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

meta_analytics/notebooks/undiagnosed/screen_undiagnosed_or.ipynb

@@ -0,0 +1,296 @@
+{
+ "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": [
+    "import itertools\n",
+    "from meta_analytics.dataframes import GlucoseEndpointsByDate, get_eos_df, get_screening_df\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_glu2 = get_glucose_tested_only_df()\n",
+    "cond_fasting2 = (df_glu2.fasting == \"Yes\") & (df_glu2.fasting_fbg_hrs >= 8.0)\n",
+    "cond_f2 = (df_glu2[\"gender\"] == \"F\")\n",
+    "cond_m2 = (df_glu2[\"gender\"] == \"M\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df_glu[cond_f & cond_fasting & (df_glu.ogtt.notna()) & ((df_glu.fbg>=7.0) | (df_glu.ogtt>=11.1))].count()\n",
+    "\n",
+    "# when ogtt not done \n",
+    "# df_glu[cond_f & cond_fasting & (df_glu.ogtt.isna())].fbg.describe()\n",
+    "\n",
+    "# we never have ogtt w/o fbg\n",
+    "# df_glu[cond_f & cond_fasting & (df_glu.fbg.isna())].ogtt.describe()\n",
+    "\n",
+    "# df_glu = df_glu.reset_index(drop=False)\n",
+    "def dx(row):\n",
+    "    # print((row.fbg>=7.0) & (row.ogtt>=11.1))\n",
+    "    # print(row.fbg, row.ogtt)\n",
+    "    if (row.fbg>=7.0) & (row.fbg<10.0) & (row.ogtt>=11.1):\n",
+    "        ret = \"fbg_ogtt\"\n",
+    "    elif (row.fbg>=7.0) & (row.fbg<10.0) & (row.ogtt<11.1):\n",
+    "        ret = \"fbg_only\"\n",
+    "    elif (row.fbg<7.0) & (row.ogtt>=11.1):\n",
+    "        ret = \"ogtt_only\"\n",
+    "    elif (row.fbg<7.0) & (row.ogtt<11.1):\n",
+    "        ret = \"neither\"\n",
+    "    else:\n",
+    "        ret = None\n",
+    "        # print(row.fbg, row.ogtt)\n",
+    "    return ret\n",
+    "    \n",
+    "df_glu2[\"glucose\"] = \"\"        \n",
+    "df_glu2[\"glucose\"] = df_glu2[cond_fasting2].apply(lambda r: dx(r), axis=1)\n",
+    "# df_glu[cond_fasting & cond_f]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[\"glucose\"].value_counts()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[cond_fasting2 & cond_f2][\"glucose\"].value_counts()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[cond_fasting2 & cond_m2][\"glucose\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import cohen_kappa_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[cond_fasting2 & cond_m2 & (df_glu2.fbg>=7.0) & (df_glu2.fbg<10.0) ].glucose.value_counts()\n",
+    "# y2 = df_glu2[cond_fasting2 & cond_f2 & (df_glu2.fbg<7.0)].glucose"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# cohen_kappa_score(y1, y2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cond_fasting = (df_glu2.fasting == \"Yes\") & (df_glu2.fasting_fbg_hrs >= 8.0)\n",
+    "\n",
+    "df_glu2[\"fbg_threshold\"] = (df_glu2[cond_fasting].fbg >= 7.0) & (df_glu2[cond_fasting].fbg < 10.0)\n",
+    "df_glu2[\"ogtt_threshold\"] = df_glu2[cond_fasting].ogtt >= 11.1\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[\"fbg_threshold\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[\"ogtt_threshold\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# female\n",
+    "df_glu2[cond_f2][[\"fbg_threshold\", \"ogtt_threshold\"]].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# male\n",
+    "df_glu2[cond_m2][[\"fbg_threshold\", \"ogtt_threshold\"]].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.stats.contingency import odds_ratio\n",
+    "\n",
+    "# female\n",
+    "res = odds_ratio([[76, 414], [72,3639]])\n",
+    "res.statistic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res.confidence_interval(confidence_level=0.95)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# male\n",
+    "res = odds_ratio([[28, 141], [48,1197]])\n",
+    "res.statistic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res.confidence_interval(confidence_level=0.95)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_glu2[cond_fasting].count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20",
+   "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
+}

meta_analytics/notebooks/undiagnosed/screening.ipynb

@@ -0,0 +1,273 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture\n",
+    "import os\n",
+    "from pathlib import Path\n",
+    "import pandas as pd\n",
+    "from dj_notebook import activate\n",
+    "import numpy as np\n",
+    "from django_pandas.io import read_frame\n",
+    "\n",
+    "env_file = os.environ[\"META_ENV\"]\n",
+    "reports_folder = Path(os.environ[\"META_REPORTS_FOLDER\"])\n",
+    "analysis_folder = Path(os.environ[\"META_ANALYSIS_FOLDER\"])\n",
+    "pharmacy_folder = Path(os.environ[\"META_PHARMACY_FOLDER\"])\n",
+    "plus = activate(dotenv_file=env_file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from meta_analytics.dataframes.screening import get_screening_df\n",
+    "from django.contrib.sites.models import Site"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = get_screening_df()\n",
+    "sites = {obj.domain: obj.id for obj in Site.objects.all()}\n",
+    "df[\"site\"] = df[\"site\"].map(sites)\n",
+    "df = df.rename(columns={\"report_datetime\": \"screening_datetime\"})\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(analysis_folder, index=False, sep=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(analysis_folder, sep=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\"screening_identifier\", \"site\", \"screening_datetime\", \"fbg_datetime\", \"fbg_value\",  \"ogtt_value\", \"repeat_glucose_performed\", \"fbg2_value\", \"ogtt2_value\", \"fbg2_datetime\", \"ogtt2_datetime\", \"consented\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "df[(df[\"fbg_value\"].notna()) & (df[\"ogtt_value\"].isna()) & (df[\"unsuitable_agreed\"]!=\"Yes\")][columns].count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\"screening_identifier\", \"site\", \"screening_datetime\", \"fbg_datetime\", \"fbg_value\",  \"ogtt_value\", \"repeat_glucose_performed\", \"fbg2_value\", \"ogtt2_value\", \"fbg2_datetime\", \"ogtt2_datetime\", \"consented\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[(df[\"fbg_value\"].notna()) & (df[\"ogtt_value\"].isna()) & (df[\"repeat_glucose_performed\"]==\"Yes\")][columns]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from edc_constants.constants import YES, NO\n",
+    "df = get_screening_df()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.groupby(by=[\"eligible_part_one\", \"eligible_part_two\"], dropna=True).size()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "erik = list(df[(df.eligible_part_one==YES) & (df.eligible_part_two==YES) & (df.hiv_pos==YES)].screening_identifier)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_peiyun = pd.read_csv(Path(\"~/Documents/ucl/protocols/intecomm/analysis/primary\") / \"peiyun.csv\")\n",
+    "peiyun = list(df_peiyun.screening_identifier)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "[x for x in erik if x not in peiyun]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[df.screening_identifier == \"SR9E8B4D\"][[\"site\", 'eligible_part_one', 'eligible_part_two', \"hiv_pos\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "[x for x in peiyun if x not in erik]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.groupby(by=[\"eligible_part_one\", \"eligible_part_two\", \"agree_to_p3\"], dropna=True).size()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[~(df.subject_identifier.isna()) & (df.agree_to_p3==NO)][[\"subject_identifier\", \"eligible_part_one\", \"eligible_part_two\", \"agree_to_p3\", \"screening_identifier\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[~(df.subject_identifier.str.startswith(\"105-\")) & (df.eligible_part_one==YES) & (df.eligible_part_two==YES)][[\"subject_identifier\", \"eligible_part_one\", \"eligible_part_two\", \"agree_to_p3\", \"screening_identifier\"]]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[(df.subject_identifier.str.startswith(\"105-\"))][[\"subject_identifier\", \"eligible_part_one\", \"eligible_part_two\", \"agree_to_p3\", \"screening_identifier\"]]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[df.agree_to_p3==NO][[\"screening_identifier\", \"subject_identifier\", \"eligible_part_one\", \"eligible_part_two\", \"eligible_part_three\"]]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22",
+   "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
+}