{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "84427819",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-23T11:34:27.597639Z",
     "iopub.status.busy": "2026-02-23T11:34:27.597226Z",
     "iopub.status.idle": "2026-02-23T11:34:44.131586Z",
     "shell.execute_reply": "2026-02-23T11:34:44.130498Z"
    },
    "papermill": {
     "duration": 16.540574,
     "end_time": "2026-02-23T11:34:44.133901",
     "exception": false,
     "start_time": "2026-02-23T11:34:27.593327",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: librosa in /usr/local/lib/python3.12/dist-packages (0.11.0)\r\n",
      "Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.12/dist-packages (from librosa) (3.1.0)\r\n",
      "Requirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (0.60.0)\r\n",
      "Requirement already satisfied: numpy>=1.22.3 in /usr/local/lib/python3.12/dist-packages (from librosa) (2.0.2)\r\n",
      "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.16.3)\r\n",
      "Requirement already satisfied: scikit-learn>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.6.1)\r\n",
      "Requirement already satisfied: joblib>=1.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.5.3)\r\n",
      "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (4.4.2)\r\n",
      "Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.12/dist-packages (from librosa) (0.13.1)\r\n",
      "Requirement already satisfied: pooch>=1.1 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.8.2)\r\n",
      "Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.0.0)\r\n",
      "Requirement already satisfied: typing_extensions>=4.1.1 in /usr/local/lib/python3.12/dist-packages (from librosa) (4.15.0)\r\n",
      "Requirement already satisfied: lazy_loader>=0.1 in /usr/local/lib/python3.12/dist-packages (from librosa) (0.4)\r\n",
      "Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.12/dist-packages (from librosa) (1.1.2)\r\n",
      "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from lazy_loader>=0.1->librosa) (25.0)\r\n",
      "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.51.0->librosa) (0.43.0)\r\n",
      "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from pooch>=1.1->librosa) (4.5.1)\r\n",
      "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.12/dist-packages (from pooch>=1.1->librosa) (2.32.4)\r\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.1.0->librosa) (3.6.0)\r\n",
      "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.12/dist-packages (from soundfile>=0.12.1->librosa) (2.0.0)\r\n",
      "Requirement already satisfied: pycparser in /usr/local/lib/python3.12/dist-packages (from cffi>=1.0->soundfile>=0.12.1->librosa) (2.23)\r\n",
      "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->pooch>=1.1->librosa) (3.4.4)\r\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->pooch>=1.1->librosa) (3.11)\r\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->pooch>=1.1->librosa) (2.5.0)\r\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->pooch>=1.1->librosa) (2026.1.4)\r\n",
      "Requirement already satisfied: soundfile in /usr/local/lib/python3.12/dist-packages (0.13.1)\r\n",
      "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.12/dist-packages (from soundfile) (2.0.0)\r\n",
      "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from soundfile) (2.0.2)\r\n",
      "Requirement already satisfied: pycparser in /usr/local/lib/python3.12/dist-packages (from cffi>=1.0->soundfile) (2.23)\r\n",
      "Collecting noisereduce\r\n",
      "  Downloading noisereduce-3.0.3-py3-none-any.whl.metadata (14 kB)\r\n",
      "Requirement already satisfied: scipy in /usr/local/lib/python3.12/dist-packages (from noisereduce) (1.16.3)\r\n",
      "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (from noisereduce) (3.10.0)\r\n",
      "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from noisereduce) (2.0.2)\r\n",
      "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from noisereduce) (4.67.1)\r\n",
      "Requirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from noisereduce) (1.5.3)\r\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (1.3.3)\r\n",
      "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (0.12.1)\r\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (4.61.1)\r\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (1.4.9)\r\n",
      "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (25.0)\r\n",
      "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (11.3.0)\r\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (3.3.1)\r\n",
      "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib->noisereduce) (2.9.0.post0)\r\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.7->matplotlib->noisereduce) (1.17.0)\r\n",
      "Downloading noisereduce-3.0.3-py3-none-any.whl (22 kB)\r\n",
      "Installing collected packages: noisereduce\r\n",
      "Successfully installed noisereduce-3.0.3\r\n",
      "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.3.3)\r\n",
      "Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.0.2)\r\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\r\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\r\n",
      "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.3)\r\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\r\n"
     ]
    }
   ],
   "source": [
    "!pip install librosa\n",
    "!pip install soundfile\n",
    "!pip install noisereduce\n",
    "!pip install pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8bff4c02",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-23T11:34:44.140482Z",
     "iopub.status.busy": "2026-02-23T11:34:44.139825Z",
     "iopub.status.idle": "2026-02-23T11:34:49.825022Z",
     "shell.execute_reply": "2026-02-23T11:34:49.824211Z"
    },
    "papermill": {
     "duration": 5.690644,
     "end_time": "2026-02-23T11:34:49.826991",
     "exception": false,
     "start_time": "2026-02-23T11:34:44.136347",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "import librosa\n",
    "import soundfile as sf\n",
    "import noisereduce as nr\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4dfbf6ff",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-23T11:34:49.833688Z",
     "iopub.status.busy": "2026-02-23T11:34:49.832979Z",
     "iopub.status.idle": "2026-02-23T11:34:49.841222Z",
     "shell.execute_reply": "2026-02-23T11:34:49.840274Z"
    },
    "papermill": {
     "duration": 0.013487,
     "end_time": "2026-02-23T11:34:49.842894",
     "exception": false,
     "start_time": "2026-02-23T11:34:49.829407",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Load audio\n",
    "def load_audio(file_path, sr=16000):\n",
    "    audio, sample_rate = librosa.load(file_path, sr=sr)\n",
    "    return audio, sample_rate\n",
    "\n",
    "# Bandpass filter for breathing range\n",
    "from scipy.signal import butter, lfilter\n",
    "\n",
    "def butter_bandpass(lowcut, highcut, fs, order=5):\n",
    "    nyq = 0.5 * fs\n",
    "    low = lowcut / nyq\n",
    "    high = highcut / nyq\n",
    "    b, a = butter(order, [low, high], btype='band')\n",
    "    return b, a\n",
    "\n",
    "def bandpass_filter(data, lowcut=100, highcut=2000, fs=16000):\n",
    "    b, a = butter_bandpass(lowcut, highcut, fs)\n",
    "    y = lfilter(b, a, data)\n",
    "    return y\n",
    "\n",
    "# Noise reduction\n",
    "def noise_suppression(audio, sr):\n",
    "    return nr.reduce_noise(y=audio, sr=sr, prop_decrease=1.0)\n",
    "\n",
    "# Full preprocessing pipeline\n",
    "def preprocess_audio(file_path):\n",
    "    audio, sr = load_audio(file_path)\n",
    "    filtered = bandpass_filter(audio, fs=sr)\n",
    "    cleaned = noise_suppression(filtered, sr)\n",
    "    return cleaned, sr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1d0977cb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-02-23T11:34:49.848932Z",
     "iopub.status.busy": "2026-02-23T11:34:49.848226Z",
     "iopub.status.idle": "2026-02-23T11:36:15.739658Z",
     "shell.execute_reply": "2026-02-23T11:36:15.738213Z"
    },
    "papermill": {
     "duration": 85.89757,
     "end_time": "2026-02-23T11:36:15.742632",
     "exception": false,
     "start_time": "2026-02-23T11:34:49.845062",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Preprocessing complete. Audio files zipped at /kaggle/working/cleaned_audio.zip\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "import soundfile as sf\n",
    "from zipfile import ZipFile\n",
    "\n",
    "input_dir = \"/kaggle/input/datasets/liamgraphics/simulated-ward-dataset\"\n",
    "output_dir = \"/kaggle/working/cleaned_audio/\"\n",
    "os.makedirs(output_dir, exist_ok=True)\n",
    "\n",
    "metadata = []\n",
    "\n",
    "for file_name in os.listdir(input_dir):\n",
    "    if file_name.endswith(\".wav\"):\n",
    "        file_path = os.path.join(input_dir, file_name)\n",
    "        cleaned_audio, sr = preprocess_audio(file_path)  # your preprocessing function\n",
    "        \n",
    "        output_path = os.path.join(output_dir, file_name)\n",
    "        sf.write(output_path, cleaned_audio, sr)\n",
    "        \n",
    "        metadata.append({\n",
    "            \"file_name\": file_name,\n",
    "            \"sample_rate\": sr,\n",
    "            \"length_sec\": len(cleaned_audio)/sr\n",
    "        })\n",
    "\n",
    "# Save metadata CSV (optional, outside ZIP)\n",
    "metadata_df = pd.DataFrame(metadata)\n",
    "metadata_csv_path = os.path.join(output_dir, \"metadata.csv\")\n",
    "metadata_df.to_csv(metadata_csv_path, index=False)\n",
    "\n",
    "# Create ZIP file containing only .wav files\n",
    "zip_path = \"/kaggle/working/cleaned_audio.zip\"\n",
    "with ZipFile(zip_path, 'w') as zipf:\n",
    "    for file_name in os.listdir(output_dir):\n",
    "        if file_name.endswith(\".wav\"):  # only include audio files\n",
    "            file_full_path = os.path.join(output_dir, file_name)\n",
    "            zipf.write(file_full_path, arcname=file_name)\n",
    "\n",
    "print(f\"Preprocessing complete. Audio files zipped at {zip_path}\")"
   ]
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "none",
   "dataSources": [
    {
     "databundleVersionId": 15774559,
     "datasetId": 9539684,
     "sourceId": 14909052,
     "sourceType": "datasetVersion"
    }
   ],
   "dockerImageVersionId": 31286,
   "isGpuEnabled": false,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.12"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 112.882623,
   "end_time": "2026-02-23T11:36:17.369657",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2026-02-23T11:34:24.487034",
   "version": "2.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}