{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Image summary and visual question answering"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebooks shows some preliminary work on Image Captioning and Visual question answering with lavis. It is mainly meant to explore its capabilities and to decide on future research directions. We package our code into a `ammico` package that is imported here:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:06:18.706226Z",
     "iopub.status.busy": "2023-05-16T09:06:18.705880Z",
     "iopub.status.idle": "2023-05-16T09:06:28.916479Z",
     "shell.execute_reply": "2023-05-16T09:06:28.915819Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from ammico import utils as mutils\n",
    "from ammico import display as mdisplay\n",
    "import ammico.summary as sm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set an image path as input file path."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:06:28.919753Z",
     "iopub.status.busy": "2023-05-16T09:06:28.919147Z",
     "iopub.status.idle": "2023-05-16T09:06:28.922900Z",
     "shell.execute_reply": "2023-05-16T09:06:28.922291Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "images = mutils.find_files(\n",
    "    path=\"data/\",\n",
    "    limit=10,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:06:28.925831Z",
     "iopub.status.busy": "2023-05-16T09:06:28.925286Z",
     "iopub.status.idle": "2023-05-16T09:06:28.928378Z",
     "shell.execute_reply": "2023-05-16T09:06:28.927805Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "mydict = mutils.initialize_dict(images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create captions for images and directly write to csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here you can choose between two models: \"base\" or \"large\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:06:28.930935Z",
     "iopub.status.busy": "2023-05-16T09:06:28.930593Z",
     "iopub.status.idle": "2023-05-16T09:06:58.888508Z",
     "shell.execute_reply": "2023-05-16T09:06:58.887817Z"
    },
    "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<01:20, 33.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 10.1M/2.50G [00:00<00:54, 49.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 18.7M/2.50G [00:00<00:39, 66.8MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 27.9M/2.50G [00:00<00:33, 78.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|▏         | 38.3M/2.50G [00:00<00:29, 89.2MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 47.0M/2.50G [00:00<00:29, 89.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 55.5M/2.50G [00:00<00:29, 87.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 64.0M/2.50G [00:00<00:35, 74.5MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 72.5M/2.50G [00:00<00:33, 78.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 80.2M/2.50G [00:01<00:33, 78.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▎         | 96.0M/2.50G [00:01<00:26, 98.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 112M/2.50G [00:01<00:21, 118MB/s]  "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▍         | 128M/2.50G [00:01<00:19, 128MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▌         | 144M/2.50G [00:01<00:19, 132MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  6%|▋         | 164M/2.50G [00:01<00:16, 152MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 179M/2.50G [00:01<00:16, 151MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 196M/2.50G [00:01<00:15, 159MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  8%|▊         | 211M/2.50G [00:01<00:15, 160MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  9%|▉         | 232M/2.50G [00:02<00:14, 174MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|▉         | 250M/2.50G [00:02<00:13, 180MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 11%|█         | 272M/2.50G [00:02<00:14, 171MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 296M/2.50G [00:02<00:12, 193MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 315M/2.50G [00:02<00:12, 189MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 13%|█▎        | 336M/2.50G [00:02<00:12, 193MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 14%|█▍        | 360M/2.50G [00:02<00:11, 206MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 15%|█▌        | 390M/2.50G [00:02<00:13, 174MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 16%|█▋        | 419M/2.50G [00:03<00:10, 205MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 440M/2.50G [00:03<00:10, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 18%|█▊        | 461M/2.50G [00:03<00:11, 186MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 19%|█▉        | 488M/2.50G [00:03<00:10, 202MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 20%|█▉        | 512M/2.50G [00:03<00:11, 181MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 21%|██        | 538M/2.50G [00:03<00:10, 204MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 559M/2.50G [00:03<00:11, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 23%|██▎       | 584M/2.50G [00:03<00:11, 186MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 24%|██▎       | 603M/2.50G [00:04<00:20, 99.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 25%|██▍       | 632M/2.50G [00:04<00:15, 132MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 25%|██▌       | 652M/2.50G [00:04<00:13, 146MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 26%|██▌       | 672M/2.50G [00:04<00:12, 158MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 704M/2.50G [00:04<00:12, 160MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▊       | 737M/2.50G [00:05<00:09, 198MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 30%|██▉       | 760M/2.50G [00:05<00:09, 203MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 31%|███       | 784M/2.50G [00:05<00:08, 215MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 31%|███▏      | 807M/2.50G [00:05<00:08, 213MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 32%|███▏      | 832M/2.50G [00:05<00:08, 216MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 34%|███▎      | 862M/2.50G [00:05<00:07, 243MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 35%|███▍      | 895M/2.50G [00:05<00:06, 268MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 36%|███▌      | 921M/2.50G [00:05<00:06, 272MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 37%|███▋      | 948M/2.50G [00:05<00:06, 271MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 38%|███▊      | 979M/2.50G [00:06<00:05, 286MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 39%|███▉      | 0.99G/2.50G [00:06<00:05, 296MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 40%|████      | 1.01G/2.50G [00:06<00:06, 233MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 42%|████▏     | 1.04G/2.50G [00:06<00:06, 256MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 43%|████▎     | 1.07G/2.50G [00:06<00:05, 265MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 44%|████▍     | 1.11G/2.50G [00:06<00:05, 295MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 45%|████▌     | 1.13G/2.50G [00:06<00:05, 286MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 46%|████▋     | 1.16G/2.50G [00:06<00:04, 289MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 48%|████▊     | 1.19G/2.50G [00:06<00:04, 299MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 49%|████▉     | 1.22G/2.50G [00:07<00:04, 298MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 50%|████▉     | 1.25G/2.50G [00:07<00:04, 288MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 51%|█████     | 1.28G/2.50G [00:07<00:04, 296MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 52%|█████▏    | 1.31G/2.50G [00:07<00:04, 307MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 54%|█████▎    | 1.34G/2.50G [00:07<00:04, 304MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 55%|█████▍    | 1.37G/2.50G [00:07<00:03, 314MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 56%|█████▌    | 1.40G/2.50G [00:07<00:04, 290MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 57%|█████▋    | 1.43G/2.50G [00:07<00:04, 288MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 58%|█████▊    | 1.45G/2.50G [00:07<00:04, 274MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 59%|█████▉    | 1.48G/2.50G [00:07<00:04, 265MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 60%|██████    | 1.51G/2.50G [00:08<00:04, 248MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 61%|██████    | 1.53G/2.50G [00:08<00:04, 242MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 62%|██████▏   | 1.55G/2.50G [00:08<00:04, 220MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 63%|██████▎   | 1.57G/2.50G [00:08<00:04, 208MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 1.60G/2.50G [00:08<00:04, 223MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 65%|██████▍   | 1.62G/2.50G [00:08<00:04, 206MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▌   | 1.64G/2.50G [00:08<00:04, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 67%|██████▋   | 1.67G/2.50G [00:08<00:03, 232MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 1.69G/2.50G [00:09<00:04, 197MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 1.71G/2.50G [00:10<00:21, 38.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▉   | 1.73G/2.50G [00:11<00:18, 45.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▉   | 1.74G/2.50G [00:11<00:15, 53.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 70%|███████   | 1.75G/2.50G [00:11<00:13, 61.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████   | 1.77G/2.50G [00:11<00:11, 69.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████   | 1.78G/2.50G [00:11<00:09, 81.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 72%|███████▏  | 1.80G/2.50G [00:11<00:08, 91.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 72%|███████▏  | 1.81G/2.50G [00:11<00:07, 98.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 1.84G/2.50G [00:11<00:05, 130MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 74%|███████▍  | 1.86G/2.50G [00:11<00:04, 156MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 75%|███████▍  | 1.88G/2.50G [00:12<00:04, 164MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 76%|███████▌  | 1.89G/2.50G [00:12<00:04, 156MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 76%|███████▋  | 1.91G/2.50G [00:12<00:07, 82.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 77%|███████▋  | 1.93G/2.50G [00:13<00:18, 33.8MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 77%|███████▋  | 1.94G/2.50G [00:14<00:16, 37.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.95G/2.50G [00:14<00:14, 42.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 78%|███████▊  | 1.95G/2.50G [00:14<00:12, 47.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▊  | 1.97G/2.50G [00:14<00:09, 62.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▉  | 1.98G/2.50G [00:14<00:08, 63.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 80%|███████▉  | 1.99G/2.50G [00:14<00:07, 73.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 80%|███████▉  | 2.00G/2.50G [00:14<00:07, 76.8MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████  | 2.02G/2.50G [00:14<00:05, 92.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████  | 2.03G/2.50G [00:15<00:04, 109MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 82%|████████▏ | 2.05G/2.50G [00:15<00:03, 144MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 2.07G/2.50G [00:15<00:03, 142MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 2.09G/2.50G [00:15<00:03, 140MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 84%|████████▍ | 2.10G/2.50G [00:15<00:03, 142MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 85%|████████▍ | 2.12G/2.50G [00:15<00:02, 140MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▌ | 2.14G/2.50G [00:15<00:02, 164MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 86%|████████▋ | 2.16G/2.50G [00:15<00:01, 184MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 87%|████████▋ | 2.19G/2.50G [00:15<00:01, 203MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 2.21G/2.50G [00:16<00:01, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 89%|████████▉ | 2.23G/2.50G [00:16<00:01, 183MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|████████▉ | 2.25G/2.50G [00:16<00:01, 175MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 2.26G/2.50G [00:16<00:01, 167MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 2.30G/2.50G [00:16<00:01, 216MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 2.32G/2.50G [00:16<00:01, 196MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 93%|█████████▎| 2.34G/2.50G [00:18<00:04, 36.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 2.35G/2.50G [00:18<00:03, 42.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 2.36G/2.50G [00:18<00:03, 48.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 95%|█████████▍| 2.37G/2.50G [00:18<00:02, 54.4MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 95%|█████████▌| 2.38G/2.50G [00:19<00:02, 58.0MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 2.39G/2.50G [00:19<00:01, 62.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 2.41G/2.50G [00:19<00:01, 74.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 97%|█████████▋| 2.42G/2.50G [00:19<00:00, 88.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 97%|█████████▋| 2.43G/2.50G [00:19<00:00, 87.1MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 2.45G/2.50G [00:19<00:00, 113MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 99%|█████████▊| 2.47G/2.50G [00:19<00:00, 128MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 99%|█████████▉| 2.48G/2.50G [00:20<00:00, 83.6MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 2.50G/2.50G [00:20<00:00, 134MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "obj = sm.SummaryDetector(mydict)\n",
    "summary_model, summary_vis_processors = obj.load_model(\"base\")\n",
    "# summary_model, summary_vis_processors = obj.load_model(\"large\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:06:58.892270Z",
     "iopub.status.busy": "2023-05-16T09:06:58.891705Z",
     "iopub.status.idle": "2023-05-16T09:07:33.768582Z",
     "shell.execute_reply": "2023-05-16T09:07:33.767942Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "for key in mydict:\n",
    "    mydict[key] = sm.SummaryDetector(mydict[key]).analyse_image(\n",
    "        summary_model, summary_vis_processors\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Convert the dictionary of dictionaries into a dictionary with lists:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:33.771870Z",
     "iopub.status.busy": "2023-05-16T09:07:33.771624Z",
     "iopub.status.idle": "2023-05-16T09:07:33.776629Z",
     "shell.execute_reply": "2023-05-16T09:07:33.775716Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "outdict = mutils.append_data_to_dict(mydict)\n",
    "df = mutils.dump_df(outdict)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the dataframe:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:33.779236Z",
     "iopub.status.busy": "2023-05-16T09:07:33.778889Z",
     "iopub.status.idle": "2023-05-16T09:07:33.790297Z",
     "shell.execute_reply": "2023-05-16T09:07:33.789679Z"
    },
    "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",
       "      <th>const_image_summary</th>\n",
       "      <th>3_non-deterministic summary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>data/102730_eng.png</td>\n",
       "      <td>two people in blue coats spray disinfection a van</td>\n",
       "      <td>[two men in blue coveralls are spraying someth...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>data/102141_2_eng.png</td>\n",
       "      <td>a collage of images including a corona sign, a...</td>\n",
       "      <td>[various photos with words on them and picture...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>data/106349S_por.png</td>\n",
       "      <td>a man wearing a face mask while looking at a c...</td>\n",
       "      <td>[man in sweater and mask on television holding...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                filename                                const_image_summary   \n",
       "0    data/102730_eng.png  two people in blue coats spray disinfection a van  \\\n",
       "1  data/102141_2_eng.png  a collage of images including a corona sign, a...   \n",
       "2   data/106349S_por.png  a man wearing a face mask while looking at a c...   \n",
       "\n",
       "                         3_non-deterministic summary  \n",
       "0  [two men in blue coveralls are spraying someth...  \n",
       "1  [various photos with words on them and picture...  \n",
       "2  [man in sweater and mask on television holding...  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Write the csv file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:33.792935Z",
     "iopub.status.busy": "2023-05-16T09:07:33.792595Z",
     "iopub.status.idle": "2023-05-16T09:07:33.797229Z",
     "shell.execute_reply": "2023-05-16T09:07:33.796672Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df.to_csv(\"./data_out.csv\")"
   ]
  },
  {
   "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": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:33.800641Z",
     "iopub.status.busy": "2023-05-16T09:07:33.800432Z",
     "iopub.status.idle": "2023-05-16T09:07:34.603284Z",
     "shell.execute_reply": "2023-05-16T09:07:34.602604Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'ammico.display' has no attribute 'explore_analysis'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[9], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexplore_analysis\u001b[49m(mydict, identify\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msummary\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "\u001b[0;31mAttributeError\u001b[0m: module 'ammico.display' has no attribute 'explore_analysis'"
     ]
    }
   ],
   "source": [
    "mdisplay.explore_analysis(mydict, identify=\"summary\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Generate answers to free-form questions about images written in natural language. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set the list of questions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:34.606284Z",
     "iopub.status.busy": "2023-05-16T09:07:34.605929Z",
     "iopub.status.idle": "2023-05-16T09:07:34.609143Z",
     "shell.execute_reply": "2023-05-16T09:07:34.608529Z"
    }
   },
   "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",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:07:34.611993Z",
     "iopub.status.busy": "2023-05-16T09:07:34.611437Z",
     "iopub.status.idle": "2023-05-16T09:08:20.283561Z",
     "shell.execute_reply": "2023-05-16T09:08:20.282870Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  0%|          | 0.00/1.35G [00:00<?, ?B/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  1%|          | 8.01M/1.35G [00:00<00:22, 63.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  2%|▏         | 23.1M/1.35G [00:00<00:12, 113MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 34.6M/1.35G [00:00<00:14, 98.7MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  3%|▎         | 44.5M/1.35G [00:00<00:19, 70.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  4%|▍         | 56.0M/1.35G [00:00<00:18, 73.3MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  5%|▌         | 72.0M/1.35G [00:00<00:14, 94.9MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  7%|▋         | 96.0M/1.35G [00:00<00:10, 131MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "  9%|▊         | 118M/1.35G [00:01<00:08, 156MB/s] "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 10%|█         | 141M/1.35G [00:01<00:07, 179MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 12%|█▏        | 161M/1.35G [00:01<00:06, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 14%|█▎        | 188M/1.35G [00:01<00:05, 215MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 16%|█▌        | 214M/1.35G [00:01<00:05, 232MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 17%|█▋        | 237M/1.35G [00:01<00:05, 236MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 19%|█▉        | 260M/1.35G [00:01<00:05, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 21%|██        | 287M/1.35G [00:01<00:04, 240MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 22%|██▏       | 310M/1.35G [00:01<00:05, 189MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 24%|██▍       | 335M/1.35G [00:02<00:05, 208MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 27%|██▋       | 370M/1.35G [00:02<00:04, 250MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 29%|██▉       | 404M/1.35G [00:02<00:03, 277MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 32%|███▏      | 435M/1.35G [00:02<00:03, 290MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 34%|███▍      | 470M/1.35G [00:02<00:03, 313MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 36%|███▋      | 501M/1.35G [00:02<00:03, 285MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 39%|███▊      | 532M/1.35G [00:02<00:02, 297MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 41%|████      | 566M/1.35G [00:02<00:02, 312MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 43%|████▎     | 596M/1.35G [00:03<00:04, 192MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 45%|████▍     | 620M/1.35G [00:03<00:04, 195MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 47%|████▋     | 645M/1.35G [00:03<00:03, 209MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 49%|████▊     | 672M/1.35G [00:03<00:03, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 51%|█████     | 699M/1.35G [00:03<00:02, 240MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 53%|█████▎    | 724M/1.35G [00:03<00:03, 182MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 54%|█████▍    | 751M/1.35G [00:03<00:03, 203MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 56%|█████▌    | 773M/1.35G [00:04<00:03, 187MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 58%|█████▊    | 795M/1.35G [00:04<00:03, 184MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 60%|█████▉    | 822M/1.35G [00:04<00:02, 207MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 62%|██████▏   | 849M/1.35G [00:04<00:02, 227MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 63%|██████▎   | 872M/1.35G [00:04<00:04, 111MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 64%|██████▍   | 890M/1.35G [00:04<00:04, 120MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 66%|██████▌   | 907M/1.35G [00:05<00:03, 128MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 68%|██████▊   | 933M/1.35G [00:05<00:02, 158MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 69%|██████▉   | 957M/1.35G [00:05<00:02, 178MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 71%|███████▏  | 984M/1.35G [00:05<00:02, 203MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 73%|███████▎  | 0.99G/1.35G [00:05<00:01, 224MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 75%|███████▌  | 1.01G/1.35G [00:05<00:01, 241MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 77%|███████▋  | 1.04G/1.35G [00:05<00:01, 246MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 79%|███████▉  | 1.06G/1.35G [00:05<00:01, 257MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 81%|████████  | 1.09G/1.35G [00:05<00:01, 262MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 83%|████████▎ | 1.12G/1.35G [00:06<00:01, 142MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 85%|████████▍ | 1.14G/1.35G [00:06<00:01, 168MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 87%|████████▋ | 1.17G/1.35G [00:06<00:00, 192MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 88%|████████▊ | 1.19G/1.35G [00:06<00:00, 202MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 90%|█████████ | 1.22G/1.35G [00:06<00:00, 221MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 92%|█████████▏| 1.24G/1.35G [00:06<00:00, 186MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 94%|█████████▍| 1.27G/1.35G [00:07<00:00, 208MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 96%|█████████▌| 1.29G/1.35G [00:07<00:00, 226MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " 98%|█████████▊| 1.32G/1.35G [00:07<00:00, 239MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|█████████▉| 1.34G/1.35G [00:07<00:00, 140MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "100%|██████████| 1.35G/1.35G [00:07<00:00, 190MB/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "for key in mydict:\n",
    "    mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:08:20.287610Z",
     "iopub.status.busy": "2023-05-16T09:08:20.286986Z",
     "iopub.status.idle": "2023-05-16T09:08:20.326900Z",
     "shell.execute_reply": "2023-05-16T09:08:20.326245Z"
    }
   },
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'ammico.display' has no attribute 'explore_analysis'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexplore_analysis\u001b[49m(mydict, identify\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msummary\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "\u001b[0;31mAttributeError\u001b[0m: module 'ammico.display' has no attribute 'explore_analysis'"
     ]
    }
   ],
   "source": [
    "mdisplay.explore_analysis(mydict, identify=\"summary\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Convert the dictionary of dictionarys into a dictionary with lists:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:08:20.329714Z",
     "iopub.status.busy": "2023-05-16T09:08:20.329505Z",
     "iopub.status.idle": "2023-05-16T09:08:20.334084Z",
     "shell.execute_reply": "2023-05-16T09:08:20.333449Z"
    }
   },
   "outputs": [],
   "source": [
    "outdict2 = mutils.append_data_to_dict(mydict)\n",
    "df2 = mutils.dump_df(outdict2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:08:20.336862Z",
     "iopub.status.busy": "2023-05-16T09:08:20.336646Z",
     "iopub.status.idle": "2023-05-16T09:08:20.346678Z",
     "shell.execute_reply": "2023-05-16T09:08:20.346039Z"
    }
   },
   "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>const_image_summary</th>\n",
       "      <th>3_non-deterministic summary</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/102730_eng.png</td>\n",
       "      <td>two people in blue coats spray disinfection a van</td>\n",
       "      <td>[two men in blue coveralls are spraying someth...</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>data/102141_2_eng.png</td>\n",
       "      <td>a collage of images including a corona sign, a...</td>\n",
       "      <td>[various photos with words on them and picture...</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>data/106349S_por.png</td>\n",
       "      <td>a man wearing a face mask while looking at a c...</td>\n",
       "      <td>[man in sweater and mask on television holding...</td>\n",
       "      <td>1</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                filename                                const_image_summary   \n",
       "0    data/102730_eng.png  two people in blue coats spray disinfection a van  \\\n",
       "1  data/102141_2_eng.png  a collage of images including a corona sign, a...   \n",
       "2   data/106349S_por.png  a man wearing a face mask while looking at a c...   \n",
       "\n",
       "                         3_non-deterministic summary   \n",
       "0  [two men in blue coveralls are spraying someth...  \\\n",
       "1  [various photos with words on them and picture...   \n",
       "2  [man in sweater and mask on television holding...   \n",
       "\n",
       "  How many persons on the picture? Are there any politicians in the picture?   \n",
       "0                                2                                        no  \\\n",
       "1                                1                                        no   \n",
       "2                                1                                       yes   \n",
       "\n",
       "  Does the picture show something from medicine?  \n",
       "0                                            yes  \n",
       "1                                            yes  \n",
       "2                                            yes  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-16T09:08:20.349896Z",
     "iopub.status.busy": "2023-05-16T09:08:20.349671Z",
     "iopub.status.idle": "2023-05-16T09:08:20.354091Z",
     "shell.execute_reply": "2023-05-16T09:08:20.353495Z"
    }
   },
   "outputs": [],
   "source": [
    "df2.to_csv(\"./data_out2.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.16"
  },
  "vscode": {
   "interpreter": {
    "hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}