meta-edc 1.1.8__py3-none-any.whl → 1.1.12__py3-none-any.whl

meta_analytics/notebooks/undiagnosed/screening2.ipynb

@@ -1,958 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%load_ext sql\n",
-    "%sql mysql+mysqldb://root:cc3721b@127.0.0.1:3306/meta3_production\n",
-    "\n",
-    "import pandas as pd\n",
-    "from dj_notebook import activate\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "plus = activate(dotenv_file=\"/Users/erikvw/source/edc_source/meta-edc/.env\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from meta_screening.models import SubjectScreening\n",
-    "from django_pandas.io import read_frame\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "qs = SubjectScreening.objects.all()\n",
-    "df = read_frame(qs)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"meta_phase_two\"] = df[\"meta_phase_two\"].apply(lambda x: \"No\" if not x else x)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pd.crosstab(df['gender'], 'subjects')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "list(df.columns)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "gender = pd.crosstab(index=df['gender'], columns=[\"gender\"], margins=True)\n",
-    "gender.columns = [\"gender\", 'rowtotal']\n",
-    "gender.index = ['female', 'male', 'coltotal']\n",
-    "gender"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# counts by site - row, column\n",
-    "gender_by_site = pd.crosstab(df['site'], df['gender'], margins=True)\n",
-    "gender_by_site.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "gender_by_site.index = [\"amana\", \"hindu-mandal\", \"mnazi-moja\", \"mwananyamala\", \"temeke\", \"coltotal\"]\n",
-    "gender_by_site"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proportion of counts by row, column\n",
-    "gender_by_site/gender_by_site.loc[\"coltotal\",\"rowtotal\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "10",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proportion of counts by column\n",
-    "gender_by_site/gender_by_site.loc[\"coltotal\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "11",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proportion of counts by row\n",
-    "prop = gender_by_site.div(gender_by_site[\"rowtotal\"], axis=0)\n",
-    "prop"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "12",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# stats for female by site => mean=.718, well balanced\n",
-    "prop['female'].describe()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "13",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# part one variables\n",
-    "\n",
-    "# \"meta_phase_two\",\n",
-    "# \"hiv_pos\",\n",
-    "# \"art_six_months\",\n",
-    "# \"on_rx_stable\",\n",
-    "# \"vl_undetectable\",\n",
-    "# \"lives_nearby\",\n",
-    "# \"staying_nearby_12\",\n",
-    "# \"pregnant\",\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "14",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "15",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "meta_phase_two = pd.crosstab(index=df['meta_phase_two'], columns=[df[\"eligible\"],df[\"gender\"]], margins=True)\n",
-    "# meta_phase_two.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "# meta_phase_two.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "meta_phase_two"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "16",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "on_rx_stable = pd.crosstab(index=df['on_rx_stable'], columns=df[\"gender\"], margins=True)\n",
-    "on_rx_stable.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "on_rx_stable.index = [\"no\", \"n/a\", \"yes\", \"coltotal\"]\n",
-    "on_rx_stable"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "17",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "on_dm_medication = pd.crosstab(index=df['on_dm_medication'], columns=df[\"gender\"], margins=True)\n",
-    "on_dm_medication.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "on_dm_medication.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "on_dm_medication"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "18",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "hiv_pos = pd.crosstab(index=df['hiv_pos'], columns=df[\"gender\"], margins=True)\n",
-    "hiv_pos.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "hiv_pos.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "hiv_pos"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "19",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "art_six_months = pd.crosstab(index=df['art_six_months'], columns=df[\"gender\"], margins=True)\n",
-    "art_six_months.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "art_six_months.index = [\"no\", \"n/a\", \"yes\", \"coltotal\"]\n",
-    "art_six_months"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "20",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vl_undetectable = pd.crosstab(index=df['vl_undetectable'], columns=df[\"gender\"], margins=True)\n",
-    "vl_undetectable.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "vl_undetectable.index = [\"no\", \"n/a\", \"yes\", \"coltotal\"]\n",
-    "vl_undetectable"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lives_nearby = pd.crosstab(index=df['lives_nearby'], columns=df[\"gender\"], margins=True)\n",
-    "lives_nearby.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "lives_nearby.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "lives_nearby"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "22",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "staying_nearby_12 = pd.crosstab(index=df['staying_nearby_12'], columns=df[\"gender\"], margins=True)\n",
-    "staying_nearby_12.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "staying_nearby_12.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "staying_nearby_12"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "23",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pregnant = pd.crosstab(index=df['pregnant'], columns=df[\"gender\"], margins=True)\n",
-    "pregnant.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "pregnant.index = [\"no\", \"n/a\", \"yes\", \"coltotal\"]\n",
-    "pregnant"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "24",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "eligible_part_one = pd.crosstab(index=df['eligible_part_one'], columns=df[\"gender\"], margins=True)\n",
-    "eligible_part_one.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "eligible_part_one.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "eligible_part_one"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "25",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df_part_one eligible\n",
-    "# \"meta_phase_two\",\n",
-    "# \"hiv_pos\",\n",
-    "# \"art_six_months\",\n",
-    "# \"on_rx_stable\",\n",
-    "# \"vl_undetectable\",\n",
-    "# \"lives_nearby\",\n",
-    "# \"staying_nearby_12\",\n",
-    "# \"pregnant\",\n",
-    "\n",
-    "df_part_one = df[(df[\"meta_phase_two\"]==\"No\") & (df[\"hiv_pos\"]==\"Yes\") & (df[\"art_six_months\"]==\"Yes\") & (df[\"on_rx_stable\"]==\"Yes\") & (df[\"vl_undetectable\"]==\"Yes\") & (df[\"lives_nearby\"]==\"Yes\") & (df[\"staying_nearby_12\"]==\"Yes\") & (df[\"pregnant\"]!=\"Yes\")]\n",
-    "len(df_part_one)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "26",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_p1_eligible = df[df[\"meta_phase_two\"]!=\"Yes\"]['meta_phase_two']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "27",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# PART TWO\n",
-    "# \"congestive_heart_failure\",\n",
-    "# \"liver_disease\",\n",
-    "# \"alcoholism\",\n",
-    "# \"acute_metabolic_acidosis\",\n",
-    "# \"renal_function_condition\",\n",
-    "# \"tissue_hypoxia_condition\",\n",
-    "# \"acute_condition\",\n",
-    "# \"metformin_sensitivity\",\n",
-    "# \"has_dm\",\n",
-    "# \"on_dm_medication\","
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "28",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "congestive_heart_failure = pd.crosstab(index=df['congestive_heart_failure'], columns=df[\"gender\"], margins=True)\n",
-    "congestive_heart_failure.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "congestive_heart_failure.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "congestive_heart_failure"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "29",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "liver_disease = pd.crosstab(index=df['liver_disease'], columns=df[\"gender\"], margins=True)\n",
-    "liver_disease.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "liver_disease.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "liver_disease"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "30",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "alcoholism = pd.crosstab(index=df['alcoholism'], columns=df[\"gender\"], margins=True)\n",
-    "alcoholism.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "alcoholism.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "alcoholism"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "acute_metabolic_acidosis = pd.crosstab(index=df['acute_metabolic_acidosis'], columns=df[\"gender\"], margins=True)\n",
-    "acute_metabolic_acidosis.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "acute_metabolic_acidosis.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "acute_metabolic_acidosis"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "32",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "renal_function_condition = pd.crosstab(index=df['renal_function_condition'], columns=df[\"gender\"], margins=True)\n",
-    "renal_function_condition.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "renal_function_condition.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "renal_function_condition"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "33",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "tissue_hypoxia_condition = pd.crosstab(index=df['tissue_hypoxia_condition'], columns=df[\"gender\"], margins=True)\n",
-    "tissue_hypoxia_condition.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "tissue_hypoxia_condition.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "tissue_hypoxia_condition"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "34",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "metformin_sensitivity = pd.crosstab(index=df['metformin_sensitivity'], columns=df[\"gender\"], margins=True)\n",
-    "metformin_sensitivity.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "metformin_sensitivity.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "metformin_sensitivity"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "acute_condition = pd.crosstab(index=df['acute_condition'], columns=df[\"gender\"], margins=True)\n",
-    "acute_condition.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "acute_condition.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "acute_condition"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "36",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# has_dm by gender (if not eligible_part_one)\n",
-    "has_dm = pd.crosstab(index=df[df[\"eligible_part_one\"]==\"Yes\"]['has_dm'], columns=df[\"gender\"], margins=True)\n",
-    "has_dm.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "has_dm.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "has_dm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "37",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# has_dm by gender, eligible_part_one\n",
-    "has_dm = pd.crosstab(index=df['has_dm'], columns=[df[\"gender\"],df[\"eligible_part_one\"]], margins=True)\n",
-    "# has_dm.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "# has_dm.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "has_dm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "38",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# has_dm by gender\n",
-    "has_dm = pd.crosstab(index=df['has_dm'], columns=df[\"gender\"], margins=True)\n",
-    "has_dm.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "has_dm.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "has_dm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "39",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "has_dm.div(has_dm[\"rowtotal\"], axis=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "40",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "has_dm / len(df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "41",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"eligible_part_one\"].value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "42",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"eligible_part_two\"].value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "43",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"eligible_part_three\"].value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "44",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"eligible\"].value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "45",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"consented\"].value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "46",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[\"eligible\"].value_counts()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "47",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pd.crosstab(index=df['eligible'], columns=df[\"gender\"], margins=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "48",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# let's start here for the consort chart"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "49",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dm1 = df[df[\"meta_phase_two\"]==\"No\"]\n",
-    "dm1 = pd.crosstab(index=dm1['eligible'], columns=df[\"gender\"], margins=True, dropna=False)\n",
-    "dm1.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "dm1.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "dm1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "50",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df1 = df[(df[\"meta_phase_two\"]==\"No\")]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "51",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "hiv_pos = pd.crosstab(index=df1['hiv_pos'], columns=df1[\"gender\"], margins=True)\n",
-    "hiv_pos.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "hiv_pos.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "hiv_pos"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "52",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "art_six_months = pd.crosstab(index=df1['art_six_months'], columns=df1[\"gender\"], margins=True)\n",
-    "art_six_months.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "art_six_months.index = [\"no\", \"na\", \"yes\", \"coltotal\"]\n",
-    "art_six_months"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "53",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "on_rx_stable = pd.crosstab(index=df1['on_rx_stable'], columns=df1[\"gender\"], margins=True)\n",
-    "on_rx_stable.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "on_rx_stable.index = [\"no\", \"na\", \"yes\", \"coltotal\"]\n",
-    "on_rx_stable"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "54",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vl_undetectable = pd.crosstab(index=df1['vl_undetectable'], columns=df1[\"gender\"], margins=True)\n",
-    "vl_undetectable.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "vl_undetectable.index = [\"no\", \"na\", \"yes\", \"coltotal\"]\n",
-    "vl_undetectable"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "55",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "len(df1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "56",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "df2 = df1[(df1[\"hiv_pos\"]==\"Yes\") & (df1[\"art_six_months\"]!=\"No\") & (df1[\"on_rx_stable\"]!=\"No\") & (df1[\"vl_undetectable\"]!=\"No\")]\n",
-    "len(df2)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "57",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df2['eligible'], columns=df2[\"gender\"], margins=True, dropna=False)\n",
-    "dftmp.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "dftmp.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "58",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# \"lives_nearby\",\n",
-    "# \"staying_nearby_12\",\n",
-    "# \"pregnant\",\n",
-    "\n",
-    "df3 = df2[(df2[\"lives_nearby\"]==\"Yes\") & (df2[\"staying_nearby_12\"]==\"Yes\")]\n",
-    "len(df3)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "59",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df3['eligible'], columns=df3[\"gender\"], margins=True, dropna=False)\n",
-    "dftmp.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "dftmp.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "60",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lives_nearby = pd.crosstab(index=df2['lives_nearby'], columns=df2[\"gender\"], margins=True, dropna=False)\n",
-    "lives_nearby.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "lives_nearby.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "lives_nearby"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "61",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tmp = df2[df2['lives_nearby']==\"Yes\"]\n",
-    "staying_nearby_12 = pd.crosstab(index=tmp['staying_nearby_12'], columns=tmp[\"gender\"], margins=True, dropna=False)\n",
-    "staying_nearby_12.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "staying_nearby_12.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "staying_nearby_12"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "62",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df4 = df3[(df3[\"pregnant\"]!=\"Yes\")]\n",
-    "len(df4)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "63",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df4['eligible'], columns=df4[\"gender\"], margins=True, dropna=False)\n",
-    "dftmp.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "dftmp.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "64",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df4['eligible_part_two'], columns=df4[\"gender\"], margins=True, dropna=True)\n",
-    "# dftmp.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "# dftmp.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "65",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# \"congestive_heart_failure\",\n",
-    "# \"liver_disease\",\n",
-    "# \"alcoholism\",\n",
-    "# \"acute_metabolic_acidosis\",\n",
-    "# \"renal_function_condition\",\n",
-    "# \"tissue_hypoxia_condition\",\n",
-    "# \"acute_condition\",\n",
-    "# \"metformin_sensitivity\",\n",
-    "# \"has_dm\",\n",
-    "# \"on_dm_medication\","
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "66",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tmp1 = pd.crosstab(index=df4['acute_condition'], columns=tmp[\"gender\"], margins=True, dropna=False)\n",
-    "tmp1.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "# tmp1.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "tmp1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "67",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "df5 = df4[(df4[\"congestive_heart_failure\"]!=\"Yes\") & (df4[\"liver_disease\"]!=\"Yes\") & (df4[\"alcoholism\"]!=\"Yes\") & (df4[\"acute_metabolic_acidosis\"]!=\"Yes\") & (df4[\"renal_function_condition\"]!=\"Yes\") & (df4[\"tissue_hypoxia_condition\"]!=\"Yes\") & (df4[\"acute_condition\"]!=\"Yes\")]\n",
-    "len(df5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "68",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df5['eligible_part_two'], columns=df5[\"gender\"], margins=True, dropna=True)\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "69",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tmp1 = pd.crosstab(index=df5['on_dm_medication'], columns=tmp[\"gender\"], margins=True, dropna=False)\n",
-    "tmp1.columns = [\"female\", \"male\", \"rowtotal\"]\n",
-    "# tmp1.index = [\"no\", \"yes\", \"coltotal\"]\n",
-    "tmp1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "70",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df6 = df5[(df5[\"has_dm\"]==\"No\") & (df5[\"on_dm_medication\"]==\"No\") & (df5[\"metformin_sensitivity\"]==\"No\")]\n",
-    "len(df6)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "71",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df6['eligible_part_two'], columns=df6[\"gender\"], margins=True, dropna=True)\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "72",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dftmp = pd.crosstab(index=df['eligible_part_two'], columns=df[\"gender\"], margins=True, dropna=True)\n",
-    "dftmp"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "73",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['eligible_part_two'].values_count()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "74",
-   "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": "3.12.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}