{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c8a1e072b9c99117",
   "metadata": {},
   "source": [
    "# B Point Detection Example"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b03dc1d8ba136bed",
   "metadata": {},
   "source": [
    "## Setup and imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9a9e1e779129bad1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from fau_colors import cmaps\n",
    "\n",
    "from pepbench.algorithms.icg import BPointExtractionPale2021, CPointExtractionScipyFindPeaks\n",
    "from pepbench.example_data import get_example_dataset\n",
    "\n",
    "%matplotlib inline\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1432ca952a994b",
   "metadata": {},
   "source": [
    "## Plotting style"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "706add995e246b0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.close(\"all\")\n",
    "palette = sns.color_palette(cmaps.faculties)\n",
    "sns.set_theme(context=\"notebook\", style=\"ticks\", font=\"sans-serif\", palette=palette)\n",
    "plt.rcParams[\"figure.figsize\"] = (10, 5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "375327a5d0584159",
   "metadata": {},
   "source": [
    "## Load Example Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6360c9f4e3a7fe50",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h4 style=\"margin-bottom: 0.1em;\">ExampleDataset [2 groups/rows]</h3>\n",
       "<div style=\"margin-top: 0em\">\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table style=\"margin-left: 3em;\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th style=\"text-align: center;\"></th>\n",
       "      <th style=\"text-align: center;\">participant</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th style=\"text-align: center;\">0</th>\n",
       "      <td style=\"text-align: center; padding-left: 2em; padding-right: 2em;\">VP_001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th style=\"text-align: center;\">1</th>\n",
       "      <td style=\"text-align: center; padding-left: 2em; padding-right: 2em;\">VP_002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "ExampleDataset [2 groups/rows]\n",
       "\n",
       "     participant\n",
       "   0      VP_001\n",
       "   1      VP_002"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset = get_example_dataset(return_clean=True)\n",
    "dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f10fbf98af3d65a6",
   "metadata": {},
   "source": [
    "Get the first datapoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d07a4130457ab975",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h4 style=\"margin-bottom: 0.1em;\">ExampleDataset [1 groups/rows]</h3>\n",
       "<div style=\"margin-top: 0em\">\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table style=\"margin-left: 3em;\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th style=\"text-align: center;\"></th>\n",
       "      <th style=\"text-align: center;\">participant</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th style=\"text-align: center;\">0</th>\n",
       "      <td style=\"text-align: center; padding-left: 2em; padding-right: 2em;\">VP_001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "ExampleDataset [1 groups/rows]\n",
       "\n",
       "     participant\n",
       "   0      VP_001"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "datapoint = list(dataset)[0]\n",
    "datapoint"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d76f77d9640e3129",
   "metadata": {},
   "source": [
    "## Run C-point extraction (used by some B-point algorithms)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f7fa44514f40a15b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CPointExtractionScipyFindPeaks(handle_missing_events='warn', window_c_correction=3)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c_algo = CPointExtractionScipyFindPeaks()\n",
    "# use the computed heartbeat segmentation\n",
    "c_algo.extract(icg=datapoint.icg, heartbeats=datapoint.heartbeats, sampling_rate_hz=datapoint.sampling_rate_icg)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "713e3a1c6db302ce",
   "metadata": {},
   "source": [
    "## Run B-point extraction (Pale et al. 2021)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7a73377e6d0ee406",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "BPointExtractionPale2021(b_point_slope_threshold_01=0.11, b_point_slope_threshold_02=0.08, c_point_amplitude_fraction=0.5, handle_missing_events='warn')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b_algo = BPointExtractionPale2021()\n",
    "# use the same heartbeat segmentation (datapoint.heartbeats) when extracting\n",
    "b_algo.extract(\n",
    "    icg=datapoint.icg,\n",
    "    heartbeats=datapoint.heartbeats,\n",
    "    c_points=c_algo.points_,\n",
    "    sampling_rate_hz=datapoint.sampling_rate_icg,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f10c1f8dc8686d45",
   "metadata": {},
   "source": [
    "## Inspect detected points (first rows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b665b4cf4ddaa9a1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>b_point_sample</th>\n",
       "      <th>nan_reason</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>heartbeat_id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>179</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>533</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1009</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1466</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1873</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              b_point_sample nan_reason\n",
       "heartbeat_id                           \n",
       "0                        179        NaN\n",
       "1                        533        NaN\n",
       "2                       1009        NaN\n",
       "3                       1466        NaN\n",
       "4                       1873        NaN"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b_algo.points_.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9998c0c956a73601",
   "metadata": {},
   "source": [
    "## Plot a few heartbeats to visualise detected B-points\n",
    "determine the first five heartbeat_ids available in the reference_heartbeats index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fc4a1a89f1cf3181",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Plotting heartbeat ids: [0, 1, 2]\n"
     ]
    }
   ],
   "source": [
    "hb_ids = list(datapoint.reference_heartbeats.index.get_level_values(\"heartbeat_id\").unique())[:3]\n",
    "print(\"Plotting heartbeat ids:\", hb_ids)\n",
    "# fig, ax = plot_b_point_extraction_pale2021(datapoint, heartbeat_subset=hb_ids, normalize_time=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84fc286daf4b9f42",
   "metadata": {},
   "source": [
    "### Notes:\n",
    "- You can swap `BPointExtractionPale2021` for other algorithms available in `pepbench.algorithms.icg`.\n",
    "- To use non-reference heartbeats, use `datapoint.heartbeats` instead of `datapoint.reference_heartbeats`.\n",
    "- For the bundled example dataset, to access raw (uncleaned) signals call `get_example_dataset(return_clean=False)` when instantiating.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dff34bddc6eb549b",
   "metadata": {},
   "source": [
    "detection + ploting signal and detected b points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ccfa953ef82574e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pepbench",
   "language": "python",
   "name": "pepbench"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}