{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import os\n",
    "# Set up project root directory\n",
    "\n",
    "\n",
    "notebook_dir = os.getcwd()  # Current working directory (assumes running from notebooks/)\n",
    "project_path = os.path.normpath(os.path.join(notebook_dir, \"..\"))  # Move up to project root\n",
    "dima_path = os.path.normpath(os.path.join(project_path, \"dima\"))  # Move up to project root\n",
    "\n",
    "if project_path not in sys.path:  # Avoid duplicate entries\n",
    "    sys.path.append(project_path)\n",
    "if dima_path not in sys.path:\n",
    "    sys.path.insert(0,dima_path)\n",
    "#sys.path.append(os.path.join(root_dir,'dima','instruments'))\n",
    "#sys.path.append(os.path.join(root_dir,'dima','src'))\n",
    "#sys.path.append(os.path.join(root_dir,'dima','utils'))\n",
    "\n",
    "#import dima.visualization.hdf5_vis as hdf5_vis\n",
    "#import dima.pipelines.data_integration as data_integration\n",
    "import subprocess\n",
    "\n",
    "\n",
    "for item in sys.path:\n",
    "    print(item)\n",
    "\n",
    "CAMPAIGN_DATA_FILE = \"../data/collection_JFJ_2024_2025-03-14_2025-03-14.h5\"\n",
    "APPEND_DATA_DIR = \"../data/collection_JFJ_2024_2025-03-14_2025-03-14\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pipelines.steps.apply_calibration_factors import main as run_apply_calibration_factors\n",
    "\n",
    "path_to_data_file = CAMPAIGN_DATA_FILE\n",
    "path_to_calibration_file = '../pipelines/params/calibration_factors.yaml'\n",
    "dataset_name = 'ACSM_TOFWARE/2024/ACSM_JFJ_2024_timeseries.txt/data_table'\n",
    "#command = ['python', 'pipelines/steps/apply_calibration_factors.py', path_to_data_file, dataset_name, path_to_calibration_file]\n",
    "#status = subprocess.run(command, capture_output=True, check=True)\n",
    "#print(status.stdout.decode())\n",
    "\n",
    "run_apply_calibration_factors(path_to_data_file,path_to_calibration_file)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pipelines.steps.generate_flags import main as run_generate_flags\n",
    "path_to_data_file = CAMPAIGN_DATA_FILE\n",
    "dataset_name = 'ACSM_TOFWARE/2024/ACSM_JFJ_2024_meta.txt/data_table'\n",
    "path_to_config_file = 'pipelines/params/validity_thresholds.yaml'\n",
    "#command = ['python', 'pipelines/steps/compute_automated_flags.py', path_to_data_file, dataset_name, path_to_config_file]\n",
    "#status = subprocess.run(command, capture_output=True, check=True)\n",
    "#print(status.stdout.decode())\n",
    "run_generate_flags(path_to_data_file, 'diagnostics')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pipelines.steps.generate_flags import main as run_generate_flags\n",
    "path_to_data_file = CAMPAIGN_DATA_FILE\n",
    "dataset_name = 'ACSM_TOFWARE/2024/ACSM_JFJ_2024_meta.txt/data_table'\n",
    "path_to_config_file = 'pipelines/params/validity_thresholds.yaml'\n",
    "#command = ['python', 'pipelines/steps/compute_automated_flags.py', path_to_data_file, dataset_name, path_to_config_file]\n",
    "#status = subprocess.run(command, capture_output=True, check=True)\n",
    "#print(status.stdout.decode())\n",
    "run_generate_flags(path_to_data_file, 'species')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pipelines.steps.prepare_ebas_submission import main as run_prepare_ebas_submission \n",
    "\n",
    "PATH1=\"../data/collection_JFJ_2024_2025-03-14_2025-03-14/ACSM_TOFWARE_processed/2024/ACSM_JFJ_2024_timeseries_calibrated.csv\"\n",
    "PATH2=\"../data/collection_JFJ_2024_2025-03-14_2025-03-14/ACSM_TOFWARE_processed/2024/ACSM_JFJ_2024_timeseries_calibrated_err.csv\"\n",
    "PATH3=\"../data/collection_JFJ_2024_2025-03-14_2025-03-14/ACSM_TOFWARE_processed/2024/ACSM_JFJ_2024_timeseries_calibration_factors.csv\"\n",
    "PATH4=\"../data/collection_JFJ_2024_2025-03-14_2025-03-14/ACSM_TOFWARE_flags/2024/ACSM_JFJ_2024_timeseries_flags.csv\"\n",
    "month = 4\n",
    "run_prepare_ebas_submission([PATH1,PATH2,PATH3], PATH4, month)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dima.src.hdf5_ops as dataOps \n",
    "#print(os.curdir)\n",
    "\n",
    "\n",
    "dataManager = dataOps.HDF5DataOpsManager(CAMPAIGN_DATA_FILE)\n",
    "print(dataManager.file_path)\n",
    "print(APPEND_DATA_DIR)\n",
    "dataManager.update_file(APPEND_DATA_DIR)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataManager = dataOps.HDF5DataOpsManager(path_to_data_file)\n",
    "dataManager.load_file_obj()\n",
    "dataManager.extract_and_load_dataset_metadata()\n",
    "df = dataManager.dataset_metadata_df\n",
    "print(df.head(10))\n",
    "dataManager.unload_file_obj()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dash_multi_chem_env",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}