{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "header",
   "metadata": {
    "papermill": {
     "duration": 0.00208,
     "end_time": "2026-01-18T07:22:47.796550",
     "exception": false,
     "start_time": "2026-01-18T07:22:47.794470",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# PaddleOCR Hyperparameter Optimization via REST API\n",
    "\n",
    "This notebook runs Ray Tune hyperparameter search calling the PaddleOCR REST API (Docker container).\n",
    "\n",
    "**Benefits:**\n",
    "- No model reload per trial - Model stays loaded in Docker container\n",
    "- Faster trials - Skip ~10s model load time per trial\n",
    "- Cleaner code - REST API replaces subprocess + CLI arg parsing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "prereq",
   "metadata": {
    "papermill": {
     "duration": 0.000961,
     "end_time": "2026-01-18T07:22:47.807230",
     "exception": false,
     "start_time": "2026-01-18T07:22:47.806269",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Prerequisites\n",
    "\n",
    "Start 2 PaddleOCR workers for parallel hyperparameter tuning:\n",
    "\n",
    "```bash\n",
    "cd src/paddle_ocr\n",
    "docker compose -f docker-compose.workers.yml up\n",
    "```\n",
    "\n",
    "This starts 2 GPU workers on ports 8001-8002, allowing 2 concurrent trials.\n",
    "\n",
    "For CPU-only systems:\n",
    "```bash\n",
    "docker compose -f docker-compose.workers.yml --profile cpu up\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ob9fsoilc4",
   "metadata": {
    "papermill": {
     "duration": 0.000901,
     "end_time": "2026-01-18T07:22:47.809075",
     "exception": false,
     "start_time": "2026-01-18T07:22:47.808174",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 0. Dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "wyr2nsoj7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:47.812056Z",
     "iopub.status.busy": "2026-01-18T07:22:47.811910Z",
     "iopub.status.idle": "2026-01-18T07:22:49.130013Z",
     "shell.execute_reply": "2026-01-18T07:22:49.129363Z"
    },
    "papermill": {
     "duration": 1.321151,
     "end_time": "2026-01-18T07:22:49.131123",
     "exception": false,
     "start_time": "2026-01-18T07:22:47.809972",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: ray[tune] in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (2.53.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: click>=7.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (8.3.1)\r\n",
      "Requirement already satisfied: filelock in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (3.20.3)\r\n",
      "Requirement already satisfied: jsonschema in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (4.26.0)\r\n",
      "Requirement already satisfied: msgpack<2.0.0,>=1.0.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (1.1.2)\r\n",
      "Requirement already satisfied: packaging>=24.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (25.0)\r\n",
      "Requirement already satisfied: protobuf>=3.20.3 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (6.33.4)\r\n",
      "Requirement already satisfied: pyyaml in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (6.0.3)\r\n",
      "Requirement already satisfied: requests in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (2.32.5)\r\n",
      "Requirement already satisfied: pandas in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (2.3.3)\r\n",
      "Requirement already satisfied: pydantic!=2.0.*,!=2.1.*,!=2.10.*,!=2.11.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*,!=2.8.*,!=2.9.*,<3 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (2.12.5)\r\n",
      "Requirement already satisfied: tensorboardX>=1.9 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (2.6.4)\r\n",
      "Requirement already satisfied: pyarrow>=9.0.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (22.0.0)\r\n",
      "Requirement already satisfied: fsspec in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from ray[tune]) (2026.1.0)\r\n",
      "Requirement already satisfied: annotated-types>=0.6.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pydantic!=2.0.*,!=2.1.*,!=2.10.*,!=2.11.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*,!=2.8.*,!=2.9.*,<3->ray[tune]) (0.7.0)\r\n",
      "Requirement already satisfied: pydantic-core==2.41.5 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pydantic!=2.0.*,!=2.1.*,!=2.10.*,!=2.11.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*,!=2.8.*,!=2.9.*,<3->ray[tune]) (2.41.5)\r\n",
      "Requirement already satisfied: typing-extensions>=4.14.1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pydantic!=2.0.*,!=2.1.*,!=2.10.*,!=2.11.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*,!=2.8.*,!=2.9.*,<3->ray[tune]) (4.15.0)\r\n",
      "Requirement already satisfied: typing-inspection>=0.4.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pydantic!=2.0.*,!=2.1.*,!=2.10.*,!=2.11.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*,!=2.8.*,!=2.9.*,<3->ray[tune]) (0.4.2)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: numpy in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from tensorboardX>=1.9->ray[tune]) (2.4.1)\r\n",
      "Requirement already satisfied: attrs>=22.2.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from jsonschema->ray[tune]) (25.4.0)\r\n",
      "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from jsonschema->ray[tune]) (2025.9.1)\r\n",
      "Requirement already satisfied: referencing>=0.28.4 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from jsonschema->ray[tune]) (0.37.0)\r\n",
      "Requirement already satisfied: rpds-py>=0.25.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from jsonschema->ray[tune]) (0.30.0)\r\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas->ray[tune]) (2.9.0.post0)\r\n",
      "Requirement already satisfied: pytz>=2020.1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas->ray[tune]) (2025.2)\r\n",
      "Requirement already satisfied: tzdata>=2022.7 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas->ray[tune]) (2025.3)\r\n",
      "Requirement already satisfied: six>=1.5 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas->ray[tune]) (1.17.0)\r\n",
      "Requirement already satisfied: charset_normalizer<4,>=2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests->ray[tune]) (3.4.4)\r\n",
      "Requirement already satisfied: idna<4,>=2.5 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests->ray[tune]) (3.11)\r\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests->ray[tune]) (2.6.3)\r\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests->ray[tune]) (2026.1.4)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: optuna in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (4.6.0)\r\n",
      "Requirement already satisfied: alembic>=1.5.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (1.18.1)\r\n",
      "Requirement already satisfied: colorlog in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (6.10.1)\r\n",
      "Requirement already satisfied: numpy in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (2.4.1)\r\n",
      "Requirement already satisfied: packaging>=20.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (25.0)\r\n",
      "Requirement already satisfied: sqlalchemy>=1.4.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (2.0.45)\r\n",
      "Requirement already satisfied: tqdm in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (4.67.1)\r\n",
      "Requirement already satisfied: PyYAML in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from optuna) (6.0.3)\r\n",
      "Requirement already satisfied: Mako in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from alembic>=1.5.0->optuna) (1.3.10)\r\n",
      "Requirement already satisfied: typing-extensions>=4.12 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from alembic>=1.5.0->optuna) (4.15.0)\r\n",
      "Requirement already satisfied: greenlet>=1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from sqlalchemy>=1.4.2->optuna) (3.3.0)\r\n",
      "Requirement already satisfied: MarkupSafe>=0.9.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from Mako->alembic>=1.5.0->optuna) (3.0.3)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: requests in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (2.32.5)\r\n",
      "Requirement already satisfied: pandas in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (2.3.3)\r\n",
      "Requirement already satisfied: charset_normalizer<4,>=2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests) (3.4.4)\r\n",
      "Requirement already satisfied: idna<4,>=2.5 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests) (3.11)\r\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests) (2.6.3)\r\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from requests) (2026.1.4)\r\n",
      "Requirement already satisfied: numpy>=1.26.0 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas) (2.4.1)\r\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas) (2.9.0.post0)\r\n",
      "Requirement already satisfied: pytz>=2020.1 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas) (2025.2)\r\n",
      "Requirement already satisfied: tzdata>=2022.7 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from pandas) (2025.3)\r\n",
      "Requirement already satisfied: six>=1.5 in /home/sergio/MastersThesis/.venv/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\r\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "# Install dependencies (run once)\n",
    "%pip install -U \"ray[tune]\"\n",
    "%pip install optuna\n",
    "%pip install requests pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "imports-header",
   "metadata": {
    "papermill": {
     "duration": 0.002313,
     "end_time": "2026-01-18T07:22:49.136199",
     "exception": false,
     "start_time": "2026-01-18T07:22:49.133886",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 1. Imports & Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "imports",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:49.141850Z",
     "iopub.status.busy": "2026-01-18T07:22:49.141713Z",
     "iopub.status.idle": "2026-01-18T07:22:50.248414Z",
     "shell.execute_reply": "2026-01-18T07:22:50.247699Z"
    },
    "papermill": {
     "duration": 1.111175,
     "end_time": "2026-01-18T07:22:50.249605",
     "exception": false,
     "start_time": "2026-01-18T07:22:49.138430",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "from datetime import datetime\n",
    "\n",
    "import requests\n",
    "import pandas as pd\n",
    "\n",
    "import ray\n",
    "from ray import tune, air\n",
    "from ray.tune.search.optuna import OptunaSearch"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "config-header",
   "metadata": {
    "papermill": {
     "duration": 0.00953,
     "end_time": "2026-01-18T07:22:50.261880",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.252350",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 2. API Configuration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "config",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:50.267482Z",
     "iopub.status.busy": "2026-01-18T07:22:50.267340Z",
     "iopub.status.idle": "2026-01-18T07:22:50.269689Z",
     "shell.execute_reply": "2026-01-18T07:22:50.269264Z"
    },
    "papermill": {
     "duration": 0.006027,
     "end_time": "2026-01-18T07:22:50.270230",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.264203",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# PaddleOCR REST API endpoints - 2 workers for parallel trials\n",
    "# Start workers with: cd src/paddle_ocr && docker compose -f docker-compose.workers.yml up\n",
    "WORKER_PORTS = [8001, 8002]\n",
    "WORKER_URLS = [f\"http://localhost:{port}\" for port in WORKER_PORTS]\n",
    "\n",
    "# Output folder for results\n",
    "OUTPUT_FOLDER = \"results\"\n",
    "os.makedirs(OUTPUT_FOLDER, exist_ok=True)\n",
    "\n",
    "# Number of concurrent trials = number of workers\n",
    "NUM_WORKERS = len(WORKER_URLS)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "health-check",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:50.275708Z",
     "iopub.status.busy": "2026-01-18T07:22:50.275626Z",
     "iopub.status.idle": "2026-01-18T07:22:50.283441Z",
     "shell.execute_reply": "2026-01-18T07:22:50.282984Z"
    },
    "papermill": {
     "duration": 0.011534,
     "end_time": "2026-01-18T07:22:50.284080",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.272546",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✓ http://localhost:8001: ok (GPU: None)\n",
      "✓ http://localhost:8002: ok (GPU: None)\n",
      "\n",
      "2/2 workers ready for parallel tuning\n"
     ]
    }
   ],
   "source": [
    "# Verify all workers are running\n",
    "healthy_workers = []\n",
    "for url in WORKER_URLS:\n",
    "    try:\n",
    "        health = requests.get(f\"{url}/health\", timeout=10).json()\n",
    "        if health['status'] == 'ok' and health['model_loaded']:\n",
    "            healthy_workers.append(url)\n",
    "            print(f\"✓ {url}: {health['status']} (GPU: {health.get('gpu_name', 'N/A')})\")\n",
    "        else:\n",
    "            print(f\"✗ {url}: not ready yet\")\n",
    "    except requests.exceptions.ConnectionError:\n",
    "        print(f\"✗ {url}: not reachable\")\n",
    "\n",
    "if not healthy_workers:\n",
    "    raise RuntimeError(\n",
    "        \"No healthy workers found. Start them with:\\n\"\n",
    "        \"  cd src/paddle_ocr && docker compose -f docker-compose.workers.yml up\"\n",
    "    )\n",
    "\n",
    "print(f\"\\n{len(healthy_workers)}/{len(WORKER_URLS)} workers ready for parallel tuning\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "search-space-header",
   "metadata": {
    "papermill": {
     "duration": 0.002325,
     "end_time": "2026-01-18T07:22:50.288969",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.286644",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 3. Search Space"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "search-space",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:50.294569Z",
     "iopub.status.busy": "2026-01-18T07:22:50.294500Z",
     "iopub.status.idle": "2026-01-18T07:22:50.296998Z",
     "shell.execute_reply": "2026-01-18T07:22:50.296295Z"
    },
    "papermill": {
     "duration": 0.006486,
     "end_time": "2026-01-18T07:22:50.297804",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.291318",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "search_space = {\n",
    "    # Whether to use document image orientation classification\n",
    "    \"use_doc_orientation_classify\": tune.choice([True, False]),\n",
    "    # Whether to use text image unwarping\n",
    "    \"use_doc_unwarping\": tune.choice([True, False]),\n",
    "    # Whether to use text line orientation classification\n",
    "    \"textline_orientation\": tune.choice([True, False]),\n",
    "    # Detection pixel threshold (pixels > threshold are considered text)\n",
    "    \"text_det_thresh\": tune.uniform(0.0, 0.7),\n",
    "    # Detection box threshold (average score within border)\n",
    "    \"text_det_box_thresh\": tune.uniform(0.0, 0.7),\n",
    "    # Text detection expansion coefficient\n",
    "    \"text_det_unclip_ratio\": tune.choice([0.0]),\n",
    "    # Text recognition threshold (filter low confidence results)\n",
    "    \"text_rec_score_thresh\": tune.uniform(0.0, 0.7),\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "trainable-header",
   "metadata": {
    "papermill": {
     "duration": 0.002321,
     "end_time": "2026-01-18T07:22:50.302532",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.300211",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 4. Trainable Function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "trainable",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:50.308222Z",
     "iopub.status.busy": "2026-01-18T07:22:50.308103Z",
     "iopub.status.idle": "2026-01-18T07:22:50.311240Z",
     "shell.execute_reply": "2026-01-18T07:22:50.310694Z"
    },
    "papermill": {
     "duration": 0.007301,
     "end_time": "2026-01-18T07:22:50.312116",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.304815",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def trainable_paddle_ocr(config):\n",
    "    \"\"\"Call PaddleOCR REST API with the given hyperparameter config.\"\"\"\n",
    "    import random\n",
    "    import requests\n",
    "    from ray import tune\n",
    "\n",
    "    # Worker URLs - random selection (load balances with 2 workers, 2 concurrent trials)\n",
    "    WORKER_PORTS = [8001, 8002]\n",
    "    api_url = f\"http://localhost:{random.choice(WORKER_PORTS)}\"\n",
    "\n",
    "    payload = {\n",
    "        \"pdf_folder\": \"/app/dataset\",\n",
    "        \"use_doc_orientation_classify\": config.get(\"use_doc_orientation_classify\", False),\n",
    "        \"use_doc_unwarping\": config.get(\"use_doc_unwarping\", False),\n",
    "        \"textline_orientation\": config.get(\"textline_orientation\", True),\n",
    "        \"text_det_thresh\": config.get(\"text_det_thresh\", 0.0),\n",
    "        \"text_det_box_thresh\": config.get(\"text_det_box_thresh\", 0.0),\n",
    "        \"text_det_unclip_ratio\": config.get(\"text_det_unclip_ratio\", 1.5),\n",
    "        \"text_rec_score_thresh\": config.get(\"text_rec_score_thresh\", 0.0),\n",
    "        \"start_page\": 5,\n",
    "        \"end_page\": 10,\n",
    "    }\n",
    "\n",
    "    try:\n",
    "        response = requests.post(f\"{api_url}/evaluate\", json=payload, timeout=None)\n",
    "        response.raise_for_status()\n",
    "        metrics = response.json()\n",
    "        metrics[\"worker\"] = api_url\n",
    "        tune.report(**metrics)\n",
    "    except Exception as e:\n",
    "        tune.report(\n",
    "            CER=1.0,\n",
    "            WER=1.0,\n",
    "            TIME=0.0,\n",
    "            PAGES=0,\n",
    "            TIME_PER_PAGE=0,\n",
    "            worker=api_url,\n",
    "            ERROR=str(e)[:500]\n",
    "        )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "tuner-header",
   "metadata": {
    "papermill": {
     "duration": 0.002522,
     "end_time": "2026-01-18T07:22:50.317277",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.314755",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## 5. Run Tuner"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ray-init",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:50.323163Z",
     "iopub.status.busy": "2026-01-18T07:22:50.323037Z",
     "iopub.status.idle": "2026-01-18T07:22:54.197904Z",
     "shell.execute_reply": "2026-01-18T07:22:54.196986Z"
    },
    "papermill": {
     "duration": 3.878908,
     "end_time": "2026-01-18T07:22:54.198593",
     "exception": false,
     "start_time": "2026-01-18T07:22:50.319685",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2026-01-18 08:22:51,904\tINFO worker.py:2007 -- Started a local Ray instance.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ray Tune ready (version: 2.53.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/sergio/MastersThesis/.venv/lib/python3.12/site-packages/ray/_private/worker.py:2046: FutureWarning: Tip: In future versions of Ray, Ray will no longer override accelerator visible devices env var if num_gpus=0 or num_gpus=None (default). To enable this behavior and turn off this error message, set RAY_ACCEL_ENV_VAR_OVERRIDE_ON_ZERO=0\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "ray.init(ignore_reinit_error=True)\n",
    "print(f\"Ray Tune ready (version: {ray.__version__})\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "tuner",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-01-18T07:22:54.213071Z",
     "iopub.status.busy": "2026-01-18T07:22:54.212310Z"
    },
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": false,
     "start_time": "2026-01-18T07:22:54.201610",
     "status": "running"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/sergio/MastersThesis/.venv/lib/python3.12/site-packages/ray/tune/impl/tuner_internal.py:144: RayDeprecationWarning: The `RunConfig` class should be imported from `ray.tune` when passing it to the Tuner. Please update your imports. See this issue for more context and migration options: https://github.com/ray-project/ray/issues/49454. Disable these warnings by setting the environment variable: RAY_TRAIN_ENABLE_V2_MIGRATION_WARNINGS=0\n",
      "  _log_deprecation_warning(\n",
      "2026-01-18 08:22:54,222\tINFO tune.py:616 -- [output] This uses the legacy output and progress reporter, as Jupyter notebooks are not supported by the new engine, yet. For more information, please see https://github.com/ray-project/ray/issues/36949\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[I 2026-01-18 08:22:54,226] A new study created in memory with name: optuna\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div class=\"tuneStatus\">\n",
       "  <div style=\"display: flex;flex-direction: row\">\n",
       "    <div style=\"display: flex;flex-direction: column;\">\n",
       "      <h3>Tune Status</h3>\n",
       "      <table>\n",
       "<tbody>\n",
       "<tr><td>Current time:</td><td>2026-01-18 08:23:19</td></tr>\n",
       "<tr><td>Running for: </td><td>00:00:25.26        </td></tr>\n",
       "<tr><td>Memory:      </td><td>57.8/119.7 GiB     </td></tr>\n",
       "</tbody>\n",
       "</table>\n",
       "    </div>\n",
       "    <div class=\"vDivider\"></div>\n",
       "    <div class=\"systemInfo\">\n",
       "      <h3>System Info</h3>\n",
       "      Using FIFO scheduling algorithm.<br>Logical resource usage: 2.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:GB10)\n",
       "    </div>\n",
       "    \n",
       "  </div>\n",
       "  <div class=\"hDivider\"></div>\n",
       "  <div class=\"trialStatus\">\n",
       "    <h3>Trial Status</h3>\n",
       "    <table>\n",
       "<thead>\n",
       "<tr><th>Trial name                   </th><th>status  </th><th>loc                   </th><th style=\"text-align: right;\">  text_det_box_thresh</th><th style=\"text-align: right;\">  text_det_thresh</th><th style=\"text-align: right;\">  text_det_unclip_rati\n",
       "o</th><th style=\"text-align: right;\">         text_rec_score_thres\n",
       "h</th><th>textline_orientation  </th><th>use_doc_orientation_\n",
       "classify      </th><th>use_doc_unwarping  </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>trainable_paddle_ocr_59252191</td><td>RUNNING </td><td>192.168.65.140:1195312</td><td style=\"text-align: right;\">             0.414043</td><td style=\"text-align: right;\">         0.337475</td><td style=\"text-align: right;\">0</td><td style=\"text-align: right;\">0.478234</td><td>True                  </td><td>True </td><td>True               </td></tr>\n",
       "<tr><td>trainable_paddle_ocr_47499299</td><td>RUNNING </td><td>192.168.65.140:1195374</td><td style=\"text-align: right;\">             0.544738</td><td style=\"text-align: right;\">         0.269735</td><td style=\"text-align: right;\">0</td><td style=\"text-align: right;\">0.30771 </td><td>True                  </td><td>False</td><td>True               </td></tr>\n",
       "</tbody>\n",
       "</table>\n",
       "  </div>\n",
       "</div>\n",
       "<style>\n",
       ".tuneStatus {\n",
       "  color: var(--jp-ui-font-color1);\n",
       "}\n",
       ".tuneStatus .systemInfo {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       ".tuneStatus td {\n",
       "  white-space: nowrap;\n",
       "}\n",
       ".tuneStatus .trialStatus {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       ".tuneStatus h3 {\n",
       "  font-weight: bold;\n",
       "}\n",
       ".tuneStatus .hDivider {\n",
       "  border-bottom-width: var(--jp-border-width);\n",
       "  border-bottom-color: var(--jp-border-color0);\n",
       "  border-bottom-style: solid;\n",
       "}\n",
       ".tuneStatus .vDivider {\n",
       "  border-left-width: var(--jp-border-width);\n",
       "  border-left-color: var(--jp-border-color0);\n",
       "  border-left-style: solid;\n",
       "  margin: 0.5em 1em 0.5em 1em;\n",
       "}\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[36m(pid=gcs_server)\u001b[0m [2026-01-18 08:23:20,495 E 1193965 1193965] (gcs_server) gcs_server.cc:303: Failed to establish connection to the event+metrics exporter agent. Events and metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[33m(raylet)\u001b[0m [2026-01-18 08:23:21,833 E 1194136 1194136] (raylet) main.cc:1032: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[36m(bundle_reservation_check_func pid=1194212)\u001b[0m [2026-01-18 08:23:23,446 E 1194212 1194301] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[2026-01-18 08:23:24,197 E 1193837 1194205] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14\n"
     ]
    }
   ],
   "source": [
    "tuner = tune.Tuner(\n",
    "    trainable_paddle_ocr,\n",
    "    tune_config=tune.TuneConfig(\n",
    "        metric=\"CER\",\n",
    "        mode=\"min\",\n",
    "        search_alg=OptunaSearch(),\n",
    "        num_samples=64,\n",
    "        max_concurrent_trials=NUM_WORKERS,  # Run trials in parallel across workers\n",
    "    ),\n",
    "    run_config=air.RunConfig(verbose=2, log_to_file=False),\n",
    "    param_space=search_space,\n",
    ")\n",
    "\n",
    "results = tuner.fit()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "analysis-header",
   "metadata": {
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": null,
     "start_time": null,
     "status": "pending"
    },
    "tags": []
   },
   "source": [
    "## 6. Results Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "results-df",
   "metadata": {
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": null,
     "start_time": null,
     "status": "pending"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df = results.get_dataframe()\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "save-results",
   "metadata": {
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": null,
     "start_time": null,
     "status": "pending"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Save results to CSV\n",
    "timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
    "filename = f\"raytune_paddle_rest_results_{timestamp}.csv\"\n",
    "filepath = os.path.join(OUTPUT_FOLDER, filename)\n",
    "\n",
    "df.to_csv(filepath, index=False)\n",
    "print(f\"Results saved: {filepath}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "best-config",
   "metadata": {
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": null,
     "start_time": null,
     "status": "pending"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Best configuration\n",
    "best = df.loc[df[\"CER\"].idxmin()]\n",
    "\n",
    "print(f\"Best CER: {best['CER']:.6f}\")\n",
    "print(f\"Best WER: {best['WER']:.6f}\")\n",
    "print(f\"\\nOptimal Configuration:\")\n",
    "print(f\"  textline_orientation: {best['config/textline_orientation']}\")\n",
    "print(f\"  use_doc_orientation_classify: {best['config/use_doc_orientation_classify']}\")\n",
    "print(f\"  use_doc_unwarping: {best['config/use_doc_unwarping']}\")\n",
    "print(f\"  text_det_thresh: {best['config/text_det_thresh']:.4f}\")\n",
    "print(f\"  text_det_box_thresh: {best['config/text_det_box_thresh']:.4f}\")\n",
    "print(f\"  text_det_unclip_ratio: {best['config/text_det_unclip_ratio']}\")\n",
    "print(f\"  text_rec_score_thresh: {best['config/text_rec_score_thresh']:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "correlation",
   "metadata": {
    "papermill": {
     "duration": null,
     "end_time": null,
     "exception": null,
     "start_time": null,
     "status": "pending"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Correlation analysis\n",
    "param_cols = [\n",
    "    \"config/text_det_thresh\",\n",
    "    \"config/text_det_box_thresh\",\n",
    "    \"config/text_det_unclip_ratio\",\n",
    "    \"config/text_rec_score_thresh\",\n",
    "]\n",
    "\n",
    "corr_cer = df[param_cols + [\"CER\"]].corr()[\"CER\"].sort_values(ascending=False)\n",
    "corr_wer = df[param_cols + [\"WER\"]].corr()[\"WER\"].sort_values(ascending=False)\n",
    "\n",
    "print(\"Correlation with CER:\")\n",
    "print(corr_cer)\n",
    "print(\"\\nCorrelation with WER:\")\n",
    "print(corr_wer)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.3"
  },
  "papermill": {
   "default_parameters": {},
   "duration": null,
   "end_time": null,
   "environment_variables": {},
   "exception": null,
   "input_path": "paddle_ocr_raytune_rest.ipynb",
   "output_path": "output_raytune.ipynb",
   "parameters": {},
   "start_time": "2026-01-18T07:22:47.169883",
   "version": "2.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}