eeg_classifier.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "PLF48faHpeBU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "fe56cdb0-41d8-4456-8bb6-a6b7cdf60bc2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting mne\n",
            "  Downloading mne-1.8.0-py3-none-any.whl.metadata (21 kB)\n",
            "Requirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from mne) (4.4.2)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from mne) (3.1.4)\n",
            "Requirement already satisfied: lazy-loader>=0.3 in /usr/local/lib/python3.10/dist-packages (from mne) (0.4)\n",
            "Requirement already satisfied: matplotlib>=3.6 in /usr/local/lib/python3.10/dist-packages (from mne) (3.7.1)\n",
            "Requirement already satisfied: numpy<3,>=1.23 in /usr/local/lib/python3.10/dist-packages (from mne) (1.26.4)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from mne) (24.1)\n",
            "Requirement already satisfied: pooch>=1.5 in /usr/local/lib/python3.10/dist-packages (from mne) (1.8.2)\n",
            "Requirement already satisfied: scipy>=1.9 in /usr/local/lib/python3.10/dist-packages (from mne) (1.13.1)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from mne) (4.66.5)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (1.3.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (4.54.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (1.4.7)\n",
            "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (10.4.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (3.1.4)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.6->mne) (2.8.2)\n",
            "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.10/dist-packages (from pooch>=1.5->mne) (4.3.6)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from pooch>=1.5->mne) (2.32.3)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->mne) (3.0.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.6->mne) (1.16.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch>=1.5->mne) (3.4.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch>=1.5->mne) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch>=1.5->mne) (2.2.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch>=1.5->mne) (2024.8.30)\n",
            "Downloading mne-1.8.0-py3-none-any.whl (7.4 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.4/7.4 MB\u001b[0m \u001b[31m23.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: mne\n",
            "Successfully installed mne-1.8.0\n"
          ]
        }
      ],
      "source": [
        "!pip install mne"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Install required Python libraries for EEG processing and machine learning\n",
        "!pip install numpy scipy matplotlib latexify-py skfeature-chappers"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "k_fH2i2LmWBk",
        "outputId": "394fd62b-674f-4f87-8058-30f729007948"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.26.4)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.13.1)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (3.7.1)\n",
            "Collecting latexify-py\n",
            "  Downloading latexify_py-0.4.3.post1-py3-none-any.whl.metadata (4.2 kB)\n",
            "Collecting skfeature-chappers\n",
            "  Downloading skfeature_chappers-1.1.0-py3-none-any.whl.metadata (926 bytes)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (1.3.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (4.54.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (1.4.7)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (24.1)\n",
            "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (10.4.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (3.1.4)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (2.8.2)\n",
            "Collecting dill>=0.3.2 (from latexify-py)\n",
            "  Downloading dill-0.3.9-py3-none-any.whl.metadata (10 kB)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from skfeature-chappers) (1.5.2)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from skfeature-chappers) (2.2.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->skfeature-chappers) (2024.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas->skfeature-chappers) (2024.2)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->skfeature-chappers) (1.4.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->skfeature-chappers) (3.5.0)\n",
            "Downloading latexify_py-0.4.3.post1-py3-none-any.whl (38 kB)\n",
            "Downloading skfeature_chappers-1.1.0-py3-none-any.whl (66 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m66.3/66.3 kB\u001b[0m \u001b[31m3.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading dill-0.3.9-py3-none-any.whl (119 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m119.4/119.4 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: dill, latexify-py, skfeature-chappers\n",
            "Successfully installed dill-0.3.9 latexify-py-0.4.3.post1 skfeature-chappers-1.1.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%matplotlib notebook\n",
        "import os  # Built-in Python module, no need to install\n",
        "import mne\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import warnings\n",
        "\n",
        "# Ignore warnings for a cleaner output\n",
        "warnings.filterwarnings(\"ignore\", message=\".*annotation.*\")"
      ],
      "metadata": {
        "id": "oDGssEyanoPK"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FHNLNVriqsMS",
        "outputId": "b263711e-d951-4f80-988d-6fafe2f3ed55"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data\"\n",
        "\n",
        "def data_path(folder_path, data_format=\"gdf\"):\n",
        "    path_files = []  # Store paths of matching files\n",
        "    files = []  # Store file names\n",
        "    folders = []  # Store folder names\n",
        "\n",
        "    # Walk through the directory and collect relevant files/folders\n",
        "    for root, dirnames, filenames in os.walk(folder_path):\n",
        "        for filename in filenames:\n",
        "            if filename.endswith(f\".{data_format}\"):\n",
        "                full_path = os.path.join(root, filename)\n",
        "                path_files.append(full_path)\n",
        "                files.append(filename)\n",
        "        folders.extend(dirnames)\n",
        "\n",
        "    return path_files, files, folders\n",
        "\n",
        "# Get the paths of all GDF files\n",
        "path_files, files, folders = data_path(folder_path, data_format=\"gdf\")\n",
        "\n",
        "# Print the collected file paths\n",
        "print(\"Found files:\", files)\n",
        "print(\"Full paths:\", path_files)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pC-djc6drvYY",
        "outputId": "99b9ca35-e6fc-422c-8423-5335fa4f7a74"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found files: ['Subject4-[2012.04.08-16.06.48].gdf', 'Subject3-[2012.04.07-18.27.18].gdf', 'Subject2-[2012.04.07-19.44.23].gdf', 'Subject3-[2012.04.07-18.45.34].gdf', 'Subject3-[2012.04.07-18.17.50].gdf', 'Subject2-[2012.04.07-19.36.29].gdf', 'Subject2-[2012.04.07-19.57.52].gdf', 'Subject3-[2012.04.07-18.53.10].gdf', 'Subject2-[2012.04.07-19.27.02].gdf', 'Subject4-[2012.04.08-16.27.27].gdf', 'Subject5-[2012.04.09-19.38.11].gdf', 'Subject5-[2012.04.09-19.48.56].gdf', 'Subject5-[2012.04.09-20.02.48].gdf', 'Subject5-[2012.04.09-19.56.38].gdf', 'Subject4-[2012.04.08-16.19.25].gdf', 'Subject4-[2012.04.08-16.35.27].gdf']\n",
            "Full paths: ['/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject4-[2012.04.08-16.06.48].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject3-[2012.04.07-18.27.18].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject2-[2012.04.07-19.44.23].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject3-[2012.04.07-18.45.34].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject3-[2012.04.07-18.17.50].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject2-[2012.04.07-19.36.29].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject2-[2012.04.07-19.57.52].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject3-[2012.04.07-18.53.10].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject2-[2012.04.07-19.27.02].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject4-[2012.04.08-16.27.27].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject5-[2012.04.09-19.38.11].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject5-[2012.04.09-19.48.56].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject5-[2012.04.09-20.02.48].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject5-[2012.04.09-19.56.38].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject4-[2012.04.08-16.19.25].gdf', '/content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject4-[2012.04.08-16.35.27].gdf']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Ensure the path_files variable contains GDF file paths\n",
        "print(f\"Using GDF file: {path_files[0]}\")\n",
        "\n",
        "# Read the GDF file into a raw MNE object\n",
        "raw = mne.io.read_raw_gdf(path_files[0], verbose=0)\n",
        "\n",
        "# Extract the channel names from the raw data\n",
        "channels_name = raw.ch_names\n",
        "\n",
        "# Get the EEG data and transpose it to have channels as rows and samples as columns\n",
        "data = 1e6 * raw.get_data().T  # Convert to microvolts if necessary\n",
        "\n",
        "# Get the sampling frequency of the EEG data\n",
        "fs = raw.info['sfreq']\n",
        "\n",
        "# Extract labels from annotations\n",
        "labels = raw.annotations.description\n",
        "\n",
        "# Get the events and their corresponding indices\n",
        "events, event_ind = mne.events_from_annotations(raw, verbose=0)\n",
        "\n",
        "# Print all the relevant information\n",
        "print(f\"Data: {data.shape} \\n\")\n",
        "print(f\"Channels Name: {channels_name} \\n\")\n",
        "print(f\"Labels: {labels} \\n\")\n",
        "print(f\"Events: {events} \\n\")\n",
        "print(f\"Event Indices: {event_ind} \\n\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ld7wRtp1tgL5",
        "outputId": "35fab330-dc0d-4969-a9d0-bde5701b2ef2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Using GDF file: /content/drive/MyDrive/SSVEP-based-EEG-signal-processing-main/SSVEP-based-EEG-signal-processing-main/Data/Subject4-[2012.04.08-16.06.48].gdf\n",
            "Data: (127200, 8) \n",
            "\n",
            "Channels Name: ['Oz', 'O1', 'O2', 'PO3', 'POz', 'PO7', 'PO8', 'PO4'] \n",
            "\n",
            "Labels: ['32769' '33024' '32779' '32780' '33026' '32779' '32780' '33027' '32779'\n",
            " '32780' '33025' '32779' '32780' '33026' '32779' '32780' '33025' '32779'\n",
            " '32780' '33024' '32779' '32780' '33027' '32779' '32780' '33025' '32779'\n",
            " '32780' '33026' '32779' '32780' '33027' '32779' '32780' '33024' '32779'\n",
            " '32780' '33026' '32779' '32780' '33024' '32779' '32780' '33027' '32779'\n",
            " '32780' '33025' '32779' '32780' '33024' '32779' '32780' '33027' '32779'\n",
            " '32780' '33025' '32779' '32780' '33026' '32779' '32780' '33027' '32779'\n",
            " '32780' '33024' '32779' '32780' '33025' '32779' '32780' '33026' '32779'\n",
            " '32780' '33025' '32779' '32780' '33027' '32779' '32780' '33026' '32779'\n",
            " '32780' '33024' '32779' '32780' '33027' '32779' '32780' '33026' '32779'\n",
            " '32780' '33024' '32779' '32780' '33025' '32779' '32780' '33024' '32779'\n",
            " '32780' '33026' '32779' '32780' '33027' '32779' '32780' '33025' '32779'\n",
            " '32780' '33024' '32779' '32780' '33026' '32779' '32780' '33027' '32779'\n",
            " '32780' '33025' '32779' '32780' '32770'] \n",
            "\n",
            "Events: [[ 44752      0      1]\n",
            " [ 45264      0      5]\n",
            " [ 45520      0      3]\n",
            " [ 46800      0      4]\n",
            " [ 47312      0      7]\n",
            " [ 47568      0      3]\n",
            " [ 48848      0      4]\n",
            " [ 49360      0      8]\n",
            " [ 49616      0      3]\n",
            " [ 50896      0      4]\n",
            " [ 51408      0      6]\n",
            " [ 51664      0      3]\n",
            " [ 52944      0      4]\n",
            " [ 53456      0      7]\n",
            " [ 53712      0      3]\n",
            " [ 54992      0      4]\n",
            " [ 55504      0      6]\n",
            " [ 55760      0      3]\n",
            " [ 57040      0      4]\n",
            " [ 57552      0      5]\n",
            " [ 57808      0      3]\n",
            " [ 59088      0      4]\n",
            " [ 59600      0      8]\n",
            " [ 59856      0      3]\n",
            " [ 61136      0      4]\n",
            " [ 61648      0      6]\n",
            " [ 61904      0      3]\n",
            " [ 63184      0      4]\n",
            " [ 63696      0      7]\n",
            " [ 63952      0      3]\n",
            " [ 65232      0      4]\n",
            " [ 65744      0      8]\n",
            " [ 66000      0      3]\n",
            " [ 67280      0      4]\n",
            " [ 67792      0      5]\n",
            " [ 68048      0      3]\n",
            " [ 69328      0      4]\n",
            " [ 69840      0      7]\n",
            " [ 70096      0      3]\n",
            " [ 71376      0      4]\n",
            " [ 71888      0      5]\n",
            " [ 72144      0      3]\n",
            " [ 73424      0      4]\n",
            " [ 73936      0      8]\n",
            " [ 74192      0      3]\n",
            " [ 75472      0      4]\n",
            " [ 75984      0      6]\n",
            " [ 76240      0      3]\n",
            " [ 77520      0      4]\n",
            " [ 78032      0      5]\n",
            " [ 78288      0      3]\n",
            " [ 79568      0      4]\n",
            " [ 80080      0      8]\n",
            " [ 80336      0      3]\n",
            " [ 81616      0      4]\n",
            " [ 82128      0      6]\n",
            " [ 82384      0      3]\n",
            " [ 83664      0      4]\n",
            " [ 84176      0      7]\n",
            " [ 84432      0      3]\n",
            " [ 85712      0      4]\n",
            " [ 86224      0      8]\n",
            " [ 86480      0      3]\n",
            " [ 87760      0      4]\n",
            " [ 88272      0      5]\n",
            " [ 88528      0      3]\n",
            " [ 89808      0      4]\n",
            " [ 90320      0      6]\n",
            " [ 90576      0      3]\n",
            " [ 91856      0      4]\n",
            " [ 92368      0      7]\n",
            " [ 92624      0      3]\n",
            " [ 93904      0      4]\n",
            " [ 94416      0      6]\n",
            " [ 94672      0      3]\n",
            " [ 95952      0      4]\n",
            " [ 96464      0      8]\n",
            " [ 96720      0      3]\n",
            " [ 98000      0      4]\n",
            " [ 98512      0      7]\n",
            " [ 98768      0      3]\n",
            " [100048      0      4]\n",
            " [100560      0      5]\n",
            " [100816      0      3]\n",
            " [102096      0      4]\n",
            " [102608      0      8]\n",
            " [102864      0      3]\n",
            " [104144      0      4]\n",
            " [104656      0      7]\n",
            " [104912      0      3]\n",
            " [106192      0      4]\n",
            " [106704      0      5]\n",
            " [106960      0      3]\n",
            " [108240      0      4]\n",
            " [108752      0      6]\n",
            " [109008      0      3]\n",
            " [110288      0      4]\n",
            " [110800      0      5]\n",
            " [111056      0      3]\n",
            " [112336      0      4]\n",
            " [112848      0      7]\n",
            " [113104      0      3]\n",
            " [114384      0      4]\n",
            " [114896      0      8]\n",
            " [115152      0      3]\n",
            " [116432      0      4]\n",
            " [116944      0      6]\n",
            " [117200      0      3]\n",
            " [118480      0      4]\n",
            " [118992      0      5]\n",
            " [119248      0      3]\n",
            " [120528      0      4]\n",
            " [121040      0      7]\n",
            " [121296      0      3]\n",
            " [122576      0      4]\n",
            " [123088      0      8]\n",
            " [123344      0      3]\n",
            " [124624      0      4]\n",
            " [125136      0      6]\n",
            " [125392      0      3]\n",
            " [126672      0      4]\n",
            " [127184      0      2]] \n",
            "\n",
            "Event Indices: {'32769': 1, '32770': 2, '32779': 3, '32780': 4, '33024': 5, '33025': 6, '33026': 7, '33027': 8} \n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Data Splitting"
      ],
      "metadata": {
        "id": "f0ts4xdqwVqr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Define the duration of each trial in seconds\n",
        "time_trial = 5\n",
        "\n",
        "# Initialize lists to store trial data for each label\n",
        "data1, data2, data3 = [], [], []\n",
        "\n",
        "# Define the labels for each stimulation frequency (as strings)\n",
        "lab = ['33025', '33026', '33027']\n",
        "\n",
        "# Create a list of the initialized data arrays to manage them easily\n",
        "data_list = [data1, data2, data3]\n",
        "\n",
        "# Loop through all GDF files in the given path\n",
        "for i in range(len(path_files)):\n",
        "    # Read the GDF file into an MNE raw object\n",
        "    raw = mne.io.read_raw_gdf(path_files[i], verbose=0)\n",
        "\n",
        "    # Get sampling frequency and channel names\n",
        "    fs = raw.info['sfreq']\n",
        "    channels_name = raw.ch_names\n",
        "\n",
        "    # Calculate the number of samples per trial\n",
        "    duration_trial = int(fs * time_trial)\n",
        "\n",
        "    # Extract EEG data and transpose (channels as rows, samples as columns)\n",
        "    data = 1e6 * raw.get_data().T  # Convert to microvolts if needed\n",
        "\n",
        "    # Extract labels from annotations\n",
        "    labels = np.array(raw.annotations.description)\n",
        "\n",
        "    # Extract events and their start times\n",
        "    events, _ = mne.events_from_annotations(raw, verbose=0)\n",
        "    time_start_trial = events[:, 0]  # Start times of trials\n",
        "\n",
        "    # Loop over the defined labels\n",
        "    for j, val in enumerate(lab):\n",
        "        # Find trials with the current label\n",
        "        num_trials = np.where(labels == val)[0]\n",
        "\n",
        "        # Initialize array to store data for this label\n",
        "        data_trial = np.zeros((duration_trial, len(channels_name), len(num_trials)))\n",
        "\n",
        "        # Extract data for each trial of the current label\n",
        "        for ind, trial_index in enumerate(num_trials):\n",
        "            start = time_start_trial[trial_index]\n",
        "            data_trial[:, :, ind] = data[start:start + duration_trial, :]\n",
        "\n",
        "        # Store the extracted trial data in the appropriate list\n",
        "        data_list[j].append(data_trial)\n",
        "\n",
        "# Concatenate all the data arrays along the third axis (trials)\n",
        "data1 = np.concatenate(data1, axis=2)\n",
        "data2 = np.concatenate(data2, axis=2)\n",
        "data3 = np.concatenate(data3, axis=2)\n",
        "\n",
        "# Print the shapes of the final concatenated data arrays\n",
        "print(f\"data1.shape: {data1.shape} \\ndata2.shape: {data2.shape} \\ndata3.shape: {data3.shape}\")"
      ],
      "metadata": {
        "id": "Rb0zQAVTg3kO",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "687e807d-209a-416b-ec38-93e2fb78e9c5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "data1.shape: (1280, 8, 160) \n",
            "data2.shape: (1280, 8, 160) \n",
            "data3.shape: (1280, 8, 160)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Filtering/ feature Extraction / Preprocessing"
      ],
      "metadata": {
        "id": "IpEf3ezRFFDB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Import required libraries\n",
        "import numpy as np\n",
        "import mne\n",
        "import warnings\n",
        "\n",
        "# Import functions from the .py files in the Functions folder\n",
        "from Filtering import filtering\n",
        "\n",
        "# Step 4: Define your parameters for filtering\n",
        "trial = 8            # Define trial number (trial 1 in Python index starts from 0)\n",
        "order = 3            # Define filter order\n",
        "f_low = 0.05         # Define lower cutoff frequency for the bandpass filter (Hz)\n",
        "f_high = 100         # Define upper cutoff frequency for the bandpass filter (Hz)\n",
        "notch_freq = 50      # Define frequency to be removed from the signal for notch filter (Hz)\n",
        "quality_factor = 20  # Define quality factor for the notch filter\n",
        "notch_filter = \"on\"  # on or off\n",
        "filter_active = \"on\" # on or off\n",
        "design_method = \"IIR\" # IIR or FIR\n",
        "type_filter = \"bandpass\"  # low, high, bandpass, or bandstop\n",
        "freq_stim = 13       # Define stimulation frequency\n",
        "\n",
        "# Step 5: Apply bandpass filtering to the EEG data\n",
        "filtered_data = filtering(data1, f_low, f_high, order, fs, notch_freq, quality_factor,\n",
        "                          filter_active, notch_filter, type_filter, design_method)\n",
        "\n",
        "# Print the shape of the filtered data to verify\n",
        "print(f\"Filtered data shape: {filtered_data.shape}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qmB7YnMGCI2l",
        "outputId": "5b874d39-000e-4c61-c710-b6845ba414dc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Filtered data shape: (1280, 8, 160)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "CAR Filter (Common average reference)"
      ],
      "metadata": {
        "id": "R7M3aFA-Wq3R"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Import the CAR filter function\n",
        "from Common_average_reference import car\n",
        "\n",
        "# Step 3: Apply CAR filter to the data\n",
        "# filtered_data shape: (1280, 8, 160)\n",
        "data_car = car(filtered_data, reference_channel=None)  # Use all channels for average reference\n",
        "\n",
        "# Step 4: Verify the shape of CAR-filtered data\n",
        "print(f\"CAR-filtered data shape: {data_car.shape}\")\n",
        "\n",
        "# Step 5: Extract the trial-specific data if needed\n",
        "trial = 0  # Define trial number (0-indexed)\n",
        "trial_data_car = data_car[:, :, trial]  # Extract data for the selected trial\n",
        "\n",
        "# Step 6: Verify the trial data shape\n",
        "print(f\"CAR-filtered data for Trial {trial + 1}: {trial_data_car.shape}\")"
      ],
      "metadata": {
        "id": "pH9pTa0ZCIpq",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "64346571-e7d1-4720-af75-cad5143d7fae"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CAR-filtered data shape: (1280, 8, 160)\n",
            "CAR-filtered data for Trial 1: (1280, 8)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "FFT (Fast Fourier Transform)"
      ],
      "metadata": {
        "id": "GwV4cMkr1eSU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from FFT import perform_fft, extract_signal\n",
        "# Define parameters\n",
        "trial = 0          # Trial number (1st trial = index 0)\n",
        "channel = 6        # Channel number (7th channel = index 6)\n",
        "fs = 256           # Sampling frequency (example value)\n",
        "\n",
        "# Extract the signal for the given trial and channel\n",
        "raw_signal, filtered_signal = extract_signal(data1, filtered_data, channel, trial)\n",
        "\n",
        "# Perform FFT on the extracted signals\n",
        "signal, filtered_signal, x_fft, x_filter_fft, f = perform_fft(raw_signal, filtered_signal, fs)\n",
        "\n",
        "# Print the frequency components and their magnitudes\n",
        "print(\"Frequencies:\", f)\n",
        "print(\"Raw FFT Magnitudes:\", np.abs(x_fft))\n",
        "print(\"Filtered FFT Magnitudes:\", np.abs(x_filter_fft))"
      ],
      "metadata": {
        "id": "d8EFWjHfOCzN",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f353625c-98c7-4bce-87f5-e10b5d459db1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Frequencies: [  0.    0.2   0.4   0.6   0.8   1.    1.2   1.4   1.6   1.8   2.    2.2\n",
            "   2.4   2.6   2.8   3.    3.2   3.4   3.6   3.8   4.    4.2   4.4   4.6\n",
            "   4.8   5.    5.2   5.4   5.6   5.8   6.    6.2   6.4   6.6   6.8   7.\n",
            "   7.2   7.4   7.6   7.8   8.    8.2   8.4   8.6   8.8   9.    9.2   9.4\n",
            "   9.6   9.8  10.   10.2  10.4  10.6  10.8  11.   11.2  11.4  11.6  11.8\n",
            "  12.   12.2  12.4  12.6  12.8  13.   13.2  13.4  13.6  13.8  14.   14.2\n",
            "  14.4  14.6  14.8  15.   15.2  15.4  15.6  15.8  16.   16.2  16.4  16.6\n",
            "  16.8  17.   17.2  17.4  17.6  17.8  18.   18.2  18.4  18.6  18.8  19.\n",
            "  19.2  19.4  19.6  19.8  20.   20.2  20.4  20.6  20.8  21.   21.2  21.4\n",
            "  21.6  21.8  22.   22.2  22.4  22.6  22.8  23.   23.2  23.4  23.6  23.8\n",
            "  24.   24.2  24.4  24.6  24.8  25.   25.2  25.4  25.6  25.8  26.   26.2\n",
            "  26.4  26.6  26.8  27.   27.2  27.4  27.6  27.8  28.   28.2  28.4  28.6\n",
            "  28.8  29.   29.2  29.4  29.6  29.8  30.   30.2  30.4  30.6  30.8  31.\n",
            "  31.2  31.4  31.6  31.8  32.   32.2  32.4  32.6  32.8  33.   33.2  33.4\n",
            "  33.6  33.8  34.   34.2  34.4  34.6  34.8  35.   35.2  35.4  35.6  35.8\n",
            "  36.   36.2  36.4  36.6  36.8  37.   37.2  37.4  37.6  37.8  38.   38.2\n",
            "  38.4  38.6  38.8  39.   39.2  39.4  39.6  39.8  40.   40.2  40.4  40.6\n",
            "  40.8  41.   41.2  41.4  41.6  41.8  42.   42.2  42.4  42.6  42.8  43.\n",
            "  43.2  43.4  43.6  43.8  44.   44.2  44.4  44.6  44.8  45.   45.2  45.4\n",
            "  45.6  45.8  46.   46.2  46.4  46.6  46.8  47.   47.2  47.4  47.6  47.8\n",
            "  48.   48.2  48.4  48.6  48.8  49.   49.2  49.4  49.6  49.8  50.   50.2\n",
            "  50.4  50.6  50.8  51.   51.2  51.4  51.6  51.8  52.   52.2  52.4  52.6\n",
            "  52.8  53.   53.2  53.4  53.6  53.8  54.   54.2  54.4  54.6  54.8  55.\n",
            "  55.2  55.4  55.6  55.8  56.   56.2  56.4  56.6  56.8  57.   57.2  57.4\n",
            "  57.6  57.8  58.   58.2  58.4  58.6  58.8  59.   59.2  59.4  59.6  59.8\n",
            "  60.   60.2  60.4  60.6  60.8  61.   61.2  61.4  61.6  61.8  62.   62.2\n",
            "  62.4  62.6  62.8  63.   63.2  63.4  63.6  63.8  64.   64.2  64.4  64.6\n",
            "  64.8  65.   65.2  65.4  65.6  65.8  66.   66.2  66.4  66.6  66.8  67.\n",
            "  67.2  67.4  67.6  67.8  68.   68.2  68.4  68.6  68.8  69.   69.2  69.4\n",
            "  69.6  69.8  70.   70.2  70.4  70.6  70.8  71.   71.2  71.4  71.6  71.8\n",
            "  72.   72.2  72.4  72.6  72.8  73.   73.2  73.4  73.6  73.8  74.   74.2\n",
            "  74.4  74.6  74.8  75.   75.2  75.4  75.6  75.8  76.   76.2  76.4  76.6\n",
            "  76.8  77.   77.2  77.4  77.6  77.8  78.   78.2  78.4  78.6  78.8  79.\n",
            "  79.2  79.4  79.6  79.8  80.   80.2  80.4  80.6  80.8  81.   81.2  81.4\n",
            "  81.6  81.8  82.   82.2  82.4  82.6  82.8  83.   83.2  83.4  83.6  83.8\n",
            "  84.   84.2  84.4  84.6  84.8  85.   85.2  85.4  85.6  85.8  86.   86.2\n",
            "  86.4  86.6  86.8  87.   87.2  87.4  87.6  87.8  88.   88.2  88.4  88.6\n",
            "  88.8  89.   89.2  89.4  89.6  89.8  90.   90.2  90.4  90.6  90.8  91.\n",
            "  91.2  91.4  91.6  91.8  92.   92.2  92.4  92.6  92.8  93.   93.2  93.4\n",
            "  93.6  93.8  94.   94.2  94.4  94.6  94.8  95.   95.2  95.4  95.6  95.8\n",
            "  96.   96.2  96.4  96.6  96.8  97.   97.2  97.4  97.6  97.8  98.   98.2\n",
            "  98.4  98.6  98.8  99.   99.2  99.4  99.6  99.8 100.  100.2 100.4 100.6\n",
            " 100.8 101.  101.2 101.4 101.6 101.8 102.  102.2 102.4 102.6 102.8 103.\n",
            " 103.2 103.4 103.6 103.8 104.  104.2 104.4 104.6 104.8 105.  105.2 105.4\n",
            " 105.6 105.8 106.  106.2 106.4 106.6 106.8 107.  107.2 107.4 107.6 107.8\n",
            " 108.  108.2 108.4 108.6 108.8 109.  109.2 109.4 109.6 109.8 110.  110.2\n",
            " 110.4 110.6 110.8 111.  111.2 111.4 111.6 111.8 112.  112.2 112.4 112.6\n",
            " 112.8 113.  113.2 113.4 113.6 113.8 114.  114.2 114.4 114.6 114.8 115.\n",
            " 115.2 115.4 115.6 115.8 116.  116.2 116.4 116.6 116.8 117.  117.2 117.4\n",
            " 117.6 117.8 118.  118.2 118.4 118.6 118.8 119.  119.2 119.4 119.6 119.8\n",
            " 120.  120.2 120.4 120.6 120.8 121.  121.2 121.4 121.6 121.8 122.  122.2\n",
            " 122.4 122.6 122.8 123.  123.2 123.4 123.6 123.8 124.  124.2 124.4 124.6\n",
            " 124.8 125.  125.2 125.4 125.6 125.8 126.  126.2 126.4 126.6 126.8 127.\n",
            " 127.2 127.4 127.6 127.8 128. ]\n",
            "Raw FFT Magnitudes: [1.56433550e+01 2.17128047e+00 2.12359660e+00 3.09789305e+00\n",
            " 3.86445728e-01 1.82312763e+00 1.82992377e+00 8.06454542e-01\n",
            " 1.42688344e+00 1.27415412e+00 1.14040254e+00 1.62418772e+00\n",
            " 4.14310000e-01 1.13268541e+00 7.49438170e-01 1.15169938e+00\n",
            " 2.72044249e-01 2.69262115e-01 6.65963536e-01 9.64210227e-01\n",
            " 7.95948231e-01 1.10083081e+00 2.94768568e-01 7.44000876e-01\n",
            " 4.53831375e-01 3.34236421e-01 3.22007785e-01 3.93744821e-01\n",
            " 2.76920224e-01 1.65501283e-01 1.96276549e-01 1.62551088e-01\n",
            " 5.65945623e-01 5.45850694e-01 3.02985984e-01 2.67715323e-01\n",
            " 6.18197351e-01 3.73715519e-01 1.41845068e-01 1.91164985e-01\n",
            " 8.24253751e-02 2.11188764e-01 2.62351450e-01 1.98560359e-01\n",
            " 2.96683994e-01 2.51473194e-01 6.89943565e-02 4.88870448e-01\n",
            " 2.23766134e-01 1.08135760e-01 2.82596446e-01 1.96307131e-01\n",
            " 2.08769252e-01 1.22993223e-01 2.80711700e-01 2.65659428e-01\n",
            " 2.07991181e-01 1.79638299e-01 3.13744589e-01 3.62318463e-01\n",
            " 3.71736528e-01 1.94169098e-01 3.69089379e-01 3.63757793e-01\n",
            " 2.50567442e-01 6.35319371e-01 2.01951072e-01 2.42839138e-01\n",
            " 2.86491525e-01 4.04745761e-01 1.16310050e-01 2.93499525e-01\n",
            " 2.55681305e-01 3.72993402e-01 2.02402675e-01 1.87104063e-01\n",
            " 1.86968881e-01 3.01311818e-01 1.63388683e-01 7.00099260e-02\n",
            " 9.28461973e-02 5.21705722e-01 5.66305905e-01 5.47530892e-01\n",
            " 3.83591753e-01 4.96642539e-01 4.84244279e-01 2.98158786e-01\n",
            " 2.46736393e-01 5.39009945e-02 1.59953994e-01 1.18129300e-01\n",
            " 3.54482569e-01 1.04023737e-01 9.41185239e-02 1.10925005e-01\n",
            " 2.93625948e-01 8.06789679e-02 9.94714383e-02 2.65579606e-01\n",
            " 1.44181155e-01 2.14017823e-01 2.18748646e-01 1.97434010e-01\n",
            " 2.09687777e-01 4.11413987e-01 1.17441121e-01 2.65001629e-01\n",
            " 2.06274938e-01 3.31311915e-01 4.59489618e-02 1.16271285e-01\n",
            " 2.00528343e-02 1.75049866e-01 2.33204331e-01 9.20400837e-02\n",
            " 1.30435123e-01 6.99372127e-02 1.71023473e-01 8.76854460e-02\n",
            " 5.46233674e-02 2.31683204e-01 1.12461824e-01 7.36528055e-02\n",
            " 1.94832833e-01 1.73560058e-01 2.84085756e-02 2.55199550e-01\n",
            " 6.00110676e-02 3.08884819e-01 6.73656669e-02 1.31511866e-01\n",
            " 1.42246489e-01 9.67755846e-02 8.94885956e-02 6.25904226e-02\n",
            " 1.97441755e-01 1.72128607e-01 1.35886241e-01 1.28183472e-01\n",
            " 2.51356372e-01 2.01619135e-01 2.08386427e-01 1.98987001e-02\n",
            " 1.19213469e-01 3.32482168e-01 2.17957128e-01 2.19805907e-01\n",
            " 2.65599897e-01 1.81361047e-01 2.68143349e-01 6.20283771e-02\n",
            " 1.42894878e-01 1.28588666e-01 1.64972703e-01 2.06503829e-01\n",
            " 1.38751871e-01 5.67867448e-02 1.83166894e-01 1.23415308e-01\n",
            " 3.37693882e-01 1.30873900e-01 9.45242961e-02 1.32916467e-01\n",
            " 1.07791953e-01 1.05004335e-01 3.48191392e-01 2.15266509e-01\n",
            " 1.04581624e-01 2.73552978e-01 1.93516707e-01 1.84363218e-01\n",
            " 9.47873527e-02 1.42206132e-01 1.65477038e-01 8.28879820e-02\n",
            " 1.91134644e-01 8.92355556e-02 1.75310306e-02 6.40638701e-02\n",
            " 2.62301040e-01 4.91931032e-02 2.66035999e-01 1.50001377e-02\n",
            " 1.18906791e-01 2.24045618e-01 2.79674644e-01 4.10277480e-01\n",
            " 1.98581931e-01 2.20858615e-01 1.29752084e-01 1.29158588e-01\n",
            " 1.73342722e-01 2.62349529e-01 1.58355931e-01 1.70342187e-01\n",
            " 1.48191756e-01 2.48990032e-01 1.45044438e-01 1.17811525e-01\n",
            " 1.77062277e-01 1.39336197e-01 2.10536811e-01 9.14578222e-02\n",
            " 1.43259005e-01 1.91462174e-01 9.70281962e-02 2.41135134e-01\n",
            " 9.56308291e-02 5.24515476e-02 2.34310937e-01 2.09782288e-01\n",
            " 1.01157603e-01 1.34450067e-01 1.41108107e-01 4.24624336e-02\n",
            " 5.01125749e-02 1.23849103e-01 1.70637503e-01 3.98624828e-01\n",
            " 1.57461668e-01 1.81289471e-01 9.96361477e-02 1.74457580e-01\n",
            " 3.34088723e-02 4.75950382e-02 1.39694872e-01 4.75275072e-01\n",
            " 9.20059607e-02 2.22833621e-01 1.83228102e-01 1.18380466e-01\n",
            " 2.50239424e-01 2.21200367e-01 1.31833314e-01 2.36119104e-01\n",
            " 1.18936941e-01 3.34267392e-01 9.98253753e-02 9.04556409e-02\n",
            " 2.37537160e-01 1.72404982e-01 1.73113715e-01 2.48914902e-01\n",
            " 9.18948661e-02 2.21636270e-01 9.40077242e-03 1.29818255e-01\n",
            " 1.27435840e-01 2.64136715e-01 2.28237652e+00 2.19225041e-01\n",
            " 1.24695915e-01 1.44352735e-01 2.94561807e-01 4.57282128e-02\n",
            " 6.10974447e-02 1.86480029e-01 1.35773076e-01 1.55534611e-01\n",
            " 6.85190750e-02 2.66872066e-02 1.27186793e-01 1.55776073e-01\n",
            " 8.91385143e-02 2.44373270e-01 9.24231371e-02 1.43251250e-01\n",
            " 1.60267322e-01 1.59113003e-01 9.42338972e-02 1.02925314e-01\n",
            " 1.05306669e-01 8.82653751e-02 1.35836044e-01 8.25950083e-02\n",
            " 5.48486483e-02 1.18369147e-01 1.30242811e-01 7.42383452e-02\n",
            " 2.97544483e-01 6.12779656e-02 9.49691343e-02 4.42111660e-02\n",
            " 2.40117115e-02 1.04607584e-01 2.33813067e-02 2.09000279e-01\n",
            " 3.28679765e-02 1.83750333e-01 7.64774082e-02 3.04403785e-01\n",
            " 1.34788108e-01 1.14963438e-01 1.42568031e-01 4.98489671e-02\n",
            " 6.54819581e-02 1.88878297e-01 8.29600924e-02 1.54579387e-01\n",
            " 8.29192248e-02 1.36591584e-01 1.46326400e-01 1.65956760e-01\n",
            " 2.41734332e-01 9.67822850e-02 1.44714302e-01 7.21677165e-02\n",
            " 6.55750350e-02 3.15091496e-01 2.39240599e-01 1.18303152e-01\n",
            " 1.70377626e-01 7.35484089e-02 1.23104247e-01 1.43017664e-01\n",
            " 1.33698888e-01 1.34028748e-01 1.37533734e-01 7.02546279e-02\n",
            " 6.30717349e-01 5.11935496e-02 9.60323531e-02 1.83632560e-01\n",
            " 1.10342421e-01 3.78967230e-01 8.40660508e-02 6.35917375e-02\n",
            " 2.73099672e-01 4.37092214e-02 1.74700974e-01 2.38729767e-01\n",
            " 1.36336601e-01 1.46060887e-01 1.54990872e-01 8.97918688e-02\n",
            " 1.39757422e-01 2.43717718e-01 8.84593215e-02 1.24051334e-01\n",
            " 8.31898093e-02 2.50608541e-01 1.18224677e-01 1.56762348e-01\n",
            " 2.57845998e-01 8.77739384e-02 1.67772628e-01 1.45859109e-01\n",
            " 1.70402260e-01 2.17725855e-01 2.02392083e-01 1.23143756e-01\n",
            " 5.11497380e-02 5.34098181e-02 1.58055488e-01 1.50619117e-01\n",
            " 1.31191292e-01 1.62271289e-01 1.89678817e-01 7.47265444e-02\n",
            " 5.36396636e-02 1.06409147e-01 1.84982434e-01 1.50628520e-01\n",
            " 8.31497082e-02 1.13532529e-01 3.67778785e-02 1.49756009e-02\n",
            " 5.97881541e-02 9.60011139e-02 2.09173367e-01 3.54066047e-02\n",
            " 1.86371504e-01 9.59690747e-02 7.68603475e-02 2.66562662e-02\n",
            " 6.97538066e-02 1.96489881e-01 7.58970434e-02 1.19759214e-01\n",
            " 6.57173034e-02 8.08965528e-02 7.12858408e-02 9.64647268e-02\n",
            " 1.28670053e-01 6.15013853e-02 2.75908268e-01 8.95625149e-02\n",
            " 2.06731988e-01 1.30090518e-01 2.38264758e-01 2.70410540e-02\n",
            " 4.56671788e-02 1.42802829e-01 7.76791290e-02 2.86910808e-02\n",
            " 1.51222099e-01 1.50270773e-01 1.29100448e-01 9.77742786e-02\n",
            " 1.14301467e-01 9.30900837e-02 4.67507475e-02 2.03976705e-01\n",
            " 7.93012655e-02 8.85890983e-02 1.35608326e-01 2.36838670e-02\n",
            " 1.57014082e-01 2.71394742e-02 1.93139437e-01 4.29921292e-02\n",
            " 9.60788075e-02 1.19373887e-01 9.79982201e-02 2.02686305e-01\n",
            " 5.36740202e-02 1.06483398e-01 1.74491570e-01 1.74829551e-01\n",
            " 1.19110640e-01 1.76500563e-01 7.05077342e-02 1.68372186e-01\n",
            " 3.79731205e-02 3.07228779e-02 2.52278412e-01 1.00755077e-01\n",
            " 2.05848135e-01 3.99349175e-02 8.71029252e-02 4.11464497e-02\n",
            " 1.01551241e-01 2.54971622e-02 2.23204934e-01 7.78931087e-02\n",
            " 6.95834436e-02 1.70609897e-01 1.05898576e-01 6.23635083e-02\n",
            " 1.01427825e-01 9.00245897e-02 1.42885289e-01 8.71875345e-02\n",
            " 9.25720032e-02 7.68702244e-02 1.86769990e-02 9.47603697e-02\n",
            " 1.34488709e-01 1.78958238e-02 1.69413311e-01 5.51092923e-02\n",
            " 8.37532056e-02 1.00204493e-01 9.34161885e-02 1.86886480e-01\n",
            " 7.85569172e-02 1.00227398e-02 8.97633789e-02 1.76853122e-01\n",
            " 1.07612128e-01 1.27075114e-01 1.15723850e-01 1.12965169e-01\n",
            " 4.53943840e-02 1.34323249e-01 1.03971473e-01 7.15044364e-02\n",
            " 3.00310454e-02 1.21929779e-01 2.26605528e-02 8.61460137e-02\n",
            " 1.29232473e-01 5.00470583e-02 3.45677446e-02 8.97113758e-02\n",
            " 4.72290670e-02 6.75709026e-02 7.02058889e-02 1.65025191e-01\n",
            " 1.80940014e-01 6.00615695e-02 4.78558451e-02 1.24769726e-01\n",
            " 9.50271364e-02 3.38960739e-02 8.10263332e-02 8.76299925e-02\n",
            " 7.63817345e-02 1.08624671e-01 6.06367947e-02 2.50273583e-02\n",
            " 5.38498737e-02 1.35240338e-01 1.32402206e-02 8.39476065e-02\n",
            " 3.37073315e-02 7.70655313e-02 1.91056100e-01 1.49254307e-01\n",
            " 1.16050863e-01 4.56654293e-02 1.21179118e-01 1.38611984e-01\n",
            " 1.44949781e-01 9.08788667e-02 1.18779041e-01 4.43948629e-02\n",
            " 9.70401515e-03 1.61040040e-01 5.72884234e-02 7.30661890e-02\n",
            " 6.51208463e-02 8.09524666e-02 5.54567039e-02 3.80274245e-02\n",
            " 1.25578724e-01 1.56543747e-01 1.43793591e-01 1.66709143e-01\n",
            " 7.11478676e-02 1.08436969e-01 8.55490961e-02 1.58412077e-01\n",
            " 5.70457262e-02 1.36765507e-01 1.35980249e-01 3.44703114e-02\n",
            " 1.36964626e-01 1.24378529e-01 2.98239872e-01 5.88657087e-02\n",
            " 1.56132161e-01 5.57073879e-02 4.86780859e-02 2.51737795e-02\n",
            " 1.46358655e-01 2.57179568e-02 4.22922120e-02 5.71597564e-02\n",
            " 8.83158735e-02 7.53495786e-02 1.99703349e-01 9.90301477e-02\n",
            " 1.34344965e-01 1.06780137e-01 9.79004837e-02 1.19931919e-01\n",
            " 3.43733965e-02 7.46593101e-02 3.84394332e-02 4.54711935e-02\n",
            " 2.20929615e-01 2.08944189e-02 6.07654974e-02 1.25599167e-01\n",
            " 8.86040821e-02 1.37128095e-01 5.22743524e-02 1.73772103e-01\n",
            " 7.06118057e-02 1.05211837e-01 1.22506453e-01 1.39194271e-01\n",
            " 1.08271688e-01 9.00978596e-02 5.55873392e-02 1.03404989e-01\n",
            " 1.04902051e-01 7.90229671e-02 1.28870286e-01 1.65456053e-02\n",
            " 3.67521386e-02 5.98058038e-02 2.98977805e-02 1.86872732e-01\n",
            " 4.69642001e-02 5.63240369e-02 7.22171420e-02 1.31374083e-01\n",
            " 1.02645197e-01 1.38568149e-01 8.47439094e-02 2.89714469e-02\n",
            " 3.62334783e-02 6.24744365e-02 1.16765715e-01 3.34616748e-02\n",
            " 6.65537990e-02 8.22554059e-02 8.61717426e-02 1.29704112e-02\n",
            " 9.39328062e-02 6.86164829e-02 1.10048789e-01 4.79483515e-02\n",
            " 8.26911031e-02 1.65064481e-01 1.07732201e-01 1.16300974e-01\n",
            " 5.97777155e-02 1.39136463e-02 7.94652531e-02 1.43503059e-02\n",
            " 6.19920600e-02 1.80150200e-01 1.39758696e-01 9.69757960e-02\n",
            " 1.53682412e-01 9.83480274e-02 1.34775015e-01 8.78743526e-02\n",
            " 5.30485346e-02 7.65744570e-02 4.45340089e-02 9.03655776e-02\n",
            " 8.20185675e-02 3.60584657e-02 1.38384069e-02 1.01688607e-01\n",
            " 7.51112526e-02 8.84844352e-02 8.89694798e-02 8.21400170e-02\n",
            " 8.51499831e-02 9.95047088e-02 2.79178307e-02 5.90602061e-02\n",
            " 1.61959931e-01 7.60504983e-02 2.39340859e-01 6.71512649e-02\n",
            " 9.96814741e-02 5.39630897e-02 1.52451343e-01 5.73406009e-02\n",
            " 6.88395439e-02 4.24194900e-02 9.84364606e-03 4.11483344e-02\n",
            " 1.02739571e-01]\n",
            "Filtered FFT Magnitudes: [7.76667671e-02 3.31048287e+00 3.08697495e+00 3.56302477e+00\n",
            " 4.67208921e-01 2.17411887e+00 1.50090679e+00 1.08762275e+00\n",
            " 1.17526312e+00 1.32677234e+00 9.73816419e-01 1.44052367e+00\n",
            " 3.66433631e-01 1.08074965e+00 6.06380806e-01 1.22904741e+00\n",
            " 1.88358544e-01 2.14898208e-01 6.60963833e-01 1.04479284e+00\n",
            " 7.07137949e-01 1.03200813e+00 2.76332936e-01 8.30624299e-01\n",
            " 4.63266207e-01 4.06315676e-01 2.75339520e-01 3.27948832e-01\n",
            " 2.07445994e-01 1.08252313e-01 1.42047376e-01 1.08365106e-01\n",
            " 6.26250097e-01 4.86246095e-01 3.33410985e-01 3.13351197e-01\n",
            " 5.72212047e-01 3.19950411e-01 8.89033323e-02 1.39868929e-01\n",
            " 5.99239605e-02 2.58820446e-01 2.33040402e-01 1.90357518e-01\n",
            " 2.51629587e-01 2.86947649e-01 1.06128586e-01 5.17961839e-01\n",
            " 1.82008901e-01 1.10502592e-01 2.43139208e-01 2.03614903e-01\n",
            " 2.11847545e-01 1.31267616e-01 2.73270266e-01 2.61796362e-01\n",
            " 1.96844222e-01 2.09444324e-01 3.45853021e-01 3.67996954e-01\n",
            " 3.78140000e-01 2.26905465e-01 3.79684850e-01 3.57951975e-01\n",
            " 2.23300809e-01 6.11873014e-01 2.24857139e-01 2.70726929e-01\n",
            " 2.74864534e-01 4.04462703e-01 1.30065465e-01 2.68322172e-01\n",
            " 2.73327317e-01 3.99801667e-01 2.27166311e-01 2.00102244e-01\n",
            " 1.63722064e-01 2.80227639e-01 1.83259962e-01 9.43770261e-02\n",
            " 1.17440863e-01 4.97088300e-01 5.42634525e-01 5.30954038e-01\n",
            " 3.60115100e-01 4.76006568e-01 4.73275491e-01 2.88682650e-01\n",
            " 2.27602539e-01 7.31586692e-02 1.48077286e-01 1.17507232e-01\n",
            " 3.74550327e-01 1.23992048e-01 1.14325655e-01 1.13725515e-01\n",
            " 3.01971771e-01 9.14695883e-02 1.16262038e-01 2.76147049e-01\n",
            " 1.24574163e-01 1.95881857e-01 2.25969801e-01 1.81346606e-01\n",
            " 2.24562820e-01 4.13158846e-01 1.34540551e-01 2.80968527e-01\n",
            " 2.21501814e-01 3.35040540e-01 2.94610464e-02 1.16783530e-01\n",
            " 7.02472428e-03 1.88678328e-01 2.20900515e-01 7.55053640e-02\n",
            " 1.22484791e-01 7.67436452e-02 1.68127391e-01 7.22143511e-02\n",
            " 3.92239500e-02 2.24129637e-01 1.24646916e-01 6.13668552e-02\n",
            " 1.81755332e-01 1.58681357e-01 1.93387826e-02 2.67196890e-01\n",
            " 6.41309305e-02 2.93975597e-01 5.50239003e-02 1.19821087e-01\n",
            " 1.28707092e-01 1.06534121e-01 8.47600845e-02 6.87864109e-02\n",
            " 1.84670698e-01 1.81557427e-01 1.47999437e-01 1.35051191e-01\n",
            " 2.43786229e-01 1.96230481e-01 1.95029517e-01 3.11966696e-02\n",
            " 1.12406629e-01 3.37893106e-01 2.23657076e-01 2.30962262e-01\n",
            " 2.68928434e-01 1.68721394e-01 2.58430416e-01 7.34939725e-02\n",
            " 1.49202399e-01 1.16720859e-01 1.55688031e-01 2.00410686e-01\n",
            " 1.30918889e-01 5.90264324e-02 1.78913307e-01 1.26106712e-01\n",
            " 3.31364267e-01 1.25032299e-01 1.02157648e-01 1.24858224e-01\n",
            " 1.17796738e-01 9.72120071e-02 3.56998515e-01 2.13595126e-01\n",
            " 1.08613049e-01 2.82145665e-01 1.90871987e-01 1.73663218e-01\n",
            " 9.56108033e-02 1.38484535e-01 1.56754449e-01 8.06881474e-02\n",
            " 1.81535113e-01 7.97459775e-02 2.60433572e-02 6.21717734e-02\n",
            " 2.59613193e-01 4.47349205e-02 2.72603674e-01 1.16248981e-02\n",
            " 1.11193855e-01 2.30117230e-01 2.74086799e-01 4.00297231e-01\n",
            " 1.99644430e-01 2.25515258e-01 1.31992828e-01 1.35519506e-01\n",
            " 1.69041817e-01 2.55748919e-01 1.57380646e-01 1.69573311e-01\n",
            " 1.39743134e-01 2.50579082e-01 1.37293538e-01 1.10376882e-01\n",
            " 1.75207795e-01 1.32109651e-01 2.06240570e-01 8.51745094e-02\n",
            " 1.39032488e-01 1.86591192e-01 9.09008262e-02 2.33399267e-01\n",
            " 8.83662420e-02 4.79323290e-02 2.25482100e-01 2.08298891e-01\n",
            " 9.75076829e-02 1.34478362e-01 1.38770349e-01 4.52119338e-02\n",
            " 5.12043384e-02 1.16368272e-01 1.61173489e-01 3.86209829e-01\n",
            " 1.54901198e-01 1.70745066e-01 9.37342666e-02 1.68946321e-01\n",
            " 3.53646433e-02 4.11458961e-02 1.33280001e-01 4.44023691e-01\n",
            " 8.49979566e-02 2.03610196e-01 1.62717710e-01 1.04061975e-01\n",
            " 2.30177026e-01 1.99467058e-01 1.15148255e-01 1.98830249e-01\n",
            " 1.05148334e-01 2.80194503e-01 7.92690835e-02 7.79091509e-02\n",
            " 1.66407026e-01 1.08507428e-01 1.04844896e-01 1.31038487e-01\n",
            " 5.15709249e-02 7.10816852e-02 1.83430250e-02 2.66048454e-02\n",
            " 2.44792335e-02 1.91572583e-02 1.64116201e-02 1.64948517e-02\n",
            " 1.42221514e-02 3.54255420e-03 6.48265738e-02 3.39298275e-02\n",
            " 9.40570234e-03 1.25685390e-01 1.04509303e-01 7.80725896e-02\n",
            " 7.77017105e-02 4.22769283e-02 9.42811687e-02 1.51814809e-01\n",
            " 9.59937704e-02 2.00255649e-01 6.90492981e-02 1.20771074e-01\n",
            " 1.62960388e-01 1.24945687e-01 8.68406619e-02 1.10998933e-01\n",
            " 9.17603925e-02 9.21521582e-02 1.07654242e-01 7.41241738e-02\n",
            " 3.94849763e-02 1.01435625e-01 1.05992921e-01 8.48137311e-02\n",
            " 2.78678890e-01 7.07583800e-02 1.06968482e-01 4.81696195e-02\n",
            " 1.10177199e-02 1.06265463e-01 3.76300763e-02 2.17620418e-01\n",
            " 4.30609533e-02 1.69859530e-01 6.07772300e-02 2.90480956e-01\n",
            " 1.17102775e-01 1.01721438e-01 1.34870533e-01 5.76382811e-02\n",
            " 7.45650633e-02 1.80091804e-01 6.79700615e-02 1.48433096e-01\n",
            " 9.00284514e-02 1.21026503e-01 1.31031042e-01 1.54740199e-01\n",
            " 2.44849682e-01 8.40808723e-02 1.35048750e-01 7.96060949e-02\n",
            " 7.67995882e-02 2.98463794e-01 2.44259599e-01 1.29091376e-01\n",
            " 1.56626402e-01 7.77780212e-02 1.21420234e-01 1.51957820e-01\n",
            " 1.23754012e-01 1.29936841e-01 1.35230828e-01 6.32497421e-02\n",
            " 6.14800779e-01 4.44367803e-02 1.03702959e-01 1.85206737e-01\n",
            " 1.08112470e-01 3.68888297e-01 7.33668007e-02 5.26225831e-02\n",
            " 2.59732758e-01 5.33739057e-02 1.83983665e-01 2.26580773e-01\n",
            " 1.28210689e-01 1.44656473e-01 1.47454113e-01 9.95014366e-02\n",
            " 1.41610109e-01 2.37654709e-01 9.02576161e-02 1.29222477e-01\n",
            " 8.15383452e-02 2.38673519e-01 1.26137653e-01 1.47207254e-01\n",
            " 2.46266801e-01 7.70623846e-02 1.75293892e-01 1.54501728e-01\n",
            " 1.78151015e-01 2.14844492e-01 2.09970082e-01 1.27822953e-01\n",
            " 4.06705959e-02 4.80621747e-02 1.65965035e-01 1.57086459e-01\n",
            " 1.35778209e-01 1.63133191e-01 1.96885967e-01 8.37337014e-02\n",
            " 4.34163666e-02 1.02964825e-01 1.74559417e-01 1.39936628e-01\n",
            " 8.66995239e-02 1.09129341e-01 4.56610527e-02 1.34829978e-02\n",
            " 6.80630024e-02 9.92032357e-02 2.08787875e-01 2.58716570e-02\n",
            " 1.92543753e-01 1.00472515e-01 7.68965259e-02 1.97692652e-02\n",
            " 5.96921836e-02 2.01102723e-01 8.32174570e-02 1.08959408e-01\n",
            " 5.98499890e-02 7.32473943e-02 7.27316241e-02 8.61745200e-02\n",
            " 1.32070059e-01 6.17856948e-02 2.63461618e-01 8.38673646e-02\n",
            " 2.06172846e-01 1.31168709e-01 2.26532830e-01 3.16800836e-02\n",
            " 4.15815414e-02 1.36402794e-01 7.25963848e-02 2.88855389e-02\n",
            " 1.41120598e-01 1.52755521e-01 1.26818125e-01 9.26328520e-02\n",
            " 1.18466910e-01 8.31000784e-02 5.13979135e-02 1.98267169e-01\n",
            " 8.31238586e-02 7.92528031e-02 1.30571730e-01 2.94916179e-02\n",
            " 1.56059202e-01 3.05507264e-02 1.87859908e-01 4.38350110e-02\n",
            " 8.47188289e-02 1.11226299e-01 8.88952134e-02 1.93498135e-01\n",
            " 5.40466856e-02 9.86878341e-02 1.67024907e-01 1.60671415e-01\n",
            " 1.13710244e-01 1.62028355e-01 6.84363410e-02 1.60242630e-01\n",
            " 2.82774688e-02 2.10132985e-02 2.45027506e-01 9.01751327e-02\n",
            " 1.98980021e-01 4.18723757e-02 7.39209608e-02 4.66016423e-02\n",
            " 9.01210958e-02 3.16641196e-02 2.00203753e-01 7.84048097e-02\n",
            " 7.22933708e-02 1.57385060e-01 1.05337373e-01 6.40356421e-02\n",
            " 8.56663550e-02 7.84185180e-02 1.29379509e-01 8.65222068e-02\n",
            " 7.94011752e-02 7.10261511e-02 2.43356161e-02 7.73369749e-02\n",
            " 1.19104856e-01 2.31298916e-02 1.54054931e-01 4.93469616e-02\n",
            " 6.68918522e-02 8.53459355e-02 8.21500937e-02 1.54363878e-01\n",
            " 6.41683120e-02 1.23245240e-02 6.93166822e-02 1.45873137e-01\n",
            " 9.02687999e-02 1.00077336e-01 1.02954531e-01 9.47771812e-02\n",
            " 4.41514725e-02 1.14650580e-01 7.72532253e-02 5.06060917e-02\n",
            " 1.72153827e-02 9.68592276e-02 2.24478224e-02 7.24750748e-02\n",
            " 9.54686470e-02 4.46509988e-02 1.96768435e-02 6.46262175e-02\n",
            " 3.29860733e-02 5.37247422e-02 5.67888992e-02 1.12284364e-01\n",
            " 1.29125832e-01 4.17199800e-02 2.71084847e-02 7.89272216e-02\n",
            " 5.87123877e-02 2.44458036e-02 4.72424055e-02 5.89140373e-02\n",
            " 5.02904862e-02 7.25851398e-02 3.54302167e-02 1.62001285e-02\n",
            " 3.67631826e-02 7.83883724e-02 7.64714599e-03 4.20204731e-02\n",
            " 2.22992656e-02 4.50196330e-02 9.51885771e-02 7.69249012e-02\n",
            " 5.34983218e-02 2.26634010e-02 6.14976564e-02 6.70538492e-02\n",
            " 6.66614686e-02 3.63234727e-02 5.40060594e-02 2.00138923e-02\n",
            " 5.29330330e-03 6.28099210e-02 2.11067076e-02 2.89869351e-02\n",
            " 2.68928491e-02 2.55034982e-02 1.96497800e-02 9.88325610e-03\n",
            " 3.63861599e-02 4.43061340e-02 4.13220317e-02 4.95081899e-02\n",
            " 2.16290602e-02 2.67723380e-02 1.89532768e-02 3.91781006e-02\n",
            " 1.48497929e-02 3.12443098e-02 2.65545703e-02 6.30834949e-03\n",
            " 2.58120074e-02 2.49648387e-02 5.12739811e-02 9.52356430e-03\n",
            " 2.36461316e-02 6.56182772e-03 8.56584250e-03 3.72563868e-03\n",
            " 2.05908151e-02 1.63476481e-03 6.58209201e-03 7.65936397e-03\n",
            " 9.73968568e-03 8.39726676e-03 1.87323745e-02 8.53709457e-03\n",
            " 9.88347053e-03 7.19204930e-03 8.03614107e-03 8.79684580e-03\n",
            " 3.03911179e-03 5.80644223e-03 9.77077487e-04 1.90075514e-03\n",
            " 1.14061500e-02 1.62056625e-03 2.30617319e-03 5.96339216e-03\n",
            " 3.08975729e-03 3.85773499e-03 2.34230799e-03 5.00998469e-03\n",
            " 1.05959917e-03 3.70106325e-03 3.86267328e-03 2.59161521e-03\n",
            " 3.01856331e-03 8.77593195e-04 1.21470647e-03 1.91862908e-03\n",
            " 7.72005216e-04 1.93171120e-03 8.14667394e-04 9.59009811e-04\n",
            " 1.20636550e-03 2.10555817e-04 5.16335089e-04 1.13388131e-03\n",
            " 8.73947933e-04 8.48625358e-04 9.83347224e-04 1.13168625e-03\n",
            " 3.50397526e-04 6.51208106e-04 9.45845654e-04 7.68804880e-04\n",
            " 6.56706721e-04 5.18694823e-04 3.99662861e-04 6.55519563e-04\n",
            " 4.71338036e-04 7.50376628e-04 7.27940371e-04 5.66563086e-04\n",
            " 4.89356496e-04 6.27419922e-04 4.35442290e-04 4.85500885e-04\n",
            " 5.02134156e-04 3.93770456e-04 4.96925619e-04 5.24196146e-04\n",
            " 4.90052676e-04 4.54873506e-04 4.21552577e-04 4.36492190e-04\n",
            " 4.30499171e-04 4.01952738e-04 3.87246413e-04 3.91284630e-04\n",
            " 3.75114215e-04 3.74438092e-04 3.49593942e-04 3.48020447e-04\n",
            " 3.34575677e-04 3.22846836e-04 3.09892532e-04 2.97056213e-04\n",
            " 2.88423629e-04 2.76966444e-04 2.66092687e-04 2.54949605e-04\n",
            " 2.44556052e-04 2.33528203e-04 2.22316724e-04 2.11586621e-04\n",
            " 2.00965800e-04 1.90422333e-04 1.79998860e-04 1.69731996e-04\n",
            " 1.59652443e-04 1.49743447e-04 1.40132711e-04 1.30791125e-04\n",
            " 1.21859605e-04 1.13390395e-04 1.05505188e-04 9.83410228e-05\n",
            " 9.20670208e-05 8.68751261e-05 8.29682427e-05 8.05333091e-05\n",
            " 7.97051570e-05]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "PSD (pre processing)"
      ],
      "metadata": {
        "id": "q-QtKL371MCC"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import your specific functions\n",
        "from Filtering import filtering\n",
        "from Common_average_reference import car\n",
        "from PSDA import psda_analysis\n",
        "\n",
        "# ----------------------------------- Step 1: Combine all datasets ----------------------------------------\n",
        "# Assume data1, data2, data3 are already loaded as numpy arrays.\n",
        "# Shape: (1280, 8, n_trials) for each dataset\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)\n",
        "\n",
        "# Create labels for the trials (modify if needed)\n",
        "labels = np.concatenate((np.full(data1.shape[-1], 0),\n",
        "                         np.full(data2.shape[-1], 1),\n",
        "                         np.full(data3.shape[-1], 2)))\n",
        "\n",
        "# -------------------------------- Step 2: Filtering for all datasets -------------------------------------\n",
        "order = 3                # Filter order\n",
        "f_low = 0.05             # Lower cutoff frequency (Hz)\n",
        "f_high = 100             # Upper cutoff frequency (Hz)\n",
        "notch_freq = 50          # Notch filter frequency to remove (Hz)\n",
        "quality_factor = 20      # Quality factor for the notch filter\n",
        "notch_filter = \"on\"      # Enable or disable notch filter\n",
        "filter_active = \"off\"    # Enable or disable bandpass filter\n",
        "type_filter = \"bandpass\" # Filter type: bandpass\n",
        "\n",
        "# Apply filtering to the combined data\n",
        "filtered_data = filtering(data_total, f_low, f_high, order, fs,\n",
        "                          notch_freq, quality_factor, filter_active,\n",
        "                          notch_filter, type_filter)\n",
        "\n",
        "print(f\"Filtered Data Shape: {filtered_data.shape}\")\n",
        "\n",
        "# ------------------------------------- Step 3: CAR Filtering --------------------------------------\n",
        "# Apply Common Average Reference (CAR) filter\n",
        "data_car = car(filtered_data)\n",
        "print(f\"CAR-Filtered Data Shape: {data_car.shape}\")\n",
        "\n",
        "# ---------------------------------- Step 4: PSDA Analysis ----------------------------------------\n",
        "num_channel = [0, 1, 2]  # Select channels for analysis\n",
        "num_harmonic = 2         # Number of harmonics per frequency\n",
        "num_sample_neigh = 30    # Neighborhood samples for each frequency\n",
        "f_stim = [13, 21, 17]    # Frequencies of stimulation (Hz)\n",
        "\n",
        "# Perform PSDA analysis on the CAR-filtered data\n",
        "predict_label = psda_analysis(data_car[:, num_channel], f_stim,\n",
        "                              num_sample_neigh, fs, num_harmonic)\n",
        "\n",
        "# Calculate and display accuracy\n",
        "accuracy = np.sum(labels == predict_label) / len(predict_label) * 100\n",
        "print(f\"Accuracy: {accuracy:.2f}%\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1zYm0PnJ1sLD",
        "outputId": "72cc6ac1-69a9-439c-d80a-002f6f478f19"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Filtered Data Shape: (1280, 8, 480)\n",
            "CAR-Filtered Data Shape: (1280, 8, 480)\n",
            "Accuracy: 94.79%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "CCA"
      ],
      "metadata": {
        "id": "Mesmd1Vc3HhI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import functions\n",
        "from Filtering import filtering\n",
        "from Common_average_reference import car\n",
        "from CCA import cca\n",
        "\n",
        "# ------------------------------------ Step 2: Load and Combine Data ----------------------------------------\n",
        "# Assuming data1, data2, and data3 are already loaded\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)\n",
        "\n",
        "# Generate labels for each dataset (0, 1, 2)\n",
        "labels = np.concatenate((np.full(data1.shape[-1], 0),\n",
        "                         np.full(data2.shape[-1], 1),\n",
        "                         np.full(data3.shape[-1], 2)))\n",
        "\n",
        "# ------------------------------------ Step 3: Filter the Data ----------------------------------------\n",
        "order = 4\n",
        "f_low = 0.05\n",
        "f_high = 100\n",
        "notch_freq = 50\n",
        "quality_factor = 20\n",
        "notch_filter = \"on\"\n",
        "filter_active = \"off\"\n",
        "type_filter = \"bandpass\"\n",
        "\n",
        "filtered_data = filtering(data_total, f_low, f_high, order, fs,\n",
        "                          notch_freq, quality_factor, filter_active,\n",
        "                          notch_filter, type_filter)\n",
        "\n",
        "print(f\"Filtered Data Shape: {filtered_data.shape}\")\n",
        "\n",
        "# ----------------------------------- Step 4: Apply CAR Filter ----------------------------------------\n",
        "data_car = car(filtered_data)\n",
        "print(f\"CAR-Filtered Data Shape: {data_car.shape}\")\n",
        "\n",
        "# ----------------------------------- Step 5: Perform CCA Classification ----------------------------------------\n",
        "num_channel = [0, 1, 2]   # List of channels to use\n",
        "num_harmonic = 4          # Number of harmonics\n",
        "f_stim = [13, 21, 17]     # Frequencies used for stimulation\n",
        "\n",
        "# Use your CCA function to classify the EEG signals\n",
        "predict_label = cca(data_car, fs, f_stim, num_channel, num_harmonic)\n",
        "\n",
        "# ------------------------------------ Step 6: Calculate Accuracy ----------------------------------------\n",
        "accuracy = np.sum(labels == predict_label) / len(predict_label) * 100\n",
        "print(f\"Classification Accuracy: {accuracy:.2f}%\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CQGdpBjm4ezb",
        "outputId": "faa2743c-d06f-4f54-eb9d-9df5ade030ff"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Filtered Data Shape: (1280, 8, 480)\n",
            "CAR-Filtered Data Shape: (1280, 8, 480)\n",
            "Classification Accuracy: 92.08%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "FoCCA"
      ],
      "metadata": {
        "id": "SMqcYckn5vC0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import the necessary modules\n",
        "from Filtering import filtering\n",
        "from Common_average_reference import car\n",
        "from FoCCA import focca_analysis  # Import the FoCCA method\n",
        "\n",
        "# Combine datasets along the third axis and create corresponding labels\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)\n",
        "labels = np.concatenate((np.full(data1.shape[-1], 0),\n",
        "                         np.full(data2.shape[-1], 1),\n",
        "                         np.full(data3.shape[-1], 2)))\n",
        "\n",
        "print(f\"Combined Data Shape: {data_total.shape}\")\n",
        "print(f\"Labels Shape: {labels.shape}\")\n",
        "\n",
        "# -------------------------- Step 3: Apply Filtering -----------------------------------------\n",
        "order = 4                # Filter order\n",
        "f_low = 0.05             # Lower cutoff frequency (Hz)\n",
        "f_high = 100             # Upper cutoff frequency (Hz)\n",
        "notch_freq = 50          # Notch frequency to remove (Hz)\n",
        "quality_factor = 20      # Quality factor for the notch filter\n",
        "notch_filter = \"on\"      # Notch filter enabled\n",
        "filter_active = \"off\"    # Bandpass filter disabled\n",
        "type_filter = \"bandpass\" # Type of filter\n",
        "\n",
        "# Apply the filtering\n",
        "fs = 256\n",
        "filtered_data = filtering(data_total, f_low, f_high, order, fs,\n",
        "                          notch_freq, quality_factor, filter_active,\n",
        "                          notch_filter, type_filter)\n",
        "\n",
        "print(f\"Filtered Data Shape: {filtered_data.shape}\")\n",
        "\n",
        "# -------------------------- Step 4: Apply CAR Filtering -------------------------------------\n",
        "# Apply Common Average Referencing\n",
        "data_car = car(filtered_data)\n",
        "print(f\"CAR-Filtered Data Shape: {data_car.shape}\")\n",
        "\n",
        "# ---------------------------- Step 5: FoCCA Analysis ---------------------------------------\n",
        "num_harmonic = 2          # Number of harmonics for each frequency\n",
        "f_stim = [13, 21, 17]     # Stimulation frequencies\n",
        "num_channel = [0, 1, 2]   # Channels to analyze\n",
        "\n",
        "# Parameters for FoCCA\n",
        "a = [0.01, 0.1, 0, 3, 5]\n",
        "b = [0.01, 0.1, 0, 1, 10]\n",
        "\n",
        "# Perform FoCCA analysis and compute accuracy\n",
        "accuracy = focca_analysis(data_car, labels, fs, f_stim, num_channel,\n",
        "                          num_harmonic, a, b)\n",
        "\n",
        "# Print the accuracy for each combination of 'a' and 'b'\n",
        "print(f\"FoCCA Accuracy Results: {accuracy}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3KV3cXoR5vcV",
        "outputId": "e32a2973-f799-4aab-ada6-ce87a30321ee"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Combined Data Shape: (1280, 8, 480)\n",
            "Labels Shape: (480,)\n",
            "Filtered Data Shape: (1280, 8, 480)\n",
            "CAR-Filtered Data Shape: (1280, 8, 480)\n",
            "0.01, 0.01 --> 94.17\n",
            "0.01, 0.1 --> 94.17\n",
            "0.01, 0 --> 94.17\n",
            "0.01, 1 --> 94.17\n",
            "0.01, 10 --> 94.17\n",
            "0.1, 0.01 --> 94.17\n",
            "0.1, 0.1 --> 94.17\n",
            "0.1, 0 --> 94.17\n",
            "0.1, 1 --> 94.17\n",
            "0.1, 10 --> 94.17\n",
            "0, 0.01 --> 94.17\n",
            "0, 0.1 --> 94.17\n",
            "0, 0 --> 94.17\n",
            "0, 1 --> 94.17\n",
            "0, 10 --> 94.17\n",
            "3, 0.01 --> 93.54\n",
            "3, 0.1 --> 93.75\n",
            "3, 0 --> 93.54\n",
            "3, 1 --> 94.17\n",
            "3, 10 --> 94.17\n",
            "5, 0.01 --> 93.54\n",
            "5, 0.1 --> 93.54\n",
            "5, 0 --> 93.54\n",
            "5, 1 --> 93.96\n",
            "5, 10 --> 94.17\n",
            "FoCCA Accuracy Results: ['94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '94.17', '93.54', '93.75', '93.54', '94.17', '94.17', '93.54', '93.54', '93.54', '93.96', '94.17']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "FBCCA"
      ],
      "metadata": {
        "id": "DthhDbEB7ot8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Import functions from the files\n",
        "import FBCCA\n",
        "import Filtering\n",
        "import Common_average_reference\n",
        "\n",
        "# Combine all datasets\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)\n",
        "labels = np.concatenate((np.full(data1.shape[-1], 0),\n",
        "                         np.full(data2.shape[-1], 1),\n",
        "                         np.full(data3.shape[-1], 2)))\n",
        "\n",
        "# Step 8: Define filtering parameters\n",
        "order = 4                # Define filter order\n",
        "f_low = 0.05             # Define lower cutoff frequency for the bandpass filter (Hz)\n",
        "f_high = 100             # Define upper cutoff frequency for the bandpass filter (Hz)\n",
        "notch_freq = 50          # Define frequency to be removed from the signal for notch filter (Hz)\n",
        "quality_factor = 20      # Define quality factor for the notch filter\n",
        "notch_filter = \"on\"      # on or off\n",
        "filter_active = \"off\"    # on or off\n",
        "type_filter = \"bandpass\" # low, high, bandpass, or bandstop\n",
        "\n",
        "# Step 9: Apply notch filter to the EEG data\n",
        "filtered_data = Filtering.filtering(data_total, f_low, f_high, order, fs,\n",
        "                                     notch_freq, quality_factor,\n",
        "                                     filter_active, notch_filter, type_filter)\n",
        "\n",
        "# Step 10: Perform Common Average Reference (CAR)\n",
        "data_car = Common_average_reference.car(filtered_data)\n",
        "\n",
        "# Step 11: Define FBCCA parameters\n",
        "method = 'm3'             # Type filter banks: M1, M2, M3\n",
        "num_harmonic = 2          # Number of harmonics for each frequency stimulation\n",
        "notch_filter = \"off\"      # on or off\n",
        "filter_active = \"on\"      # on or off\n",
        "type_filter = \"bandpass\"  # low, high, bandpass, or bandstop\n",
        "f_stim = [13, 21, 17]     # Frequencies stimulation\n",
        "num_channel = [0, 1]      # Number of Channels\n",
        "a = [0.01, 0]\n",
        "b = [0.001, 0]\n",
        "filter_banks = [[10, 20, 30, 40, 50, 60, 70, 80, 90],\n",
        "                [100, 100, 100, 100, 100, 100, 100, 100, 100]]\n",
        "\n",
        "# Step 12: Perform FBCCA analysis\n",
        "accuracy = FBCCA.fbcca_analysis(data_car, labels, fs, f_stim, num_channel,\n",
        "                                 num_harmonic, a, b, filter_banks, order,\n",
        "                                 notch_freq, quality_factor, filter_active,\n",
        "                                 notch_filter, type_filter)\n",
        "\n",
        "# Step 13: Print the accuracy results\n",
        "print(\"Accuracy Results: \", accuracy)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SNnNUUqK7pJG",
        "outputId": "d1292783-dc8f-4c46-cc90-942c64629761"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.01, 0.001 --> 97.71\n",
            "0.01, 0 --> 97.71\n",
            "0, 0.001 --> 97.71\n",
            "0, 0 --> 97.71\n",
            "Accuracy Results:  ['97.71', '97.71', '97.71', '97.71']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "FFT for feature extraction(The fft_feature_extraction function computes the FFT of the signal for the selected channels and extracts the power spectral density (PSD) for specified frequency subbands.)"
      ],
      "metadata": {
        "id": "z_IRdb3iWhIn"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Import required modules from your project\n",
        "import numpy as np\n",
        "from Filtering import filtering\n",
        "from Common_average_reference import car\n",
        "from FFT_Feature_Extraction import fft_feature_extraction\n",
        "\n",
        "#Combine datasets\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)  # Combine along trial axis\n",
        "labels = np.concatenate((\n",
        "    np.full(data1.shape[-1], 0),  # Label 0 for data1\n",
        "    np.full(data2.shape[-1], 1),  # Label 1 for data2\n",
        "    np.full(data3.shape[-1], 2)   # Label 2 for data3\n",
        "))\n",
        "print(f\"Combined Data Shape: {data_total.shape}\")\n",
        "\n",
        "# Apply Filtering\n",
        "order = 3\n",
        "notch_freq = 50\n",
        "quality_factor = 20\n",
        "subbands = [[12, 16, 20], [14, 18, 22]]\n",
        "f_low = np.min(subbands) - 1\n",
        "f_high = np.max(subbands) + 1\n",
        "notch_filter = \"on\"\n",
        "filter_active = \"on\"\n",
        "type_filter = \"bandpass\"\n",
        "\n",
        "filtered_data = filtering(\n",
        "    data_total, f_low, f_high, order, fs, notch_freq,\n",
        "    quality_factor, filter_active, notch_filter, type_filter\n",
        ")\n",
        "print(f\"Filtered Data Shape: {filtered_data.shape}\")\n",
        "\n",
        "# Apply CAR\n",
        "data_car = car(filtered_data)\n",
        "print(f\"CAR-Filtered Data Shape: {data_car.shape}\")\n",
        "\n",
        "# Perform FFT-Based Feature Extraction\n",
        "num_channel = [0, 1]  # Select channels to analyze\n",
        "features = fft_feature_extraction(data_car, fs, num_channel, subbands)\n",
        "\n",
        "# Print the shape of the extracted features\n",
        "print(f\"Extracted Features Shape: {features.shape}\")"
      ],
      "metadata": {
        "id": "B702NVPlOCvP",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "316da74b-9b2a-4f3a-ba27-30fdf89c2444"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Combined Data Shape: (1280, 8, 480)\n",
            "Filtered Data Shape: (1280, 8, 480)\n",
            "CAR-Filtered Data Shape: (1280, 8, 480)\n",
            "Extracted Features Shape: (480, 6)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Feature Extraction using CCA"
      ],
      "metadata": {
        "id": "CkFhtNHJ-kmb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Import functions from the files\n",
        "import Filtering\n",
        "import Common_average_reference\n",
        "import CCA_Feature_Extraction\n",
        "import numpy as np\n",
        "\n",
        "#Combine all datasets\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)\n",
        "labels = np.concatenate((np.full(data1.shape[-1], 0),\n",
        "                         np.full(data2.shape[-1], 1),\n",
        "                         np.full(data3.shape[-1], 2)))\n",
        "\n",
        "# Define filtering parameters\n",
        "order = 3                # Define filter order\n",
        "notch_freq = 50          # Define frequency to be removed from the signal for notch filter (Hz)\n",
        "quality_factor = 20      # Define quality factor for the notch filter\n",
        "subbands = [[12, 16, 20], [14, 18, 22]]\n",
        "f_low = np.min(subbands) - 1  # Define lower cutoff frequency for the bandpass filter (Hz)\n",
        "f_high = np.max(subbands) + 1  # Define upper cutoff frequency for the bandpass filter (Hz)\n",
        "notch_filter = \"on\"       # on or off\n",
        "filter_active = \"on\"      # on or off\n",
        "type_filter = \"bandpass\"  # low, high, bandpass, or bandstop\n",
        "\n",
        "# Apply notch filter to the EEG data\n",
        "filtered_data = Filtering.filtering(data_total, f_low, f_high, order, fs,\n",
        "                                     notch_freq, quality_factor,\n",
        "                                     filter_active, notch_filter, type_filter)\n",
        "\n",
        "# Perform Common Average Reference (CAR)\n",
        "data_car = Common_average_reference.car(filtered_data)\n",
        "\n",
        "# Define parameters for feature extraction\n",
        "num_harmonic = 2          # Number of harmonics for each frequency stimulation\n",
        "f_stim = [13, 21, 17]     # Frequencies stimulation\n",
        "num_channel = [0, 1]      # Number of Channels\n",
        "title = f\"Feature Extraction using CCA\"\n",
        "\n",
        "# Perform CCA feature extraction\n",
        "features_extraction = CCA_Feature_Extraction.cca_feature_extraction(data_car, fs, f_stim, num_channel, num_harmonic)\n",
        "\n",
        "# Print or visualize the extracted features\n",
        "print(\"Extracted Features: \", features_extraction)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ARyIJ-lY1n_z",
        "outputId": "6b852de0-e109-4ecc-dc3f-2348e0c40b27"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracted Features:  [[1.31473878e-02 4.47446529e-04 7.23512216e-04 5.25305136e-06\n",
            "  1.48902109e-03 1.21476982e-04]\n",
            " [1.57979926e-02 9.73690912e-04 6.71145550e-04 9.26370324e-05\n",
            "  2.74740987e-04 1.72638880e-04]\n",
            " [1.09002187e-02 3.13242206e-05 6.44542967e-04 1.18700034e-04\n",
            "  3.18971401e-04 3.94740802e-05]\n",
            " ...\n",
            " [3.02284920e-03 3.22529111e-04 5.34918553e-04 1.25956542e-04\n",
            "  7.17385467e-03 3.18247696e-03]\n",
            " [5.77669553e-04 1.19810596e-04 2.11972687e-04 4.13915635e-05\n",
            "  1.05652861e-02 5.62028309e-03]\n",
            " [1.89009765e-03 7.64488800e-04 3.03384722e-04 6.15841800e-05\n",
            "  1.36425044e-02 7.38821934e-03]]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Feature Selection"
      ],
      "metadata": {
        "id": "9SZE1aAV_8D6"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import the feature selection function from the uploaded file\n",
        "from Feature_selections import feature_selecions\n",
        "\n",
        "# Define parameters for feature selection\n",
        "num_features = 4\n",
        "n_neighbors_MI = 5                 # Number of neighbors to consider for mutual information calculation.\n",
        "L1_Parameter = 0.1                 # Parameter value for L1 regularization.\n",
        "threshold_var = 0.001              # The threshold used for variance thresholding.\n",
        "type_feature_selection = \"anova\"    # Options: var, anova, mi, ufs, rfe, rf, l1fs, tfs, fs, ffs, bfs\n",
        "title = f\"Feature selection using {type_feature_selection}\"\n",
        "\n",
        "# Perform feature selection\n",
        "features = feature_selecions(features_extraction, labels, num_features, threshold_var,\n",
        "                              n_neighbors_MI, L1_Parameter, type_feature_selection)\n",
        "\n",
        "# Display the selected features\n",
        "print(f\"Selected features shape: {features.shape}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OpejSg62_74i",
        "outputId": "57927e35-e7a5-425d-8c3e-30f5342d5e72"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Selected features shape: (480, 4)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Festure_extraction and Label values"
      ],
      "metadata": {
        "id": "1BSXv8UFJ5Li"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from Filtering import filtering\n",
        "from Common_average_reference import car\n",
        "from FFT_Feature_Extraction import fft_feature_extraction\n",
        "\n",
        "fs = 256  # Sampling frequency\n",
        "\n",
        "# Step 1: Combine all datasets along the trial axis\n",
        "data_total = np.concatenate((data1, data2, data3), axis=2)  # (9, 1280, 160)\n",
        "print(f\"Combined Data Shape: {data_total.shape}\")\n",
        "\n",
        "# Step 2: Generate labels for each trial\n",
        "labels = np.concatenate((\n",
        "    np.full(data1.shape[-1], 0),  # Label 0 for 13 Hz stimulation (50 trials)\n",
        "    np.full(data2.shape[-1], 1),  # Label 1 for 21 Hz stimulation (60 trials)\n",
        "    np.full(data3.shape[-1], 2)   # Label 2 for 17 Hz stimulation (50 trials)\n",
        "))\n",
        "print(f\"Labels Shape: {labels.shape}\")\n",
        "print(f\"Labels: {np.unique(labels, return_counts=True)}\")  # Check distribution\n",
        "\n",
        "# Step 3: Apply Filtering\n",
        "order = 3\n",
        "notch_freq = 50\n",
        "quality_factor = 20\n",
        "subbands = [[12, 16, 20], [14, 18, 22]]\n",
        "f_low = np.min(subbands) - 1  # 11 Hz\n",
        "f_high = np.max(subbands) + 1  # 23 Hz\n",
        "notch_filter = \"on\"\n",
        "filter_active = \"on\"\n",
        "type_filter = \"bandpass\"\n",
        "\n",
        "filtered_data = filtering(\n",
        "    data_total, f_low, f_high, order, fs, notch_freq,\n",
        "    quality_factor, filter_active, notch_filter, type_filter\n",
        ")\n",
        "print(f\"Filtered Data Shape: {filtered_data.shape}\")\n",
        "\n",
        "# Step 4: Apply Common Average Referencing (CAR)\n",
        "data_car = car(filtered_data)\n",
        "print(f\"CAR-Filtered Data Shape: {data_car.shape}\")\n",
        "\n",
        "# Step 5: Perform FFT-Based Feature Extraction\n",
        "num_channel = [0, 1]  # Example: Analyze first two channels\n",
        "features_extraction = fft_feature_extraction(data_car, fs, num_channel, subbands)\n",
        "\n",
        "print(f\"Extracted Features Shape: {features_extraction.shape}\")\n",
        "\n",
        "# Step 6: Store Features and Labels for Classification\n",
        "np.save(\"features_extraction.npy\", features_extraction)\n",
        "np.save(\"labels.npy\", labels)\n",
        "\n",
        "print(\"Features and labels saved successfully!\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AJv7Ptj_LkkM",
        "outputId": "49ac96d8-22a2-427f-a98b-f902bb25f7d6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Combined Data Shape: (1280, 8, 480)\n",
            "Labels Shape: (480,)\n",
            "Labels: (array([0, 1, 2]), array([160, 160, 160]))\n",
            "Filtered Data Shape: (1280, 8, 480)\n",
            "CAR-Filtered Data Shape: (1280, 8, 480)\n",
            "Extracted Features Shape: (480, 6)\n",
            "Features and labels saved successfully!\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Classification Models"
      ],
      "metadata": {
        "id": "uczhDeR7CXl8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Step 1: Import necessary libraries\n",
        "import numpy as np\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.svm import SVC\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.metrics import accuracy_score, classification_report\n",
        "\n",
        "# Assuming `features_extraction` and `labels` are already available from the previous steps\n",
        "\n",
        "# Step 2: Split the data into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(\n",
        "    features_extraction, labels, test_size=0.2, random_state=42\n",
        ")\n",
        "\n",
        "# Step 3: Standardize the features (important for models like SVM)\n",
        "scaler = StandardScaler()\n",
        "X_train = scaler.fit_transform(X_train)\n",
        "X_test = scaler.transform(X_test)\n",
        "\n",
        "# Step 4: Train classifiers (Logistic Regression, SVM, and Random Forest)\n",
        "\n",
        "# Logistic Regression\n",
        "logreg = LogisticRegression(max_iter=1000, random_state=42)\n",
        "logreg.fit(X_train, y_train)\n",
        "\n",
        "# Support Vector Machine\n",
        "svm_model = SVC(kernel='linear', probability=True, random_state=42)\n",
        "svm_model.fit(X_train, y_train)\n",
        "\n",
        "# Random Forest Classifier\n",
        "rf_model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
        "rf_model.fit(X_train, y_train)\n",
        "\n",
        "# Step 5: Evaluate models on the test set\n",
        "models = {\"Logistic Regression\": logreg, \"SVM\": svm_model, \"Random Forest\": rf_model}\n",
        "\n",
        "for name, model in models.items():\n",
        "    y_pred = model.predict(X_test)\n",
        "    print(f\"--- {name} ---\")\n",
        "    print(f\"Accuracy: {accuracy_score(y_test, y_pred):.2f}\")\n",
        "    print(classification_report(y_test, y_pred))\n",
        "\n",
        "# Step 6: Define action mapping based on predictions\n",
        "def action_mapping(prediction):\n",
        "    actions = {\n",
        "        0: 13Hz,1: 21Hz, 2:17Hz\n",
        "    }\n",
        "    return actions.get(prediction, \"Unknown Action\")\n",
        "\n",
        "# Step 7: Test the model with some example data\n",
        "sample = X_test[0].reshape(1, -1)  # Example data point\n",
        "predicted_label = rf_model.predict(sample)[0]\n",
        "predicted_action = action_mapping(predicted_label)\n",
        "\n",
        "print(f\"Predicted Action: {predicted_action}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fZYQha0Z_72Z",
        "outputId": "4cae88b5-f799-499a-fd49-32bac8fc8d59"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- Logistic Regression ---\n",
            "Accuracy: 0.96\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.92      0.97      0.94        34\n",
            "           1       0.96      0.89      0.92        27\n",
            "           2       1.00      1.00      1.00        35\n",
            "\n",
            "    accuracy                           0.96        96\n",
            "   macro avg       0.96      0.95      0.96        96\n",
            "weighted avg       0.96      0.96      0.96        96\n",
            "\n",
            "--- SVM ---\n",
            "Accuracy: 0.97\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.92      1.00      0.96        34\n",
            "           1       1.00      0.93      0.96        27\n",
            "           2       1.00      0.97      0.99        35\n",
            "\n",
            "    accuracy                           0.97        96\n",
            "   macro avg       0.97      0.97      0.97        96\n",
            "weighted avg       0.97      0.97      0.97        96\n",
            "\n",
            "--- Random Forest ---\n",
            "Accuracy: 0.96\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.92      0.97      0.94        34\n",
            "           1       0.96      0.93      0.94        27\n",
            "           2       1.00      0.97      0.99        35\n",
            "\n",
            "    accuracy                           0.96        96\n",
            "   macro avg       0.96      0.96      0.96        96\n",
            "weighted avg       0.96      0.96      0.96        96\n",
            "\n",
            "Predicted Action: Hand Movement (13Hz)\n"
          ]
        }
      ]
    }
  ]
}