{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4f641d0b",
   "metadata": {},
   "source": [
    "# Tutorial 1: Encoding histology image features using H-ViT"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "08ea17b8",
   "metadata": {},
   "source": [
    "This tutorial shows how to apply H-ViT to extract the latent representation of each spot image. Here we take the slice 151674 of the DLPFC dataset as example. The histology image is available at https://github.com/LieberInstitute/spatialLIBD.\n",
    "To reduce your waiting time, we upload obtained histological image representation data to https://zenodo.org/record/8185216/files/DLPFC.rar?download=1."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "62f8d5ad",
   "metadata": {},
   "source": [
    "## Preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2c712a75",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "import pandas as pd\n",
    "import os\n",
    "from stGCL.image_processing import image_representation\n",
    "import os\n",
    "import torch\n",
    "import random\n",
    "import numpy as np\n",
    "from torch.backends import cudnn\n",
    "import pandas as pd\n",
    "from stGCL.process import set_seed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4fe82954",
   "metadata": {},
   "outputs": [],
   "source": [
    "# seed=0\n",
    "# set_seed(seed)\n",
    "section_id=\"151676\"\n",
    "pca_num = 3000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b21db3cb",
   "metadata": {},
   "outputs": [],
   "source": [
    "labeldf = pd.read_csv(\"/home/dell/stproject/stGCL/Data/DLPFC/{}/cluster_labels_{}.csv\".format(section_id, section_id), sep=\",\", header=0,\n",
    "                      na_filter=False, index_col=0)\n",
    "label = labeldf[\"ground_truth\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "503c3a56",
   "metadata": {},
   "outputs": [],
   "source": [
    "positionsdata = pd.read_csv(\"/home/dell/stproject/stGCL/Data/DLPFC/{}/spatial/tissue_positions_list.csv\".format(section_id), sep=\",\", header=None,\n",
    "                            na_filter=False, index_col=0)\n",
    "positionsdata = positionsdata.loc[positionsdata[1] == 1].iloc[: , 3:5]\n",
    "positionsdata.columns = ['x','y']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b33c6069",
   "metadata": {},
   "outputs": [],
   "source": [
    "scale_file=\"/home/dell/stproject/stGCL/Data/DLPFC/{}/spatial/scalefactors_json.json\".format(section_id)\n",
    "image_adress=\"/home/dell/stproject/stGCL/Data/DLPFC/{}/spatial\".format(section_id)\n",
    "score_adress=\"/home/dell/stproject/stGCL/image_representation/\".format(section_id)\n",
    "image_file=\"tissue_hires_image.png\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "167632cc",
   "metadata": {},
   "source": [
    "## Extract histology image features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "99d03109",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading image data...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Tiling image: 100%|████████████████████████████████████████████████████████████████████████████████ [ time left: 00:00 ]\n",
      "extract representation by ViT: 100%|████████████████████████████████████████████████████| 28/28 [00:09<00:00,  2.98it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PCA dimensionality reduction\n",
      "Image features are stored in:  /home/dell/stproject/stGCL/image_representation//ViT_representation.csv\n",
      "PCA Image features are stored in:  /home/dell/stproject/stGCL/image_representation//ViT_pca_representation.csv\n",
      "Complete the extraction of image representation\n"
     ]
    }
   ],
   "source": [
    "image_representation(positionsdata,image_adress,image_file,label,score_adress,pca_num=3000,k=7,scale_file=scale_file,\n",
    "                     image_net=\"ViT\",image_type=\"hires\",crop_size=256,patch_size=64,load=False,batch_size_lw=128)"
   ]
  }
 ],
 "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": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}