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

meta_analytics/notebooks/liver.ipynb

@@ -0,0 +1,389 @@
+{
+ "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",
+    "\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)\n",
+    "pd.set_option('future.no_silent_downcasting', True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import date\n",
+    "from edc_pdutils.dataframes import get_subject_visit, get_subject_consent\n",
+    "from meta_analytics.dataframes import get_screening_df\n",
+    "from edc_pdutils.dataframes import get_crf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cutoff_date = date(2025,5, 31)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_visit = get_subject_visit(\"meta_subject.subjectvisit\").query(\"visit_code==1000.0\").reset_index(drop=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# merge with consent for dob\n",
+    "df_consent = get_subject_consent(model=\"meta_consent.subjectconsent\")[[\"subject_identifier\", \"gender\", \"dob\", \"age_in_years\", \"consent_datetime\"]]\n",
+    "df_visit = df_visit.merge(df_consent, on=\"subject_identifier\", how=\"left\")\n",
+    "df_visit[\"age_in_years\"] = df_visit[\"age_in_years\"].astype(\"Int64\")\n",
+    "df_visit[\"dob\"] = df_visit[\"dob\"].astype(\"datetime64[ns]\")\n",
+    "df_visit[\"consent_datetime\"] = df_visit[\"consent_datetime\"].dt.normalize()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "    \"subject_identifier\",\n",
+    "    # \"gender\",\n",
+    "    # \"age_in_years\",\n",
+    "    \"ethnicity\",\n",
+    "    \"fbg_value\",\n",
+    "    \"fbg_date\",\n",
+    "    \"fbg_units\",\n",
+    "    \"bmi\",\n",
+    "    \"weight\",\n",
+    "    \"height\",\n",
+    "    \"severe_htn\",\n",
+    "    \"dia_blood_pressure_avg\",\n",
+    "    \"sys_blood_pressure_avg\",\n",
+    "    \"waist_circumference\",\n",
+    "]\n",
+    "\n",
+    "df_screening = (\n",
+    "    get_screening_df()\n",
+    "    .query(\"subject_identifier.str.startswith('105-')\")\n",
+    "    .rename(columns={\"calculated_bmi_value\":\"bmi\", \"fbg_datetime\":\"fbg_date\"})\n",
+    "    .reset_index()\n",
+    ")\n",
+    "df_screening[\"fbg_value\"] = df_screening[\"fbg_value\"].astype(\"Float64\")\n",
+    "df_screening[\"bmi\"] = df_screening[\"bmi\"].astype(\"Float64\")\n",
+    "df_screening[\"height\"] = df_screening[\"height\"].astype(\"Float64\")\n",
+    "df_screening[\"weight\"] = df_screening[\"weight\"].astype(\"Float64\")\n",
+    "df_screening[\"waist_circumference\"] = df_screening[\"waist_circumference\"].astype(\"Float64\")\n",
+    "df_screening[\"dia_blood_pressure_avg\"] = df_screening[\"dia_blood_pressure_avg\"].astype(\"Float64\")\n",
+    "df_screening[\"sys_blood_pressure_avg\"] = df_screening[\"sys_blood_pressure_avg\"].astype(\"Float64\")\n",
+    "df_screening[\"fbg_date\"] = df_screening[\"fbg_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "\n",
+    "df_screening.loc[df_screening.fasting_duration_delta.dt.total_seconds()<28800, \"fbg\"] = pd.NA\n",
+    "df_screening.loc[df_screening.fasting_duration_delta.dt.total_seconds()<28800, \"fbg_units\"] = pd.NA\n",
+    "\n",
+    "# merge with vars from screening\n",
+    "df_visit = df_visit.merge(df_screening[columns], on=\"subject_identifier\", how=\"left\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "    \"subject_visit_id\",\n",
+    "    \"rft_date\",\n",
+    "    \"crf\",\n",
+    "    \"creatinine_value\",\n",
+    "    \"creatinine_units\",\n",
+    "    \"creatinine_abnormal\",\n",
+    "    \"egfr_value\",\n",
+    "    \"egfr_units\",\n",
+    "    \"egfr_abnormal\",\n",
+    "    \"urea_value\",\n",
+    "    \"urea_units\",\n",
+    "    \"urea_abnormal\",\n",
+    "    \"uric_acid_value\",\n",
+    "    \"uric_acid_units\",\n",
+    "    \"uric_acid_abnormal\",\n",
+    "]\n",
+    "df_bloodresultsrft = get_crf(model=\"meta_subject.bloodresultsrft\", subject_visit_model=\"meta_subject.subjectvisit\").rename(columns={\"report_datetime\": \"rft_date\"}).reset_index(drop=True)\n",
+    "df_bloodresultsrft[\"rft_date\"] = df_bloodresultsrft[\"rft_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "df_bloodresultsrft[\"crf\"] = \"bloodresultsrft\"\n",
+    "\n",
+    "for col in columns:\n",
+    "    if col.endswith(\"_value\"):\n",
+    "        df_bloodresultsrft[col] = df_bloodresultsrft[col].astype(\"Float64\")\n",
+    "\n",
+    "df_visit = df_visit.merge(df_bloodresultsrft.query(\"visit_code==1000.0\")[columns], on=\"subject_visit_id\", how=\"left\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "    \"subject_visit_id\",\n",
+    "    \"ast_value\",\n",
+    "    \"ast_units\",\n",
+    "    \"ast_abnormal\",\n",
+    "    \"alt_value\",\n",
+    "    \"alt_units\",\n",
+    "    \"alt_abnormal\",\n",
+    "    \"alp_value\",\n",
+    "    \"alp_units\",\n",
+    "    \"alp_abnormal\",\n",
+    "    \"amylase_value\",\n",
+    "    \"amylase_units\",\n",
+    "    \"amylase_abnormal\",\n",
+    "    \"ggt_value\",\n",
+    "    \"ggt_units\",\n",
+    "    \"ggt_abnormal\",\n",
+    "    \"albumin_value\",\n",
+    "    \"albumin_units\",\n",
+    "    \"albumin_abnormal\",\n",
+    "]\n",
+    "df_bloodresultslft = get_crf(model=\"meta_subject.bloodresultslft\", subject_visit_model=\"meta_subject.subjectvisit\").rename(columns={\"report_datetime\":\"lft_date\"}).reset_index(drop=True)\n",
+    "df_bloodresultslft[\"lft_date\"] = df_bloodresultslft[\"lft_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "df_bloodresultslft[\"crf\"] = \"bloodresultslft\"\n",
+    "\n",
+    "for col in columns:\n",
+    "    if col.endswith(\"_value\"):\n",
+    "        df_bloodresultslft[col] = df_bloodresultslft[col].astype(\"Float64\")\n",
+    "\n",
+    "# df_bloodresultslft.query(\"visit_code==1000.0\")[columns]\n",
+    "df_visit = df_visit.merge(df_bloodresultslft.query(\"visit_code==1000.0\")[columns], on=\"subject_visit_id\", how=\"left\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "    \"subject_visit_id\",\n",
+    "    \"lipids_date\",\n",
+    "    \"crf\",\n",
+    "    \"hdl_value\",\n",
+    "    \"hdl_units\",\n",
+    "    \"hdl_abnormal\",\n",
+    "    \"ldl_value\",\n",
+    "    \"ldl_units\",\n",
+    "    \"ldl_abnormal\",\n",
+    "    \"trig_value\",\n",
+    "    \"trig_units\",\n",
+    "    \"trig_abnormal\",\n",
+    "    \"chol_value\",\n",
+    "    \"chol_units\",\n",
+    "    \"chol_abnormal\",\n",
+    "]\n",
+    "df_bloodresultslipids = get_crf(model=\"meta_subject.bloodresultslipids\", subject_visit_model=\"meta_subject.subjectvisit\").rename(columns={\"report_datetime\": \"lipids_date\"}).reset_index(drop=True)\n",
+    "df_bloodresultslipids[\"lipids_date\"] = df_bloodresultslipids[\"lipids_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "df_bloodresultslipids[\"crf\"] = \"bloodresultslipids\"\n",
+    "for col in columns:\n",
+    "    if col.endswith(\"_value\"):\n",
+    "        df_bloodresultslipids[col] = df_bloodresultslipids[col].astype(\"Float64\")\n",
+    "# df_bloodresultslipids.query(\"visit_code==1000.0\")[columns]\n",
+    "df_visit = df_visit.merge(df_bloodresultslipids.query(\"visit_code==1000.0\")[columns], on=\"subject_visit_id\", how=\"left\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "    \"subject_visit_id\",\n",
+    "    \"fbc_date\",\n",
+    "    \"crf\",\n",
+    "    \"haemoglobin_value\",\n",
+    "    \"haemoglobin_units\",\n",
+    "    \"haemoglobin_abnormal\",\n",
+    "    \"wbc_value\",\n",
+    "    \"wbc_units\",\n",
+    "    \"wbc_abnormal\",\n",
+    "    \"rbc_value\",\n",
+    "    \"rbc_units\",\n",
+    "    \"rbc_abnormal\",\n",
+    "    \"platelets_value\",\n",
+    "    \"platelets_units\",\n",
+    "    \"platelets_abnormal\",\n",
+    "]\n",
+    "df_bloodresultsfbc = get_crf(model=\"meta_subject.bloodresultsfbc\", subject_visit_model=\"meta_subject.subjectvisit\").rename(columns={\"report_datetime\": \"fbc_date\"}).reset_index(drop=True)\n",
+    "df_bloodresultsfbc[\"fbc_date\"] = df_bloodresultsfbc[\"fbc_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "df_bloodresultsfbc[\"crf\"] = \"bloodresultsfbc\"\n",
+    "for col in columns:\n",
+    "    if col.endswith(\"_value\"):\n",
+    "        df_bloodresultsfbc[col] = df_bloodresultsfbc[col].astype(\"Float64\")\n",
+    "\n",
+    "df_visit = df_visit.merge(df_bloodresultsfbc.query(\"visit_code==1000.0\")[columns], on=\"subject_visit_id\", how=\"left\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\n",
+    "        \"subject_visit_id\",\n",
+    "        \"current_smoker\",\n",
+    "        \"former_smoker\",\n",
+    "        \"hiv_diagnosis_date\",\n",
+    "        \"current_arv_regimen\",\n",
+    "        \"current_arv_regimen_start_date\",\n",
+    "    ]\n",
+    "df_patient_history = get_crf(\n",
+    "        model=\"meta_subject.patienthistory\",\n",
+    "        subject_visit_model=\"meta_subject.subjectvisit\")\n",
+    "df_patient_history[\"hiv_diagnosis_date\"] = df_patient_history[\"hiv_diagnosis_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "df_patient_history[\"current_arv_regimen_start_date\"] = df_patient_history[\"current_arv_regimen_start_date\"].dt.tz_localize(None).dt.normalize()\n",
+    "\n",
+    "df_visit = df_visit.merge(df_patient_history.query(\"visit_code==1000.0\")[columns], on=\"subject_visit_id\", how=\"left\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = [\"subject_visit_id\", \"weight\", \"waist_circumference\", \"severe_htn\", \"dia_blood_pressure_avg\", \"sys_blood_pressure_avg\"]\n",
+    "df_physical_exam = get_crf(\n",
+    "        model=\"meta_subject.physicalexam\",\n",
+    "        subject_visit_model=\"meta_subject.subjectvisit\",\n",
+    ")\n",
+    "\n",
+    "df_visit = df_visit.merge(df_physical_exam[[\"subject_visit_id\", \"weight\", \"waist_circumference\"]], on=\"subject_visit_id\", how=\"left\", suffixes=(\"\", \"_physicalexam\"))\n",
+    "df_visit['weight_physicalexam'] = df_visit['weight_physicalexam'].astype(\"Float64\")\n",
+    "df_visit['waist_circumference_physicalexam'] = df_visit['waist_circumference_physicalexam'].astype(\"Float64\")\n",
+    "\n",
+    "df_visit['weight'] = df_visit['weight'].fillna(df_visit['weight_physicalexam'])\n",
+    "df_visit['waist_circumference'] = df_visit['waist_circumference'].fillna(df_visit['waist_circumference_physicalexam'])\n",
+    "\n",
+    "df_visit = df_visit.drop(columns=[\"weight_physicalexam\", \"waist_circumference_physicalexam\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_visit = (df_visit\n",
+    "    .drop(columns=[col for col in df_visit.columns if col.endswith(\"_y\")])\n",
+    "    .drop(columns=[col for col in df_visit.columns if col.endswith(\"_x\")])\n",
+    "    .drop(columns=[\n",
+    "        \"appointment_id\",\n",
+    "        \"appt_datetime\",\n",
+    "        \"appt_status\",\n",
+    "        \"appt_timing\",\n",
+    "        \"baseline_datetime\",\n",
+    "        \"crf\",\n",
+    "        \"endline_visit_code\",\n",
+    "        \"endline_visit_code_str\",\n",
+    "        \"endline_visit_datetime\",\n",
+    "        \"followup_days\",\n",
+    "        \"reason\",\n",
+    "        \"reason_missed\",\n",
+    "        \"reason_missed_other\",\n",
+    "        \"reason_unscheduled\",\n",
+    "        \"reason_unscheduled_other\",\n",
+    "        \"subject_visit_id\",\n",
+    "        \"visit_code_str\",\n",
+    "]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for col in [col for col in df_visit.columns if col.endswith(\"_abnormal\")]:\n",
+    "    df_visit[col] = df_visit[col].astype(str)\n",
+    "for col in [col for col in df_visit.columns if col.endswith(\"_units\")]:\n",
+    "    df_visit[col] = df_visit[col].astype(str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_visit.to_stata(\n",
+    "    path=analysis_folder / \"liver.dta\",\n",
+    "    version=118,\n",
+    "    write_index=False,\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}