{
 "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": "2023-09-18T09:54:46.905930Z",
     "iopub.status.busy": "2023-09-18T09:54:46.905517Z",
     "iopub.status.idle": "2023-09-18T09:54:46.913913Z",
     "shell.execute_reply": "2023-09-18T09:54:46.913307Z"
    }
   },
   "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": "2023-09-18T09:54:46.917007Z",
     "iopub.status.busy": "2023-09-18T09:54:46.916440Z",
     "iopub.status.idle": "2023-09-18T09:54:57.533366Z",
     "shell.execute_reply": "2023-09-18T09:54:57.532708Z"
    },
    "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": "2023-09-18T09:54:57.536974Z",
     "iopub.status.busy": "2023-09-18T09:54:57.536124Z",
     "iopub.status.idle": "2023-09-18T09:54:57.541743Z",
     "shell.execute_reply": "2023-09-18T09:54:57.541166Z"
    },
    "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": "2023-09-18T09:54:57.544632Z",
     "iopub.status.busy": "2023-09-18T09:54:57.544208Z",
     "iopub.status.idle": "2023-09-18T09:54:57.548381Z",
     "shell.execute_reply": "2023-09-18T09:54:57.547797Z"
    },
    "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": "2023-09-18T09:54:57.551332Z",
     "iopub.status.busy": "2023-09-18T09:54:57.550718Z",
     "iopub.status.idle": "2023-09-18T09:56:04.546623Z",
     "shell.execute_reply": "2023-09-18T09:56:04.541379Z"
    },
    "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<01:28, 30.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 11.6M/2.50G [00:00<00:48, 55.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 17.3M/2.50G [00:00<00:51, 52.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 24.0M/2.50G [00:00<00:45, 58.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 32.0M/2.50G [00:00<00:40, 65.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 40.0M/2.50G [00:00<00:37, 70.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 48.0M/2.50G [00:00<00:36, 73.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 56.1M/2.50G [00:00<00:34, 76.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 64.8M/2.50G [00:00<00:32, 81.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 73.4M/2.50G [00:01<00:31, 83.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 82.8M/2.50G [00:01<00:29, 88.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▎         | 91.4M/2.50G [00:01<00:29, 89.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 102M/2.50G [00:01<00:27, 94.6MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 112M/2.50G [00:01<00:30, 83.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▍         | 128M/2.50G [00:01<00:24, 104MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▌         | 144M/2.50G [00:01<00:21, 119MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▌         | 160M/2.50G [00:01<00:18, 133MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 176M/2.50G [00:01<00:17, 143MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 193M/2.50G [00:02<00:16, 152MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 210M/2.50G [00:02<00:15, 161MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  9%|▉         | 228M/2.50G [00:02<00:14, 169MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|▉         | 248M/2.50G [00:02<00:13, 179MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|█         | 269M/2.50G [00:02<00:12, 192MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 11%|█         | 287M/2.50G [00:02<00:12, 191MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 310M/2.50G [00:02<00:11, 204MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 13%|█▎        | 336M/2.50G [00:02<00:10, 224MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 14%|█▍        | 360M/2.50G [00:02<00:10, 214MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 15%|█▌        | 386M/2.50G [00:02<00:09, 232MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 16%|█▌        | 414M/2.50G [00:03<00:09, 247MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 439M/2.50G [00:03<00:08, 254MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 18%|█▊        | 469M/2.50G [00:03<00:08, 271MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 19%|█▉        | 497M/2.50G [00:03<00:07, 277MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 20%|██        | 524M/2.50G [00:03<00:11, 178MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 554M/2.50G [00:03<00:10, 208MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 23%|██▎       | 583M/2.50G [00:03<00:09, 231MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 24%|██▎       | 609M/2.50G [00:04<00:09, 222MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 25%|██▍       | 635M/2.50G [00:04<00:08, 237MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 26%|██▌       | 660M/2.50G [00:04<00:21, 94.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 685M/2.50G [00:04<00:16, 117MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 28%|██▊       | 706M/2.50G [00:05<00:15, 127MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 28%|██▊       | 730M/2.50G [00:05<00:12, 149MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▉       | 756M/2.50G [00:05<00:10, 173MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 30%|███       | 780M/2.50G [00:05<00:09, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 31%|███▏      | 807M/2.50G [00:05<00:08, 214MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 32%|███▏      | 831M/2.50G [00:05<00:08, 223MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 34%|███▎      | 861M/2.50G [00:05<00:07, 247MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 35%|███▍      | 887M/2.50G [00:05<00:07, 250MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 36%|███▌      | 913M/2.50G [00:05<00:06, 257MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 37%|███▋      | 942M/2.50G [00:05<00:06, 271MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 38%|███▊      | 969M/2.50G [00:06<00:08, 192MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 39%|███▉      | 999M/2.50G [00:06<00:07, 220MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 40%|███▉      | 1.00G/2.50G [00:06<00:11, 143MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 41%|████      | 1.03G/2.50G [00:06<00:09, 168MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 42%|████▏     | 1.05G/2.50G [00:06<00:07, 197MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 43%|████▎     | 1.08G/2.50G [00:06<00:06, 218MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▍     | 1.11G/2.50G [00:07<00:08, 186MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 45%|████▌     | 1.14G/2.50G [00:07<00:06, 214MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 46%|████▋     | 1.16G/2.50G [00:07<00:06, 231MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 48%|████▊     | 1.19G/2.50G [00:07<00:05, 247MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 49%|████▊     | 1.22G/2.50G [00:07<00:05, 263MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 50%|████▉     | 1.24G/2.50G [00:07<00:08, 163MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 51%|█████     | 1.27G/2.50G [00:07<00:06, 189MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 52%|█████▏    | 1.30G/2.50G [00:08<00:05, 216MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 53%|█████▎    | 1.33G/2.50G [00:08<00:05, 239MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 54%|█████▍    | 1.36G/2.50G [00:08<00:04, 250MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 55%|█████▌    | 1.38G/2.50G [00:08<00:04, 253MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 56%|█████▋    | 1.41G/2.50G [00:08<00:04, 268MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 58%|█████▊    | 1.44G/2.50G [00:08<00:04, 279MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 59%|█████▊    | 1.47G/2.50G [00:08<00:03, 283MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 60%|█████▉    | 1.50G/2.50G [00:08<00:03, 286MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 61%|██████    | 1.52G/2.50G [00:09<00:06, 174MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 62%|██████▏   | 1.55G/2.50G [00:09<00:05, 194MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 63%|██████▎   | 1.58G/2.50G [00:09<00:08, 117MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 1.61G/2.50G [00:09<00:06, 147MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 65%|██████▌   | 1.64G/2.50G [00:09<00:05, 173MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▋   | 1.66G/2.50G [00:09<00:04, 195MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 67%|██████▋   | 1.69G/2.50G [00:10<00:04, 216MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▊   | 1.72G/2.50G [00:10<00:03, 234MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 70%|██████▉   | 1.74G/2.50G [00:10<00:04, 199MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████   | 1.77G/2.50G [00:10<00:03, 217MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 72%|███████▏  | 1.79G/2.50G [00:10<00:03, 228MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 1.82G/2.50G [00:10<00:02, 251MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 74%|███████▍  | 1.85G/2.50G [00:10<00:02, 247MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 75%|███████▍  | 1.88G/2.50G [00:10<00:02, 260MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 76%|███████▌  | 1.90G/2.50G [00:10<00:02, 267MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 77%|███████▋  | 1.93G/2.50G [00:11<00:03, 155MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.96G/2.50G [00:11<00:03, 184MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▉  | 1.98G/2.50G [00:11<00:02, 212MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 80%|████████  | 2.01G/2.50G [00:11<00:02, 211MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████▏ | 2.04G/2.50G [00:11<00:02, 233MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 82%|████████▏ | 2.06G/2.50G [00:11<00:01, 243MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 2.09G/2.50G [00:11<00:01, 253MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 85%|████████▍ | 2.12G/2.50G [00:12<00:01, 266MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▌ | 2.15G/2.50G [00:12<00:01, 276MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 87%|████████▋ | 2.17G/2.50G [00:12<00:01, 282MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 2.20G/2.50G [00:12<00:01, 284MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 89%|████████▉ | 2.23G/2.50G [00:12<00:01, 286MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 2.26G/2.50G [00:12<00:00, 292MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 91%|█████████ | 2.28G/2.50G [00:12<00:00, 266MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.31G/2.50G [00:12<00:00, 278MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 2.34G/2.50G [00:12<00:00, 281MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 95%|█████████▍| 2.37G/2.50G [00:13<00:00, 285MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 2.39G/2.50G [00:13<00:00, 238MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 97%|█████████▋| 2.42G/2.50G [00:13<00:00, 255MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 2.45G/2.50G [00:13<00:00, 269MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 99%|█████████▉| 2.48G/2.50G [00:13<00:00, 281MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 2.50G/2.50G [00:13<00:00, 198MB/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<00:50, 28.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 12.0M/1.35G [00:00<00:25, 55.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|▏         | 20.1M/1.35G [00:00<00:20, 68.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 27.0M/1.35G [00:00<00:20, 69.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 46.4M/1.35G [00:00<00:12, 115MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▍         | 64.0M/1.35G [00:00<00:12, 107MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▌         | 74.7M/1.35G [00:00<00:13, 99.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▌         | 84.5M/1.35G [00:00<00:14, 93.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 93.6M/1.35G [00:01<00:15, 87.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 104M/1.35G [00:01<00:16, 80.7MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 114M/1.35G [00:01<00:15, 87.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|█         | 144M/1.35G [00:01<00:09, 143MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 160M/1.35G [00:01<00:08, 148MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 13%|█▎        | 176M/1.35G [00:01<00:08, 150MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 14%|█▍        | 198M/1.35G [00:01<00:07, 171MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 16%|█▌        | 220M/1.35G [00:01<00:06, 188MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 238M/1.35G [00:02<00:08, 147MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 18%|█▊        | 254M/1.35G [00:02<00:09, 121MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 20%|██        | 277M/1.35G [00:02<00:07, 148MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 21%|██▏       | 293M/1.35G [00:02<00:08, 135MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 308M/1.35G [00:02<00:08, 139MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 23%|██▎       | 322M/1.35G [00:02<00:08, 134MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 25%|██▌       | 351M/1.35G [00:02<00:06, 177MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 370M/1.35G [00:03<00:08, 122MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▉       | 399M/1.35G [00:03<00:06, 161MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 31%|███       | 425M/1.35G [00:03<00:05, 186MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 33%|███▎      | 454M/1.35G [00:03<00:04, 214MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 35%|███▍      | 478M/1.35G [00:03<00:04, 224MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 37%|███▋      | 507M/1.35G [00:03<00:03, 246MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 39%|███▊      | 533M/1.35G [00:03<00:03, 248MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 40%|████      | 558M/1.35G [00:03<00:03, 249MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 42%|████▏     | 582M/1.35G [00:03<00:03, 248MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▍     | 608M/1.35G [00:04<00:04, 184MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 46%|████▌     | 632M/1.35G [00:04<00:04, 193MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 48%|████▊     | 661M/1.35G [00:04<00:03, 221MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 50%|████▉     | 687M/1.35G [00:04<00:03, 234MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 52%|█████▏    | 712M/1.35G [00:04<00:02, 240MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 54%|█████▍    | 741M/1.35G [00:04<00:02, 259MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 56%|█████▌    | 768M/1.35G [00:04<00:02, 241MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 58%|█████▊    | 797M/1.35G [00:04<00:02, 257MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 60%|█████▉    | 826M/1.35G [00:05<00:02, 272MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 62%|██████▏   | 853M/1.35G [00:05<00:02, 191MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 880M/1.35G [00:05<00:02, 212MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▌   | 904M/1.35G [00:05<00:02, 181MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 932M/1.35G [00:05<00:02, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▉   | 955M/1.35G [00:05<00:02, 155MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████   | 975M/1.35G [00:06<00:02, 167MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 0.98G/1.35G [00:06<00:01, 199MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 74%|███████▍  | 1.00G/1.35G [00:06<00:01, 206MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 76%|███████▌  | 1.03G/1.35G [00:06<00:01, 213MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.05G/1.35G [00:06<00:01, 237MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 80%|████████  | 1.08G/1.35G [00:06<00:01, 254MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 82%|████████▏ | 1.11G/1.35G [00:06<00:01, 251MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 84%|████████▍ | 1.13G/1.35G [00:06<00:00, 263MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▋ | 1.16G/1.35G [00:06<00:00, 276MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 1.19G/1.35G [00:06<00:00, 280MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 1.22G/1.35G [00:07<00:00, 285MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 1.24G/1.35G [00:07<00:00, 269MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 1.27G/1.35G [00:07<00:00, 164MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 1.29G/1.35G [00:07<00:00, 181MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 1.32G/1.35G [00:07<00:00, 210MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|█████████▉| 1.35G/1.35G [00:08<00:00, 129MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 1.35G/1.35G [00:08<00:00, 178MB/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": "2023-09-18T09:56:04.585109Z",
     "iopub.status.busy": "2023-09-18T09:56:04.584036Z",
     "iopub.status.idle": "2023-09-18T09:56:45.770274Z",
     "shell.execute_reply": "2023-09-18T09:56:45.769474Z"
    },
    "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": "2023-09-18T09:56:45.783809Z",
     "iopub.status.busy": "2023-09-18T09:56:45.783340Z",
     "iopub.status.idle": "2023-09-18T09:56:45.809657Z",
     "shell.execute_reply": "2023-09-18T09:56:45.809014Z"
    },
    "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": "2023-09-18T09:56:45.814126Z",
     "iopub.status.busy": "2023-09-18T09:56:45.813560Z",
     "iopub.status.idle": "2023-09-18T09:56:45.856440Z",
     "shell.execute_reply": "2023-09-18T09:56:45.855613Z"
    },
    "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>102141_2_eng</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>102730_eng</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>106349S_por</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       filename\n",
       "0  102141_2_eng\n",
       "1    102730_eng\n",
       "2   106349S_por"
      ]
     },
     "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": "2023-09-18T09:56:45.863713Z",
     "iopub.status.busy": "2023-09-18T09:56:45.863464Z",
     "iopub.status.idle": "2023-09-18T09:56:45.878075Z",
     "shell.execute_reply": "2023-09-18T09:56:45.877481Z"
    }
   },
   "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": "2023-09-18T09:56:45.883715Z",
     "iopub.status.busy": "2023-09-18T09:56:45.883185Z",
     "iopub.status.idle": "2023-09-18T09:56:45.917234Z",
     "shell.execute_reply": "2023-09-18T09:56:45.916200Z"
    },
    "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": "2023-09-18T09:56:45.922991Z",
     "iopub.status.busy": "2023-09-18T09:56:45.922552Z",
     "iopub.status.idle": "2023-09-18T09:56:45.926675Z",
     "shell.execute_reply": "2023-09-18T09:56:45.925667Z"
    }
   },
   "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": "2023-09-18T09:56:45.930421Z",
     "iopub.status.busy": "2023-09-18T09:56:45.930043Z",
     "iopub.status.idle": "2023-09-18T09:56:45.961350Z",
     "shell.execute_reply": "2023-09-18T09:56:45.960415Z"
    }
   },
   "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": "2023-09-18T09:56:45.966415Z",
     "iopub.status.busy": "2023-09-18T09:56:45.965918Z",
     "iopub.status.idle": "2023-09-18T09:57:20.186476Z",
     "shell.execute_reply": "2023-09-18T09:57:20.184777Z"
    }
   },
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: '102141_2_eng'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[13], 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_questions\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlist_of_questions\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/work/AMMICO/AMMICO/ammico/summary.py:244\u001b[0m, in \u001b[0;36mSummaryDetector.analyse_questions\u001b[0;34m(self, list_of_questions)\u001b[0m\n\u001b[1;32m    242\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(list_of_questions) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m    243\u001b[0m     path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubdict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfilename\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m--> 244\u001b[0m     raw_image \u001b[38;5;241m=\u001b[39m \u001b[43mImage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mconvert(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRGB\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    245\u001b[0m     image \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    246\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msummary_vqa_vis_processors[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124meval\u001b[39m\u001b[38;5;124m\"\u001b[39m](raw_image)\n\u001b[1;32m    247\u001b[0m         \u001b[38;5;241m.\u001b[39munsqueeze(\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m    248\u001b[0m         \u001b[38;5;241m.\u001b[39mto(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msummary_device)\n\u001b[1;32m    249\u001b[0m     )\n\u001b[1;32m    250\u001b[0m     question_batch \u001b[38;5;241m=\u001b[39m []\n",
      "File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/PIL/Image.py:3236\u001b[0m, in \u001b[0;36mopen\u001b[0;34m(fp, mode, formats)\u001b[0m\n\u001b[1;32m   3233\u001b[0m     filename \u001b[38;5;241m=\u001b[39m fp\n\u001b[1;32m   3235\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m filename:\n\u001b[0;32m-> 3236\u001b[0m     fp \u001b[38;5;241m=\u001b[39m \u001b[43mbuiltins\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrb\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3237\u001b[0m     exclusive_fp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m   3239\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '102141_2_eng'"
     ]
    }
   ],
   "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": "2023-09-18T09:57:20.212577Z",
     "iopub.status.busy": "2023-09-18T09:57:20.211741Z",
     "iopub.status.idle": "2023-09-18T09:57:20.265917Z",
     "shell.execute_reply": "2023-09-18T09:57:20.265077Z"
    }
   },
   "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": "2023-09-18T09:57:20.271455Z",
     "iopub.status.busy": "2023-09-18T09:57:20.270897Z",
     "iopub.status.idle": "2023-09-18T09:57:20.324003Z",
     "shell.execute_reply": "2023-09-18T09:57:20.323246Z"
    }
   },
   "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>102141_2_eng</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>102730_eng</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>106349S_por</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       filename\n",
       "0  102141_2_eng\n",
       "1    102730_eng\n",
       "2   106349S_por"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-18T09:57:20.329964Z",
     "iopub.status.busy": "2023-09-18T09:57:20.329711Z",
     "iopub.status.idle": "2023-09-18T09:57:20.340460Z",
     "shell.execute_reply": "2023-09-18T09:57:20.339853Z"
    }
   },
   "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": "3.9.18"
  },
  "vscode": {
   "interpreter": {
    "hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}