $y_{i, t}$, $y_{i, t} \\sim N(\\mu_{i, t}, \\sigma^2)$ with\n",
    "\n",
    "$$\\mu_{i, t} = \\beta \\cdot \\mathbf{x}_i + \\gamma_{i, t},$$\n",
    "\n",
    "where $\\gamma_{i, t}$ is a set of [random effects](https://en.wikipedia.org/wiki/Random_effects_model) that can vary based on the subject and time.\n",
    "\n",
    "Our conditional independence model assumes that the longitudinal outcome only influences survival through the randome effects $\\gamma_{i, t}$, and incorporates these into the survival model as\n",
    "\n",
    "$$\\lambda(t\\ |\\ \\mathbf{x}_i, \\gamma_{i, t}) = \\lambda_0(t) \\cdot \\exp(\\alpha \\cdot \\mathbf{x}_i + \\nu \\cdot \\gamma_{i, t}).$$"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8fe82ecf-b707-4273-91ec-2f53234450d9",
   "metadata": {},
   "source": [
    "## Worked example"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "023146e4-b963-48f0-b718-9ac070b7fb76",
   "metadata": {},
   "source": [
    "First we make the necessary Python imports and do some light configuration."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "24ccfd3c-2493-4da5-9deb-8143cd438063",
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ccc5b703-a817-4931-bc11-c60e15f04c79",
   "metadata": {},
   "outputs": [],
   "source": [
    "import arviz as az\n",
    "from matplotlib import pyplot as plt\n",
    "import numpy as np\n",
    "import nutpie\n",
    "import polars as pl\n",
    "import pymc as pm\n",
    "from pytensor import tensor as pt\n",
    "import seaborn as sns\n",
    "from seaborn import objects as so"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "fb1bed02-0d07-4327-8349-69a3f8806557",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set(color_codes=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "790400e5-f319-4730-91ac-5af9a1ece9fc",
   "metadata": {},
   "source": [
    "### Load the data\n",
    "\n",
    "In this worked example, we use longitudinal [data](https://vincentarelbundock.github.io/Rdatasets/doc/survival/pbcseq.html) from a Mayo Clinic study on primary biliary cirrhosis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "076dd427-b9cf-483f-809c-642945de1897",
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_PATH = \"https://vincentarelbundock.github.io/Rdatasets/csv/survival/pbcseq.csv\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fb2f44ec-f393-4116-9340-298f182be677",
   "metadata": {},
   "outputs": [],
   "source": [
    "COLS = [\n",
    "    \"id\",\n",
    "    \"status\",\n",
    "    \"trt\",\n",
    "    \"day\",\n",
    "    \"bili\",\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4ec683b4-0a1c-41d0-b57d-198f70f8c6f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pl.read_csv(DATA_PATH, columns=COLS)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1653250c-0784-4b1d-80d3-a199026dd0ee",
   "metadata": {},
   "source": [
    "#### Data exploration and transformation\n",
    "\n",
    "We examine this data below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "266bdcb5-3704-48d2-a6f2-feb7466cbc12",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><style>\n",
       ".dataframe > thead > tr,\n",
       ".dataframe > tbody > tr {\n",
       "  text-align: right;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       "</style>\n",
       "<small>shape: (1_945, 5)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>id</th><th>status</th><th>trt</th><th>day</th><th>bili</th></tr><tr><td>i64</td><td>i64</td><td>i64</td><td>i64</td><td>f64</td></tr></thead><tbody><tr><td>1</td><td>2</td><td>1</td><td>0</td><td>14.5</td></tr><tr><td>1</td><td>2</td><td>1</td><td>192</td><td>21.3</td></tr><tr><td>2</td><td>0</td><td>1</td><td>0</td><td>1.1</td></tr><tr><td>2</td><td>0</td><td>1</td><td>182</td><td>0.8</td></tr><tr><td>2</td><td>0</td><td>1</td><td>365</td><td>1.0</td></tr><tr><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td></tr><tr><td>312</td><td>0</td><td>0</td><td>0</td><td>6.4</td></tr><tr><td>312</td><td>0</td><td>0</td><td>206</td><td>5.5</td></tr><tr><td>312</td><td>0</td><td>0</td><td>390</td><td>7.4</td></tr><tr><td>312</td><td>0</td><td>0</td><td>775</td><td>16.3</td></tr><tr><td>312</td><td>0</td><td>0</td><td>1075</td><td>23.4</td></tr></tbody></table></div>"
      ],
      "text/plain": [
       "shape: (1_945, 5)\n",
       "┌─────┬────────┬─────┬──────┬──────┐\n",
       "│ id  ┆ status ┆ trt ┆ day  ┆ bili │\n",
       "│ --- ┆ ---    ┆ --- ┆ ---  ┆ ---  │\n",
       "│ i64 ┆ i64    ┆ i64 ┆ i64  ┆ f64  │\n",
       "╞═════╪════════╪═════╪══════╪══════╡\n",
       "│ 1   ┆ 2      ┆ 1   ┆ 0    ┆ 14.5 │\n",
       "│ 1   ┆ 2      ┆ 1   ┆ 192  ┆ 21.3 │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 0    ┆ 1.1  │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 182  ┆ 0.8  │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 365  ┆ 1.0  │\n",
       "│ …   ┆ …      ┆ …   ┆ …    ┆ …    │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 0    ┆ 6.4  │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 206  ┆ 5.5  │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 390  ┆ 7.4  │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 775  ┆ 16.3 │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 1075 ┆ 23.4 │\n",
       "└─────┴────────┴─────┴──────┴──────┘"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d02229c-4a7c-4fd2-8549-2c9cd86692b0",
   "metadata": {},
   "source": [
    "* `id` is the case number of the subject.\n",
    "* `status` indicates the subject's status at the end of their time in the study:\n",
    "    * `0` indicates that they were alive at the end of the study,\n",
    "    * `1` indicates that they exited the study upon receiving a liver transplant,\n",
    "    * and `2` indicates that they died during the study.\n",
    "* `trt` indicates if they received a placebo or the true treatment.\n",
    "* `day` indicates the number of days between enrollment of the patient and the visit.\n",
    "* `bili` indicates the concentration of [bilirubin](https://www.mayoclinic.org/tests-procedures/bilirubin/about/pac-20393041) in the blood during that visit, in mg/dL.\n",
    "\n",
    "The survival outcome is derived from the `status`, and the longitudinal outcome is derived from `bili`.\n",
    "\n",
    "First we (crudely) reduce the `day` column to monthly (really 30 day) granularity for ease of modeling."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "fe9fe0e8-ef06-4e54-b29a-f6dfeabda25e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.with_columns(month=pl.col(\"day\") // 30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f707877c-3ae0-4df3-b557-df261a138f2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><style>\n",
       ".dataframe > thead > tr,\n",
       ".dataframe > tbody > tr {\n",
       "  text-align: right;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       "</style>\n",
       "<small>shape: (1_945, 6)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>id</th><th>status</th><th>trt</th><th>day</th><th>bili</th><th>month</th></tr><tr><td>i64</td><td>i64</td><td>i64</td><td>i64</td><td>f64</td><td>i64</td></tr></thead><tbody><tr><td>1</td><td>2</td><td>1</td><td>0</td><td>14.5</td><td>0</td></tr><tr><td>1</td><td>2</td><td>1</td><td>192</td><td>21.3</td><td>6</td></tr><tr><td>2</td><td>0</td><td>1</td><td>0</td><td>1.1</td><td>0</td></tr><tr><td>2</td><td>0</td><td>1</td><td>182</td><td>0.8</td><td>6</td></tr><tr><td>2</td><td>0</td><td>1</td><td>365</td><td>1.0</td><td>12</td></tr><tr><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td></tr><tr><td>312</td><td>0</td><td>0</td><td>0</td><td>6.4</td><td>0</td></tr><tr><td>312</td><td>0</td><td>0</td><td>206</td><td>5.5</td><td>6</td></tr><tr><td>312</td><td>0</td><td>0</td><td>390</td><td>7.4</td><td>13</td></tr><tr><td>312</td><td>0</td><td>0</td><td>775</td><td>16.3</td><td>25</td></tr><tr><td>312</td><td>0</td><td>0</td><td>1075</td><td>23.4</td><td>35</td></tr></tbody></table></div>"
      ],
      "text/plain": [
       "shape: (1_945, 6)\n",
       "┌─────┬────────┬─────┬──────┬──────┬───────┐\n",
       "│ id  ┆ status ┆ trt ┆ day  ┆ bili ┆ month │\n",
       "│ --- ┆ ---    ┆ --- ┆ ---  ┆ ---  ┆ ---   │\n",
       "│ i64 ┆ i64    ┆ i64 ┆ i64  ┆ f64  ┆ i64   │\n",
       "╞═════╪════════╪═════╪══════╪══════╪═══════╡\n",
       "│ 1   ┆ 2      ┆ 1   ┆ 0    ┆ 14.5 ┆ 0     │\n",
       "│ 1   ┆ 2      ┆ 1   ┆ 192  ┆ 21.3 ┆ 6     │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 0    ┆ 1.1  ┆ 0     │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 182  ┆ 0.8  ┆ 6     │\n",
       "│ 2   ┆ 0      ┆ 1   ┆ 365  ┆ 1.0  ┆ 12    │\n",
       "│ …   ┆ …      ┆ …   ┆ …    ┆ …    ┆ …     │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 0    ┆ 6.4  ┆ 0     │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 206  ┆ 5.5  ┆ 6     │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 390  ┆ 7.4  ┆ 13    │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 775  ┆ 16.3 ┆ 25    │\n",
       "│ 312 ┆ 0      ┆ 0   ┆ 1075 ┆ 23.4 ┆ 35    │\n",
       "└─────┴────────┴─────┴──────┴──────┴───────┘"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27faec9e-5b97-46e4-bc50-a7a2df6fd847",
   "metadata": {},
   "source": [
    "Next we reduce this longitudinal dataframe, which may have multiple rows per subject, to a dataframe that has one row per subject."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4dc90926-e9ce-4f9f-a406-8a4cbf3fd4ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "subj_df = (\n",
    "    df.group_by(\"id\")\n",
    "    .agg(pl.col(\"month\").max(), pl.col(\"trt\").first(), pl.col(\"status\").first())\n",
    "    .sort(\"id\")\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "f198f6c2-a6dc-4005-9600-b4b9296ba1e9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><style>\n",
       ".dataframe > thead > tr,\n",
       ".dataframe > tbody > tr {\n",
       "  text-align: right;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       "</style>\n",
       "<small>shape: (312, 4)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>id</th><th>month</th><th>trt</th><th>status</th></tr><tr><td>i64</td><td>i64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>1</td><td>6</td><td>1</td><td>2</td></tr><tr><td>2</td><td>107</td><td>1</td><td>0</td></tr><tr><td>3</td><td>24</td><td>1</td><td>2</td></tr><tr><td>4</td><td>60</td><td>1</td><td>2</td></tr><tr><td>5</td><td>48</td><td>0</td><td>1</td></tr><tr><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td></tr><tr><td>308</td><td>38</td><td>1</td><td>0</td></tr><tr><td>309</td><td>42</td><td>0</td><td>0</td></tr><tr><td>310</td><td>45</td><td>1</td><td>0</td></tr><tr><td>311</td><td>36</td><td>1</td><td>0</td></tr><tr><td>312</td><td>35</td><td>0</td><td>0</td></tr></tbody></table></div>"
      ],
      "text/plain": [
       "shape: (312, 4)\n",
       "┌─────┬───────┬─────┬────────┐\n",
       "│ id  ┆ month ┆ trt ┆ status │\n",
       "│ --- ┆ ---   ┆ --- ┆ ---    │\n",
       "│ i64 ┆ i64   ┆ i64 ┆ i64    │\n",
       "╞═════╪═══════╪═════╪════════╡\n",
       "│ 1   ┆ 6     ┆ 1   ┆ 2      │\n",
       "│ 2   ┆ 107   ┆ 1   ┆ 0      │\n",
       "│ 3   ┆ 24    ┆ 1   ┆ 2      │\n",
       "│ 4   ┆ 60    ┆ 1   ┆ 2      │\n",
       "│ 5   ┆ 48    ┆ 0   ┆ 1      │\n",
       "│ …   ┆ …     ┆ …   ┆ …      │\n",
       "│ 308 ┆ 38    ┆ 1   ┆ 0      │\n",
       "│ 309 ┆ 42    ┆ 0   ┆ 0      │\n",
       "│ 310 ┆ 45    ┆ 1   ┆ 0      │\n",
       "│ 311 ┆ 36    ┆ 1   ┆ 0      │\n",
       "│ 312 ┆ 35    ┆ 0   ┆ 0      │\n",
       "└─────┴───────┴─────┴────────┘"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subj_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de38b14c-659c-4717-9408-bbbd90d1cfbb",
   "metadata": {},
   "source": [
    "* `id`, `trt`, and `status` have retained their meanings from the longitudinal data frame.\n",
    "* `month` indicates the number of months (really 30-day periods) after which they exited the study."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cae7c1e3-4536-4acb-bd9c-4a1f06d2d5a5",
   "metadata": {},
   "source": [
    "### Modeling\n",
    "\n",
    "We now turn to modeling impact of treatment on survival using this data."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e95681e2-887e-4d14-aa9f-0554956b10da",
   "metadata": {},
   "source": [
    "#### Survival model\n",
    "\n",
    "We first implement a pure survival model for two reasons:\n",
    "\n",
    "1. it is a key component of the joint model, and\n",
    "2. its inferences will provide a good baseline against which to compare those of the joint model.\n",
    "\n",
    "First we derive NumPy arrays indicating the time each subject spent in the study (`t`), whether or not they died during the study (`died`), and whether or not they were treated (`trt`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cc840a85-1097-4e37-a4ae-b04fa4eacef6",
   "metadata": {},
   "outputs": [],
   "source": [
    "t = subj_df[\"month\"].to_numpy()\n",
    "died = subj_df[\"status\"].eq(2).to_numpy()\n",
    "trt = subj_df[\"trt\"].eq(1).to_numpy()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f20c7ba6-a559-4468-aac7-2525fdbe4ee6",
   "metadata": {},
   "source": [
    "Next we derive some ancillary quantities necessary to use a Poisson likelihood to perform inference on the proportional hazard model.  For a detailed treatment of these quantities, refer to a prior [post](https://austinrochford.com/posts/revisit-survival-pymc.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "bd4c1a72-6da9-41bf-9341-8a064fd78365",
   "metadata": {},
   "outputs": [],
   "source": [
    "exposed = np.full((subj_df.shape[0], t.max() + 2), True, dtype=np.bool_)\n",
    "np.put_along_axis(exposed, t[:, np.newaxis] + 1, False, axis=1)\n",
    "exposed = np.minimum.accumulate(exposed, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "49b4ed08-2d18-4c5f-a4e3-2757074bb2fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "died_ = np.full_like(exposed, False, dtype=np.bool_)\n",
    "np.put_along_axis(died_, t[:, np.newaxis], died[:, np.newaxis], axis=1)\n",
    "\n",
    "assert (died_ & ~exposed).sum() == 0"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "712a2b28-a300-4388-9f4e-de64679330a6",
   "metadata": {},
   "source": [
    "We are now ready to begin building the survival model with PyMC.  For the baseline hazard we choose a hierachical normal prior,\n",
    "\n",
    "$$\n",
    "\\begin{align}\n",
    "    \\mu_{\\lambda_0}\n",
    "        & \\sim N(0, 2.5^2) \\\\\n",
    "    \\sigma_{\\lambda_0}\n",
    "        & \\sim \\text{Half}-N(1) \\\\\n",
    "    \\log \\lambda_0(t)\n",
    "        & \\sim N(\\mu_{\\lambda_0}, \\sigma_{\\lambda_0}^2).\n",
    "\\end{align}\n",
    "$$\n",
    "\n",
    "For computational efficiency, we implement this prior using a [non-centered parameterization](https://twiecki.io/blog/2017/02/08/bayesian-hierchical-non-centered/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "965ecf65-79ba-4079-babf-b91ff3cee51b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# the scale necessary to make a halfnormal distribution have unit variance\n",
    "HALFNORMAL_SCALE = 1 / np.sqrt(1 - 2 / np.pi)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7f263dd3-8f2b-4025-95f2-9bbd995fb214",
   "metadata": {},
   "outputs": [],
   "source": [
    "def noncentered_normal(name, *, dims, μ=None):\n",
    "    if μ is None:\n",
    "        μ = pm.Normal(f\"μ_{name}\", 0, 2.5)\n",
    "\n",
    "    Δ = pm.Normal(f\"Δ_{name}\", 0, 1, dims=dims)\n",
    "    σ = pm.HalfNormal(f\"σ_{name}\", 2.5 * HALFNORMAL_SCALE)\n",
    "\n",
    "    return pm.Deterministic(name, μ + Δ * σ, dims=dims)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "a2727155-3d17-401a-8849-715732978029",
   "metadata": {},
   "outputs": [],
   "source": [
    "coords = {\"drug\": np.array([False, True]), \"t\": np.arange(t.max() + 2)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "200bf773-e090-4e84-bec7-c4f535f9c622",
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model(coords=coords) as surv_model:\n",
    "    log_λ0 = noncentered_normal(\"log_λ0\", dims=\"t\")\n",
    "    λ0 = pt.exp(log_λ0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8dbc0db5-2b06-41fe-a672-85d8991adf47",
   "metadata": {},
   "source": [
    "Now we introduce the regression component of the model, making survival dependent on treatment.\n",
    "\n",
    "We let $\\alpha_{\\text{trt}} \\sim N(0, 2.5^2)$ and define the hazard function as\n",
    "\n",
    "$$\\lambda(t\\ |\\ x_{\\text{trt}, i}) = \\lambda_0(t) \\cdot \\exp(\\alpha_{\\text{trt}} \\cdot x_{\\text{trt}, i}).$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "d5225384-c321-4aec-8a0e-6638662082e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "with surv_model:\n",
    "    α_trt = pm.Normal(\"α_trt\", 0, 2.5)\n",
    "\n",
    "    λ = pt.outer(pt.exp(α_trt * trt), λ0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec74b4d5-251a-4152-b6f8-9b9b7d31fc12",
   "metadata": {},
   "source": [
    "Note that we have not included an intercept term in our regression, as that combined with the baseline hazard would lead to an [unidentified](https://en.wikipedia.org/wiki/Identifiability) model.\n",
    "\n",
    "Finally we specify the Poisson likelihood for our model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "28414ff6-4582-490f-b90d-062d969a4c15",
   "metadata": {},
   "outputs": [],
   "source": [
    "with surv_model:\n",
    "    pm.Poisson(\"died\", exposed * λ, observed=died_)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d8abc89-8ccc-48c5-b84f-55d8ca4f2ae4",
   "metadata": {},
   "source": [
    "Before sampling, we define the cumulative survival function of our model, in order to obtain samples from its posterior predictive distribution."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "24a70e35-7665-48a0-ac11-f7e9bef583b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "with surv_model:\n",
    "    λ_pred = pt.outer(pt.exp(α_trt * np.array([0, 1])), λ0)\n",
    "    Λ_pred = λ_pred.cumsum(axis=1)\n",
    "    sf_pred = pm.Deterministic(\"sf_pred\", pt.exp(-Λ_pred), dims=(\"drug\", \"t\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ebb4098a-b2e8-4db3-b29f-b395afb3c55f",
   "metadata": {},
   "source": [
    "We are now ready to sample from our model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "5835ca18-bac3-435a-8689-4df8b92d4fdf",
   "metadata": {},
   "outputs": [],
   "source": [
    "SAMPLER_KWARGS = {\"cores\": 8, \"seed\": 1234567890}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "14f6c7d7-04fa-4288-acfa-05d2148a76ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    :root {\n",
       "        --column-width-1: 40%; /* Progress column width */\n",
       "        --column-width-2: 15%; /* Chain column width */\n",
       "        --column-width-3: 15%; /* Divergences column width */\n",
       "        --column-width-4: 15%; /* Step Size column width */\n",
       "        --column-width-5: 15%; /* Gradients/Draw column width */\n",
       "    }\n",
       "\n",
       "    .nutpie {\n",
       "        max-width: 800px;\n",
       "        margin: 10px auto;\n",
       "        font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;\n",
       "        //color: #333;\n",
       "        //background-color: #fff;\n",
       "        padding: 10px;\n",
       "        box-shadow: 0 4px 6px rgba(0,0,0,0.1);\n",
       "        border-radius: 8px;\n",
       "        font-size: 14px; /* Smaller font size for a more compact look */\n",
       "    }\n",
       "    .nutpie table {\n",
       "        width: 100%;\n",
       "        border-collapse: collapse; /* Remove any extra space between borders */\n",
       "    }\n",
       "    .nutpie th, .nutpie td {\n",
       "        padding: 8px 10px; /* Reduce padding to make table more compact */\n",
       "        text-align: left;\n",
       "        border-bottom: 1px solid #888;\n",
       "    }\n",
       "    .nutpie th {\n",
       "        //background-color: #f0f0f0;\n",
       "    }\n",
       "\n",
       "    .nutpie th:nth-child(1) { width: var(--column-width-1); }\n",
       "    .nutpie th:nth-child(2) { width: var(--column-width-2); }\n",
       "    .nutpie th:nth-child(3) { width: var(--column-width-3); }\n",
       "    .nutpie th:nth-child(4) { width: var(--column-width-4); }\n",
       "    .nutpie th:nth-child(5) { width: var(--column-width-5); }\n",
       "\n",
       "    .nutpie progress {\n",
       "        width: 100%;\n",
       "        height: 15px; /* Smaller progress bars */\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-webkit-progress-bar {\n",
       "        background-color: #eee;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-webkit-progress-value {\n",
       "        background-color: #5cb85c;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-moz-progress-bar {\n",
       "        background-color: #5cb85c;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    .nutpie .progress-cell {\n",
       "        width: 100%;\n",
       "    }\n",
       "\n",
       "    .nutpie p strong { font-size: 16px; font-weight: bold; }\n",
       "\n",
       "    @media (prefers-color-scheme: dark) {\n",
       "        .nutpie {\n",
       "            //color: #ddd;\n",
       "            //background-color: #1e1e1e;\n",
       "            box-shadow: 0 4px 6px rgba(0,0,0,0.2);\n",
       "        }\n",
       "        .nutpie table, .nutpie th, .nutpie td {\n",
       "            border-color: #555;\n",
       "            color: #ccc;\n",
       "        }\n",
       "        .nutpie th {\n",
       "            background-color: #2a2a2a;\n",
       "        }\n",
       "        .nutpie progress::-webkit-progress-bar {\n",
       "            background-color: #444;\n",
       "        }\n",
       "        .nutpie progress::-webkit-progress-value {\n",
       "            background-color: #3178c6;\n",
       "        }\n",
       "        .nutpie progress::-moz-progress-bar {\n",
       "            background-color: #3178c6;\n",
       "        }\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<div class=\"nutpie\">\n",
       "    <p><strong>Sampler Progress</strong></p>\n",
       "    <p>Total Chains: <span id=\"total-chains\">6</span></p>\n",
       "    <p>Active Chains: <span id=\"active-chains\">0</span></p>\n",
       "    <p>\n",
       "        Finished Chains:\n",
       "        <span id=\"active-chains\">6</span>\n",
       "    </p>\n",
       "    <p>Sampling for now</p>\n",
       "    <p>\n",
       "        Estimated Time to Completion:\n",
       "        <span id=\"eta\">now</span>\n",
       "    </p>\n",
       "\n",
       "    <progress\n",
       "        id=\"total-progress-bar\"\n",
       "        max=\"7800\"\n",
       "        value=\"7800\">\n",
       "    </progress>\n",
       "    <table>\n",
       "        <thead>\n",
       "            <tr>\n",
       "                <th>Progress</th>\n",
       "                <th>Draws</th>\n",
       "                <th>Divergences</th>\n",
       "                <th>Step Size</th>\n",
       "                <th>Gradients/Draw</th>\n",
       "            </tr>\n",
       "        </thead>\n",
       "        <tbody id=\"chain-details\">\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.41</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.39</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.41</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.40</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.40</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.42</td>\n",
       "                    <td>15</td>\n",
       "                </tr>\n",
       "            \n",
       "            </tr>\n",
       "        </tbody>\n",
       "    </table>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<nutpie.sample._BackgroundSampler at 0x30ad7f2c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "surv_trace = nutpie.sample(nutpie.compile_pymc_model(surv_model), **SAMPLER_KWARGS)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3811197-52b7-4e7e-b80d-3b851c09152d",
   "metadata": {},
   "source": [
    "Standard sampling diagnostics show no cause for concern."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "b2fdc5ae-2786-4d41-9b53-51b49a140ec5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
       "<defs>\n",
       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "</symbol>\n",
       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "</symbol>\n",
       "</defs>\n",
       "</svg>\n",
       "<style>/* CSS stylesheet for displaying xarray objects in jupyterlab.\n",
       " *\n",
       " */\n",
       "\n",
       ":root {\n",
       "  --xr-font-color0: var(--jp-content-font-color0, rgba(0, 0, 0, 1));\n",
       "  --xr-font-color2: var(--jp-content-font-color2, rgba(0, 0, 0, 0.54));\n",
       "  --xr-font-color3: var(--jp-content-font-color3, rgba(0, 0, 0, 0.38));\n",
       "  --xr-border-color: var(--jp-border-color2, #e0e0e0);\n",
       "  --xr-disabled-color: var(--jp-layout-color3, #bdbdbd);\n",
       "  --xr-background-color: var(--jp-layout-color0, white);\n",
       "  --xr-background-color-row-even: var(--jp-layout-color1, white);\n",
       "  --xr-background-color-row-odd: var(--jp-layout-color2, #eeeeee);\n",
       "}\n",
       "\n",
       "html[theme=dark],\n",
       "html[data-theme=dark],\n",
       "body[data-theme=dark],\n",
       "body.vscode-dark {\n",
       "  --xr-font-color0: rgba(255, 255, 255, 1);\n",
       "  --xr-font-color2: rgba(255, 255, 255, 0.54);\n",
       "  --xr-font-color3: rgba(255, 255, 255, 0.38);\n",
       "  --xr-border-color: #1F1F1F;\n",
       "  --xr-disabled-color: #515151;\n",
       "  --xr-background-color: #111111;\n",
       "  --xr-background-color-row-even: #111111;\n",
       "  --xr-background-color-row-odd: #313131;\n",
       "}\n",
       "\n",
       ".xr-wrap {\n",
       "  display: block !important;\n",
       "  min-width: 300px;\n",
       "  max-width: 700px;\n",
       "}\n",
       "\n",
       ".xr-text-repr-fallback {\n",
       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-header {\n",
       "  padding-top: 6px;\n",
       "  padding-bottom: 6px;\n",
       "  margin-bottom: 4px;\n",
       "  border-bottom: solid 1px var(--xr-border-color);\n",
       "}\n",
       "\n",
       ".xr-header > div,\n",
       ".xr-header > ul {\n",
       "  display: inline;\n",
       "  margin-top: 0;\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-obj-type,\n",
       ".xr-array-name {\n",
       "  margin-left: 2px;\n",
       "  margin-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-obj-type {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-sections {\n",
       "  padding-left: 0 !important;\n",
       "  display: grid;\n",
       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
       "}\n",
       "\n",
       ".xr-section-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-section-item input {\n",
       "  display: inline-block;\n",
       "  opacity: 0;\n",
       "}\n",
       "\n",
       ".xr-section-item input + label {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label {\n",
       "  cursor: pointer;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-item input:focus + label {\n",
       "  border: 2px solid var(--xr-font-color0);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label:hover {\n",
       "  color: var(--xr-font-color0);\n",
       "}\n",
       "\n",
       ".xr-section-summary {\n",
       "  grid-column: 1;\n",
       "  color: var(--xr-font-color2);\n",
       "  font-weight: 500;\n",
       "}\n",
       "\n",
       ".xr-section-summary > span {\n",
       "  display: inline-block;\n",
       "  padding-left: 0.5em;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in + label:before {\n",
       "  display: inline-block;\n",
       "  content: '►';\n",
       "  font-size: 11px;\n",
       "  width: 15px;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label:before {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label:before {\n",
       "  content: '▼';\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label > span {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-section-summary,\n",
       ".xr-section-inline-details {\n",
       "  padding-top: 4px;\n",
       "  padding-bottom: 4px;\n",
       "}\n",
       "\n",
       ".xr-section-inline-details {\n",
       "  grid-column: 2 / -1;\n",
       "}\n",
       "\n",
       ".xr-section-details {\n",
       "  display: none;\n",
       "  grid-column: 1 / -1;\n",
       "  margin-bottom: 5px;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-array-wrap {\n",
       "  grid-column: 1 / -1;\n",
       "  display: grid;\n",
       "  grid-template-columns: 20px auto;\n",
       "}\n",
       "\n",
       ".xr-array-wrap > label {\n",
       "  grid-column: 1;\n",
       "  vertical-align: top;\n",
       "}\n",
       "\n",
       ".xr-preview {\n",
       "  color: var(--xr-font-color3);\n",
       "}\n",
       "\n",
       ".xr-array-preview,\n",
       ".xr-array-data {\n",
       "  padding: 0 5px !important;\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-array-data,\n",
       ".xr-array-in:checked ~ .xr-array-preview {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-array-in:checked ~ .xr-array-data,\n",
       ".xr-array-preview {\n",
       "  display: inline-block;\n",
       "}\n",
       "\n",
       ".xr-dim-list {\n",
       "  display: inline-block !important;\n",
       "  list-style: none;\n",
       "  padding: 0 !important;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list li {\n",
       "  display: inline-block;\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list:before {\n",
       "  content: '(';\n",
       "}\n",
       "\n",
       ".xr-dim-list:after {\n",
       "  content: ')';\n",
       "}\n",
       "\n",
       ".xr-dim-list li:not(:last-child):after {\n",
       "  content: ',';\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-has-index {\n",
       "  font-weight: bold;\n",
       "}\n",
       "\n",
       ".xr-var-list,\n",
       ".xr-var-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-var-item > div,\n",
       ".xr-var-item label,\n",
       ".xr-var-item > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-even);\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-var-item > .xr-var-name:hover span {\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-var-list > li:nth-child(odd) > div,\n",
       ".xr-var-list > li:nth-child(odd) > label,\n",
       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-odd);\n",
       "}\n",
       "\n",
       ".xr-var-name {\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-var-dims {\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-var-dtype {\n",
       "  grid-column: 3;\n",
       "  text-align: right;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-var-preview {\n",
       "  grid-column: 4;\n",
       "}\n",
       "\n",
       ".xr-index-preview {\n",
       "  grid-column: 2 / 5;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-var-name,\n",
       ".xr-var-dims,\n",
       ".xr-var-dtype,\n",
       ".xr-preview,\n",
       ".xr-attrs dt {\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-var-name:hover,\n",
       ".xr-var-dims:hover,\n",
       ".xr-var-dtype:hover,\n",
       ".xr-attrs dt:hover {\n",
       "  overflow: visible;\n",
       "  width: auto;\n",
       "  z-index: 1;\n",
       "}\n",
       "\n",
       ".xr-var-attrs,\n",
       ".xr-var-data,\n",
       ".xr-index-data {\n",
       "  display: none;\n",
       "  background-color: var(--xr-background-color) !important;\n",
       "  padding-bottom: 5px !important;\n",
       "}\n",
       "\n",
       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
       ".xr-var-data-in:checked ~ .xr-var-data,\n",
       ".xr-index-data-in:checked ~ .xr-index-data {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       ".xr-var-data > table {\n",
       "  float: right;\n",
       "}\n",
       "\n",
       ".xr-var-name span,\n",
       ".xr-var-data,\n",
       ".xr-index-name div,\n",
       ".xr-index-data,\n",
       ".xr-attrs {\n",
       "  padding-left: 25px !important;\n",
       "}\n",
       "\n",
       ".xr-attrs,\n",
       ".xr-var-attrs,\n",
       ".xr-var-data,\n",
       ".xr-index-data {\n",
       "  grid-column: 1 / -1;\n",
       "}\n",
       "\n",
       "dl.xr-attrs {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  display: grid;\n",
       "  grid-template-columns: 125px auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt,\n",
       ".xr-attrs dd {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  float: left;\n",
       "  padding-right: 10px;\n",
       "  width: auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt {\n",
       "  font-weight: normal;\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-attrs dt:hover span {\n",
       "  display: inline-block;\n",
       "  background: var(--xr-background-color);\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-attrs dd {\n",
       "  grid-column: 2;\n",
       "  white-space: pre-wrap;\n",
       "  word-break: break-all;\n",
       "}\n",
       "\n",
       ".xr-icon-database,\n",
       ".xr-icon-file-text2,\n",
       ".xr-no-icon {\n",
       "  display: inline-block;\n",
       "  vertical-align: middle;\n",
       "  width: 1em;\n",
       "  height: 1.5em !important;\n",
       "  stroke-width: 0;\n",
       "  stroke: currentColor;\n",
       "  fill: currentColor;\n",
       "}\n",
       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataArray ()&gt; Size: 8B\n",
       "array(1.00598908)</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataArray</div><div class='xr-array-name'></div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-array-wrap'><input id='section-98fc2642-d0e5-4743-87cf-d04c1e4840e6' class='xr-array-in' type='checkbox' checked><label for='section-98fc2642-d0e5-4743-87cf-d04c1e4840e6' title='Show/hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-array-preview xr-preview'><span>1.006</span></div><div class='xr-array-data'><pre>array(1.00598908)</pre></div></div></li><li class='xr-section-item'><input id='section-f580247d-c8df-4ec3-805a-7768c555ec67' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-f580247d-c8df-4ec3-805a-7768c555ec67' class='xr-section-summary'  title='Expand/collapse section'>Coordinates: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'></ul></div></li><li class='xr-section-item'><input id='section-153c886e-5dba-4b8c-8dcb-653327a8238d' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-153c886e-5dba-4b8c-8dcb-653327a8238d' class='xr-section-summary'  title='Expand/collapse section'>Indexes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'></ul></div></li><li class='xr-section-item'><input id='section-89d5aceb-5eb7-424a-97f9-d3045e338b4d' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-89d5aceb-5eb7-424a-97f9-d3045e338b4d' class='xr-section-summary'  title='Expand/collapse section'>Attributes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'></dl></div></li></ul></div></div>"
      ],
      "text/plain": [
       "<xarray.DataArray ()> Size: 8B\n",
       "array(1.00598908)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.rhat(surv_trace).max().to_array().max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "33bc4d44-1d92-4d3c-b597-e4c00e068bd9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "az.plot_energy(surv_trace);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bbe3598-0107-4105-95cd-60a32ebe2faf",
   "metadata": {},
   "source": [
    "This model shows little, if any, influence of treatment on survival, as illustrated in the following plots."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "86725096-4c03-4d53-af46-56e210aac5d1",
   "metadata": {},
   "outputs": [],
   "source": [
    "ALPHA = 0.05\n",
    "\n",
    "ci = so.Perc([100 * ALPHA / 2, 100 * (1 - ALPHA / 2)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "1bda569c-3fc8-400a-b7ae-0a98638861f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, (α_ax, sf_ax) = plt.subplots(figsize=(14, 6), ncols=2)\n",
    "\n",
    "az.plot_posterior(surv_trace, var_names=\"α_trt\", ref_val=0, ax=α_ax)\n",
    "\n",
    "(\n",
    "    so.Plot(\n",
    "        surv_trace.posterior[\"sf_pred\"].to_dataframe(), x=\"t\", y=\"sf_pred\", color=\"drug\"\n",
    "    )\n",
    "    .add(so.Line(), so.Agg())\n",
    "    .add(so.Band(), ci)\n",
    "    .scale(color=so.Nominal(), y=so.Continuous().tick(every=0.25).label(like=\"{x:.0%}\"))\n",
    "    .limit(x=(0, t.max()), y=(0, 1))\n",
    "    .label(x=\"Month\", y=\"Posterior predictive\\nsurvival function\")\n",
    "    .on(sf_ax)\n",
    "    .show()\n",
    ")\n",
    "\n",
    "fig.tight_layout();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d05e84a4-7aa0-42ff-859e-e1f4a900cb8a",
   "metadata": {},
   "source": [
    "#### Joint model\n",
    "\n",
    "We now get to the core of this post: implementing the joint model and observing how its inferences differ from those of the pure survival model.\n",
    "\n",
    "First we derive a NumPy arrays for the longitudinal outcome, the concentration of bilirubin (`bili`), the index of each subject (`i`), and the time of each visit (`t_visit`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "c4a0acd4-234e-4a0d-980d-0d039d7b5537",
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_time_scaler(t_max):\n",
    "    def time_scaler(t):\n",
    "        return t // t_max\n",
    "\n",
    "    return time_scaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "02fc60b1-4971-47cc-85b8-f139d9d177ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "bili = df[\"bili\"].to_numpy()\n",
    "i = (df[\"id\"] - df[\"id\"].min()).to_numpy()\n",
    "\n",
    "time_scaler = make_time_scaler(df[\"month\"].max())\n",
    "t_visit = time_scaler(df[\"month\"].to_numpy())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18fd5c25-36e1-4926-b7cc-d09459c24532",
   "metadata": {},
   "source": [
    "We also add subject ID to our model's coordinates."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "0c6f5fdd-b0dd-4a80-a742-d36667d03ecb",
   "metadata": {},
   "outputs": [],
   "source": [
    "coords[\"id\"] = subj_df[\"id\"].to_numpy()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7381a1d-f9f7-4cca-86b6-6221e9e6afab",
   "metadata": {},
   "source": [
    "We are now ready to specify a random effects model for the longitudinal outcome.  We let\n",
    "\n",
    "$$\\mu_{\\text{bili}, t, i} = \\gamma_{0, i} + \\gamma_{t, i} \\cdot t + \\beta_{\\text{trt}} \\cdot x_{\\text{trt}, i}.$$\n",
    "\n",
    "We place a normal prior on the treatment coefficient and noncentered hierarchical normal random effects priors on the intercept and time coefficient."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "fdf17a80-587f-49f2-8f25-2f045dce93d3",
   "metadata": {},
   "outputs": [],
   "source": [
    "with pm.Model(coords=coords) as joint_model:\n",
    "    γ0 = noncentered_normal(\"γ0\", dims=\"id\")\n",
    "    γ_t = noncentered_normal(\"γ\", dims=\"id\")\n",
    "    β_trt = pm.Normal(\"β_trt\", 0, 2.5)\n",
    "\n",
    "    μ_bili = γ0[i] + γ_t[i] * t_visit + β_trt * trt[i]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "689443e1-d9b3-466a-a519-fc15d0b85f06",
   "metadata": {},
   "source": [
    "We then specify the likelihood for the longitudinal outcome as\n",
    "\n",
    "$$\\log y_{\\text{bili}, i, t} \\sim N(\\mu_{\\text{bili}, i, t}, \\sigma_{\\text{bili}}^2)$$\n",
    "\n",
    "with $\\sigma_{\\text{bili}} \\sim \\text{Half}-N(2.5^2)$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "a0420c8b-ea25-445d-8269-f9976bf0a6b8",
   "metadata": {},
   "outputs": [],
   "source": [
    "with joint_model:\n",
    "    σ_bili = pm.HalfNormal(\"σ_bili\", 2.5 * HALFNORMAL_SCALE)\n",
    "    pm.Normal(\"log_bili\", μ_bili, σ_bili, observed=np.log(bili))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e877b7f-3c9a-4992-85ea-40247218f0eb",
   "metadata": {},
   "source": [
    "The baseline hazard is specified the same as in the survival model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "ca2cc066-a576-4a98-84bd-99d1e07f8ff0",
   "metadata": {},
   "outputs": [],
   "source": [
    "with joint_model:\n",
    "    log_λ0 = noncentered_normal(\"log_λ0\", dims=\"t\")\n",
    "    λ0 = pt.exp(log_λ0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f208a58-232e-42c5-9263-545a38128885",
   "metadata": {},
   "source": [
    "Now let\n",
    "\n",
    "$$\\eta_{i, t} = \\alpha_\\text{trt} \\cdot x_{\\text{trt}, i} + \\nu_0 \\cdot \\gamma_{0, i} + \\nu_t \\cdot \\gamma_{t, i}$$\n",
    "\n",
    "with $\\alpha_\\text{trt}, \\nu_0, \\nu_t \\sim N(0, 2.5^2)$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "c7d65767-0910-4193-946a-94bb57927b8a",
   "metadata": {},
   "outputs": [],
   "source": [
    "t_surv = time_scaler(coords[\"t\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "b4290406-e5cf-4f59-acd8-c97e274e6f73",
   "metadata": {},
   "outputs": [],
   "source": [
    "with joint_model:\n",
    "    α_trt = pm.Normal(\"α_trt\", 0, 2.5)\n",
    "    ν0 = pm.Normal(\"ν0\", 0, 2.5)\n",
    "    ν_t = pm.Normal(\"ν_t\", 0, 2.5)\n",
    "\n",
    "    η = sum(\n",
    "        [\n",
    "            pt.atleast_2d(α_trt * trt + ν0 * γ0).T,\n",
    "            ν_t * pt.outer(γ_t, pt.as_tensor(t_surv)),\n",
    "        ]\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0e1e2590-61aa-4646-816c-0afc9328fd47",
   "metadata": {},
   "source": [
    "As before we model the hazard rate as $\\lambda_{i, t} = \\lambda_{0, t} \\cdot \\exp(\\eta_{i, t})$ and use the Poisson likelihood."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "e27bd685-1f23-422e-bf36-cae6ee51fed1",
   "metadata": {},
   "outputs": [],
   "source": [
    "with joint_model:\n",
    "    λ = λ0 * pt.exp(η)\n",
    "\n",
    "    pm.Poisson(\"died\", exposed * λ, observed=died_)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3756e02a-d5be-45ed-933f-05bcf108b757",
   "metadata": {},
   "source": [
    "As before, we define the cumulative survival function of our model, then sample from the model.  Note that we add the average values of the random effects $\\gamma_0$ and $\\gamma_t$ to obtain predictions for the average subject."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "669925c4-364f-40fd-ab0f-6a2eee494c1e",
   "metadata": {},
   "outputs": [],
   "source": [
    "with joint_model:\n",
    "    η_pred = pt.add.outer(\n",
    "        α_trt * np.array([0, 1]) + ν0 * γ0.mean(),\n",
    "        ν_t * γ_t.mean() * t_surv,\n",
    "    )\n",
    "    λ_pred = λ0 * pt.exp(η_pred)\n",
    "    Λ_pred = λ_pred.cumsum(axis=1)\n",
    "    sf_pred = pm.Deterministic(\"sf_pred\", pt.exp(-Λ_pred), dims=(\"drug\", \"t\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "01a3d9f8-8be3-4a53-b5b5-6e3f74a06105",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    :root {\n",
       "        --column-width-1: 40%; /* Progress column width */\n",
       "        --column-width-2: 15%; /* Chain column width */\n",
       "        --column-width-3: 15%; /* Divergences column width */\n",
       "        --column-width-4: 15%; /* Step Size column width */\n",
       "        --column-width-5: 15%; /* Gradients/Draw column width */\n",
       "    }\n",
       "\n",
       "    .nutpie {\n",
       "        max-width: 800px;\n",
       "        margin: 10px auto;\n",
       "        font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;\n",
       "        //color: #333;\n",
       "        //background-color: #fff;\n",
       "        padding: 10px;\n",
       "        box-shadow: 0 4px 6px rgba(0,0,0,0.1);\n",
       "        border-radius: 8px;\n",
       "        font-size: 14px; /* Smaller font size for a more compact look */\n",
       "    }\n",
       "    .nutpie table {\n",
       "        width: 100%;\n",
       "        border-collapse: collapse; /* Remove any extra space between borders */\n",
       "    }\n",
       "    .nutpie th, .nutpie td {\n",
       "        padding: 8px 10px; /* Reduce padding to make table more compact */\n",
       "        text-align: left;\n",
       "        border-bottom: 1px solid #888;\n",
       "    }\n",
       "    .nutpie th {\n",
       "        //background-color: #f0f0f0;\n",
       "    }\n",
       "\n",
       "    .nutpie th:nth-child(1) { width: var(--column-width-1); }\n",
       "    .nutpie th:nth-child(2) { width: var(--column-width-2); }\n",
       "    .nutpie th:nth-child(3) { width: var(--column-width-3); }\n",
       "    .nutpie th:nth-child(4) { width: var(--column-width-4); }\n",
       "    .nutpie th:nth-child(5) { width: var(--column-width-5); }\n",
       "\n",
       "    .nutpie progress {\n",
       "        width: 100%;\n",
       "        height: 15px; /* Smaller progress bars */\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-webkit-progress-bar {\n",
       "        background-color: #eee;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-webkit-progress-value {\n",
       "        background-color: #5cb85c;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    progress::-moz-progress-bar {\n",
       "        background-color: #5cb85c;\n",
       "        border-radius: 5px;\n",
       "    }\n",
       "    .nutpie .progress-cell {\n",
       "        width: 100%;\n",
       "    }\n",
       "\n",
       "    .nutpie p strong { font-size: 16px; font-weight: bold; }\n",
       "\n",
       "    @media (prefers-color-scheme: dark) {\n",
       "        .nutpie {\n",
       "            //color: #ddd;\n",
       "            //background-color: #1e1e1e;\n",
       "            box-shadow: 0 4px 6px rgba(0,0,0,0.2);\n",
       "        }\n",
       "        .nutpie table, .nutpie th, .nutpie td {\n",
       "            border-color: #555;\n",
       "            color: #ccc;\n",
       "        }\n",
       "        .nutpie th {\n",
       "            background-color: #2a2a2a;\n",
       "        }\n",
       "        .nutpie progress::-webkit-progress-bar {\n",
       "            background-color: #444;\n",
       "        }\n",
       "        .nutpie progress::-webkit-progress-value {\n",
       "            background-color: #3178c6;\n",
       "        }\n",
       "        .nutpie progress::-moz-progress-bar {\n",
       "            background-color: #3178c6;\n",
       "        }\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<div class=\"nutpie\">\n",
       "    <p><strong>Sampler Progress</strong></p>\n",
       "    <p>Total Chains: <span id=\"total-chains\">6</span></p>\n",
       "    <p>Active Chains: <span id=\"active-chains\">0</span></p>\n",
       "    <p>\n",
       "        Finished Chains:\n",
       "        <span id=\"active-chains\">6</span>\n",
       "    </p>\n",
       "    <p>Sampling for a minute</p>\n",
       "    <p>\n",
       "        Estimated Time to Completion:\n",
       "        <span id=\"eta\">now</span>\n",
       "    </p>\n",
       "\n",
       "    <progress\n",
       "        id=\"total-progress-bar\"\n",
       "        max=\"7800\"\n",
       "        value=\"7800\">\n",
       "    </progress>\n",
       "    <table>\n",
       "        <thead>\n",
       "            <tr>\n",
       "                <th>Progress</th>\n",
       "                <th>Draws</th>\n",
       "                <th>Divergences</th>\n",
       "                <th>Step Size</th>\n",
       "                <th>Gradients/Draw</th>\n",
       "            </tr>\n",
       "        </thead>\n",
       "        <tbody id=\"chain-details\">\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>1</td>\n",
       "                    <td>0.14</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>2</td>\n",
       "                    <td>0.13</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>1</td>\n",
       "                    <td>0.15</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>1</td>\n",
       "                    <td>0.15</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>1</td>\n",
       "                    <td>0.14</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "                <tr>\n",
       "                    <td class=\"progress-cell\">\n",
       "                        <progress\n",
       "                            max=\"1300\"\n",
       "                            value=\"1300\">\n",
       "                        </progress>\n",
       "                    </td>\n",
       "                    <td>1300</td>\n",
       "                    <td>0</td>\n",
       "                    <td>0.13</td>\n",
       "                    <td>31</td>\n",
       "                </tr>\n",
       "            \n",
       "            </tr>\n",
       "        </tbody>\n",
       "    </table>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<nutpie.sample._BackgroundSampler at 0x34b514a70>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "joint_trace = nutpie.sample(\n",
    "    nutpie.compile_pymc_model(joint_model), target_accept=0.95, **SAMPLER_KWARGS\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01271828-1af0-4d2a-be05-707ce7e7d628",
   "metadata": {},
   "source": [
    "Again, the standard sampling diagnostics show no cause for concern."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "870b8cd0-b9d4-48a6-b528-fda3f6628572",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
       "<defs>\n",
       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
       "</symbol>\n",
       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
       "</symbol>\n",
       "</defs>\n",
       "</svg>\n",
       "<style>/* CSS stylesheet for displaying xarray objects in jupyterlab.\n",
       " *\n",
       " */\n",
       "\n",
       ":root {\n",
       "  --xr-font-color0: var(--jp-content-font-color0, rgba(0, 0, 0, 1));\n",
       "  --xr-font-color2: var(--jp-content-font-color2, rgba(0, 0, 0, 0.54));\n",
       "  --xr-font-color3: var(--jp-content-font-color3, rgba(0, 0, 0, 0.38));\n",
       "  --xr-border-color: var(--jp-border-color2, #e0e0e0);\n",
       "  --xr-disabled-color: var(--jp-layout-color3, #bdbdbd);\n",
       "  --xr-background-color: var(--jp-layout-color0, white);\n",
       "  --xr-background-color-row-even: var(--jp-layout-color1, white);\n",
       "  --xr-background-color-row-odd: var(--jp-layout-color2, #eeeeee);\n",
       "}\n",
       "\n",
       "html[theme=dark],\n",
       "html[data-theme=dark],\n",
       "body[data-theme=dark],\n",
       "body.vscode-dark {\n",
       "  --xr-font-color0: rgba(255, 255, 255, 1);\n",
       "  --xr-font-color2: rgba(255, 255, 255, 0.54);\n",
       "  --xr-font-color3: rgba(255, 255, 255, 0.38);\n",
       "  --xr-border-color: #1F1F1F;\n",
       "  --xr-disabled-color: #515151;\n",
       "  --xr-background-color: #111111;\n",
       "  --xr-background-color-row-even: #111111;\n",
       "  --xr-background-color-row-odd: #313131;\n",
       "}\n",
       "\n",
       ".xr-wrap {\n",
       "  display: block !important;\n",
       "  min-width: 300px;\n",
       "  max-width: 700px;\n",
       "}\n",
       "\n",
       ".xr-text-repr-fallback {\n",
       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-header {\n",
       "  padding-top: 6px;\n",
       "  padding-bottom: 6px;\n",
       "  margin-bottom: 4px;\n",
       "  border-bottom: solid 1px var(--xr-border-color);\n",
       "}\n",
       "\n",
       ".xr-header > div,\n",
       ".xr-header > ul {\n",
       "  display: inline;\n",
       "  margin-top: 0;\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-obj-type,\n",
       ".xr-array-name {\n",
       "  margin-left: 2px;\n",
       "  margin-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-obj-type {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-sections {\n",
       "  padding-left: 0 !important;\n",
       "  display: grid;\n",
       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
       "}\n",
       "\n",
       ".xr-section-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-section-item input {\n",
       "  display: inline-block;\n",
       "  opacity: 0;\n",
       "}\n",
       "\n",
       ".xr-section-item input + label {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label {\n",
       "  cursor: pointer;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-item input:focus + label {\n",
       "  border: 2px solid var(--xr-font-color0);\n",
       "}\n",
       "\n",
       ".xr-section-item input:enabled + label:hover {\n",
       "  color: var(--xr-font-color0);\n",
       "}\n",
       "\n",
       ".xr-section-summary {\n",
       "  grid-column: 1;\n",
       "  color: var(--xr-font-color2);\n",
       "  font-weight: 500;\n",
       "}\n",
       "\n",
       ".xr-section-summary > span {\n",
       "  display: inline-block;\n",
       "  padding-left: 0.5em;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label {\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in + label:before {\n",
       "  display: inline-block;\n",
       "  content: '►';\n",
       "  font-size: 11px;\n",
       "  width: 15px;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:disabled + label:before {\n",
       "  color: var(--xr-disabled-color);\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label:before {\n",
       "  content: '▼';\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked + label > span {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-section-summary,\n",
       ".xr-section-inline-details {\n",
       "  padding-top: 4px;\n",
       "  padding-bottom: 4px;\n",
       "}\n",
       "\n",
       ".xr-section-inline-details {\n",
       "  grid-column: 2 / -1;\n",
       "}\n",
       "\n",
       ".xr-section-details {\n",
       "  display: none;\n",
       "  grid-column: 1 / -1;\n",
       "  margin-bottom: 5px;\n",
       "}\n",
       "\n",
       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-array-wrap {\n",
       "  grid-column: 1 / -1;\n",
       "  display: grid;\n",
       "  grid-template-columns: 20px auto;\n",
       "}\n",
       "\n",
       ".xr-array-wrap > label {\n",
       "  grid-column: 1;\n",
       "  vertical-align: top;\n",
       "}\n",
       "\n",
       ".xr-preview {\n",
       "  color: var(--xr-font-color3);\n",
       "}\n",
       "\n",
       ".xr-array-preview,\n",
       ".xr-array-data {\n",
       "  padding: 0 5px !important;\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-array-data,\n",
       ".xr-array-in:checked ~ .xr-array-preview {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       ".xr-array-in:checked ~ .xr-array-data,\n",
       ".xr-array-preview {\n",
       "  display: inline-block;\n",
       "}\n",
       "\n",
       ".xr-dim-list {\n",
       "  display: inline-block !important;\n",
       "  list-style: none;\n",
       "  padding: 0 !important;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list li {\n",
       "  display: inline-block;\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "}\n",
       "\n",
       ".xr-dim-list:before {\n",
       "  content: '(';\n",
       "}\n",
       "\n",
       ".xr-dim-list:after {\n",
       "  content: ')';\n",
       "}\n",
       "\n",
       ".xr-dim-list li:not(:last-child):after {\n",
       "  content: ',';\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-has-index {\n",
       "  font-weight: bold;\n",
       "}\n",
       "\n",
       ".xr-var-list,\n",
       ".xr-var-item {\n",
       "  display: contents;\n",
       "}\n",
       "\n",
       ".xr-var-item > div,\n",
       ".xr-var-item label,\n",
       ".xr-var-item > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-even);\n",
       "  margin-bottom: 0;\n",
       "}\n",
       "\n",
       ".xr-var-item > .xr-var-name:hover span {\n",
       "  padding-right: 5px;\n",
       "}\n",
       "\n",
       ".xr-var-list > li:nth-child(odd) > div,\n",
       ".xr-var-list > li:nth-child(odd) > label,\n",
       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
       "  background-color: var(--xr-background-color-row-odd);\n",
       "}\n",
       "\n",
       ".xr-var-name {\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-var-dims {\n",
       "  grid-column: 2;\n",
       "}\n",
       "\n",
       ".xr-var-dtype {\n",
       "  grid-column: 3;\n",
       "  text-align: right;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-var-preview {\n",
       "  grid-column: 4;\n",
       "}\n",
       "\n",
       ".xr-index-preview {\n",
       "  grid-column: 2 / 5;\n",
       "  color: var(--xr-font-color2);\n",
       "}\n",
       "\n",
       ".xr-var-name,\n",
       ".xr-var-dims,\n",
       ".xr-var-dtype,\n",
       ".xr-preview,\n",
       ".xr-attrs dt {\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-var-name:hover,\n",
       ".xr-var-dims:hover,\n",
       ".xr-var-dtype:hover,\n",
       ".xr-attrs dt:hover {\n",
       "  overflow: visible;\n",
       "  width: auto;\n",
       "  z-index: 1;\n",
       "}\n",
       "\n",
       ".xr-var-attrs,\n",
       ".xr-var-data,\n",
       ".xr-index-data {\n",
       "  display: none;\n",
       "  background-color: var(--xr-background-color) !important;\n",
       "  padding-bottom: 5px !important;\n",
       "}\n",
       "\n",
       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
       ".xr-var-data-in:checked ~ .xr-var-data,\n",
       ".xr-index-data-in:checked ~ .xr-index-data {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       ".xr-var-data > table {\n",
       "  float: right;\n",
       "}\n",
       "\n",
       ".xr-var-name span,\n",
       ".xr-var-data,\n",
       ".xr-index-name div,\n",
       ".xr-index-data,\n",
       ".xr-attrs {\n",
       "  padding-left: 25px !important;\n",
       "}\n",
       "\n",
       ".xr-attrs,\n",
       ".xr-var-attrs,\n",
       ".xr-var-data,\n",
       ".xr-index-data {\n",
       "  grid-column: 1 / -1;\n",
       "}\n",
       "\n",
       "dl.xr-attrs {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  display: grid;\n",
       "  grid-template-columns: 125px auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt,\n",
       ".xr-attrs dd {\n",
       "  padding: 0;\n",
       "  margin: 0;\n",
       "  float: left;\n",
       "  padding-right: 10px;\n",
       "  width: auto;\n",
       "}\n",
       "\n",
       ".xr-attrs dt {\n",
       "  font-weight: normal;\n",
       "  grid-column: 1;\n",
       "}\n",
       "\n",
       ".xr-attrs dt:hover span {\n",
       "  display: inline-block;\n",
       "  background: var(--xr-background-color);\n",
       "  padding-right: 10px;\n",
       "}\n",
       "\n",
       ".xr-attrs dd {\n",
       "  grid-column: 2;\n",
       "  white-space: pre-wrap;\n",
       "  word-break: break-all;\n",
       "}\n",
       "\n",
       ".xr-icon-database,\n",
       ".xr-icon-file-text2,\n",
       ".xr-no-icon {\n",
       "  display: inline-block;\n",
       "  vertical-align: middle;\n",
       "  width: 1em;\n",
       "  height: 1.5em !important;\n",
       "  stroke-width: 0;\n",
       "  stroke: currentColor;\n",
       "  fill: currentColor;\n",
       "}\n",
       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataArray ()&gt; Size: 8B\n",
       "array(1.02313563)</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataArray</div><div class='xr-array-name'></div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-array-wrap'><input id='section-3c4b5629-2a41-4ca5-ae58-50610ee7792c' class='xr-array-in' type='checkbox' checked><label for='section-3c4b5629-2a41-4ca5-ae58-50610ee7792c' title='Show/hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-array-preview xr-preview'><span>1.023</span></div><div class='xr-array-data'><pre>array(1.02313563)</pre></div></div></li><li class='xr-section-item'><input id='section-b2f78b0f-7d5c-40da-98bf-f3505e64a25f' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-b2f78b0f-7d5c-40da-98bf-f3505e64a25f' class='xr-section-summary'  title='Expand/collapse section'>Coordinates: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'></ul></div></li><li class='xr-section-item'><input id='section-3ed04038-aebc-4377-a8dc-bf2488183fc1' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-3ed04038-aebc-4377-a8dc-bf2488183fc1' class='xr-section-summary'  title='Expand/collapse section'>Indexes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'></ul></div></li><li class='xr-section-item'><input id='section-02741fae-2529-4e2a-aef0-20f92bd758d1' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-02741fae-2529-4e2a-aef0-20f92bd758d1' class='xr-section-summary'  title='Expand/collapse section'>Attributes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'></dl></div></li></ul></div></div>"
      ],
      "text/plain": [
       "<xarray.DataArray ()> Size: 8B\n",
       "array(1.02313563)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.rhat(joint_trace).max().to_array().max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "53293951-7508-4b25-a901-289aac4b7d4d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "az.plot_energy(joint_trace);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5588e21d-da30-47a0-93b8-5e62cf1f1f65",
   "metadata": {},
   "source": [
    "This model shows a stronger influence of treatment on survival, as illustrated in the following charts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "aedfad58-2a3b-4187-877c-e4f6fe50e7c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, (α_ax, sf_ax) = plt.subplots(figsize=(14, 6), ncols=2)\n",
    "\n",
    "az.plot_posterior(joint_trace, var_names=\"α_trt\", ref_val=0, ax=α_ax)\n",
    "\n",
    "(\n",
    "    so.Plot(\n",
    "        joint_trace.posterior[\"sf_pred\"].to_dataframe(),\n",
    "        x=\"t\",\n",
    "        y=\"sf_pred\",\n",
    "        color=\"drug\",\n",
    "    )\n",
    "    .add(so.Line(), so.Agg())\n",
    "    .add(so.Band(), ci)\n",
    "    .scale(color=so.Nominal(), y=so.Continuous().tick(every=0.25).label(like=\"{x:.0%}\"))\n",
    "    .limit(x=(0, t.max()), y=(0, 1))\n",
    "    .label(x=\"Month\", y=\"Posterior predictive\\nsurvival function\")\n",
    "    .on(sf_ax)\n",
    "    .show()\n",
    ")\n",
    "\n",
    "fig.tight_layout();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae697ea0-068f-4144-b2c1-705f474ecaee",
   "metadata": {},
   "source": [
    "The actual data from this study contains more covariates and longitudinal outcomes than we have included in this model.  This example illustrates a framework for including more of the information in order to improve our estimate of the impact of treatment on survival."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bb3d7051-7e58-4e4a-aae4-5d3ee710773c",
   "metadata": {},
   "source": [
    "This post is available as a Jupyter notebook [here]()."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "1c507e76-5772-4d81-874e-0c437816ef39",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Last updated: Sat Mar 15 2025\n",
      "\n",
      "Python implementation: CPython\n",
      "Python version       : 3.12.5\n",
      "IPython version      : 8.29.0\n",
      "\n",
      "pytensor  : 2.26.3\n",
      "pymc      : 5.18.2\n",
      "arviz     : 0.20.0\n",
      "matplotlib: 3.9.2\n",
      "numpy     : 1.26.4\n",
      "polars    : 1.14.0\n",
      "seaborn   : 0.13.2\n",
      "nutpie    : 0.13.2\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark -n -u -v -iv"
   ]
  }
 ],
 "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": "3.12.5"
  },
  "nikola": {
   "date": "2025-03-15",
   "slug": "joint-long-surv",
   "title": "Joint Modeling of Longitudinal and Survival Outcomes in PyMC"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}