{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eef90c68",
   "metadata": {},
   "outputs": [],
   "source": [
    "from openmed.core import ModelLoader\n",
    "from openmed.processing import format_predictions\n",
    "\n",
    "loader = ModelLoader()  # uses the default configuration\n",
    "ner = loader.create_pipeline(\n",
    "    \"disease_detection_superclinical\",  # registry key or full model ID\n",
    "    aggregation_strategy=\"simple\",      # group sub-token predictions for quick wins\n",
    ")\n",
    "\n",
    "text = \"Patient diagnosed with acute lymphoblastic leukemia and started on imatinib.\"\n",
    "raw_predictions = ner(text)\n",
    "\n",
    "result = format_predictions(raw_predictions, text, model_name=\"Disease Detection\")\n",
    "for entity in result.entities:\n",
    "    print(f\"{entity.label:<12} -> {entity.text} (confidence={entity.confidence:.2f})\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a14de1a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import json\n",
    "\n",
    "data_dir = \"/home/mshahidul/readctrl/data/kyw_def_raw\"\n",
    "json_list = []\n",
    "\n",
    "for filename in os.listdir(data_dir):\n",
    "    print(f\"Processing file: {filename}\")\n",
    "    if filename.endswith(\".json\"):\n",
    "        file_path = os.path.join(data_dir, filename)\n",
    "        with open(file_path, \"r\") as f:\n",
    "            json_file=json.load(f)\n",
    "            if \"chatgpt_answer\" in json_file:\n",
    "                json_file=json_file[\"chatgpt_answer\"]\n",
    "            json_list.append(json_file)\n",
    "\n",
    "# Save the combined list to a new file\n",
    "save_dir = \"/home/mshahidul/readctrl/data/kyw_def_train\"\n",
    "os.makedirs(save_dir, exist_ok=True)\n",
    "with open(os.path.join(save_dir, \"kyw_gen_gpt5.json\"), \"w\") as out_f:\n",
    "    json.dump(json_list, out_f, indent=4)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "unsloth",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}