{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Image summary and visual question answering"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebooks shows how to generate image captions and use the visual question answering with [LAVIS](https://github.com/salesforce/LAVIS). \n",
    "\n",
    "The first cell is only run on google colab and installs the [ammico](https://github.com/ssciwr/AMMICO) package.\n",
    "\n",
    "After that, we can import `ammico` and read in the files given a folder path."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:03:47.867208Z",
     "iopub.status.busy": "2023-06-27T09:03:47.866989Z",
     "iopub.status.idle": "2023-06-27T09:03:47.875293Z",
     "shell.execute_reply": "2023-06-27T09:03:47.874718Z"
    }
   },
   "outputs": [],
   "source": [
    "# if running on google colab\n",
    "# flake8-noqa-cell\n",
    "import os\n",
    "\n",
    "if \"google.colab\" in str(get_ipython()):\n",
    "    # update python version\n",
    "    # install setuptools\n",
    "    # %pip install setuptools==61 -qqq\n",
    "    # install ammico\n",
    "    %pip install git+https://github.com/ssciwr/ammico.git -qqq\n",
    "    # mount google drive for data and API key\n",
    "    from google.colab import drive\n",
    "\n",
    "    drive.mount(\"/content/drive\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:03:47.878143Z",
     "iopub.status.busy": "2023-06-27T09:03:47.877647Z",
     "iopub.status.idle": "2023-06-27T09:03:58.213427Z",
     "shell.execute_reply": "2023-06-27T09:03:58.212816Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import ammico\n",
    "from ammico import utils as mutils\n",
    "from ammico import display as mdisplay\n",
    "import ammico.summary as sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:03:58.216430Z",
     "iopub.status.busy": "2023-06-27T09:03:58.215954Z",
     "iopub.status.idle": "2023-06-27T09:03:58.219780Z",
     "shell.execute_reply": "2023-06-27T09:03:58.219162Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Here you need to provide the path to your google drive folder\n",
    "# or local folder containing the images\n",
    "images = mutils.find_files(\n",
    "    path=\"data/\",\n",
    "    limit=10,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:03:58.222438Z",
     "iopub.status.busy": "2023-06-27T09:03:58.222102Z",
     "iopub.status.idle": "2023-06-27T09:03:58.225151Z",
     "shell.execute_reply": "2023-06-27T09:03:58.224542Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "mydict = mutils.initialize_dict(images)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create captions for images and directly write to csv"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here you can choose between two models: \"base\" or \"large\". This will generate the caption for each image and directly put the results in a dataframe. This dataframe can be exported as a csv file.\n",
    "\n",
    "The results are written into the columns `const_image_summary` - this will always be the same result (as always the same seed will be used). The column `3_non-deterministic summary` displays three different answers generated with different seeds, these are most likely different when you run the analysis again."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:03:58.228652Z",
     "iopub.status.busy": "2023-06-27T09:03:58.228311Z",
     "iopub.status.idle": "2023-06-27T09:05:07.932578Z",
     "shell.execute_reply": "2023-06-27T09:05:07.928904Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 0.00/2.50G [00:00<?, ?B/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 4.01M/2.50G [00:00<01:05, 41.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 15.7M/2.50G [00:00<00:30, 88.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 24.1M/2.50G [00:00<00:36, 72.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 32.0M/2.50G [00:00<00:37, 71.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 44.7M/2.50G [00:00<00:29, 91.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 55.9M/2.50G [00:00<00:26, 99.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 65.6M/2.50G [00:00<00:30, 84.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 80.0M/2.50G [00:00<00:25, 102MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▎         | 90.4M/2.50G [00:01<00:26, 99.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 109M/2.50G [00:01<00:20, 125MB/s]  "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▍         | 121M/2.50G [00:01<00:23, 110MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▌         | 140M/2.50G [00:01<00:19, 134MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▌         | 154M/2.50G [00:01<00:19, 132MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 171M/2.50G [00:01<00:17, 146MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 195M/2.50G [00:01<00:14, 175MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 213M/2.50G [00:01<00:14, 171MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  9%|▉         | 238M/2.50G [00:01<00:12, 200MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|█         | 263M/2.50G [00:02<00:11, 217MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 11%|█         | 288M/2.50G [00:02<00:11, 210MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 316M/2.50G [00:02<00:10, 233MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 13%|█▎        | 344M/2.50G [00:02<00:09, 250MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 15%|█▍        | 374M/2.50G [00:02<00:08, 268MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 16%|█▌        | 400M/2.50G [00:02<00:08, 263MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 425M/2.50G [00:02<00:10, 215MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 448M/2.50G [00:02<00:10, 220MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 18%|█▊        | 470M/2.50G [00:02<00:10, 208MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 19%|█▉        | 491M/2.50G [00:03<00:16, 129MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 20%|█▉        | 507M/2.50G [00:03<00:15, 135MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 21%|██        | 530M/2.50G [00:03<00:13, 157MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 558M/2.50G [00:03<00:11, 189MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 23%|██▎       | 579M/2.50G [00:03<00:12, 164MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 24%|██▍       | 611M/2.50G [00:03<00:10, 201MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 25%|██▍       | 639M/2.50G [00:04<00:08, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 26%|██▌       | 664M/2.50G [00:04<00:11, 169MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 689M/2.50G [00:04<00:10, 189MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 28%|██▊       | 710M/2.50G [00:04<00:09, 197MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▊       | 735M/2.50G [00:04<00:09, 211MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 30%|██▉       | 757M/2.50G [00:04<00:09, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 30%|███       | 777M/2.50G [00:04<00:09, 196MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 31%|███▏      | 802M/2.50G [00:04<00:08, 212MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 32%|███▏      | 830M/2.50G [00:05<00:07, 236MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 33%|███▎      | 854M/2.50G [00:05<00:09, 191MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 34%|███▍      | 880M/2.50G [00:05<00:17, 104MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 35%|███▌      | 908M/2.50G [00:05<00:13, 132MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 36%|███▌      | 928M/2.50G [00:05<00:12, 137MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 37%|███▋      | 956M/2.50G [00:06<00:10, 167MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 38%|███▊      | 985M/2.50G [00:06<00:08, 196MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 40%|███▉      | 0.99G/2.50G [00:06<00:07, 222MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 41%|████      | 1.01G/2.50G [00:06<00:07, 209MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 42%|████▏     | 1.04G/2.50G [00:06<00:06, 228MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 43%|████▎     | 1.07G/2.50G [00:06<00:08, 192MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▎     | 1.09G/2.50G [00:06<00:07, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▍     | 1.11G/2.50G [00:07<00:11, 128MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 45%|████▌     | 1.14G/2.50G [00:07<00:09, 158MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 47%|████▋     | 1.17G/2.50G [00:07<00:07, 188MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 48%|████▊     | 1.19G/2.50G [00:07<00:06, 210MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 49%|████▊     | 1.22G/2.50G [00:07<00:06, 213MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 50%|████▉     | 1.25G/2.50G [00:07<00:05, 236MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 51%|█████     | 1.27G/2.50G [00:07<00:05, 250MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 52%|█████▏    | 1.30G/2.50G [00:07<00:04, 265MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 53%|█████▎    | 1.33G/2.50G [00:07<00:04, 267MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 54%|█████▍    | 1.36G/2.50G [00:08<00:04, 274MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 55%|█████▌    | 1.38G/2.50G [00:08<00:05, 241MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 56%|█████▌    | 1.41G/2.50G [00:08<00:05, 223MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 57%|█████▋    | 1.43G/2.50G [00:08<00:04, 241MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 58%|█████▊    | 1.46G/2.50G [00:08<00:05, 224MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 59%|█████▉    | 1.49G/2.50G [00:08<00:04, 244MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 60%|██████    | 1.51G/2.50G [00:09<00:06, 154MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 61%|██████    | 1.53G/2.50G [00:09<00:06, 173MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 62%|██████▏   | 1.56G/2.50G [00:09<00:05, 199MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 63%|██████▎   | 1.58G/2.50G [00:09<00:04, 204MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 1.61G/2.50G [00:09<00:04, 229MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▌   | 1.64G/2.50G [00:09<00:03, 245MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 67%|██████▋   | 1.67G/2.50G [00:09<00:03, 254MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 1.69G/2.50G [00:09<00:03, 266MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▊   | 1.72G/2.50G [00:09<00:03, 267MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 70%|██████▉   | 1.75G/2.50G [00:10<00:04, 201MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████   | 1.77G/2.50G [00:10<00:03, 219MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 72%|███████▏  | 1.80G/2.50G [00:10<00:03, 232MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 1.82G/2.50G [00:10<00:03, 235MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 74%|███████▍  | 1.85G/2.50G [00:10<00:02, 254MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 75%|███████▍  | 1.88G/2.50G [00:10<00:02, 268MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 76%|███████▌  | 1.90G/2.50G [00:11<00:06, 97.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 77%|███████▋  | 1.92G/2.50G [00:11<00:05, 111MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.95G/2.50G [00:11<00:04, 141MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▉  | 1.98G/2.50G [00:11<00:03, 166MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 80%|███████▉  | 2.00G/2.50G [00:11<00:02, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████  | 2.03G/2.50G [00:12<00:04, 106MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 82%|████████▏ | 2.05G/2.50G [00:12<00:04, 116MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 2.07G/2.50G [00:12<00:03, 145MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 84%|████████▎ | 2.09G/2.50G [00:12<00:02, 155MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 84%|████████▍ | 2.11G/2.50G [00:14<00:13, 31.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 85%|████████▍ | 2.13G/2.50G [00:14<00:11, 36.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 85%|████████▌ | 2.14G/2.50G [00:14<00:09, 42.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▌ | 2.15G/2.50G [00:15<00:08, 47.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▋ | 2.16G/2.50G [00:15<00:06, 55.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 87%|████████▋ | 2.17G/2.50G [00:15<00:06, 58.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 87%|████████▋ | 2.18G/2.50G [00:15<00:05, 65.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 2.20G/2.50G [00:15<00:04, 81.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 2.21G/2.50G [00:15<00:03, 96.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 89%|████████▉ | 2.22G/2.50G [00:17<00:13, 22.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 89%|████████▉ | 2.23G/2.50G [00:17<00:13, 20.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 89%|████████▉ | 2.24G/2.50G [00:18<00:12, 23.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|████████▉ | 2.24G/2.50G [00:18<00:10, 26.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|████████▉ | 2.25G/2.50G [00:18<00:08, 30.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 2.26G/2.50G [00:18<00:07, 36.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 2.27G/2.50G [00:18<00:06, 40.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 91%|█████████ | 2.27G/2.50G [00:18<00:05, 47.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 91%|█████████ | 2.28G/2.50G [00:18<00:05, 44.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.29G/2.50G [00:19<00:04, 56.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.30G/2.50G [00:19<00:04, 48.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.30G/2.50G [00:19<00:05, 41.8MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.31G/2.50G [00:19<00:03, 54.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 2.32G/2.50G [00:19<00:03, 60.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 2.33G/2.50G [00:19<00:02, 70.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▎| 2.34G/2.50G [00:19<00:02, 72.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 2.35G/2.50G [00:20<00:02, 74.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 2.36G/2.50G [00:20<00:01, 87.8MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 95%|█████████▌| 2.38G/2.50G [00:20<00:01, 113MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 2.39G/2.50G [00:20<00:01, 85.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 2.40G/2.50G [00:20<00:01, 85.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▋| 2.41G/2.50G [00:20<00:00, 98.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 97%|█████████▋| 2.43G/2.50G [00:20<00:00, 89.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 2.45G/2.50G [00:21<00:00, 106MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 2.46G/2.50G [00:21<00:00, 85.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 99%|█████████▉| 2.47G/2.50G [00:21<00:00, 103MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 99%|█████████▉| 2.48G/2.50G [00:22<00:00, 29.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|█████████▉| 2.49G/2.50G [00:22<00:00, 32.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|█████████▉| 2.50G/2.50G [00:22<00:00, 41.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 2.50G/2.50G [00:22<00:00, 118MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 0.00/1.35G [00:00<?, ?B/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 4.01M/1.35G [00:00<00:38, 37.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 16.0M/1.35G [00:00<00:19, 72.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 35.7M/1.35G [00:00<00:11, 126MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 56.0M/1.35G [00:00<00:09, 153MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▌         | 75.6M/1.35G [00:00<00:07, 171MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 92.4M/1.35G [00:00<00:08, 164MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  9%|▉         | 122M/1.35G [00:00<00:06, 208MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 11%|█         | 149M/1.35G [00:00<00:05, 233MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 13%|█▎        | 182M/1.35G [00:00<00:04, 266MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 15%|█▌        | 208M/1.35G [00:01<00:04, 269MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 238M/1.35G [00:01<00:04, 283MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 20%|█▉        | 273M/1.35G [00:01<00:03, 308MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 303M/1.35G [00:01<00:04, 278MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 24%|██▍       | 335M/1.35G [00:01<00:03, 293MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 367M/1.35G [00:01<00:03, 306MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▉       | 402M/1.35G [00:01<00:03, 325MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 32%|███▏      | 437M/1.35G [00:01<00:02, 337MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 34%|███▍      | 473M/1.35G [00:01<00:02, 347MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 37%|███▋      | 507M/1.35G [00:02<00:02, 352MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 39%|███▉      | 541M/1.35G [00:02<00:04, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 41%|████▏     | 570M/1.35G [00:02<00:03, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▍     | 605M/1.35G [00:02<00:03, 257MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 46%|████▌     | 635M/1.35G [00:02<00:03, 239MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 48%|████▊     | 661M/1.35G [00:02<00:03, 202MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 50%|█████     | 692M/1.35G [00:02<00:03, 228MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 53%|█████▎    | 725M/1.35G [00:03<00:02, 257MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 55%|█████▍    | 753M/1.35G [00:03<00:03, 179MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 57%|█████▋    | 786M/1.35G [00:03<00:02, 211MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 59%|█████▉    | 819M/1.35G [00:03<00:02, 240MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 61%|██████▏   | 846M/1.35G [00:03<00:02, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 882M/1.35G [00:03<00:02, 259MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▌   | 910M/1.35G [00:04<00:02, 212MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 939M/1.35G [00:04<00:01, 234MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 70%|███████   | 967M/1.35G [00:04<00:02, 173MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 0.98G/1.35G [00:04<00:01, 211MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 75%|███████▌  | 1.01G/1.35G [00:04<00:01, 247MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.04G/1.35G [00:04<00:01, 215MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▉  | 1.07G/1.35G [00:04<00:01, 216MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████  | 1.09G/1.35G [00:05<00:01, 223MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 1.12G/1.35G [00:05<00:01, 170MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▌ | 1.15G/1.35G [00:05<00:01, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 1.19G/1.35G [00:05<00:00, 242MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 91%|█████████ | 1.22G/1.35G [00:05<00:00, 270MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 1.25G/1.35G [00:05<00:00, 293MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 1.29G/1.35G [00:05<00:00, 314MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 1.32G/1.35G [00:05<00:00, 267MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 1.35G/1.35G [00:06<00:00, 221MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "obj = sm.SummaryDetector(mydict)\n",
    "summary_model, summary_vis_processors = obj.load_model(model_type=\"base\")\n",
    "# summary_model, summary_vis_processors = mutils.load_model(\"large\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:07.941454Z",
     "iopub.status.busy": "2023-06-27T09:05:07.940339Z",
     "iopub.status.idle": "2023-06-27T09:05:49.783091Z",
     "shell.execute_reply": "2023-06-27T09:05:49.781170Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "analyse_image() got an unexpected keyword argument 'summary_model'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[6], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m mydict:\n\u001b[0;32m----> 2\u001b[0m     mydict[key] \u001b[38;5;241m=\u001b[39m \u001b[43msm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSummaryDetector\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m[\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43manalyse_image\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      3\u001b[0m \u001b[43m        \u001b[49m\u001b[43msummary_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msummary_model\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msummary_vis_processors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msummary_vis_processors\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[0;31mTypeError\u001b[0m: analyse_image() got an unexpected keyword argument 'summary_model'"
     ]
    }
   ],
   "source": [
    "for key in mydict:\n",
    "    mydict[key] = sm.SummaryDetector(mydict[key]).analyse_image(\n",
    "        summary_model=summary_model, summary_vis_processors=summary_vis_processors\n",
    "    )"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Convert the dictionary of dictionarys into a dictionary with lists:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:49.846542Z",
     "iopub.status.busy": "2023-06-27T09:05:49.845037Z",
     "iopub.status.idle": "2023-06-27T09:05:49.929066Z",
     "shell.execute_reply": "2023-06-27T09:05:49.928420Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "outdict = mutils.append_data_to_dict(mydict)\n",
    "df = mutils.dump_df(outdict)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the dataframe:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:49.935760Z",
     "iopub.status.busy": "2023-06-27T09:05:49.935520Z",
     "iopub.status.idle": "2023-06-27T09:05:50.071123Z",
     "shell.execute_reply": "2023-06-27T09:05:50.070326Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>filename</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>data/106349S_por.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>data/102141_2_eng.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>data/102730_eng.png</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                filename\n",
       "0   data/106349S_por.png\n",
       "1  data/102141_2_eng.png\n",
       "2    data/102730_eng.png"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Write the csv file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:50.085192Z",
     "iopub.status.busy": "2023-06-27T09:05:50.084726Z",
     "iopub.status.idle": "2023-06-27T09:05:50.131221Z",
     "shell.execute_reply": "2023-06-27T09:05:50.130584Z"
    }
   },
   "outputs": [],
   "source": [
    "df.to_csv(\"data_out.csv\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Manually inspect the summaries\n",
    "\n",
    "To check the analysis, you can inspect the analyzed elements here. Loading the results takes a moment, so please be patient. If you are sure of what you are doing.\n",
    "\n",
    "`const_image_summary` - the permanent summarys, which does not change from run to run (analyse_image).\n",
    "\n",
    "`3_non-deterministic summary` - 3 different summarys examples that change from run to run (analyse_image). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:50.136495Z",
     "iopub.status.busy": "2023-06-27T09:05:50.136136Z",
     "iopub.status.idle": "2023-06-27T09:05:50.168474Z",
     "shell.execute_reply": "2023-06-27T09:05:50.167780Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "__init__() got an unexpected keyword argument 'identify'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m analysis_explorer \u001b[38;5;241m=\u001b[39m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mAnalysisExplorer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midentify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msummary\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m analysis_explorer\u001b[38;5;241m.\u001b[39mrun_server(port\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m8055\u001b[39m)\n",
      "\u001b[0;31mTypeError\u001b[0m: __init__() got an unexpected keyword argument 'identify'"
     ]
    }
   ],
   "source": [
    "analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
    "analysis_explorer.run_server(port=8055)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Generate answers to free-form questions about images written in natural language. "
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set the list of questions as a list of strings:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:50.175012Z",
     "iopub.status.busy": "2023-06-27T09:05:50.174534Z",
     "iopub.status.idle": "2023-06-27T09:05:50.178293Z",
     "shell.execute_reply": "2023-06-27T09:05:50.177589Z"
    }
   },
   "outputs": [],
   "source": [
    "list_of_questions = [\n",
    "    \"How many persons on the picture?\",\n",
    "    \"Are there any politicians in the picture?\",\n",
    "    \"Does the picture show something from medicine?\",\n",
    "]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Explore the analysis using the interface:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:50.183463Z",
     "iopub.status.busy": "2023-06-27T09:05:50.182925Z",
     "iopub.status.idle": "2023-06-27T09:05:50.212836Z",
     "shell.execute_reply": "2023-06-27T09:05:50.212044Z"
    }
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "__init__() got an unexpected keyword argument 'identify'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m analysis_explorer \u001b[38;5;241m=\u001b[39m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mAnalysisExplorer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midentify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msummary\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m analysis_explorer\u001b[38;5;241m.\u001b[39mrun_server(port\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m8055\u001b[39m)\n",
      "\u001b[0;31mTypeError\u001b[0m: __init__() got an unexpected keyword argument 'identify'"
     ]
    }
   ],
   "source": [
    "analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
    "analysis_explorer.run_server(port=8055)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Or directly analyze for further processing\n",
    "Instead of inspecting each of the images, you can also directly carry out the analysis and export the result into a csv. This may take a while depending on how many images you have loaded."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:05:50.217587Z",
     "iopub.status.busy": "2023-06-27T09:05:50.217229Z",
     "iopub.status.idle": "2023-06-27T09:07:33.102446Z",
     "shell.execute_reply": "2023-06-27T09:07:33.100338Z"
    }
   },
   "outputs": [],
   "source": [
    "for key in mydict:\n",
    "    mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Convert to dataframe and write csv\n",
    "These steps are required to convert the dictionary of dictionarys into a dictionary with lists, that can be converted into a pandas dataframe and exported to a csv file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:07:33.184466Z",
     "iopub.status.busy": "2023-06-27T09:07:33.183900Z",
     "iopub.status.idle": "2023-06-27T09:07:33.194912Z",
     "shell.execute_reply": "2023-06-27T09:07:33.194204Z"
    }
   },
   "outputs": [],
   "source": [
    "outdict2 = mutils.append_data_to_dict(mydict)\n",
    "df2 = mutils.dump_df(outdict2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:07:33.199785Z",
     "iopub.status.busy": "2023-06-27T09:07:33.199557Z",
     "iopub.status.idle": "2023-06-27T09:07:33.216692Z",
     "shell.execute_reply": "2023-06-27T09:07:33.216036Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>filename</th>\n",
       "      <th>How many persons on the picture?</th>\n",
       "      <th>Are there any politicians in the picture?</th>\n",
       "      <th>Does the picture show something from medicine?</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>data/106349S_por.png</td>\n",
       "      <td>1</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>data/102141_2_eng.png</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>data/102730_eng.png</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                filename How many persons on the picture?  \\\n",
       "0   data/106349S_por.png                                1   \n",
       "1  data/102141_2_eng.png                                1   \n",
       "2    data/102730_eng.png                                2   \n",
       "\n",
       "  Are there any politicians in the picture?  \\\n",
       "0                                       yes   \n",
       "1                                        no   \n",
       "2                                        no   \n",
       "\n",
       "  Does the picture show something from medicine?  \n",
       "0                                            yes  \n",
       "1                                            yes  \n",
       "2                                            yes  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-27T09:07:33.222046Z",
     "iopub.status.busy": "2023-06-27T09:07:33.221438Z",
     "iopub.status.idle": "2023-06-27T09:07:33.228304Z",
     "shell.execute_reply": "2023-06-27T09:07:33.226867Z"
    }
   },
   "outputs": [],
   "source": [
    "df2.to_csv(\"data_out2.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.9.17"
  },
  "vscode": {
   "interpreter": {
    "hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}