{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e2a5d1d7-6bb3-4e24-9067-880296de1fc9",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import imageio\n",
    "from skimage import color, transform\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b37f1351-0a00-4a4b-9067-ea55a662bc80",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "main_folder = 'data/Bel_Training_Set/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "76f41177-fd53-4bf6-9e75-ba1a98c414ff",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "subfolders = [f for f in os.listdir(main_folder) if os.path.isdir(os.path.join(main_folder, f))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "706d2a6d-8147-42a1-ba19-3cc7108fcfea",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "image_data = []\n",
    "label_data = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "86841170-b9bc-46cf-b482-f2d653060bc0",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "docnames = [\"Pixel \" + str(i) for i in range(1024)]\n",
    "docnames.insert(0, 'Label')\n",
    "df1 = pd.DataFrame(columns = docnames) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d9e5d953-1652-47d3-a832-d71d87c2b7ee",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def add_to_dataset(x,y,z,l):\n",
    "    y.at[z,'Label'] = l\n",
    "    for i in range(0,1024):\n",
    "        y.at[z,docnames[i+1]] = x[i]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "82fe02ed-8471-493f-aded-58c54edb7ef6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "i = 0\n",
    "for subfolder in subfolders:\n",
    "    subfolder_path = os.path.join(main_folder, subfolder)\n",
    "    for filename in os.listdir(subfolder_path):\n",
    "        \n",
    "        file_path = os.path.join(subfolder_path, filename)\n",
    "        if filename.lower().endswith('.ppm'):\n",
    "            img_array = imageio.v2.imread(file_path)\n",
    "            resized_img_array = transform.resize(img_array, (32, 32))\n",
    "            gray_img_array = color.rgb2gray(resized_img_array)\n",
    "            flattened_img_array = gray_img_array.flatten()\n",
    "            add_to_dataset(flattened_img_array,df1,i,int(subfolder))\n",
    "            i = i + 1\n",
    "            #print(\"Image From\", int(subfolder), \"Image Name\", filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7bdcd7d7-56f3-4b9f-924f-dd811dddf605",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df1.to_csv('bel_data_test.csv', index = False) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "12d9c974-85ed-4d10-af2e-0984a367d4be",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}