meta-edc 1.0.7__py3-none-any.whl → 1.1.0__py3-none-any.whl

meta_analytics/notebooks/monitoring_report.ipynb

@@ -2,8 +2,10 @@
  "cells": [
   {
    "cell_type": "code",
-   "id": "28e21930-b943-4a08-a79a-ff2712ae9215",
+   "execution_count": null,
+   "id": "0",
    "metadata": {},
+   "outputs": [],
    "source": [
     "%%capture\n",
     "import os\n",
@@ -19,17 +21,17 @@
     "pharmacy_folder = Path(os.environ[\"META_PHARMACY_FOLDER\"])\n",
     "plus = activate(dotenv_file=env_file)\n",
     "pd.set_option('future.no_silent_downcasting', True)"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
-   "id": "52d4bb98-18a5-4528-be8d-e8370b1b5d1e",
+   "execution_count": null,
+   "id": "1",
    "metadata": {},
+   "outputs": [],
    "source": [
-    "\n",
     "import pdfkit\n",
+    "from typing import Callable\n",
     "from datetime import date\n",
     "from edc_pdutils.dataframes import get_subject_visit\n",
     "from meta_visit_schedule.constants import MONTH15, MONTH18, MONTH21, MONTH27, MONTH30, MONTH33, MONTH39\n",
@@ -43,33 +45,36 @@
     "from edc_appointment.analytics import get_appointment_df\n",
     "from edc_appointment.constants import NEW_APPT, CANCELLED_APPT, ONTIME_APPT, MISSED_APPT\n",
     "from meta_consent.models import SubjectConsentV1Ext\n",
-    "from meta_analytics.dataframes import get_glucose_df\n",
+    "from meta_analytics.dataframes import get_glucose_df, get_screening_df\n",
     "\n",
     "from edc_appointment.constants import SCHEDULED_APPT, UNSCHEDULED_APPT # noqa\n",
-    "from edc_constants.constants import YES # noqa\n"
-   ],
-   "outputs": [],
-   "execution_count": null
+    "from edc_constants.constants import YES # noqa"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "2",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "html_data = []\n",
-    "cutoff_date = date(2025,3, 31)\n",
-    "end_of_trial_date= date(2026,3, 1)\n",
-    "document_title = f\"<h2>Monitoring Report: {cutoff_date.strftime('%B %Y')}</h2><h5>Data Download: {cutoff_date.strftime('%d %B %Y')}</h5>\"\n",
+    "data_download_date= date(2025,6, 17)\n",
+    "cutoff_date = date(2025,6, 17)\n",
+    "end_of_trial_date= date(2026,7, 1)\n",
+    "document_title = f\"<h2>Monitoring Report: {cutoff_date.strftime('%B %Y')}</h2><h5>Data Download: {data_download_date.strftime('%d %B %Y')}</h5>\"\n",
     "study_title = 'META3 - Metformin treatment for diabetes prevention in Africa'\n",
     "pdf_filename = f\"monitoring_report_{cutoff_date.strftime('%Y%m%d')}.pdf\"\n"
-   ],
-   "id": "b255fd34cd6f50c0",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
    "source": [
+    "# 105-30-0288-5 should also be late excluded based on the haemoglobin 4.8 presented at baseline\n",
     "\n",
     "df_visit = get_subject_visit(\"meta_subject.subjectvisit\")\n",
     "late_exlusion_offstudy_reasons = ['Patient fulfilled late exclusion criteria (due to abnormal blood values or raised blood pressure at enrolment']\n",
@@ -117,27 +122,41 @@
     "    .pivot_table(columns=\"site_id\", values=0, observed=True)\n",
     ")\n",
     "enrolled_pivot.columns.name=\"\"\n",
-    "enrolled_pivot[\"total\"] = enrolled_pivot[[\"10\", \"20\",\"30\",\"40\",\"60\"]].sum(axis=1)\n",
-    "\n"
-   ],
-   "id": "215212f9d44e79df",
-   "outputs": [],
-   "execution_count": null
+    "enrolled_pivot[\"total\"] = enrolled_pivot[[\"10\", \"20\",\"30\",\"40\",\"60\"]].sum(axis=1)"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df_eos.query(\"offstudy_reason.isin(@late_exlusion_offstudy_reasons)\")[[\"subject_identifier\", \"offstudy_datetime\", \"offstudy_reason\"]].to_stata(\n",
+    "#         path=analysis_folder / \"late_exclusions.dta\",\n",
+    "#         variable_labels={},\n",
+    "#         version=118,\n",
+    "#         write_index=False,\n",
+    "#     )"
+   ]
+  },
+  {
    "cell_type": "code",
+   "execution_count": null,
+   "id": "5",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "column_headers = {\"label\": \"Label\", \"visit_code\": \"Visit code\", \"10\": \"Hindu Mandal\", \"20\": \"Amana\", \"30\": \"Temeke\", \"40\": \"Mwananyamala\", \"60\": \"Mnazi Moja\", \"total\": \"Total\"}\n",
     "column_headers_with_str = {\"label\": \"Label\", \"10_str\": \"Hindu Mandal\", \"20_str\": \"Amana\", \"30_str\": \"Temeke\", \"40_str\": \"Mwananyamala\", \"60_str\": \"Mnazi Moja\", \"total_str\": \"Total\"}"
-   ],
-   "id": "fe90271ff1799692",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 1a Visits completed to date\n",
     "\n",
@@ -151,14 +170,14 @@
     "df1.fillna(0, inplace=True)\n",
     "df_attended = df1.copy().reset_index(drop=True)\n",
     "df_attended = df_attended.fillna(0.0)"
-   ],
-   "id": "9e3d608809eea5",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "gt = df_as_great_table(\n",
     "    df_attended[[\"visit_code\", \"10\", \"20\", \"30\", \"40\", \"60\", \"total\"]],\n",
@@ -179,14 +198,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "a43c2fbd8a7a692c",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 1b Total scheduled appointments\n",
     "df_appt_pivot = (\n",
@@ -226,14 +245,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "70eb34a139ff7095",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 1c Past scheduled appointments -- no information provided\n",
     "df_appt_pivot = (\n",
@@ -272,14 +291,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "f243552177b216d7",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "10",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 1d Unscheduled appointments\n",
     "df_appt = (\n",
@@ -338,14 +357,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "6e55569e322370a",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 1e Future scheduled appointments\n",
     "df_appt_pivot = (\n",
@@ -384,14 +403,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "8193005de33cae6f",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 2 Visits Missed to Date as % of Visits Attended + Visits Missed\n",
     "subject_count = (\n",
@@ -453,14 +472,14 @@
     "    df_result[col] = df_result.apply(lambda x: f\"{x[col]} ({x[col_perc]*100:.2f})\", axis=1)\n",
     "df_result = df_result.reset_index().sort_values(by=[\"visit_code\"], ascending=True)\n",
     "df_result = df_result.fillna(0.0)"
-   ],
-   "id": "c86c5f0ffe59e951",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "df_table = df_result[[\"visit_code\", \"10\", \"20\", \"30\", \"40\", \"60\", \"total\"]].copy()\n",
     "gt = df_as_great_table(\n",
@@ -485,14 +504,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n"
-   ],
-   "id": "3cd8b1290091660c",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 2b: Number of missed visits by participant\n",
     "subject_count = (\n",
@@ -549,17 +568,17 @@
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n",
     "\n"
-   ],
-   "id": "b18088e16e0bf7f7",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "15",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# func for tables 3,4,5\n",
-    "def get_row_df(row_df:pd.DataFrame, label:str)->pd.DataFrame:\n",
+    "def get_row_df(row_df:pd.DataFrame, label:str=None, **kwargs)->pd.DataFrame:\n",
     "    row_df = row_df.groupby(by=[\"site_id\"]).site_id.count().to_frame(name=\"n\")\n",
     "    row_df[\"label\"] = label\n",
     "    row_df = row_df.reset_index()\n",
@@ -573,49 +592,60 @@
     "    return row_df\n",
     "\n",
     "\n",
-    "def get_table_df(df_source:pd.DataFrame, visit_code:float|None=None, month_label:str|None=None)->pd.DataFrame:\n",
+    "def get_table_df(\n",
+    "        df_source:pd.DataFrame,\n",
+    "        visit_code:float|None=None,\n",
+    "        month_label:str|None=None,\n",
+    "        visit_codes:list[float]|None=None,\n",
+    "        get_row_func:Callable|None=None,\n",
+    "        category_labels:list[str]|None=None,\n",
+    ")->pd.DataFrame:\n",
+    "    get_row_df_func = get_row_func or get_row_df\n",
     "    if visit_code:\n",
     "        df_month = df_source[df_source.visit_code==visit_code].copy()\n",
+    "    elif visit_codes:\n",
+    "        df_month = df_source[df_source.visit_code.isin(visit_codes)].copy()\n",
     "    elif month_label:\n",
     "        df_month = df_source.copy()\n",
     "\n",
     "    \n",
     "    row_df = df_month.copy()\n",
-    "    table_df = get_row_df(row_df, \"Total (n)\")\n",
+    "    table_df = get_row_df_func(row_df, \"Total (n)\", category_labels=category_labels)\n",
     "    \n",
     "    row_df = df_month.query(\"ogtt_value<7.8 and fbg_value<6.1\").copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT <7.8; FBG <6.1\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT <7.8; FBG <6.1\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value<7.8) & (df_month.fbg_value>=6.1) & (df_month.fbg_value<7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT <7.8; FBG >=6.1 <7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT <7.8; FBG >=6.1 <7.0\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value<7.8) & (df_month.fbg_value>=7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT <7.8; FBG >=7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT <7.8; FBG >=7.0\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=7.8) & (df_month.ogtt_value<11.1) & (df_month.fbg_value<6.1)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥7.8 to <11.1; FBG <6.1\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥7.8 to <11.1; FBG <6.1\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=7.8) & (df_month.ogtt_value<11.1) & (df_month.fbg_value>=6.1) & (df_month.fbg_value<7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥7.8 to <11.1; FBG >=6.1 <7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥7.8 to <11.1; FBG >=6.1 <7.0\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=7.8) & (df_month.ogtt_value<11.1) & (df_month.fbg_value>=7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥7.8 to <11.1; FBG >=7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥7.8 to <11.1; FBG >=7.0\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=11.1) & (df_month.fbg_value<6.1)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥11.1; FBG <6.1\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥11.1; FBG <6.1\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=11.1) & (df_month.fbg_value>=6.1) & (df_month.fbg_value<7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥11.1; FBG >=6.1 <7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥11.1; FBG >=6.1 <7.0\", category_labels=category_labels)])\n",
     "    \n",
     "    row_df = df_month[(df_month.ogtt_value>=11.1) & (df_month.fbg_value>=7.0)].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"OGTT ≥11.1; FBG >=7.0\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"OGTT ≥11.1; FBG >=7.0\", category_labels=category_labels)])\n",
     "\n",
     "    row_df = df_month[(df_month.ogtt_value.isna())].copy()\n",
-    "    table_df = pd.concat([table_df, get_row_df(row_df, \"Missing OGTT\")])\n",
+    "    table_df = pd.concat([table_df, get_row_df_func(row_df, \"Missing OGTT\", category_labels=category_labels)])\n",
     "    return table_df\n",
     "\n",
     "\n",
     "def format_table_df(tbl_df, add_totals:bool|None=None):\n",
+    "    \"\"\"Pivot on site\"\"\"\n",
     "    add_totals = True if add_totals is None else add_totals\n",
     "    tbl_df = tbl_df.fillna(0.0)\n",
     "    tbl_df[\"total\"] = tbl_df.iloc[:,1:].sum(axis=1)\n",
@@ -647,44 +677,201 @@
     "    cols = [\"label\", *[f\"{site}_str\" for site in [\"10\", \"20\", \"30\", \"40\", \"60\", \"total\"]]]\n",
     "    tbl_df1 = tbl_df[cols]\n",
     "    tbl_df1.loc[tbl_df.label==\"Total (n)\"] = tbl_df.iloc[0][[\"label\", \"10\", \"20\", \"30\", \"40\", \"60\", \"total\"]].to_list()\n",
-    "    return tbl_df1"
-   ],
-   "id": "e1bcc6507b1e49c7",
-   "outputs": [],
-   "execution_count": null
+    "    return tbl_df1\n",
+    "\n",
+    "def format_table_with_bmi_df(tbl_df, add_totals:bool|None=None, category_labels:list[str]=None):\n",
+    "    \"\"\"Pivot on BMI categories\"\"\"\n",
+    "\n",
+    "    add_totals = True if add_totals is None else add_totals\n",
+    "    tbl_df = tbl_df.fillna(0.0)\n",
+    "    tbl_df[\"total\"] = tbl_df.iloc[:,1:].sum(axis=1)\n",
+    "    tbl_df = tbl_df.reset_index(drop=True)\n",
+    "\n",
+    "    if add_totals:\n",
+    "        df_last = tbl_df[1:].sum().to_frame()\n",
+    "        df_last.loc[\"label\"] = np.nan\n",
+    "        df_last = df_last.reset_index()\n",
+    "        df_last.columns = [\"label\", \"value\"]\n",
+    "        df_last = df_last.pivot_table(columns=\"label\",  values=\"value\").reset_index(drop=True)\n",
+    "        df_last.columns.name = \"\"\n",
+    "        df_last[\"label\"] = \"Totals\"\n",
+    "\n",
+    "        tbl_df = pd.concat([tbl_df, df_last])\n",
+    "        tbl_df = tbl_df.reset_index(drop=True)\n",
+    "\n",
+    "    tbl_df.columns = [\"label\", *category_labels, \"total\"]\n",
+    "\n",
+    "    for label in [*category_labels, \"total\"]:\n",
+    "        tbl_df[f\"{label}_perc\"] = (tbl_df[label]/tbl_df.iloc[0][label]) * 100 if tbl_df.iloc[0][label]>0 else 0\n",
+    "        tbl_df[f\"{label}_perc_str\"] = tbl_df[f\"{label}_perc\"].map('{:.1f}'.format)\n",
+    "\n",
+    "    for cat in [*category_labels, \"total\"]:\n",
+    "        tbl_df[f\"{label}_str\"] = tbl_df[[f\"{label}\", f\"{label}_perc_str\"]].apply(lambda x: ' ('.join(x.astype(str)), axis=1)\n",
+    "        tbl_df[f\"{label}_str\"] = tbl_df[f\"{label}_str\"] + \")\"\n",
+    "\n",
+    "    cols = [\"label\", *[f\"{label}_str\" for label in [*category_labels, \"total\"]]]\n",
+    "    tbl_df1 = tbl_df[cols]\n",
+    "    tbl_df1.loc[tbl_df.label==\"Total (n)\"] = tbl_df.iloc[0][[\"label\", *category_labels, \"total\"]].to_list()\n",
+    "    return tbl_df1\n",
+    "\n",
+    "\n",
+    "def get_row_by_df(row_df:pd.DataFrame, label:str, category_labels:list[str])->pd.DataFrame:\n",
+    "    # if label not in category_labels:\n",
+    "    #     raise ValueError(f\"Invalid label. Expected one of {category_labels}. Got {label}.\")\n",
+    "    row_df = row_df.groupby(by=[\"site_id\"]).site_id.count().to_frame(name=\"n\")\n",
+    "    row_df[\"label\"] = label\n",
+    "    row_df = row_df.reset_index()\n",
+    "    row_df = row_df.pivot(index=\"label\", values=\"n\", columns=\"site_id\").reset_index()\n",
+    "    row_df.columns.name = \"\"\n",
+    "\n",
+    "    for label in category_labels:\n",
+    "        if label not in row_df.columns:\n",
+    "            row_df[label] = None\n",
+    "    row_df = row_df.reset_index(drop=True)\n",
+    "    return row_df"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_fbg_value(r):\n",
+    "    if not pd.isna(r[\"converted_fbg2_value\"]):\n",
+    "        return r[\"converted_fbg2_value\"]\n",
+    "    return r[\"converted_fbg_value\"]\n",
+    "\n",
+    "def get_ogtt_value(r):\n",
+    "    if not pd.isna(r[\"converted_ogtt2_value\"]):\n",
+    "        return r[\"converted_ogtt2_value\"]\n",
+    "    return r[\"converted_ogtt_value\"]\n"
+   ]
+  },
+  {
    "cell_type": "code",
+   "execution_count": null,
+   "id": "17",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 3: OGTT and FBG at 12-month visit\n",
-    "df_table3 = get_table_df(df_glucose, 1120.0)\n",
+    "# Table 3: OGTT and FBG at Enrolment\n",
+    "\n",
+    "subjects = df_visit.subject_identifier.unique()\n",
+    "df_screening = get_screening_df().query(\"consented==True and subject_identifier.isin(@subjects)\")\n",
+    "df_screening[\"visit_code\"] = \"Enrol\"\n",
+    "df_screening[\"fbg_value\"] = df_screening.apply(get_fbg_value, axis=1)\n",
+    "df_screening[\"ogtt_value\"] = df_screening.apply(get_ogtt_value, axis=1)\n",
+    "df_screening[\"site_id\"] = df_screening.site.astype(int)\n",
+    "df_screening = df_screening.drop(columns=[\"site\"])\n",
+    "df_table3 = get_table_df(df_screening, month_label=\"enrol\")\n",
     "df_table3 = format_table_df(df_table3)\n",
     "df_table3 = df_table3.fillna(0.0)\n",
-    "gt = df_as_great_table(df_table3, title=\"Table 3: OGTT and FBG at 12-month visit\")\n",
+    "gt = df_as_great_table(df_table3, title=\"Table 3a: OGTT and FBG at Screening / Enrolment\")\n",
+    "\n",
+    "column_headers_enrol = {k:v for k,v in column_headers_with_str.items() if k not in \"visit_code\"}\n",
     "gt = (\n",
     "    gt\n",
-    "    .cols_label(column_headers_with_str)\n",
+    "    .cols_label(column_headers_enrol)\n",
     "    .cols_align(align=\"center\", columns=[\"10_str\", \"20_str\", \"30_str\", \"40_str\", \"60_str\", \"total_str\"])\n",
     "    .cols_align(align=\"left\", columns=[\"label\"])\n",
     "    .cols_width(cases={\"label\": \"35%\"})\n",
+    "    .tab_source_note(source_note=\"Excluding patients eventually withdrawn for `late exclusion` criteria\")\n",
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n"
-   ],
-   "id": "9a9616a118ae674d",
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# bmi_categories:\n",
+    "#     1 calculated_bmi_value<25\n",
+    "#     2 calculated_bmi_value>=25 & calculated_bmi_value<30\n",
+    "#     3 calculated_bmi_value>=30\n",
+    "\n",
+    "\n",
+    "# subjects = df_visit.subject_identifier.unique()\n",
+    "# df_screening = get_screening_df().query(\"consented==True and subject_identifier.isin(@subjects)\")\n",
+    "# df_screening[\"visit_code\"] = \"Enrol\"\n",
+    "# df_screening[\"fbg_value\"] = df_screening.apply(get_fbg_value, axis=1)\n",
+    "# df_screening[\"ogtt_value\"] = df_screening.apply(get_ogtt_value, axis=1)\n",
+    "# df_screening[\"site_id\"] = df_screening.site.astype(int)\n",
+    "# df_screening = df_screening.drop(columns=[\"site\"])\n",
+    "# df_screening[\"bmi\"] = pd.NA\n",
+    "# df_screening.loc[df_screening[\"calculated_bmi_value\"] < 25.0, \"bmi\"] = \"bmi<25\"\n",
+    "# df_screening.loc[(df_screening[\"calculated_bmi_value\"]>=25.0) & (df_screening[\"calculated_bmi_value\"] < 30.0), \"bmi\"] = \"25<=bmi<30\"\n",
+    "# df_screening.loc[df_screening[\"calculated_bmi_value\"] > 30.0, \"bmi\"] = \"bmi>30\"\n",
+    "#\n",
+    "# category_labels = [ \"bmi<25\", \"25<=bmi<30\", \"bmi>=30\", \"Total (n)\"]\n",
+    "# df_table3 = get_table_df(df_screening, month_label=\"enrol\", get_row_func=get_row_by_df, category_labels=category_labels)\n",
+    "# df_table3 = format_table_with_bmi_df(df_table3, category_labels=category_labels)\n",
+    "# df_table3 = df_table3.fillna(0.0)\n",
+    "# gt = df_as_great_table(df_table3, title=\"Table 3b: OGTT/FBG by BMI at Screening / Enrolment\")\n",
+    "# column_headers_enrol = {\"bmi<25_str\":\"bmi<25\", \"25<=bmi<30_str\":\"25<=bmi<30\", \"bmi>30_str\":\"bmi>30\", \"total_str\": \"total\"}\n",
+    "# gt = (\n",
+    "#     gt\n",
+    "#     .cols_label(column_headers_enrol)\n",
+    "#     .cols_align(align=\"center\", columns=[\"bmi<25_str\", \"25<=bmi<30_str\", \"bmi>30_str\", \"total_str\"])\n",
+    "#     .cols_align(align=\"left\", columns=[\"label\"])\n",
+    "#     .cols_width(cases={\"label\": \"35%\"})\n",
+    "#     .tab_source_note(source_note=\"Excluding patients eventually withdrawn for `late exclusion` criteria\")\n",
+    "# )\n",
+    "# html_data.append(gt.as_raw_html())\n",
+    "# gt.show()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": [
+    "[col for col in df_screening.columns if \"bmi\" in col]"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Table 4: OGTT and FBG at 12-month visit\n",
+    "df_table3 = get_table_df(df_glucose, visit_codes=[1120.0])\n",
+    "df_table3 = format_table_df(df_table3)\n",
+    "df_table3 = df_table3.fillna(0.0)\n",
+    "gt = df_as_great_table(df_table3, title=\"Table 4: OGTT and FBG at 12-month visit\")\n",
+    "gt = (\n",
+    "    gt\n",
+    "    .cols_label(column_headers_with_str)\n",
+    "    .cols_align(align=\"center\", columns=[\"10_str\", \"20_str\", \"30_str\", \"40_str\", \"60_str\", \"total_str\"])\n",
+    "    .cols_align(align=\"left\", columns=[\"label\"])\n",
+    "    .cols_width(cases={\"label\": \"35%\"})\n",
+    ")\n",
+    "html_data.append(gt.as_raw_html())\n",
+    "gt.show()\n"
+   ]
+  },
+  {
    "cell_type": "code",
+   "execution_count": null,
+   "id": "21",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 4: OGTT and FBG at 24-month visit\n",
+    "# Table 5: OGTT and FBG at 24-month visit\n",
     "df_table4 = get_table_df(df_glucose, 1240.0)\n",
     "df_table4 = format_table_df(df_table4)\n",
     "df_table4 = df_table4.fillna(0.0)\n",
-    "gt = df_as_great_table(df_table4, title=\"Table 4: OGTT and FBG at 24-month visit\")\n",
+    "gt = df_as_great_table(df_table4, title=\"Table 5: OGTT and FBG at 24-month visit\")\n",
     "gt = (\n",
     "    gt\n",
     "    .cols_label(column_headers_with_str)\n",
@@ -694,20 +881,20 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "ec0988364166e130",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "22",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 5: OGTT and FBG at 36-month visit\n",
+    "# Table 6: OGTT and FBG at 36-month visit\n",
     "df_table5 = get_table_df(df_glucose, 1360.0)\n",
     "df_table5 = format_table_df(df_table5)\n",
     "df_table5 = df_table5.fillna(0.0)\n",
-    "gt = df_as_great_table(df_table5, title=\"Table 5: OGTT and FBG at 36-month visit\")\n",
+    "gt = df_as_great_table(df_table5, title=\"Table 6: OGTT and FBG at 36-month visit\")\n",
     "gt = (\n",
     "    gt\n",
     "    .cols_label(column_headers_with_str)\n",
@@ -717,21 +904,21 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "59be72121202df15",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "23",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 6: Any OGTT>11.1 ever\n",
+    "# Table 7: Any OGTT>11.1 ever\n",
     "row_df = df_glucose[df_glucose.ogtt_value>=11.1].copy()\n",
     "table_df = get_row_df(row_df, \"Total (n)\")\n",
     "df_table6 = format_table_df(table_df)\n",
     "df_table = df_table6[:1].fillna(0.0).copy().reset_index(drop=True)\n",
-    "gt = df_as_great_table(df_table, title=\"Table 6: Any OGTT>11.1 ever\")\n",
+    "gt = df_as_great_table(df_table, title=\"Table 7: Any OGTT>11.1 ever\")\n",
     "gt = (\n",
     "    gt\n",
     "    .cols_label(column_headers_with_str)\n",
@@ -741,14 +928,14 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "f016ddbe736c2f93",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "24",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# func for table 7\n",
     "def get_table7_df(df_source:pd.DataFrame, visit_code:float)->pd.DataFrame:\n",
@@ -766,16 +953,16 @@
     "    row_df = df_month[(df_month.fbg_value>=7.0)].copy()\n",
     "    table_df = pd.concat([table_df, get_row_df(row_df, \"FBG >=7.0\")])\n",
     "    return table_df"
-   ],
-   "id": "6193907cc12f5b5c",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "25",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 7: Interim FBG results\n",
+    "# Table 8: Interim FBG results\n",
     "df_table7 = get_table7_df(df_glucose, 1150.0)\n",
     "df_table7 = format_table_df(df_table7, add_totals=False)\n",
     "df_table7[\"visit_code\"] = MONTH15\n",
@@ -807,17 +994,17 @@
     "df_table = pd.concat([df_table7, df_table71, df_table72, df_table73, df_table74, df_table75, df_table76])\n",
     "df_table = df_table.reset_index(drop=True)\n",
     "df_table = df_table.fillna(0.0)"
-   ],
-   "id": "16adb1f965081358",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "26",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "column_headers_with_str = {\"visit_code\": \"Visit Code\", **column_headers_with_str}\n",
-    "gt = df_as_great_table2(df_table, title=\"Table 7: Interim FBG results\")\n",
+    "gt = df_as_great_table2(df_table, title=\"Table 8: Interim FBG results\")\n",
     "gt = (\n",
     "    gt\n",
     "    .cols_label(column_headers_with_str)\n",
@@ -835,16 +1022,16 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "81bcfe52d364b646",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "27",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 8: Primary Endpoint met\n",
+    "# Table 9: Primary Endpoint met\n",
     "df_endpoint_grp = df_endpoint.groupby(by=[\"site_id\", \"endpoint_label\"]).size().to_frame().reset_index()\n",
     "df_endpoint_grp.columns = [\"site_id\", \"label\", \"endpoints\"]\n",
     "df_endpoint_pivot = df_endpoint_grp.pivot_table(index=\"label\", columns=\"site_id\", values=\"endpoints\").reset_index()\n",
@@ -857,7 +1044,7 @@
     "\n",
     "gt = df_as_great_table(\n",
     "    df_endpoint_pivot,\n",
-    "    title=\"Table 8: Primary Endpoint met\"\n",
+    "    title=\"Table 9a: Primary Endpoint met\"\n",
     ")\n",
     "gt = (\n",
     "    gt\n",
@@ -868,26 +1055,28 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "37904c7ce49724e6",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "#read_frame(SubjectScheduleHistory.objects.filter(offschedule_model=\"meta_prn.offschedule\"), verbose=False).rename(columns={\"site\": \"site_id\"})",
-   "id": "562a1cc911a71255",
+   "execution_count": null,
+   "id": "28",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": [
+    "#read_frame(SubjectScheduleHistory.objects.filter(offschedule_model=\"meta_prn.offschedule\"), verbose=False).rename(columns={\"site\": \"site_id\"})"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "29",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from great_tables import html\n",
     "\n",
-    "# Table 8a: Primary Endpoint no EOS or DM Referral\n",
+    "# Table 9b: Primary Endpoint no EOS or DM Referral\n",
     "df_subjecthistory = read_frame(SubjectScheduleHistory.objects.filter(offschedule_model=\"meta_prn.offschedule\", offschedule_datetime__isnull=False), verbose=False).rename(columns={\"site\": \"site_id\"})\n",
     "df_subjecthistory[\"site_id\"] = df_subjecthistory[\"site_id\"].astype(str)\n",
     "df_endpoint_no_off = df_endpoint.merge(df_subjecthistory[[\"subject_identifier\", \"offschedule_datetime\"]], on=[\"subject_identifier\"], how=\"left\")\n",
@@ -907,7 +1096,7 @@
     "\n",
     "gt = df_as_great_table(\n",
     "    df_endpoint_pivot,\n",
-    "    title=\"Table 8a: Primary Endpoint met -- participant not referred\"\n",
+    "    title=\"Table 9b: Primary Endpoint met -- participant not referred\"\n",
     ")\n",
     "gt = (\n",
     "    gt\n",
@@ -919,24 +1108,24 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "a74cd253ec5827f9",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
-   "id": "4df949cb48b088d7",
+   "execution_count": null,
+   "id": "30",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "31",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 9: Incident Rate per 1000 person years\n",
+    "# Table 10: Incident Rate per 1000 person years\n",
     "\n",
     "def get_df_main(df_visit:pd.DataFrame, lower_days:float|None=None, upper_days:float|None=None):\n",
     "    if not lower_days:\n",
@@ -989,14 +1178,14 @@
     "    person_years_total = df_main.followup_years.sum()\n",
     "    data.update({term:[person_years_total, subjects, events, *get_rate_and_ci(events, person_years_total)]})\n",
     "    return data"
-   ],
-   "id": "920db81ad440edab",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "32",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "incidence_data = {}\n",
     "incidence_data.update(get_incidence_data(\"total\", lower_days=-1, upper_days=10000))\n",
@@ -1017,18 +1206,18 @@
     "    data[\"upper_ci\"].append(v[5])\n",
     "\n",
     "df_table9 = pd.DataFrame(data={k:v for k,v in data.items() if k!=\"subjects\"})"
-   ],
-   "id": "44651e865641b75d",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "33",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "gt = df_as_great_table(\n",
     "    df_table9,\n",
-    "    title=\"Table 9: Incident Rate per 1000 person years\",\n",
+    "    title=\"Table 10: Incident Rate per 1000 person years\",\n",
     "    subtitle=md(\"using randomisation to diabetes/last seen\"),\n",
     ")\n",
     "gt = gt.fmt_number(columns=[\"person_years\", \"failures\", \"rate\", \"lower_ci\", \"upper_ci\"], decimals=2)\n",
@@ -1044,21 +1233,21 @@
     ")\n",
     "gt.show()\n",
     "html_data.append(gt.as_raw_html())"
-   ],
-   "id": "da4e67d83522768a",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "34",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 10: Proportion meeting primary endpoint\n",
+    "# Table 11: Proportion meeting primary endpoint\n",
     "df_table10 = pd.DataFrame(data=data)\n",
     "df_table10[\"proportion\"] = df_table10[\"failures\"]/df_table10[\"subjects\"]*100\n",
     "gt = df_as_great_table(\n",
     "    df_table10[[\"label\", \"subjects\", 'failures', \"proportion\"]],\n",
-    "    title=\"Table 10: Proportion meeting primary endpoint\",\n",
+    "    title=\"Table 11: Proportion meeting primary endpoint\",\n",
     ")\n",
     "gt = (\n",
     "    gt\n",
@@ -1070,23 +1259,25 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n"
-   ],
-   "id": "2376a30803fbc743",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
-   "id": "afc730c0bd9d03aa",
+   "execution_count": null,
+   "id": "35",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "36",
+   "metadata": {},
+   "outputs": [],
    "source": [
+    "# TODO: EoS should be for all 1691, not 1631\n",
+    "\n",
     "# Table 11a: End of Study Table (for those who have completed an end of study form)\n",
     "df_eos = get_eos_df()\n",
     "offstudy_reasons = {\n",
@@ -1125,7 +1316,7 @@
     "\n",
     "gt = df_as_great_table(\n",
     "    df_eos_pivot,\n",
-    "    title=\"Table 11a: End of study report\",\n",
+    "    title=\"Table 12a: End of study report\",\n",
     "    subtitle=md(\"for those who have completed an End of study report\"),\n",
     ")\n",
     "gt = (\n",
@@ -1163,24 +1354,24 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n"
-   ],
-   "id": "37dcd320411bd9c5",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
-   "id": "9acdb7515d1490a3",
+   "execution_count": null,
+   "id": "37",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "38",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 11b: Study status\n",
+    "# Table 12b: Study status\n",
     "def get_schedule_df(df_subjecthistory:pd.DataFrame, onschedule_model:str, offschedule_model:str, mode:str)->pd.DataFrame:\n",
     "    columns = {k:f\"{k}_{mode}\" for k in [\"10\", \"20\", \"30\", \"40\", \"60\"]}\n",
     "    df_schedule = (\n",
@@ -1236,7 +1427,7 @@
     "\n",
     "gt = df_as_great_table(\n",
     "    df_status,\n",
-    "    title=\"Table 11b: Study status\",\n",
+    "    title=\"Table 12b: Study status\",\n",
     "    subtitle=md(\"Calculated from Offschedule form; not End of study report\"),\n",
     ")\n",
     "# gt = gt.fmt_number(columns=[\"person_years\", \"failures\", \"rate\", \"lower_ci\", \"upper_ci\"], decimals=0)\n",
@@ -1300,16 +1491,16 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "35840b9a7971e4cf",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "39",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 12: Loss to Follow Up\n",
+    "# Table 13: Loss to Follow Up\n",
     "df_ltfu = read_frame(LossToFollowup.objects.all(), verbose=False).rename(columns={\"site\": \"site_id\"})\n",
     "df_ltfu_pivot = (\n",
     "    df_ltfu\n",
@@ -1328,16 +1519,16 @@
     "sum_row_df = pd.DataFrame(sum_row).T\n",
     "df_ltfu_pivot = pd.concat([df_ltfu_pivot, sum_row_df], ignore_index=True)\n",
     "df_ltfu_pivot\n"
-   ],
-   "id": "534c51e7321e2ef3",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "40",
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "# Table 11c: End of study report not submitted\n",
+    "# Table 13c: End of study report not submitted\n",
     "\n",
     "df1 = (\n",
     "    df_status\n",
@@ -1358,7 +1549,7 @@
     "\n",
     "gt = df_as_great_table(\n",
     "    df_eos_not_reported,\n",
-    "    title=\"Table 11c: End of study report not submitted\",\n",
+    "    title=\"Table 13c: End of study report not submitted\",\n",
     "    subtitle=md(\"End of study report expected based on Offschedule form\"),\n",
     ")\n",
     "gt = (\n",
@@ -1389,22 +1580,24 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()\n"
-   ],
-   "id": "25d05831ef76f267",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "# Table 13: Baseline Sample",
-   "id": "b607a436749cc3b2",
+   "execution_count": null,
+   "id": "41",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": [
+    "# Table 14: Baseline Sample"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "42",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Table 15: Consented to extended followup\n",
     "df_consented = (\n",
@@ -1462,22 +1655,22 @@
     ")\n",
     "html_data.append(gt.as_raw_html())\n",
     "gt.show()"
-   ],
-   "id": "8acd2dd7e5a958e9",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
-   "id": "45ee71bc4a06f8f7",
+   "execution_count": null,
+   "id": "43",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "44",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# gather raw html\n",
     "raw_html = [f'<div class=\"page-break\">{s}</div>' for s in html_data]\n",
@@ -1496,14 +1689,14 @@
     "\"\"\"\n",
     "raw_html = ''.join(raw_html)\n",
     "raw_html = f'<!DOCTYPE html>\\n<html lang=\"en\">\\n{style_css}\\n<head>\\n<meta charset=\"utf-8\"/>\\n</head>\\n<body>\\n' + document_title + raw_html + '\\n</body>\\n</html>\\n'"
-   ],
-   "id": "a38e9d7ba59d063b",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "45",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# render html to PDF\n",
     "pdfkit.from_string(raw_html, str(analysis_folder / pdf_filename),\n",
@@ -1523,18 +1716,15 @@
     "    'no-outline': None,\n",
     "},\n",
     "verbose=True)"
-   ],
-   "id": "792243aad557cc86",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
-   "id": "4cfdfa6f69c3916a",
+   "execution_count": null,
+   "id": "46",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   }
  ],
  "metadata": {