{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Artifact Removal"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Mean Subtraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import plotly.io as pio\n",
    "pio.renderers.default = \"sphinx_gallery\"\n",
    "# pio.renderers.default = \"plotly_mimetype\"  # or \"plotly_mimetype\"\n",
    "# from IPython.display import display, HTML\n",
    "# display(HTML('<script src=\"https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js\"></script>'))\n",
    "import numpy as np\n",
    "from plotly import graph_objects as go\n",
    "import os\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ar = ArtifactRemoval(signal_col)\n",
    "cleaned_signal = ar.mean_subtraction()\n",
    "\n",
    "plot_trace(signal_col,cleaned_signal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Baseline Correction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import numpy as np\n",
    "from plotly import graph_objects as go\n",
    "import os\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ar = ArtifactRemoval(signal_col)\n",
    "cleaned_signal = ar.baseline_correction(cutoff=0.5, fs=fs)\n",
    "\n",
    "plot_trace(signal_col,cleaned_signal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Wavelet Denoising"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import numpy as np\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ar = ArtifactRemoval(signal_col)\n",
    "\n",
    "# Daubechies db4, level 2 + Gaussian post-smoothing\n",
    "cleaned_db = ar.wavelet_denoising(\n",
    "    wavelet_type=\"db\", level=2, order=4,\n",
    "    smoothing=\"gaussian\", sigma=1.0\n",
    ")\n",
    "plot_trace(signal_col, np.real(cleaned_db), title=\"Daubechies db4 + Gaussian\")\n",
    "\n",
    "# Haar, level 2 + median post-smoothing\n",
    "cleaned_haar = ar.wavelet_denoising(wavelet_type=\"haar\", level=2,\n",
    "                                     smoothing=\"median\", kernel_size=5)\n",
    "plot_trace(signal_col, np.real(cleaned_haar), title=\"Haar + Median\")\n",
    "\n",
    "# Symlet sym4, level 2 + moving average post-smoothing\n",
    "cleaned_sym = ar.wavelet_denoising(wavelet_type=\"sym\", order=4, level=2,\n",
    "                                    smoothing=\"moving_average\", window_size=7)\n",
    "plot_trace(signal_col, np.real(cleaned_sym), title=\"Symlet sym4 + Moving Average\")\n",
    "\n",
    "# Custom wavelet (user-defined FIR) + low-pass post-smoothing\n",
    "custom_wavelet = np.array([0.1, 0.2, 0.4, 0.2, 0.1, 1.0, -0.5, 0.1, 0.2, 0.5, 0.2, 0.2])\n",
    "cleaned_custom = ar.wavelet_denoising(wavelet_type=\"custom\",\n",
    "                                       custom_wavelet=custom_wavelet,\n",
    "                                       smoothing=\"lowpass\", cutoff=0.3, fs=float(fs))\n",
    "plot_trace(signal_col, np.real(cleaned_custom), title=\"Custom wavelet + Low-pass\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Adaptive Filtering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import numpy as np\n",
    "from vitalDSP.utils.data_processing.synthesize_data import generate_ecg_signal\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "# Synthetic ECG used as reference (correlated with real signal rhythm)\n",
    "reference = generate_ecg_signal(sfecg=128, N=30, Anoise=0.005, hrmean=70, sfint=512)\n",
    "reference = np.array(reference)\n",
    "\n",
    "n = min(len(reference), len(signal_col))\n",
    "signal_slice = signal_col[:n]\n",
    "reference_slice = reference[:n]\n",
    "\n",
    "ar = ArtifactRemoval(signal_slice)\n",
    "cleaned_signal = ar.adaptive_filtering(reference_slice, learning_rate=0.01, num_iterations=50)\n",
    "\n",
    "plot_trace(signal_slice, cleaned_signal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Notch Filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import numpy as np\n",
    "from plotly import graph_objects as go\n",
    "import os\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ar = ArtifactRemoval(signal_col)\n",
    "cleaned_signal = ar.notch_filter(freq=5, fs=fs, Q=2)\n",
    "\n",
    "plot_trace(signal_col,cleaned_signal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PCA Artifact Removal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\n",
    "import numpy as np\n",
    "from plotly import graph_objects as go\n",
    "import os\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ar = ArtifactRemoval(signal_col)\n",
    "cleaned_signal = ar.pca_artifact_removal(num_components=1,window_size=5, overlap=1) #QRS T Components\n",
    "\n",
    "plot_trace(signal_col,cleaned_signal)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ICA Artifact Removal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.filtering.artifact_removal import ArtifactRemoval\nimport numpy as np\nfrom plotly import graph_objects as go\nimport os\nfrom vitalDSP.notebooks import load_sample_ecg_small, plot_trace\n\nfs = 128\nsignal_col, date_col = load_sample_ecg_small()\nsignal_col = np.array(signal_col)\n\nar = ArtifactRemoval(signal_col)\ncleaned_signal = ar.ica_artifact_removal(num_components=3)\n\nplot_trace(signal_col,cleaned_signal)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "wearables",
   "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": "3.9.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}