meta-edc 1.0.7__py3-none-any.whl → 1.1.1__py3-none-any.whl

meta_analytics/notebooks/undiagnosed/meta3_screening_undiagnosed.ipynb

@@ -0,0 +1,519 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture\n",
+    "# output is suppressed but normally would spew out all the edc loading messages\n",
+    "\n",
+    "import os\n",
+    "from pathlib import Path\n",
+    "from datetime import datetime\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import math\n",
+    "# import matplotlxib.pyplot as plt\n",
+    "# import seaborn as sns\n",
+    "import scipy.stats as stats\n",
+    "\n",
+    "from dj_notebook import activate\n",
+    "\n",
+    "env_file = os.environ[\"META_ENV\"]\n",
+    "documents_folder = os.environ[\"META_DOCUMENTS_FOLDER\"]\n",
+    "report_folder = Path(documents_folder)\n",
+    "\n",
+    "plus = activate(dotenv_file=env_file)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from meta_screening.models import SubjectScreening\n",
+    "from meta_consent.models import SubjectConsent\n",
+    "from meta_subject.models import PhysicalExam, SubjectVisit\n",
+    "from django_pandas.io import read_frame\n",
+    "from django.contrib.sites.models import Site\n",
+    "from edc_analytics.custom_tables import (\n",
+    "    BmiTable, BpTable, AgeTable, ArtTable, GenderTable, FbgTable, OgttTable, \n",
+    "    FbgOgttTable, WaistCircumferenceTable, HbA1cTable\n",
+    ")\n",
+    "from meta_analytics.dataframes.screening import get_glucose_tested_only_df\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all = get_glucose_tested_only_df() # slow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sites = {obj.domain: obj.id for obj in Site.objects.all()}\n",
+    "df_all[\"site\"] = df_all[\"site\"].map(sites)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df_all.copy()\n",
+    "df = df[df[\"has_dm\"]==\"No\"]\n",
+    "df = df.reset_index(drop=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = GenderTable(df)\n",
+    "gender_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = WaistCircumferenceTable(df)\n",
+    "waist_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = ArtTable(df)\n",
+    "art_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = AgeTable(df)\n",
+    "age_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = BpTable(df)\n",
+    "bp_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = FbgTable(df)\n",
+    "fbg_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = OgttTable(df)\n",
+    "ogtt_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = FbgOgttTable(df)\n",
+    "fbg_ogtt_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = BmiTable(df)\n",
+    "bmi_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl = HbA1cTable(df)\n",
+    "hba1c_df = tbl.table_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tbl_df = pd.concat([gender_df, age_df, bmi_df, waist_df, bp_df, art_df, fbg_df, ogtt_df, fbg_ogtt_df, hba1c_df], ignore_index=True)\n",
+    "tbl_df.iloc[:, :5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "fname = f\"meta3_table2-{datetime.now().strftime(\"%Y-%m-%d-%H%M\")}.csv\"\n",
+    "tbl_df.iloc[:, :5].to_csv(path_or_buf=report_folder / fname, encoding=\"utf-8\", index=0, sep=\"|\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all[df_all[\"waist_circumference\"].notna()].count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "subject_identifiers = list(df[\"subject_identifier\"])\n",
+    "qs_subject_visit = SubjectVisit.objects.filter(subject_identifier__in=subject_identifiers)\n",
+    "df_subject_visit = read_frame(qs_subject_visit)\n",
+    "df_subject_visit.rename(columns={\"id\": \"subject_visit\"}, inplace=True)\n",
+    "qs_physical_exam = PhysicalExam.objects.filter(\n",
+    "    subject_visit__subject_identifier__in=subject_identifiers\n",
+    ")\n",
+    "df_physical_exam = read_frame(qs_physical_exam)\n",
+    "# merge w/ subject visit to get subject_identifier\n",
+    "# df_physical_exam = pd.merge(\n",
+    "#     df_physical_exam,\n",
+    "#     df_subject_visit[\n",
+    "#         [\"subject_visit\", \"subject_identifier\", \"visit_code\", \"visit_code_sequence\"]\n",
+    "#     ],\n",
+    "#     on=\"subject_visit\",\n",
+    "#     how=\"left\",\n",
+    "# )\n",
+    "# df_physical_exam = df_physical_exam[\n",
+    "#     [\"subject_identifier\", \"visit_code\", \"visit_code_sequence\", \"waist_circumference\"]\n",
+    "# ]\n",
+    "# df_physical_exam[[\"waist_circumference\"]] = df[[\"waist_circumference\"]].apply(\n",
+    "#     pd.to_numeric\n",
+    "# )\n",
+    "# # rename column to waist_circumference_baseline\n",
+    "# df_physical_exam[\"waist_circumference_baseline\"] = df_physical_exam[\"waist_circumference\"]\n",
+    "# df_physical_exam.drop(columns=[\"waist_circumference\"])\n",
+    "# df_physical_exam[[\"waist_circumference_baseline\"]] = df_physical_exam[\n",
+    "#     [\"waist_circumference_baseline\"]\n",
+    "# ].apply(pd.to_numeric)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_physical_exam.count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_physical_exam = pd.merge(\n",
+    "    df_physical_exam,\n",
+    "    df_subject_visit[\n",
+    "        [\"subject_visit\", \"subject_identifier\", \"visit_code\", \"visit_code_sequence\"]\n",
+    "    ],\n",
+    "    on=\"subject_visit\",\n",
+    "    how=\"left\",\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(df_physical_exam)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "24",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_physical_exam = df_physical_exam[\n",
+    "    [\"subject_identifier\", \"visit_code\", \"visit_code_sequence\", \"waist_circumference\"]\n",
+    "]\n",
+    "df_physical_exam[[\"waist_circumference\"]] = df_physical_exam[[\"waist_circumference\"]].apply(\n",
+    "    pd.to_numeric\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(df_physical_exam)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# rename column to waist_circumference_baseline\n",
+    "df_physical_exam[\"waist_circumference_baseline\"] = df_physical_exam[\"waist_circumference\"]\n",
+    "df_physical_exam.drop(columns=[\"waist_circumference\"])\n",
+    "df_physical_exam[[\"waist_circumference_baseline\"]] = df_physical_exam[\n",
+    "    [\"waist_circumference_baseline\"]\n",
+    "].apply(pd.to_numeric)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(df_physical_exam)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1 = df_all.copy()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1 = pd.merge(\n",
+    "    df1,\n",
+    "    df_physical_exam[[\"subject_identifier\", \"waist_circumference_baseline\"]],\n",
+    "    on=\"subject_identifier\",\n",
+    "    how=\"left\",\n",
+    "    indicator=True\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1.count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "cond = (df1[\"waist_circumference\"].isna()) & (df1[\"waist_circumference_baseline\"].notna())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "32",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1.loc[cond, \"waist_circumference\"] = df1[\"waist_circumference_baseline\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1.count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1[[\"waist_circumference\", \"waist_circumference_baseline\"]].count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_physical_exam[\"waist_circumference\"].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_physical_exam[[\"waist_circumference\"]] = df_physical_exam[\n",
+    "    [\"waist_circumference\"]\n",
+    "].apply(pd.to_numeric)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "37",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1[\"waist_circumference\"].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1[~df1[\"screening_identifier\"].isin(df1['screening_identifier'].unique())]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}