Added jupyter notebooks to explore functionalities of the flaggging app manager object

workflow_data_integration.ipynb

@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -29,9 +29,12 @@
     "root_dir = os.path.abspath(os.curdir)\n",
     "sys.path.append(root_dir)\n",
     "sys.path.append(os.path.join(root_dir,'dima'))\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.src.hdf5_vis as hdf5_vis\n",
-    "import dima.src.data_integration_lib as dilib\n"
+    "import dima.pipelines.data_integration as dilib\n"
    ]
   },
   {
@@ -47,11 +50,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
-    "yaml_config_file_path = 'dima_config.yaml'\n"
+    "yaml_config_file_path = 'dima_config.yaml'"
    ]
   },
   {
@@ -104,13 +107,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import dima.src.metadata_review_lib as metadata\n",
+    "import dima.pipelines.metadata_revision as metadata\n",
     "\n",
-    "import dima.src.hdf5_data_extraction as h5de\n",
+    "import dima.src.hdf5_ops as h5de\n",
     "\n",
     "channels1 = ['Chl_11000','NH4_11000','SO4_11000','NO3_11000','Org_11000']\n",
     "channels2 = ['FilamentEmission_mA','VaporizerTemp_C','FlowRate_mb','ABsamp']\n",
@@ -121,14 +124,15 @@
     "diagnostic_channels = {'location':'ACSM_TOFWARE/ACSM_JFJ_2024_JantoFeb_meta.txt/data_table',\n",
     "                       'names': ','.join(['t_base','FilamentEmission_mA','VaporizerTemp_C','FlowRate_mb','ABsamp'])}\n",
     "\n",
-    "DataOpsAPI = h5de.HDF5DataOpsManager(hdf5_file_path)\n",
+    "DataOpsAPI = h5de.HDF5DataOpsManager(hdf5_file_path[0])\n",
     "\n",
-    "DataOpsAPI.append_annotations('/',{'target_channels' : target_channels, 'diagnostic_channels' : diagnostic_channels})\n",
+    "DataOpsAPI.load_file_obj()\n",
+    "DataOpsAPI.append_metadata('/ACSM_TOFWARE/',{'target_channels' : target_channels, 'diagnostic_channels' : diagnostic_channels})\n",
     "\n",
     "DataOpsAPI.reformat_datetime_column('ACSM_TOFWARE/ACSM_JFJ_2024_JantoFeb_timeseries.txt/data_table','t_start_Buf',src_format='%d.%m.%Y %H:%M:%S.%f')\n",
     "DataOpsAPI.reformat_datetime_column('ACSM_TOFWARE/ACSM_JFJ_2024_JantoFeb_meta.txt/data_table','t_base',src_format='%d.%m.%Y %H:%M:%S')\n",
     "\n",
-    "DataOpsAPI.close_file()"
+    "DataOpsAPI.unload_file_obj()"
    ]
   },
   {

workflow_test_flaggingapp_manager.ipynb

@@ -0,0 +1,115 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "# Set up project root directory\n",
+    "root_dir = os.path.abspath(os.curdir)\n",
+    "sys.path.append(root_dir)\n",
+    "sys.path.append(os.path.join(root_dir,'dima'))\n",
+    "\n",
+    "import data_flagging_utils as utils\n",
+    "\n",
+    "DataOpsObj = utils.FlaggingAppDataManager('data_products/collection_acsm_campaign_NoraN_2024-01-01_2024-02-29.h5')\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_append_dir = 'data_products/collection_acsm_campaign_NoraN_2024-01-01_2024-02-29'\n",
+    "DataOpsObj.load_file_obj()\n",
+    "DataOpsObj.transfer_flags()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj.load_file_obj()\n",
+    "DataOpsObj._data_ops_obj.extract_and_load_dataset_metadata()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj._data_ops_obj.dataset_metadata_df.head(n=15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj.load_file_obj()\n",
+    "DataOpsObj.apply_flags('ACSM_TOFWARE')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj._data_ops_obj.unload_file_obj()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj.load_file_obj()\n",
+    "DataOpsObj._data_ops_obj.append_metadata('ACSM_TOFWARE__cleaned/ACSM_JFJ_2024_JantoFeb_timeseries.txt/data_table',{ 'creation_date' : b'2024-10-09_15-33-54_UTC-OFST_+0200' })\n",
+    "DataOpsObj._data_ops_obj.unload_file_obj()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DataOpsObj.load_file_obj()\n",
+    "DataOpsObj._data_ops_obj.delete_metadata('ACSM_TOFWARE__cleaned/ACSM_JFJ_2024_JantoFeb_timeseries.txt/data_table',{ 'created_at' : {'delete': True }})\n",
+    "DataOpsObj._data_ops_obj.unload_file_obj()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "multiphase_chemistry_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
+}