{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "cell-0",
   "metadata": {},
   "source": [
    "# Signal Preprocessing\n",
    "\n",
    "This notebook demonstrates noise reduction, baseline correction, bandpass filtering, and respiratory extraction for physiological signals using vitalDSP."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-1",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import plotly.io as pio\n",
    "pio.renderers.default = \"sphinx_gallery\"\n",
    "from plotly import graph_objects as go\n",
    "from vitalDSP.notebooks import load_sample_ecg_small, load_sample_ppg, plot_trace\n",
    "\n",
    "fs = 128\n",
    "signal_col, date_col = load_sample_ecg_small()\n",
    "signal_col = np.array(signal_col)\n",
    "\n",
    "ppg_col, ppg_date = load_sample_ppg()\n",
    "ppg_col = np.array(ppg_col)\n",
    "\n",
    "print(f\"ECG signal: {len(signal_col)} samples at {fs} Hz\")\n",
    "plot_trace(signal_col)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-3",
   "metadata": {},
   "source": [
    "## Wavelet Denoising"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.preprocess.noise_reduction import wavelet_denoising\n",
    "\n",
    "# Soft-threshold wavelet denoising\n",
    "wavelet_denoised = wavelet_denoising(signal_col, wavelet_name='db4', level=4)\n",
    "\n",
    "plot_trace(signal_col, wavelet_denoised)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-5",
   "metadata": {},
   "source": [
    "## Median, Moving Average, and Gaussian Denoising"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.preprocess.noise_reduction import median_denoising, moving_average_denoising, gaussian_denoising\n",
    "\n",
    "median_denoised = median_denoising(signal_col, kernel_size=5)\n",
    "ma_denoised     = moving_average_denoising(signal_col, window_size=5)\n",
    "gauss_denoised  = gaussian_denoising(signal_col, sigma=1.0)\n",
    "\n",
    "fig = go.Figure()\n",
    "fig.add_trace(go.Scatter(y=signal_col[:512], mode='lines', name='Raw ECG', opacity=0.5))\n",
    "fig.add_trace(go.Scatter(y=median_denoised[:512], mode='lines', name='Median Filter'))\n",
    "fig.add_trace(go.Scatter(y=ma_denoised[:512], mode='lines', name='Moving Average'))\n",
    "fig.add_trace(go.Scatter(y=gauss_denoised[:512], mode='lines', name='Gaussian'))\n",
    "fig.update_layout(title='Noise Reduction Comparison', xaxis_title='Sample', yaxis_title='Amplitude')\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-7",
   "metadata": {},
   "source": [
    "## Savitzky-Golay Smoothing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-8",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.preprocess.noise_reduction import savgol_denoising\n",
    "\n",
    "savgol_denoised = savgol_denoising(signal_col, window_length=11, polyorder=3)\n",
    "plot_trace(signal_col, savgol_denoised)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-9",
   "metadata": {},
   "source": [
    "## Full Preprocessing Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-10",
   "metadata": {},
   "outputs": [],
   "source": "from vitalDSP.preprocess.preprocess_operations import preprocess_signal\n\n# Apply bandpass filter + wavelet denoising in one call\npreprocessed = preprocess_signal(\n    signal_col,\n    sampling_rate=fs,\n    filter_type='bandpass',\n    lowcut=0.5,\n    highcut=40.0,\n    order=4,\n    noise_reduction_method='wavelet',\n    wavelet_name='db4',\n    level=3\n)\n\nplot_trace(signal_col, preprocessed)"
  },
  {
   "cell_type": "markdown",
   "id": "cell-11",
   "metadata": {},
   "source": [
    "## Baseline Estimation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-12",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.preprocess.preprocess_operations import estimate_baseline\n",
    "\n",
    "# Estimate slow baseline drift via moving average\n",
    "baseline = estimate_baseline(signal_col, fs=fs, method='moving_average', window_size=64)\n",
    "corrected = signal_col - baseline\n",
    "\n",
    "fig = go.Figure()\n",
    "fig.add_trace(go.Scatter(y=signal_col[:512], mode='lines', name='Raw ECG', opacity=0.5))\n",
    "fig.add_trace(go.Scatter(y=baseline[:512], mode='lines', name='Baseline', line=dict(dash='dash')))\n",
    "fig.add_trace(go.Scatter(y=corrected[:512], mode='lines', name='Baseline Corrected'))\n",
    "fig.update_layout(title='Baseline Estimation and Correction', xaxis_title='Sample', yaxis_title='Amplitude')\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-13",
   "metadata": {},
   "source": [
    "## Respiratory Component Extraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-14",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vitalDSP.preprocess.preprocess_operations import respiratory_filtering\n",
    "\n",
    "# Bandpass filter to isolate the respiratory frequency band (0.1–0.5 Hz)\n",
    "resp_signal = respiratory_filtering(signal_col, sampling_rate=fs, lowcut=0.1, highcut=0.5)\n",
    "\n",
    "t = np.arange(len(signal_col)) / fs\n",
    "fig = go.Figure()\n",
    "fig.add_trace(go.Scatter(x=t, y=signal_col, mode='lines', name='ECG', opacity=0.4))\n",
    "fig.add_trace(go.Scatter(x=t, y=resp_signal, mode='lines', name='Respiratory Component (0.1–0.5 Hz)'))\n",
    "fig.update_layout(\n",
    "    title='Respiratory Component Extraction from ECG',\n",
    "    xaxis_title='Time (s)', yaxis_title='Amplitude'\n",
    ")\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cell-15",
   "metadata": {},
   "source": [
    "## PPG Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cell-16",
   "metadata": {},
   "outputs": [],
   "source": "# Chain denoising and bandpass filtering for PPG\nppg_denoised = wavelet_denoising(ppg_col, wavelet_name='db4', level=3)\nppg_preprocessed = preprocess_signal(\n    ppg_denoised,\n    sampling_rate=fs,\n    filter_type='bandpass',\n    lowcut=0.5,\n    highcut=8.0,\n    order=4,\n    noise_reduction_method='moving_average'\n)\n\nplot_trace(ppg_col, ppg_preprocessed)"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.9.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}