09-Task-Evaluate_Data/03e1_EVAL_VIS_Reading_Metrics.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "7c9a9ba0-1fa4-467c-be6d-de2c92c50a30",
   "metadata": {},
   "source": [
    "# EVALUATION: Reading Metrics\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "ed68a5f5-cc8e-44cd-b916-6c4c8f4a9809",
   "metadata": {},
   "source": [
    "## Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "774c436e-1ab4-477b-ba08-dcf2008f1774",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from tqdm.notebook import tqdm\n",
    "from utils.utils import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "370f8463",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "in subfolder ../08-Data-Trial_Recordings/processed/total, no participant number could be identified.\n",
      "{'003': WindowsPath('../08-Data-Trial_Recordings/processed/003'), '004': WindowsPath('../08-Data-Trial_Recordings/processed/004'), '005': WindowsPath('../08-Data-Trial_Recordings/processed/005'), '007': WindowsPath('../08-Data-Trial_Recordings/processed/007'), '008': WindowsPath('../08-Data-Trial_Recordings/processed/008'), '009': WindowsPath('../08-Data-Trial_Recordings/processed/009'), '010': WindowsPath('../08-Data-Trial_Recordings/processed/010'), '011': WindowsPath('../08-Data-Trial_Recordings/processed/011'), '012': WindowsPath('../08-Data-Trial_Recordings/processed/012'), '013': WindowsPath('../08-Data-Trial_Recordings/processed/013'), '014': WindowsPath('../08-Data-Trial_Recordings/processed/014'), '015': WindowsPath('../08-Data-Trial_Recordings/processed/015'), '016': WindowsPath('../08-Data-Trial_Recordings/processed/016'), '017': WindowsPath('../08-Data-Trial_Recordings/processed/017'), '018': WindowsPath('../08-Data-Trial_Recordings/processed/018'), '019': WindowsPath('../08-Data-Trial_Recordings/processed/019'), '020': WindowsPath('../08-Data-Trial_Recordings/processed/020'), '021': WindowsPath('../08-Data-Trial_Recordings/processed/021'), '022': WindowsPath('../08-Data-Trial_Recordings/processed/022'), '023': WindowsPath('../08-Data-Trial_Recordings/processed/023'), '024': WindowsPath('../08-Data-Trial_Recordings/processed/024'), '101': WindowsPath('../08-Data-Trial_Recordings/processed/101'), '102': WindowsPath('../08-Data-Trial_Recordings/processed/102'), '106': WindowsPath('../08-Data-Trial_Recordings/processed/106')}\n"
     ]
    },
    {
     "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>NO</th>\n",
       "      <th>Snippet</th>\n",
       "      <th>Snippet_base</th>\n",
       "      <th>number</th>\n",
       "      <th>version</th>\n",
       "      <th>AoI_size</th>\n",
       "      <th>OPTIMAL</th>\n",
       "      <th>bottom</th>\n",
       "      <th>left</th>\n",
       "      <th>right</th>\n",
       "      <th>top</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>NEXP</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>--v0</td>\n",
       "      <td>0</td>\n",
       "      <td>v0</td>\n",
       "      <td>1836</td>\n",
       "      <td>True</td>\n",
       "      <td>413</td>\n",
       "      <td>743</td>\n",
       "      <td>794</td>\n",
       "      <td>377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>STAT</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>--v0</td>\n",
       "      <td>0</td>\n",
       "      <td>v0</td>\n",
       "      <td>22578</td>\n",
       "      <td>False</td>\n",
       "      <td>422</td>\n",
       "      <td>555</td>\n",
       "      <td>981</td>\n",
       "      <td>369</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>WEXP</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>--v0</td>\n",
       "      <td>0</td>\n",
       "      <td>v0</td>\n",
       "      <td>10428</td>\n",
       "      <td>False</td>\n",
       "      <td>417</td>\n",
       "      <td>739</td>\n",
       "      <td>976</td>\n",
       "      <td>373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>NEXP</td>\n",
       "      <td>-obf-v0</td>\n",
       "      <td>--v0</td>\n",
       "      <td>0</td>\n",
       "      <td>v0</td>\n",
       "      <td>2304</td>\n",
       "      <td>True</td>\n",
       "      <td>413</td>\n",
       "      <td>781</td>\n",
       "      <td>845</td>\n",
       "      <td>377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>STAT</td>\n",
       "      <td>-obf-v0</td>\n",
       "      <td>--v0</td>\n",
       "      <td>0</td>\n",
       "      <td>v0</td>\n",
       "      <td>27348</td>\n",
       "      <td>False</td>\n",
       "      <td>422</td>\n",
       "      <td>555</td>\n",
       "      <td>1071</td>\n",
       "      <td>369</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>OP</td>\n",
       "      <td>9-clean-v2</td>\n",
       "      <td>9--v2</td>\n",
       "      <td>9</td>\n",
       "      <td>v2</td>\n",
       "      <td>496</td>\n",
       "      <td>False</td>\n",
       "      <td>407</td>\n",
       "      <td>581</td>\n",
       "      <td>612</td>\n",
       "      <td>391</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>WEXP</td>\n",
       "      <td>9-clean-v2</td>\n",
       "      <td>9--v2</td>\n",
       "      <td>9</td>\n",
       "      <td>v2</td>\n",
       "      <td>7084</td>\n",
       "      <td>False</td>\n",
       "      <td>364</td>\n",
       "      <td>739</td>\n",
       "      <td>900</td>\n",
       "      <td>320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>NEXP</td>\n",
       "      <td>9-obf-v2</td>\n",
       "      <td>9--v2</td>\n",
       "      <td>9</td>\n",
       "      <td>v2</td>\n",
       "      <td>1920</td>\n",
       "      <td>True</td>\n",
       "      <td>357</td>\n",
       "      <td>756</td>\n",
       "      <td>820</td>\n",
       "      <td>327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>OP</td>\n",
       "      <td>9-obf-v2</td>\n",
       "      <td>9--v2</td>\n",
       "      <td>9</td>\n",
       "      <td>v2</td>\n",
       "      <td>465</td>\n",
       "      <td>False</td>\n",
       "      <td>353</td>\n",
       "      <td>785</td>\n",
       "      <td>816</td>\n",
       "      <td>338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>WEXP</td>\n",
       "      <td>9-obf-v2</td>\n",
       "      <td>9--v2</td>\n",
       "      <td>9</td>\n",
       "      <td>v2</td>\n",
       "      <td>8184</td>\n",
       "      <td>False</td>\n",
       "      <td>364</td>\n",
       "      <td>739</td>\n",
       "      <td>925</td>\n",
       "      <td>320</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>306 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               NO     Snippet Snippet_base  number version  AoI_size  OPTIMAL   \n",
       "Condition                                                                       \n",
       "unambiguous  NEXP   -clean-v0         --v0       0      v0      1836     True  \\\n",
       "unambiguous  STAT   -clean-v0         --v0       0      v0     22578    False   \n",
       "unambiguous  WEXP   -clean-v0         --v0       0      v0     10428    False   \n",
       "ambiguous    NEXP     -obf-v0         --v0       0      v0      2304     True   \n",
       "ambiguous    STAT     -obf-v0         --v0       0      v0     27348    False   \n",
       "...           ...         ...          ...     ...     ...       ...      ...   \n",
       "unambiguous    OP  9-clean-v2        9--v2       9      v2       496    False   \n",
       "unambiguous  WEXP  9-clean-v2        9--v2       9      v2      7084    False   \n",
       "ambiguous    NEXP    9-obf-v2        9--v2       9      v2      1920     True   \n",
       "ambiguous      OP    9-obf-v2        9--v2       9      v2       465    False   \n",
       "ambiguous    WEXP    9-obf-v2        9--v2       9      v2      8184    False   \n",
       "\n",
       "             bottom  left  right  top  \n",
       "Condition                              \n",
       "unambiguous     413   743    794  377  \n",
       "unambiguous     422   555    981  369  \n",
       "unambiguous     417   739    976  373  \n",
       "ambiguous       413   781    845  377  \n",
       "ambiguous       422   555   1071  369  \n",
       "...             ...   ...    ...  ...  \n",
       "unambiguous     407   581    612  391  \n",
       "unambiguous     364   739    900  320  \n",
       "ambiguous       357   756    820  327  \n",
       "ambiguous       353   785    816  338  \n",
       "ambiguous       364   739    925  320  \n",
       "\n",
       "[306 rows x 11 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# get all files from participants\n",
    "folders = get_participant_folder_per_participant(raw_folder=False)\n",
    "print(folders)\n",
    "aoi_data = pd.read_csv(AOI_SIZE_PATH, sep=SEPARATOR, index_col=0)\n",
    "display(aoi_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "de792fa3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3ecc0f245bb745d8bef4bee48c15ca8b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/24 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "----------------------------------------------\n",
      "Participant 003\n",
      "\t-clean-v1 was excluded due to Excluded\n",
      "\t-clean-v2 was excluded due to Excluded\n",
      "\t10-obf-v2 was excluded due to Excluded\n",
      "\t12-clean-v1 was excluded due to Excluded\n",
      "\t12-clean-v2 was excluded due to Excluded\n",
      "\t13-clean-v2 was excluded due to Excluded\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t17-obf-v2 was excluded due to Excluded\n",
      "\t4-obf-v2 was excluded due to Excluded\n",
      "\t49-obf-v1 was excluded due to Excluded\n",
      "\t54-obf-v0 was excluded due to Excluded\n",
      "\t54-obf-v1 was excluded due to Excluded\n",
      "\t57-clean-v0 was excluded due to Excluded\n",
      "\t60-clean-v0 was excluded due to Excluded\n",
      "\t60-clean-v1 was excluded due to Excluded\n",
      "\t63-obf-v0 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "\t7-clean-v2 was excluded due to Excluded\n",
      "\t9-clean-v2 was excluded due to Excluded\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "22 1970-01-01 00:00:07.866     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:08.568     0.002  Stimulus/S  4\n",
      "\t4-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "20 1970-01-01 00:00:07.866     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:08.568     0.002  Stimulus/S  4\n",
      "\t4-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 004\n",
      "\t-obf-v0 was excluded due to Excluded\n",
      "\t-obf-v1 was excluded due to Excluded\n",
      "\t10-clean-v2 was excluded due to Excluded\n",
      "\t11-clean-v0 was excluded due to Excluded\n",
      "\t12-obf-v0 was excluded due to Excluded\n",
      "\t13-obf-v1 was excluded due to Excluded\n",
      "\t15-obf-v0 was excluded due to Excluded\n",
      "\t16-clean-v0 was excluded due to Excluded\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t17-clean-v1 was excluded due to Excluded\n",
      "\t17-clean-v2 was excluded due to Excluded\n",
      "\t30-obf-v0 was excluded due to Excluded\n",
      "\t30-obf-v2 was excluded due to Excluded\n",
      "\t4-clean-v0 was excluded due to Excluded\n",
      "\t5-obf-v0 was excluded due to Excluded\n",
      "\t57-obf-v2 was excluded due to Excluded\n",
      "\t6-obf-v0 was excluded due to Excluded\n",
      "\t6-obf-v1 was excluded due to Excluded\n",
      "\t61-obf-v1 was excluded due to Excluded\n",
      "\t62-clean-v1 was excluded due to Excluded\n",
      "\t62-clean-v2 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t7-obf-v0 was excluded due to Excluded\n",
      "\t7-obf-v2 was excluded due to Excluded\n",
      "\t8-clean-v2 was excluded due to Excluded\n",
      "\t9-obf-v0 was excluded due to Excluded\n",
      "\t9-obf-v1 was excluded due to Excluded\n",
      "\t18-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t18-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 005\n",
      "\t13-obf-v1 was excluded due to Excluded\n",
      "\t16-clean-v0 was excluded due to Excluded\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t18-obf-v0 was excluded due to Excluded\n",
      "\t6-clean-v1 was excluded due to Excluded\n",
      "\t6-clean-v2 was excluded due to Excluded\n",
      "\t61-clean-v0 was excluded due to Excluded\n",
      "\t62-obf-v2 was excluded due to Excluded\n",
      "\t63-obf-v0 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "\t8-clean-v1 was excluded due to Excluded\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t17-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:08.374     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:08.814     0.002  Stimulus/S  4\n",
      "\t30-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "11 1970-01-01 00:00:08.534     0.002  Stimulus/S191\n",
      "23 1970-01-01 00:00:09.432     0.002  Stimulus/S  4\n",
      "\t5-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t17-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:08.374     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:08.814     0.002  Stimulus/S  4\n",
      "\t30-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "9  1970-01-01 00:00:08.534     0.002  Stimulus/S171\n",
      "23 1970-01-01 00:00:09.432     0.002  Stimulus/S  4\n",
      "\t5-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 007\n",
      "\t17-obf-v0 was excluded due to Excluded\n",
      "\t17-obf-v1 was excluded due to Excluded\n",
      "\t57-obf-v1 was excluded due to Excluded\n",
      "\t60-clean-v0 was excluded due to Excluded\n",
      "\t62-obf-v2 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t63-clean-v2 was excluded due to Excluded\n",
      "\t11-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t57-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t63-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-obf-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t57-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t63-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 008\n",
      "\t-obf-v1 was excluded due to Excluded\n",
      "\t-obf-v2 was excluded due to Excluded\n",
      "\t11-obf-v1 was excluded due to Excluded\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t17-clean-v0 was excluded due to Excluded\n",
      "\t17-clean-v2 was excluded due to Excluded\n",
      "\t18-obf-v2 was excluded due to Excluded\n",
      "\t30-clean-v1 was excluded due to Excluded\n",
      "\t4-clean-v2 was excluded due to Excluded\n",
      "\t57-clean-v1 was excluded due to Excluded\n",
      "\t60-obf-v1 was excluded due to Excluded\n",
      "\t61-obf-v2 was excluded due to Excluded\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t8-obf-v1 was excluded due to Excluded\n",
      "\t8-obf-v2 was excluded due to Excluded\n",
      "\t14-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.998     0.002  Stimulus/S 11\n",
      "21 1970-01-01 00:00:09.128     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:09.346     0.002  Stimulus/S  4\n",
      "\t6-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t9-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.998     0.002  Stimulus/S 11\n",
      "19 1970-01-01 00:00:09.128     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:09.346     0.002  Stimulus/S  4\n",
      "\t6-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t9-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 009\n",
      "\t11-clean-v0 was excluded due to Excluded\n",
      "\t16-obf-v1 was excluded due to Excluded\n",
      "\t16-obf-v2 was excluded due to Excluded\n",
      "\t62-obf-v0 was excluded due to Excluded\n",
      "\t18-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:16.196     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:17.150     0.002  Stimulus/S  4\n",
      "\t49-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "12 1970-01-01 00:00:10.284     0.002  Stimulus/S192\n",
      "22 1970-01-01 00:00:11.098     0.002  Stimulus/S  4\n",
      "\t18-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:16.196     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:17.150     0.002  Stimulus/S  4\n",
      "\t49-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "10 1970-01-01 00:00:10.284     0.002  Stimulus/S172\n",
      "22 1970-01-01 00:00:11.098     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 010\n",
      "\t14-clean-v2 was excluded due to Excluded\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t49-clean-v0 was excluded due to Excluded\n",
      "\t54-obf-v0 was excluded due to Excluded\n",
      "\t6-clean-v0 was excluded due to Excluded\n",
      "\t6-clean-v1 was excluded due to Excluded\n",
      "\t60-obf-v1 was excluded due to Excluded\n",
      "\t60-obf-v2 was excluded due to Excluded\n",
      "\t62-clean-v1 was excluded due to Excluded\n",
      "\t7-obf-v2 was excluded due to Excluded\n",
      "\t8-clean-v0 was excluded due to Excluded\n",
      "\t13-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "14 1970-01-01 00:00:07.656     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:08.598     0.002  Stimulus/S  4\n",
      "\t14-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t4-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "12 1970-01-01 00:00:12.290     0.002  Stimulus/S192\n",
      "19 1970-01-01 00:00:12.600     0.002  Stimulus/S  4\n",
      "\t-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "23 1970-01-01 00:00:17.268     0.002  Stimulus/S171\n",
      "26 1970-01-01 00:00:18.182     0.002  Stimulus/S  4\n",
      "\t13-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:07.656     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:08.598     0.002  Stimulus/S  4\n",
      "\t14-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t4-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "10 1970-01-01 00:00:12.290     0.002  Stimulus/S172\n",
      "19 1970-01-01 00:00:12.600     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 011\n",
      "\t12-clean-v2 was excluded due to Excluded\n",
      "\t17-clean-v0 was excluded due to Excluded\n",
      "\t6-obf-v2 was excluded due to Excluded\n",
      "\t62-clean-v2 was excluded due to Excluded\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t8-clean-v1 was excluded due to Excluded\n",
      "\t12-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:09.340     0.002  Stimulus/S191\n",
      "20 1970-01-01 00:00:10.034     0.002  Stimulus/S  4\n",
      "\t12-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "8  1970-01-01 00:00:09.340     0.002  Stimulus/S171\n",
      "20 1970-01-01 00:00:10.034     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 012\n",
      "\t16-obf-v1 was excluded due to Excluded\n",
      "\t16-obf-v2 was excluded due to Excluded\n",
      "\t49-obf-v2 was excluded due to Excluded\n",
      "\t57-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v2 was excluded due to Excluded\n",
      "\t15-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.982     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:11.398     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:12.164     0.002  Stimulus/S  4\n",
      "\t15-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.982     0.002  Stimulus/S 11\n",
      "9  1970-01-01 00:00:11.398     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:12.164     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 013\n",
      "\t15-obf-v1 was excluded due to Excluded\n",
      "\t54-obf-v1 was excluded due to Excluded\n",
      "\t54-obf-v2 was excluded due to Excluded\n",
      "\t60-obf-v0 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t10-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t16-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t63-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:15.492     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:16.300     0.002  Stimulus/S  4\n",
      "\t10-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t16-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t30-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t63-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:15.492     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:16.300     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 014\n",
      "\t13-obf-v0 was excluded due to Excluded\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t54-clean-v1 was excluded due to Excluded\n",
      "\t62-obf-v0 was excluded due to Excluded\n",
      "\t-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.018     0.002  Stimulus/S 12\n",
      "17 1970-01-01 00:00:07.228     0.002  Stimulus/S192\n",
      "27 1970-01-01 00:00:08.134     0.002  Stimulus/S  4\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "13 1970-01-01 00:00:08.886     0.002  Stimulus/S191\n",
      "23 1970-01-01 00:00:09.634     0.002  Stimulus/S  4\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-obf-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.018     0.002  Stimulus/S 12\n",
      "15 1970-01-01 00:00:07.228     0.002  Stimulus/S172\n",
      "27 1970-01-01 00:00:08.134     0.002  Stimulus/S  4\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "11 1970-01-01 00:00:08.886     0.002  Stimulus/S171\n",
      "23 1970-01-01 00:00:09.634     0.002  Stimulus/S  4\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 015\n",
      "\t-obf-v0 was excluded due to Excluded\n",
      "\t14-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t18-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-obf-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "19 1970-01-01 00:00:07.138     0.002  Stimulus/S192\n",
      "27 1970-01-01 00:00:08.114     0.002  Stimulus/S  4\n",
      "\t6-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t18-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-obf-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "17 1970-01-01 00:00:07.138     0.002  Stimulus/S172\n",
      "27 1970-01-01 00:00:08.114     0.002  Stimulus/S  4\n",
      "\t6-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 016\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t16-obf-v1 was excluded due to Excluded\n",
      "\t16-obf-v2 was excluded due to Excluded\n",
      "\t17-obf-v2 was excluded due to Excluded\n",
      "\t18-obf-v1 was excluded due to Excluded\n",
      "\t49-clean-v1 was excluded due to Excluded\n",
      "\t6-clean-v2 was excluded due to Excluded\n",
      "\t62-obf-v0 was excluded due to Excluded\n",
      "\t62-obf-v1 was excluded due to Excluded\n",
      "\t62-obf-v2 was excluded due to Excluded\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "\t11-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t14-obf-v1 was excluded due to Data for existing stimuli too short,                       onset  duration    description\n",
      "159 1970-01-01 00:00:04.982     0.002  Stimulus/S 12\n",
      "168 1970-01-01 00:00:08.018     0.002  Stimulus/S192\n",
      "180 1970-01-01 00:00:08.916     0.002  Stimulus/S  4\n",
      "\t14-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-clean-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t15-clean-v1 was excluded due to Voltage violation in interval of segment\n",
      "\t17-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t5-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t61-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t14-obf-v1 was excluded due to Data for existing stimuli too short,                       onset  duration    description\n",
      "159 1970-01-01 00:00:04.982     0.002  Stimulus/S 12\n",
      "166 1970-01-01 00:00:08.018     0.002  Stimulus/S172\n",
      "180 1970-01-01 00:00:08.916     0.002  Stimulus/S  4\n",
      "\t14-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-clean-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t15-clean-v1 was excluded due to Voltage violation in interval of segment\n",
      "\t17-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t5-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t5-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t61-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 017\n",
      "\t-clean-v2 was excluded due to Excluded\n",
      "\t10-clean-v1 was excluded due to Excluded\n",
      "\t10-clean-v2 was excluded due to Excluded\n",
      "\t12-clean-v0 was excluded due to Excluded\n",
      "\t13-clean-v1 was excluded due to Excluded\n",
      "\t17-obf-v1 was excluded due to Excluded\n",
      "\t18-obf-v1 was excluded due to Excluded\n",
      "\t18-obf-v2 was excluded due to Excluded\n",
      "\t49-obf-v1 was excluded due to Excluded\n",
      "\t57-obf-v0 was excluded due to Excluded\n",
      "\t63-obf-v0 was excluded due to Excluded\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "\t8-clean-v1 was excluded due to Excluded\n",
      "\t12-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "22 1970-01-01 00:00:08.318     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:09.018     0.002  Stimulus/S  4\n",
      "\t16-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t49-obf-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "12 1970-01-01 00:00:08.032     0.002  Stimulus/S192\n",
      "22 1970-01-01 00:00:08.298     0.002  Stimulus/S  4\n",
      "\t54-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "13 1970-01-01 00:00:07.998     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:08.432     0.002  Stimulus/S  4\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t62-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:10.704     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:11.314     0.002  Stimulus/S  4\n",
      "\t7-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t12-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t13-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t14-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "20 1970-01-01 00:00:08.318     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:09.018     0.002  Stimulus/S  4\n",
      "\t16-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t49-obf-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 12\n",
      "10 1970-01-01 00:00:08.032     0.002  Stimulus/S172\n",
      "22 1970-01-01 00:00:08.298     0.002  Stimulus/S  4\n",
      "\t54-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "11 1970-01-01 00:00:07.998     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:08.432     0.002  Stimulus/S  4\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t62-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:10.704     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:11.314     0.002  Stimulus/S  4\n",
      "\t7-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 018\n",
      "\t11-clean-v1 was excluded due to Excluded\n",
      "\t12-obf-v1 was excluded due to Excluded\n",
      "\t15-clean-v0 was excluded due to Excluded\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t7-obf-v1 was excluded due to Excluded\n",
      "\t8-obf-v0 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:17.666     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:18.180     0.002  Stimulus/S  4\n",
      "\t16-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:17.666     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:18.180     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 019\n",
      "\t-clean-v1 was excluded due to Excluded\n",
      "\t13-obf-v1 was excluded due to Excluded\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t17-obf-v0 was excluded due to Excluded\n",
      "\t18-clean-v1 was excluded due to Excluded\n",
      "\t49-clean-v1 was excluded due to Excluded\n",
      "\t54-clean-v1 was excluded due to Excluded\n",
      "\t57-clean-v0 was excluded due to Excluded\n",
      "\t6-obf-v2 was excluded due to Excluded\n",
      "\t62-obf-v1 was excluded due to Excluded\n",
      "\t63-obf-v0 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "\t15-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t15-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 020\n",
      "\t11-clean-v1 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t60-obf-v0 was excluded due to Excluded\n",
      "\t62-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "19 1970-01-01 00:00:14.876     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:15.230     0.002  Stimulus/S  4\n",
      "\t18-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t49-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t57-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t7-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:09.750     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:10.698     0.002  Stimulus/S  4\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "17 1970-01-01 00:00:14.876     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:15.230     0.002  Stimulus/S  4\n",
      "\t18-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t49-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t57-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t7-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:04.980     0.002  Stimulus/S 11\n",
      "9  1970-01-01 00:00:09.750     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:10.698     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 021\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t14-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 12\n",
      "12 1970-01-01 00:00:21.762     0.002  Stimulus/S192\n",
      "22 1970-01-01 00:00:22.250     0.002  Stimulus/S  4\n",
      "\t14-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t54-clean-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t60-obf-v1 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 12\n",
      "10 1970-01-01 00:00:21.762     0.002  Stimulus/S172\n",
      "22 1970-01-01 00:00:22.250     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 022\n",
      "\t16-clean-v1 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t17-obf-v2 was excluded due to Excluded\n",
      "\t4-obf-v2 was excluded due to Excluded\n",
      "\t5-obf-v2 was excluded due to Excluded\n",
      "\t6-obf-v2 was excluded due to Excluded\n",
      "\t60-clean-v0 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v2 was excluded due to Excluded\n",
      "\t9-clean-v0 was excluded due to Excluded\n",
      "\t9-clean-v2 was excluded due to Excluded\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t49-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t12-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t49-obf-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 023\n",
      "\t10-clean-v2 was excluded due to Excluded\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t63-obf-v0 was excluded due to Excluded\n",
      "\t11-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t12-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "9  1970-01-01 00:00:08.650     0.002  Stimulus/S191\n",
      "27 1970-01-01 00:00:09.532     0.002  Stimulus/S  4\n",
      "\t12-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:09.626     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:10.114     0.002  Stimulus/S  4\n",
      "\t13-clean-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t16-clean-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t17-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t11-obf-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t12-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "8  1970-01-01 00:00:08.650     0.002  Stimulus/S171\n",
      "27 1970-01-01 00:00:09.532     0.002  Stimulus/S  4\n",
      "\t12-clean-v2 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:09.626     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:10.114     0.002  Stimulus/S  4\n",
      "\t13-clean-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t16-clean-v1 was excluded due to Voltage violation absolute of segment\n",
      "\t17-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 024\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "12 1970-01-01 00:00:13.010     0.002  Stimulus/S191\n",
      "22 1970-01-01 00:00:13.668     0.002  Stimulus/S  4\n",
      "\t11-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t17-obf-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t61-clean-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.000     0.002  Stimulus/S 11\n",
      "10 1970-01-01 00:00:13.010     0.002  Stimulus/S171\n",
      "22 1970-01-01 00:00:13.668     0.002  Stimulus/S  4\n",
      "----------------------------------------------\n",
      "Participant 101\n",
      "\t12-clean-v2 was excluded due to Excluded\n",
      "\t16-obf-v2 was excluded due to Excluded\n",
      "\t18-clean-v2 was excluded due to Excluded\n",
      "\t6-obf-v1 was excluded due to Excluded\n",
      "\t63-obf-v1 was excluded due to Excluded\n",
      "\t63-obf-v2 was excluded due to Excluded\n",
      "----------------------------------------------\n",
      "Participant 102\n",
      "\t16-clean-v2 was excluded due to Excluded\n",
      "\t63-clean-v1 was excluded due to Excluded\n",
      "\t63-clean-v2 was excluded due to Excluded\n",
      "\t7-obf-v1 was excluded due to Excluded\n",
      "\t57-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t57-clean-v2 was excluded due to Voltage violation absolute of segment\n",
      "\t6-clean-v2 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "----------------------------------------------\n",
      "Participant 106\n",
      "\t-obf-v0 was excluded due to Excluded\n",
      "\t-obf-v1 was excluded due to Excluded\n",
      "\t10-clean-v1 was excluded due to Excluded\n",
      "\t11-clean-v0 was excluded due to Excluded\n",
      "\t11-clean-v1 was excluded due to Excluded\n",
      "\t12-obf-v2 was excluded due to Excluded\n",
      "\t16-obf-v0 was excluded due to Excluded\n",
      "\t16-obf-v1 was excluded due to Excluded\n",
      "\t16-obf-v2 was excluded due to Excluded\n",
      "\t18-clean-v0 was excluded due to Excluded\n",
      "\t30-obf-v0 was excluded due to Excluded\n",
      "\t30-obf-v2 was excluded due to Excluded\n",
      "\t4-obf-v0 was excluded due to Excluded\n",
      "\t4-obf-v1 was excluded due to Excluded\n",
      "\t4-obf-v2 was excluded due to Excluded\n",
      "\t49-obf-v2 was excluded due to Excluded\n",
      "\t57-clean-v0 was excluded due to Excluded\n",
      "\t57-clean-v1 was excluded due to Excluded\n",
      "\t57-clean-v2 was excluded due to Excluded\n",
      "\t6-obf-v1 was excluded due to Excluded\n",
      "\t6-obf-v2 was excluded due to Excluded\n",
      "\t60-clean-v1 was excluded due to Excluded\n",
      "\t61-obf-v1 was excluded due to Excluded\n",
      "\t61-obf-v2 was excluded due to Excluded\n",
      "\t62-clean-v2 was excluded due to Excluded\n",
      "\t63-clean-v0 was excluded due to Excluded\n",
      "\t7-clean-v2 was excluded due to Excluded\n",
      "\t8-obf-v1 was excluded due to Excluded\n",
      "\t9-clean-v0 was excluded due to Excluded\n",
      "\t9-clean-v1 was excluded due to Excluded\n",
      "\t49-obf-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 12\n",
      "12 1970-01-01 00:00:14.162     0.002  Stimulus/S192\n",
      "22 1970-01-01 00:00:14.714     0.002  Stimulus/S  4\n",
      "\t49-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t62-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t7-clean-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t49-obf-v0 was excluded due to Data for existing stimuli too short,                      onset  duration    description\n",
      "2  1970-01-01 00:00:05.016     0.002  Stimulus/S 12\n",
      "10 1970-01-01 00:00:14.162     0.002  Stimulus/S172\n",
      "22 1970-01-01 00:00:14.714     0.002  Stimulus/S  4\n",
      "\t49-obf-v1 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t6-obf-v0 was excluded due to Voltage violation absolute of segment\n",
      "\t62-clean-v0 was excluded due to No stimulus found, fixation data of this trials likely did not contain any fixation fulfilling the requirements for this FRP calculation.\n",
      "\t7-clean-v0 was excluded due to Voltage violation absolute of segment\n"
     ]
    },
    {
     "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>Participant</th>\n",
       "      <th>Snippet</th>\n",
       "      <th>total_reading_time_snippet</th>\n",
       "      <th>total_reading_time_aoi</th>\n",
       "      <th>first_pass_aoi</th>\n",
       "      <th>number_fixations_aoi</th>\n",
       "      <th>number_visits_aoi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>003</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>9.955393</td>\n",
       "      <td>2.601564</td>\n",
       "      <td>0.290816</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v0</td>\n",
       "      <td>13.225277</td>\n",
       "      <td>10.129551</td>\n",
       "      <td>3.579827</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v1</td>\n",
       "      <td>6.064087</td>\n",
       "      <td>2.155049</td>\n",
       "      <td>0.300928</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v0</td>\n",
       "      <td>4.058192</td>\n",
       "      <td>2.304095</td>\n",
       "      <td>0.719979</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v1</td>\n",
       "      <td>4.064852</td>\n",
       "      <td>3.710688</td>\n",
       "      <td>0.868316</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1495</th>\n",
       "      <td>106</td>\n",
       "      <td>7-clean-v0</td>\n",
       "      <td>9.776206</td>\n",
       "      <td>2.436565</td>\n",
       "      <td>1.532436</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1496</th>\n",
       "      <td>106</td>\n",
       "      <td>7-clean-v1</td>\n",
       "      <td>11.441558</td>\n",
       "      <td>2.415726</td>\n",
       "      <td>0.742453</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1497</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v0</td>\n",
       "      <td>11.652681</td>\n",
       "      <td>4.357403</td>\n",
       "      <td>0.351646</td>\n",
       "      <td>10</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1498</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v2</td>\n",
       "      <td>11.240359</td>\n",
       "      <td>2.772411</td>\n",
       "      <td>1.125800</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1499</th>\n",
       "      <td>106</td>\n",
       "      <td>9-clean-v2</td>\n",
       "      <td>7.431035</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1500 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Participant     Snippet  total_reading_time_snippet   \n",
       "0            003   -clean-v0                    9.955393  \\\n",
       "1            003   10-obf-v0                   13.225277   \n",
       "2            003   10-obf-v1                    6.064087   \n",
       "3            003   11-obf-v0                    4.058192   \n",
       "4            003   11-obf-v1                    4.064852   \n",
       "...          ...         ...                         ...   \n",
       "1495         106  7-clean-v0                    9.776206   \n",
       "1496         106  7-clean-v1                   11.441558   \n",
       "1497         106    8-obf-v0                   11.652681   \n",
       "1498         106    8-obf-v2                   11.240359   \n",
       "1499         106  9-clean-v2                    7.431035   \n",
       "\n",
       "      total_reading_time_aoi  first_pass_aoi  number_fixations_aoi   \n",
       "0                   2.601564        0.290816                     5  \\\n",
       "1                  10.129551        3.579827                     7   \n",
       "2                   2.155049        0.300928                     4   \n",
       "3                   2.304095        0.719979                     3   \n",
       "4                   3.710688        0.868316                     5   \n",
       "...                      ...             ...                   ...   \n",
       "1495                2.436565        1.532436                     3   \n",
       "1496                2.415726        0.742453                     6   \n",
       "1497                4.357403        0.351646                    10   \n",
       "1498                2.772411        1.125800                     4   \n",
       "1499                1.197443        1.197443                     1   \n",
       "\n",
       "      number_visits_aoi  \n",
       "0                     5  \n",
       "1                     3  \n",
       "2                     4  \n",
       "3                     2  \n",
       "4                     2  \n",
       "...                 ...  \n",
       "1495                  3  \n",
       "1496                  5  \n",
       "1497                  7  \n",
       "1498                  4  \n",
       "1499                  1  \n",
       "\n",
       "[1500 rows x 7 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Participant</th>\n",
       "      <th>Snippet</th>\n",
       "      <th>total_reading_time_snippet</th>\n",
       "      <th>total_reading_time_aoi</th>\n",
       "      <th>first_pass_aoi</th>\n",
       "      <th>number_fixations_aoi</th>\n",
       "      <th>number_visits_aoi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>003</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>9.955393</td>\n",
       "      <td>2.601564</td>\n",
       "      <td>0.290816</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v0</td>\n",
       "      <td>13.225277</td>\n",
       "      <td>10.129551</td>\n",
       "      <td>3.579827</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v1</td>\n",
       "      <td>6.064087</td>\n",
       "      <td>2.155049</td>\n",
       "      <td>0.300928</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v0</td>\n",
       "      <td>4.058192</td>\n",
       "      <td>2.304095</td>\n",
       "      <td>0.719979</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v1</td>\n",
       "      <td>4.064852</td>\n",
       "      <td>3.710688</td>\n",
       "      <td>0.868316</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1382</th>\n",
       "      <td>106</td>\n",
       "      <td>63-clean-v2</td>\n",
       "      <td>14.411309</td>\n",
       "      <td>1.277451</td>\n",
       "      <td>0.749141</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1383</th>\n",
       "      <td>106</td>\n",
       "      <td>7-clean-v1</td>\n",
       "      <td>11.441558</td>\n",
       "      <td>2.415726</td>\n",
       "      <td>0.742453</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1384</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v0</td>\n",
       "      <td>11.652681</td>\n",
       "      <td>4.357403</td>\n",
       "      <td>0.351646</td>\n",
       "      <td>10</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1385</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v2</td>\n",
       "      <td>11.240359</td>\n",
       "      <td>2.772411</td>\n",
       "      <td>1.125800</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1386</th>\n",
       "      <td>106</td>\n",
       "      <td>9-clean-v2</td>\n",
       "      <td>7.431035</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1387 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Participant      Snippet  total_reading_time_snippet   \n",
       "0            003    -clean-v0                    9.955393  \\\n",
       "1            003    10-obf-v0                   13.225277   \n",
       "2            003    10-obf-v1                    6.064087   \n",
       "3            003    11-obf-v0                    4.058192   \n",
       "4            003    11-obf-v1                    4.064852   \n",
       "...          ...          ...                         ...   \n",
       "1382         106  63-clean-v2                   14.411309   \n",
       "1383         106   7-clean-v1                   11.441558   \n",
       "1384         106     8-obf-v0                   11.652681   \n",
       "1385         106     8-obf-v2                   11.240359   \n",
       "1386         106   9-clean-v2                    7.431035   \n",
       "\n",
       "      total_reading_time_aoi  first_pass_aoi  number_fixations_aoi   \n",
       "0                   2.601564        0.290816                     5  \\\n",
       "1                  10.129551        3.579827                     7   \n",
       "2                   2.155049        0.300928                     4   \n",
       "3                   2.304095        0.719979                     3   \n",
       "4                   3.710688        0.868316                     5   \n",
       "...                      ...             ...                   ...   \n",
       "1382                1.277451        0.749141                     3   \n",
       "1383                2.415726        0.742453                     6   \n",
       "1384                4.357403        0.351646                    10   \n",
       "1385                2.772411        1.125800                     4   \n",
       "1386                1.197443        1.197443                     1   \n",
       "\n",
       "      number_visits_aoi  \n",
       "0                     5  \n",
       "1                     3  \n",
       "2                     4  \n",
       "3                     2  \n",
       "4                     2  \n",
       "...                 ...  \n",
       "1382                  2  \n",
       "1383                  5  \n",
       "1384                  7  \n",
       "1385                  4  \n",
       "1386                  1  \n",
       "\n",
       "[1387 rows x 7 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Participant</th>\n",
       "      <th>Snippet</th>\n",
       "      <th>total_reading_time_snippet</th>\n",
       "      <th>total_reading_time_aoi</th>\n",
       "      <th>first_pass_aoi</th>\n",
       "      <th>number_fixations_aoi</th>\n",
       "      <th>number_visits_aoi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>003</td>\n",
       "      <td>-clean-v0</td>\n",
       "      <td>9.955393</td>\n",
       "      <td>2.601564</td>\n",
       "      <td>0.290816</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v0</td>\n",
       "      <td>13.225277</td>\n",
       "      <td>10.129551</td>\n",
       "      <td>3.579827</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>003</td>\n",
       "      <td>10-obf-v1</td>\n",
       "      <td>6.064087</td>\n",
       "      <td>2.155049</td>\n",
       "      <td>0.300928</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v0</td>\n",
       "      <td>4.058192</td>\n",
       "      <td>2.304095</td>\n",
       "      <td>0.719979</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>003</td>\n",
       "      <td>11-obf-v1</td>\n",
       "      <td>4.064852</td>\n",
       "      <td>3.710688</td>\n",
       "      <td>0.868316</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1380</th>\n",
       "      <td>106</td>\n",
       "      <td>63-clean-v2</td>\n",
       "      <td>14.411309</td>\n",
       "      <td>1.277451</td>\n",
       "      <td>0.749141</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1381</th>\n",
       "      <td>106</td>\n",
       "      <td>7-clean-v1</td>\n",
       "      <td>11.441558</td>\n",
       "      <td>2.415726</td>\n",
       "      <td>0.742453</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1382</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v0</td>\n",
       "      <td>11.652681</td>\n",
       "      <td>4.357403</td>\n",
       "      <td>0.351646</td>\n",
       "      <td>10</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1383</th>\n",
       "      <td>106</td>\n",
       "      <td>8-obf-v2</td>\n",
       "      <td>11.240359</td>\n",
       "      <td>2.772411</td>\n",
       "      <td>1.125800</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1384</th>\n",
       "      <td>106</td>\n",
       "      <td>9-clean-v2</td>\n",
       "      <td>7.431035</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1.197443</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1385 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Participant      Snippet  total_reading_time_snippet   \n",
       "0            003    -clean-v0                    9.955393  \\\n",
       "1            003    10-obf-v0                   13.225277   \n",
       "2            003    10-obf-v1                    6.064087   \n",
       "3            003    11-obf-v0                    4.058192   \n",
       "4            003    11-obf-v1                    4.064852   \n",
       "...          ...          ...                         ...   \n",
       "1380         106  63-clean-v2                   14.411309   \n",
       "1381         106   7-clean-v1                   11.441558   \n",
       "1382         106     8-obf-v0                   11.652681   \n",
       "1383         106     8-obf-v2                   11.240359   \n",
       "1384         106   9-clean-v2                    7.431035   \n",
       "\n",
       "      total_reading_time_aoi  first_pass_aoi  number_fixations_aoi   \n",
       "0                   2.601564        0.290816                     5  \\\n",
       "1                  10.129551        3.579827                     7   \n",
       "2                   2.155049        0.300928                     4   \n",
       "3                   2.304095        0.719979                     3   \n",
       "4                   3.710688        0.868316                     5   \n",
       "...                      ...             ...                   ...   \n",
       "1380                1.277451        0.749141                     3   \n",
       "1381                2.415726        0.742453                     6   \n",
       "1382                4.357403        0.351646                    10   \n",
       "1383                2.772411        1.125800                     4   \n",
       "1384                1.197443        1.197443                     1   \n",
       "\n",
       "      number_visits_aoi  \n",
       "0                     5  \n",
       "1                     3  \n",
       "2                     4  \n",
       "3                     2  \n",
       "4                     2  \n",
       "...                 ...  \n",
       "1380                  2  \n",
       "1381                  5  \n",
       "1382                  7  \n",
       "1383                  4  \n",
       "1384                  1  \n",
       "\n",
       "[1385 rows x 7 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "algorithms = [True, FIXATION_SELECTION_ALGORITHM_FIRST_AOI_PADDING_SMALL]\n",
    "metrics = ['total_reading_time_snippet', 'total_reading_time_aoi', 'first_pass_aoi', 'number_fixations_aoi', 'number_visits_aoi']\n",
    "results = {\n",
    "    algorithm: pd.DataFrame(\n",
    "        columns=[PARTICIPANT, SNIPPET, *metrics]\n",
    "    ) for algorithm in algorithms\n",
    "}\n",
    "\n",
    "for participant in tqdm(folders):\n",
    "    print('----------------------------------------------')\n",
    "    print(PARTICIPANT, participant)\n",
    "    # skip participant if excluded\n",
    "    exclusions = get_exclusions(participant, [PARTICIPANT])[PARTICIPANT]\n",
    "    if any(exclusions.values()):\n",
    "        print('excluded')\n",
    "        continue\n",
    "    for algorithm in algorithms:\n",
    "        if algorithm==True:\n",
    "            erp_status = {s:(\"Excluded\" if any(exc.values()) else \"Included\") for s, exc in get_exclusions(participant, [SNIPPET])[SNIPPET].items()}\n",
    "        else:\n",
    "            erp_status_path = get_erp_status_path(algorithm, SNIPPET_GROUP_ALL, get_erp_description(algorithm, False, (-0.3, 1.0)), participant)\n",
    "            with open(erp_status_path, 'r') as f:\n",
    "                erp_status = json.load(f)\n",
    "        for snippet in erp_status:\n",
    "            if erp_status[snippet]!=\"Included\":\n",
    "                print(f'\\t{snippet} was excluded due to {erp_status[snippet]}')\n",
    "                continue\n",
    "            aois = aoi_data[aoi_data[SNIPPET] == snippet]\n",
    "            optimal_aoi = aois[aois[OPTIMAL]]\n",
    "            snippet_fixations_path = get_selected_fixations_path(participant, snippet)\n",
    "            fixation_data = pd.read_csv(\n",
    "                snippet_fixations_path, index_col=False, sep=SEPARATOR, dtype={PARTICIPANT: str})\n",
    "            aoi_fixation_data = get_fixations_in_aoi(fixation_data, aois, AOI_PADDING_SMALL)\n",
    "            fixation_data['AOI'] = fixation_data.index.map(lambda id: id in aoi_fixation_data.index)\n",
    "            fixation_data['visit_counter'] = (1-fixation_data['AOI']*1).cumsum()\n",
    "            fixation_data['visit_counter'] = fixation_data['visit_counter'].mask(~fixation_data['AOI'], other=0)\n",
    "            visit_indices = fixation_data[fixation_data['AOI']]['visit_counter'].drop_duplicates(keep='first').reset_index(drop=True).to_dict()\n",
    "            visit_indices = {v: k+1 for k, v in visit_indices.items()}\n",
    "            assert(not len(visit_indices) or (len(visit_indices) == max(visit_indices.values())))\n",
    "            # TODO: special fixation benutzen\n",
    "            fixation_data['visit_counter'] = fixation_data.apply(lambda x: visit_indices[x['visit_counter']] if x['AOI'] else 0, axis=1)\n",
    "            # metric 1 total reading time snippet (sum of all fixation durations)\n",
    "            total_reading_time_snippet = fixation_data[FIXATION_COLUMN_DURATION].sum()\n",
    "            # metric 2 total reading time optimal aoi (sum of all fixation durations in optimal aoi)\n",
    "            total_reading_time_aoi = aoi_fixation_data[FIXATION_COLUMN_DURATION].sum()\n",
    "            # metric 3 duration first pass optimal aoi (sum of all fixations beginning from special fixation to leaving the aoi for the first time)\n",
    "            first_pass_aoi = fixation_data[fixation_data['visit_counter']==1][FIXATION_COLUMN_DURATION].sum()\n",
    "            # metric 4 number of fixations in optimal aoi\n",
    "            number_fixations_aoi = aoi_fixation_data.shape[0]\n",
    "            # metric 5 number of visiting optimal aoi (1 visited once, 2 visited, left and visited again)\n",
    "            number_visits_aoi = len(visit_indices)\n",
    "            # metric 6 go-past time (sum of all fixation durations until leaving the aoi for the  first time to either right or lower)\n",
    "            # TODO\n",
    "            \n",
    "            results[algorithm].loc[len(results[algorithm])] = [participant, snippet, total_reading_time_snippet, total_reading_time_aoi, first_pass_aoi, number_fixations_aoi, number_visits_aoi] \n",
    "\n",
    "for algorithm in results:\n",
    "    results[algorithm].to_csv(get_erp_fixation_analysis_path(algorithm, SNIPPET_GROUP_ALL, 'all', 'reading metrics'), sep=SEPARATOR, index=False)\n",
    "    display(results[algorithm])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "47037961",
   "metadata": {},
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>Metric</th>\n",
       "      <th colspan=\"8\" halign=\"left\">total_reading_time_snippet</th>\n",
       "      <th colspan=\"2\" halign=\"left\">total_reading_time_aoi</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">number_fixations_aoi</th>\n",
       "      <th colspan=\"8\" halign=\"left\">number_visits_aoi</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Statistic</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>743</td>\n",
       "      <td>9.498736</td>\n",
       "      <td>6.654228</td>\n",
       "      <td>1.698284</td>\n",
       "      <td>4.648408</td>\n",
       "      <td>7.12821</td>\n",
       "      <td>12.172524</td>\n",
       "      <td>28.518223</td>\n",
       "      <td>743</td>\n",
       "      <td>2.61962</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>24</td>\n",
       "      <td>743</td>\n",
       "      <td>3.227456</td>\n",
       "      <td>2.381012</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>757</td>\n",
       "      <td>8.678278</td>\n",
       "      <td>6.103357</td>\n",
       "      <td>0.722448</td>\n",
       "      <td>4.284828</td>\n",
       "      <td>6.82339</td>\n",
       "      <td>10.479799</td>\n",
       "      <td>28.981631</td>\n",
       "      <td>757</td>\n",
       "      <td>1.77958</td>\n",
       "      <td>...</td>\n",
       "      <td>4.0</td>\n",
       "      <td>27</td>\n",
       "      <td>757</td>\n",
       "      <td>2.718626</td>\n",
       "      <td>2.218569</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Metric      total_reading_time_snippet                                 \n",
       "Statistic                        count      mean       std       min   \n",
       "Condition                                                              \n",
       "ambiguous                          743  9.498736  6.654228  1.698284  \\\n",
       "unambiguous                        757  8.678278  6.103357  0.722448   \n",
       "\n",
       "Metric                                               total_reading_time_aoi   \n",
       "Statistic         25%   median        75%        max                  count   \n",
       "Condition                                                                     \n",
       "ambiguous    4.648408  7.12821  12.172524  28.518223                    743  \\\n",
       "unambiguous  4.284828  6.82339  10.479799  28.981631                    757   \n",
       "\n",
       "Metric                ... number_fixations_aoi     number_visits_aoi   \n",
       "Statistic       mean  ...                  75% max             count   \n",
       "Condition             ...                                              \n",
       "ambiguous    2.61962  ...                  6.0  24               743  \\\n",
       "unambiguous  1.77958  ...                  4.0  27               757   \n",
       "\n",
       "Metric                                                    \n",
       "Statistic        mean       std min  25% median  75% max  \n",
       "Condition                                                 \n",
       "ambiguous    3.227456  2.381012   0  2.0    3.0  4.0  17  \n",
       "unambiguous  2.718626  2.218569   0  1.0    2.0  3.0  15  \n",
       "\n",
       "[2 rows x 40 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>Metric</th>\n",
       "      <th colspan=\"8\" halign=\"left\">total_reading_time_snippet</th>\n",
       "      <th colspan=\"2\" halign=\"left\">total_reading_time_aoi</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">number_fixations_aoi</th>\n",
       "      <th colspan=\"8\" halign=\"left\">number_visits_aoi</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Statistic</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>700</td>\n",
       "      <td>9.624905</td>\n",
       "      <td>6.707699</td>\n",
       "      <td>1.698284</td>\n",
       "      <td>4.725556</td>\n",
       "      <td>7.279017</td>\n",
       "      <td>12.252157</td>\n",
       "      <td>28.518223</td>\n",
       "      <td>700</td>\n",
       "      <td>2.733849</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>24</td>\n",
       "      <td>700</td>\n",
       "      <td>3.358571</td>\n",
       "      <td>2.352668</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>687</td>\n",
       "      <td>8.983344</td>\n",
       "      <td>6.230035</td>\n",
       "      <td>0.722448</td>\n",
       "      <td>4.578648</td>\n",
       "      <td>7.028172</td>\n",
       "      <td>10.896309</td>\n",
       "      <td>28.981631</td>\n",
       "      <td>687</td>\n",
       "      <td>1.936278</td>\n",
       "      <td>...</td>\n",
       "      <td>4.0</td>\n",
       "      <td>27</td>\n",
       "      <td>687</td>\n",
       "      <td>2.940320</td>\n",
       "      <td>2.196125</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Metric      total_reading_time_snippet                                 \n",
       "Statistic                        count      mean       std       min   \n",
       "Condition                                                              \n",
       "ambiguous                          700  9.624905  6.707699  1.698284  \\\n",
       "unambiguous                        687  8.983344  6.230035  0.722448   \n",
       "\n",
       "Metric                                                total_reading_time_aoi   \n",
       "Statistic         25%    median        75%        max                  count   \n",
       "Condition                                                                      \n",
       "ambiguous    4.725556  7.279017  12.252157  28.518223                    700  \\\n",
       "unambiguous  4.578648  7.028172  10.896309  28.981631                    687   \n",
       "\n",
       "Metric                 ... number_fixations_aoi     number_visits_aoi   \n",
       "Statistic        mean  ...                  75% max             count   \n",
       "Condition              ...                                              \n",
       "ambiguous    2.733849  ...                  6.0  24               700  \\\n",
       "unambiguous  1.936278  ...                  4.0  27               687   \n",
       "\n",
       "Metric                                                    \n",
       "Statistic        mean       std min  25% median  75% max  \n",
       "Condition                                                 \n",
       "ambiguous    3.358571  2.352668   1  2.0    3.0  4.0  17  \n",
       "unambiguous  2.940320  2.196125   1  1.0    2.0  4.0  15  \n",
       "\n",
       "[2 rows x 40 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>Metric</th>\n",
       "      <th colspan=\"8\" halign=\"left\">total_reading_time_snippet</th>\n",
       "      <th colspan=\"2\" halign=\"left\">total_reading_time_aoi</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">number_fixations_aoi</th>\n",
       "      <th colspan=\"8\" halign=\"left\">number_visits_aoi</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Statistic</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>median</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ambiguous</th>\n",
       "      <td>699</td>\n",
       "      <td>9.612951</td>\n",
       "      <td>6.705037</td>\n",
       "      <td>1.698284</td>\n",
       "      <td>4.723101</td>\n",
       "      <td>7.278144</td>\n",
       "      <td>12.214543</td>\n",
       "      <td>28.518223</td>\n",
       "      <td>699</td>\n",
       "      <td>2.732504</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>24</td>\n",
       "      <td>699</td>\n",
       "      <td>3.359084</td>\n",
       "      <td>2.354314</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unambiguous</th>\n",
       "      <td>686</td>\n",
       "      <td>8.978836</td>\n",
       "      <td>6.233460</td>\n",
       "      <td>0.722448</td>\n",
       "      <td>4.576391</td>\n",
       "      <td>7.027654</td>\n",
       "      <td>10.869910</td>\n",
       "      <td>28.981631</td>\n",
       "      <td>686</td>\n",
       "      <td>1.936902</td>\n",
       "      <td>...</td>\n",
       "      <td>4.0</td>\n",
       "      <td>27</td>\n",
       "      <td>686</td>\n",
       "      <td>2.943149</td>\n",
       "      <td>2.196475</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Metric      total_reading_time_snippet                                 \n",
       "Statistic                        count      mean       std       min   \n",
       "Condition                                                              \n",
       "ambiguous                          699  9.612951  6.705037  1.698284  \\\n",
       "unambiguous                        686  8.978836  6.233460  0.722448   \n",
       "\n",
       "Metric                                                total_reading_time_aoi   \n",
       "Statistic         25%    median        75%        max                  count   \n",
       "Condition                                                                      \n",
       "ambiguous    4.723101  7.278144  12.214543  28.518223                    699  \\\n",
       "unambiguous  4.576391  7.027654  10.869910  28.981631                    686   \n",
       "\n",
       "Metric                 ... number_fixations_aoi     number_visits_aoi   \n",
       "Statistic        mean  ...                  75% max             count   \n",
       "Condition              ...                                              \n",
       "ambiguous    2.732504  ...                  6.0  24               699  \\\n",
       "unambiguous  1.936902  ...                  4.0  27               686   \n",
       "\n",
       "Metric                                                    \n",
       "Statistic        mean       std min  25% median  75% max  \n",
       "Condition                                                 \n",
       "ambiguous    3.359084  2.354314   1  2.0    3.0  4.0  17  \n",
       "unambiguous  2.943149  2.196475   1  1.0    2.0  4.0  15  \n",
       "\n",
       "[2 rows x 40 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for algorithm in results:\n",
    "    results[algorithm][CONDITION] = results[algorithm][SNIPPET].map(lambda snippet: CONDITION_VARIANT_MATCH[get_snippet_variant(snippet)])\n",
    "    stats = results[algorithm].groupby([CONDITION])[metrics].agg(PANDAS_DESCRIPTION_AGG_FUNCTIONS)\n",
    "    stats.columns = pd.MultiIndex.from_product([metrics, PANDAS_DESCRIPTION_AGG_NAMES], names=['Metric', 'Statistic'])\n",
    "    stats.to_csv(get_erp_fixation_analysis_path(algorithm, SNIPPET_GROUP_ALL, 'all', 'reading metrics stats'), sep=SEPARATOR)\n",
    "    display(stats)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "facf3432",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{}\n",
      "\ttotal_reading_time_snippet diff_ambiguous-unambiguous might be normally distributed due to 0.636 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9687525629997253, pvalue=0.6362825036048889)\n",
      "\tFor total_reading_time_snippet, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.007: H1 accepted; Result TtestResult(statistic=2.6418123728518563, pvalue=0.007287673975513888, df=23)\n",
      "\t\tEffect size 0.25206624936478345 small\n",
      "\ttotal_reading_time_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.15 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9383494257926941, pvalue=0.14986033737659454)\n",
      "\tFor total_reading_time_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=5.376017088687812, pvalue=9.221812272989994e-06, df=23)\n",
      "\t\tEffect size 0.8034103679742503 large\n",
      "\tfirst_pass_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.707 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9716038703918457, pvalue=0.7066540718078613)\n",
      "\tFor first_pass_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=3.89772983995859, pvalue=0.000362482426477271, df=23)\n",
      "\t\tEffect size 0.8155706595340239 large\n",
      "\tnumber_fixations_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.146 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9378770589828491, pvalue=0.1462632119655609)\n",
      "\tFor number_fixations_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=5.086317014183773, pvalue=1.8832953371945468e-05, df=23)\n",
      "\t\tEffect size 0.582716368259611 medium\n",
      "\tnumber_visits_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.168 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9405875205993652, pvalue=0.1681167036294937)\n",
      "\tFor number_visits_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=4.9336731613239415, pvalue=2.7492567628620062e-05, df=23)\n",
      "\t\tEffect size 0.472674500990907 small\n",
      "{}\n",
      "\ttotal_reading_time_snippet diff_ambiguous-unambiguous might be normally distributed due to 0.483 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9621656537055969, pvalue=0.48345863819122314)\n",
      "\tFor total_reading_time_snippet, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.021: H1 accepted; Result TtestResult(statistic=2.147812741525501, pvalue=0.02124829355474799, df=23)\n",
      "\t\tEffect size 0.20893183271386845 small\n",
      "\ttotal_reading_time_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.061 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9208249449729919, pvalue=0.0609150193631649)\n",
      "\tFor total_reading_time_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=5.135117184994385, pvalue=1.669215084742761e-05, df=23)\n",
      "\t\tEffect size 0.7647876858127416 medium\n",
      "\tfirst_pass_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.874 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.978886604309082, pvalue=0.8744900226593018)\n",
      "\tFor first_pass_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=3.9226232328439496, pvalue=0.00034079932859297377, df=23)\n",
      "\t\tEffect size 0.765333930188007 medium\n",
      "\tnumber_fixations_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.254 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9486991167068481, pvalue=0.25388309359550476)\n",
      "\tFor number_fixations_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=4.5958668087118095, pvalue=6.372467363575989e-05, df=23)\n",
      "\t\tEffect size 0.5306874050582564 medium\n",
      "\tnumber_visits_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.181 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.941979169845581, pvalue=0.18054074048995972)\n",
      "\tFor number_visits_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=4.244561819958556, pvalue=0.0001530429306740161, df=23)\n",
      "\t\tEffect size 0.40993429536147274 small\n",
      "{}\n",
      "\ttotal_reading_time_snippet diff_ambiguous-unambiguous might be normally distributed due to 0.508 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9633012413978577, pvalue=0.5082424879074097)\n",
      "\tFor total_reading_time_snippet, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.023: H1 accepted; Result TtestResult(statistic=2.1123884259000283, pvalue=0.022859791597515045, df=23)\n",
      "\t\tEffect size 0.20612076261337223 small\n",
      "\ttotal_reading_time_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.061 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9208905696868896, pvalue=0.06111903116106987)\n",
      "\tFor total_reading_time_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=5.137305330083729, pvalue=1.6602135134933894e-05, df=23)\n",
      "\t\tEffect size 0.7642096131550662 medium\n",
      "\tfirst_pass_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.79 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9750258326530457, pvalue=0.7897239327430725)\n",
      "\tFor first_pass_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=3.9056033343993386, pvalue=0.00035548075765521757, df=23)\n",
      "\t\tEffect size 0.7728872919708958 medium\n",
      "\tnumber_fixations_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.254 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9487080574035645, pvalue=0.25399696826934814)\n",
      "\tFor number_fixations_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=4.589696927673473, pvalue=6.47125304946729e-05, df=23)\n",
      "\t\tEffect size 0.530819658271285 medium\n",
      "\tnumber_visits_aoi diff_ambiguous-unambiguous might be normally distributed due to 0.251 greater equals to alpha 0.05; Result ShapiroResult(statistic=0.9485017657279968, pvalue=0.2513812482357025)\n",
      "\tFor number_visits_aoi, the t-test paired's stance on the H1 `confusing greater than clean` indicates with alpha=0.05 and the p-value of 0.0: H1 accepted; Result TtestResult(statistic=4.271608557979052, pvalue=0.00014306471737732105, df=23)\n",
      "\t\tEffect size 0.40805740284717273 small\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAi8AAAG9CAYAAADdkpaRAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAABSDUlEQVR4nO3deViU5f4G8HuAYWDYFEQWQUBQEUQtRHMDcU1xQcWltNzq1HHB3dIyxcpdtNTcU4+lZYZaHjTIAMkTiZqZOxpuuaUoy0AwwPP7w4v358gi6MDwwv25rq6c53143u8w88zcvKtCCCFAREREJBNGhi6AiIiIqCIYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheapHk5GS0b98eFhYWUCgUOHnyJObNmweFQmHo0iTVrcatW7dCoVDgypUrBll/Zalur3tFlfS6dO7cGZ07dzZYTc+jc+fOaN68uaHLqLBn+Z3XhDnl7u6OUaNGGbqMWs3E0AVQ1dBqtRg8eDDMzMywYsUKqNVquLm56X09Z8+exa5duzBq1Ci4u7tXyxpLsmDBAvj4+CA0NLRK1kdE/++zzz6DWq1mIKByU/DeRrXD+fPn0axZM2zcuBFvvPGG1J6fn4/8/HyYmZnpZT27d+/G4MGDERcXV+G/yKqqxpJYWloiLCwMW7du1WkvKCiAVquFSqWS9ZaKJ1XF77Qybd26FaNHj0ZqaqoUkoveb/Hx8Qar61l17twZ9+7dw+nTpw1dSoXk5eUBAExNTcv9MyXNqebNm6NevXqyee1yc3NhZGQEpVJp6FJqLW55qSXu3r0LAKhTp45Ou4mJCUxMyn4bFBYWIi8vr9K/6J6nxspibGwMY2Njg6y7Mhnyd0qGURnzuCKhpUhNmFMqlcrQJdR6POalFhg1ahSCgoIAAIMHD4ZCoZD+Si3p2AeFQoEJEybgyy+/hK+vL1QqFQ4ePAgA+Oqrr+Dv7w8rKytYW1vDz88Pn3zyCYBHfw0PHjwYABAcHAyFQgGFQlGuv6YqUuOWLVugUCjw+eef64yxYMECKBQKREdHS23Lli1D+/btYWdnB3Nzc/j7+2P37t3Fnq9Go8G2bdukmos2X5e2f/6zzz6TfjfOzs4YP348Hj58qNOn6DiGs2fPIjg4GGq1Gg0aNMCSJUue+vt40r59+xASEgJnZ2eoVCp4enriww8/REFBQbG+33zzDfz9/WFubo569ephxIgR+Ouvv3T6PMsxL7dv38bo0aPh4uIClUoFJycn9O/fX+d34+7ujj59+iA+Ph6tW7eGubk5/Pz8pPdAVFQU/Pz8YGZmBn9/f/z222866zh16hRGjRqFRo0awczMDI6OjhgzZgzu379foVrLUvT+3rt3L5o3bw6VSgVfX1/pPV6ktF2fZc2Zb775Bj4+PjA3N0e7du3wxx9/AADWr18PLy8vmJmZoXPnzqUe73H8+HG0b98e5ubm8PDwwLp164r1yc3Nxdy5c+Hl5QWVSgVXV1fMnDkTubm5JdZU0jwuy4QJE2BpaYns7Oxiy1555RU4OjpK77uSjnlZtWoVfH19oVarUbduXbRu3Ro7duyQlj85p9zd3XHmzBkkJCRI869oTK1Wi4iICDRu3BhmZmaws7NDx44dERsb+9TnUSQvLw8ffPAB/P39YWNjAwsLC3Tq1AlxcXHF+mo0GkybNg2urq5QqVRo2rQpli1bhid3UPCYl2pAUI33v//9T8yePVsAEOHh4WL79u0iJiZGCCHE3LlzxZNvAwCiWbNmwt7eXkRERIg1a9aI3377TcTExAgAomvXrmLNmjVizZo1YsKECWLw4MFCCCEuX74swsPDBQAxe/ZssX37drF9+3Zx+/ZtvdfYp08fYWNjI65duyaEEOLUqVPC1NRUjB07Vqefi4uLGDdunFi9erWIjIwUbdq0EQDE/v37pT7bt28XKpVKdOrUSar5f//7nxBCiC1btggAIjU1VepfVE+3bt3EqlWrxIQJE4SxsbEICAgQeXl5Ur+goCDh7OwsXF1dxaRJk8Rnn30munTpIgCI6Ojop/5OHhcaGiqGDBkili5dKtauXSsGDx4sAIjp06fr9CuqNyAgQKxYsUK8++67wtzcXLi7u4sHDx4Uew4V0b59e2FjYyPef/99sWnTJrFgwQIRHBwsEhISpD5ubm6iadOmwsnJScybN0+sWLFCNGjQQFhaWoovvvhCNGzYUCxatEgsWrRI2NjYCC8vL1FQUCD9/LJly0SnTp3E/PnzxYYNG8SkSZOEubm5aNOmjSgsLCz2PB9/XYKCgkRQUNBTnwcA0bJlS+Hk5CQ+/PBDsXLlStGoUSOhVqvFvXv3pH4jR44Ubm5uxX6+tDnTokUL4erqqvP8GjZsKFavXi18fHzE8uXLxfvvvy9MTU1FcHCwzs8XvVfq168vJkyYID799FPRsWNHAUBs3rxZ6ldQUCB69Ogh1Gq1mDx5sli/fr2YMGGCMDExEf379y9WU0nz+GkOHz4sAIhdu3bptGs0GmFhYSHGjx+vU/fjv/MNGzYIACIsLEysX79efPLJJ2Ls2LEiPDxc6vPka7dnzx7h4uIivL29pflXNPdnz54tFAqFePPNN8XGjRvF8uXLxSuvvCIWLVr01OdR5O+//xZOTk5i6tSpYu3atWLJkiWiadOmQqlU6vw+CgsLRZcuXYRCoRBvvPGGWL16tejbt68AICZPnqwzppubmxg5cmS5ayD9Y3ipJeLi4gQA8c033+i0l/ZBbGRkJM6cOaPTPmnSJGFtbS3y8/NLXc8333wjAIi4uLhKrfHWrVvC1tZWdO/eXeTm5ooXXnhBNGzYUKSnp+v0y87O1nmcl5cnmjdvLrp06aLTbmFhUeKH0ZMftHfv3hWmpqaiR48eOl+6q1evFgDE559/LrUFBQUJAOI///mP1JabmyscHR3FoEGDnv4LKeN5CCHEW2+9JdRqtfjnn3+k51a/fn3RvHlzkZOTI/Xbv3+/ACA++OADqa2i4eXBgwcCgFi6dGmZ/dzc3AQAKfwJIcQPP/wgAAhzc3Nx9epVqX39+vXF3islPc+dO3cKAOLw4cNS2/OGF1NTU3Hp0iWp7ffffxcAxKpVq6S2ioYXlUqlU0/R83N0dBQZGRlS+6xZs0qsHYBYvny51JabmytatWol6tevL4Xi7du3CyMjI5GYmKiz/nXr1gkA4siRIzo1lTSPn6awsFA0aNCg2Ht0165dxV6HJ3/n/fv3F76+vmWOX9Jr5+vrW+Jr17JlSxESElKh+p+Un58vcnNzddoePHggHBwcxJgxY6S2vXv3CgDio48+0ukbFhYmFAqFzvuF4cXwuNuIShQUFAQfHx+dtjp16kCj0VRok21lcXR0xJo1axAbG4tOnTrh5MmT+Pzzz2Ftba3Tz9zcXPr3gwcPkJ6ejk6dOuHEiRPPtN4ff/wReXl5mDx5MoyM/n/6vPnmm7C2tsZ///tfnf6WlpYYMWKE9NjU1BRt2rTBn3/+WaH1Pv48MjMzce/ePXTq1AnZ2dk4f/48AODYsWO4e/cuxo0bp3NcQ0hICLy9vYvVVtH1m5qaIj4+Hg8ePCizr4+PD9q1ayc9btu2LQCgS5cuaNiwYbH2x38Xjz/Pf/75B/fu3cNLL70EAM/8mpWkW7du8PT0lB63aNEC1tbWFX5dHte1a1ed3UxFz2/QoEGwsrIq1v7kukxMTPDWW29Jj01NTfHWW2/h7t27OH78OIBHuwSbNWsGb29v3Lt3T/qvS5cuAFBsV0hJ8/hpFAoFBg8ejOjoaGRlZUntX3/9NRo0aICOHTuW+rN16tTBjRs3kJycXKF1ljXemTNnkJKS8sxjGBsbS8fmFBYWIi0tDfn5+WjdurXOeyo6OhrGxsYIDw/X+flp06ZBCIEDBw48cw2kfwwvVCIPD49ibePGjUOTJk3Qq1cvuLi4YMyYMeXah15Zhg0bhpCQEBw9ehRvvvkmunbtWqzP/v378dJLL8HMzAy2trawt7fH2rVrkZ6e/kzrvHr1KgCgadOmOu2mpqZo1KiRtLyIi4tLseMj6tat+9QA8KQzZ85gwIABsLGxgbW1Nezt7aVQVPRcSqsNALy9vYvVVhEqlQqLFy/GgQMH4ODggMDAQCxZsgS3b98u1vfxgAIANjY2AABXV9cS2x//XaSlpWHSpElwcHCAubk57O3tpffis75mJXmyRuDZXpeyxqzI8wYAZ2dnWFhY6LQ1adIEAKTjQ1JSUnDmzBnY29vr/FfUr+ig9yIlzePyGDp0KHJycvDdd98BALKyshAdHS0dj1aad955B5aWlmjTpg0aN26M8ePH48iRI89UAwDMnz8fDx8+RJMmTeDn54cZM2bg1KlTFR5n27ZtaNGihXTcjL29Pf773//qvKeuXr0KZ2dnnaAJAM2aNZOWU/XB8EIlevwv4CL169fHyZMn8d1336Ffv36Ii4tDr169MHLkSANUCNy/fx/Hjh0D8Oj6MoWFhTrLExMT0a9fP5iZmeGzzz5DdHQ0YmNj8eqrrxY7AK+ylHZWRUXW//DhQwQFBeH333/H/Pnz8f333yM2NhaLFy8GgGLPu7JMnjwZFy9exMKFC2FmZoY5c+agWbNmxQ66Le05l+d3MWTIEGzcuBFvv/02oqKiEBMTIwVkfT7P8tRS2pd0SQdJlzWmPt4DRQoLC+Hn54fY2NgS/xs3bpxO/5LmcXm89NJLcHd3x65duwAA33//PXJycjB06NAyf65Zs2a4cOECvvrqK3Ts2BHffvstOnbsiLlz5z5THYGBgbh8+TI+//xzNG/eHJs2bcKLL76ITZs2lXuML774AqNGjYKnpyc2b96MgwcPIjY2Fl26dKmyuUP6x3MlqUJMTU3Rt29f9O3bF4WFhRg3bhzWr1+POXPmwMvLq0qvhTJ+/HhkZmZi4cKFmDVrFlauXImpU6dKy7/99luYmZnhhx9+0Dm1ccuWLcXGKm/dRRfNu3DhAho1aiS15+XlITU1Fd26dXvWp1Oq+Ph43L9/H1FRUQgMDJTaU1NTS62taDdCkQsXLujlgn+enp6YNm0apk2bhpSUFLRq1QrLly/HF1988dxjP3jwAIcOHUJERAQ++OADqf15dhk8j7p16xY7gwyovL/Ab968CY1Go7P15eLFiwAg7Y7y9PTE77//jq5du1b6XBsyZAg++eQTZGRk4Ouvv4a7u7u0C68sFhYWGDp0KIYOHYq8vDwMHDgQH3/8MWbNmlXqadplPRdbW1uMHj0ao0ePRlZWFgIDAzFv3jyda0GVZffu3WjUqBGioqJ01vNkoHJzc8OPP/6IzMxMna0vRbtlq+qCmVQ+3PJC5fbk6apGRkZo0aIFAEinaRZ98Jb0oa9Pu3fvxtdff41Fixbh3XffxbBhw/D+++9LH/bAo794FQqFzl/KV65cwd69e4uNZ2FhUa6au3XrBlNTU3z66ac6fzlv3rwZ6enpCAkJea7nVZKiv9wfX19eXh4+++wznX6tW7dG/fr1sW7dOp3TZg8cOIBz5849V23Z2dn4559/dNo8PT1hZWVV7BTdZ1XS8wSAlStX6mX8ivL09ER6errObopbt25hz549lbK+/Px8rF+/Xnqcl5eH9evXw97eHv7+/gAeBYq//voLGzduLPbzOTk50Gg0eqtn6NChyM3NxbZt23Dw4EEMGTLkqT/z5GeEqakpfHx8IISAVqst9edKm39PjmdpaQkvL68KvedKel/9+uuv+OWXX3T69e7dGwUFBVi9erVO+4oVK6BQKNCrV69yr5MqH7e8ULm98cYbSEtLQ5cuXeDi4oKrV69i1apVaNWqlbRfuFWrVjA2NsbixYuRnp4OlUqFLl26oH79+nqr4+7du/j3v/+N4OBgTJgwAQCwevVqxMXFYdSoUfj5559hZGSEkJAQREZG4uWXX8arr76Ku3fvYs2aNfDy8iq239zf3x8//vgjIiMj4ezsDA8PD+nAysfZ29tj1qxZiIiIwMsvv4x+/frhwoUL+OyzzxAQEKBzcK6+tG/fHnXr1sXIkSMRHh4OhUKB7du3F/uSVyqVWLx4MUaPHo2goCC88soruHPnDj755BO4u7tjypQpz1zDxYsX0bVrVwwZMgQ+Pj4wMTHBnj17cOfOHQwbNux5nyIAwNraWjqWRqvVokGDBoiJiSm2hamqDBs2DO+88w4GDBiA8PBwZGdnY+3atWjSpIleDx4u4uzsjMWLF+PKlSto0qQJvv76a5w8eRIbNmyQruT62muvYdeuXXj77bcRFxeHDh06oKCgAOfPn8euXbvwww8/oHXr1nqp58UXX4SXlxfee+895ObmPnWXEQD06NEDjo6O6NChAxwcHHDu3DmsXr0aISEhxY4leZy/vz/Wrl2Ljz76CF5eXqhfvz66dOkCHx8fdO7cGf7+/rC1tcWxY8ewe/duad6XR58+fRAVFYUBAwYgJCQEqampWLduHXx8fHQOSO7bty+Cg4Px3nvv4cqVK2jZsiViYmKwb98+TJ48WecAb6oGDHOSE1W1ip4q/fi1HIrs3r1b9OjRQ9SvX1+YmpqKhg0birfeekvcunVLp9/GjRtFo0aNhLGxcYVOmy5vjQMHDhRWVlbiypUrOv327dsnAIjFixdLbZs3bxaNGzcWKpVKeHt7iy1btpT4nM+fPy8CAwOFubm5ACCdBlnSaZ1CPDo12tvbWyiVSuHg4CD+/e9/61xHRYhHp5GWdNpoaafgluXIkSPipZdeEubm5sLZ2VnMnDlTOgX5yd/v119/LV544QWhUqmEra2tGD58uLhx44ZOn4qeKn3v3j0xfvx44e3tLSwsLISNjY1o27ZtsWuBuLm5lXhqa0nvqdTU1GKnX9+4cUMMGDBA1KlTR9jY2IjBgweLmzdvCgBi7ty5Ur/nPVW6pPd3Sae/xsTEiObNmwtTU1PRtGlT8cUXX5R7zpT0/IQo+X1e9F45duyYaNeunTAzMxNubm5i9erVxerMy8sTixcvFr6+vkKlUom6desKf39/ERERoXOpgNKeZ0W89957AoDw8vIqcfmTv/P169eLwMBAYWdnJ1QqlfD09BQzZszQqauk1+727dsiJCREWFlZCQDSmB999JFo06aNqFOnjjA3Nxfe3t7i448/1rme0tMUFhaKBQsWCDc3N6FSqcQLL7wg9u/fX+I8zMzMFFOmTBHOzs5CqVSKxo0bi6VLl+pcY0gInipdHfDeRkRERCQrPOaFiIiIZIXHvFCly8rK0tm3XBJ7e3vZ36ztWfz999+lnnoLPDrg0dbWtlJrSE9PR05OTpl9HB0dK7UGqhppaWnSnaBLYmxsDHt7+yqs6Nnl5eUhLS2tzD42NjbPfLo4VW/cbUSVbt68eYiIiCizT2pqaok3wavp3N3dyzz1NigoqFw3tnweo0aNwrZt28rsw4+JmqFz585ISEgodbmbm1upN42sbuLj4xEcHFxmny1btvAGijUUwwtVuj///POpl13v2LFjqdeAqMmOHDlS5laPunXrSqfJVpazZ8/i5s2bZfapjOvXUNU7fvx4mVcRNjc3R4cOHaqwomf34MED6bYJpfH19YWTk1MVVURVieGFiIiIZIUH7BIREZGsVLsDdgsLC3Hz5k1YWVlV6aXmiYiIyHCEEMjMzISzszOMjMretlLtwsvNmzeL3YWViIiIaofr16/DxcWlzD7VLrwUXUL6+vXrsLa2NnA1VNW0Wi1iYmLQo0cP6ZLoRFQ7cP7XbhkZGXB1dS3zVhJFql14KdpVZG1tzfBSC2m1WqjValhbW/PDi6iW4fwnoOy7jBfhAbtEREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML1RtFBQUICEhAYcPH0ZCQgIKCgoMXRIREVVDDC9ULURFRcHLywvdu3dHZGQkunfvDi8vL0RFRRm6NCIiqmYYXsjgoqKiEBYWBj8/PyQmJmLnzp1ITEyEn58fwsLCGGCIiEgHwwsZVEFBAaZNm4Y+ffpg7969aNu2LczNzdG2bVvs3bsXffr0wfTp07kLiYiIJAwvZFCJiYm4cuUKZs+eDSMj3bejkZERZs2ahdTUVCQmJhqoQiIiqm4YXsigbt26BQBo3rx5icuL2ov6ERERMbyQQTk5OQEATp8+XeLyovaifkRERAwvZFCdOnWCu7s7FixYgMLCQp1lhYWFWLhwITw8PNCpUycDVUhERNUNwwsZlLGxMZYvX479+/cjNDQUSUlJyMnJQVJSEkJDQ7F//34sW7YMxsbGhi6ViIiqCRNDF0A0cOBA7N69G9OmTUNgYKDU7uHhgd27d2PgwIEGrI6IiKobhheqFgYOHIj+/fsjLi4OBw4cQK9evRAcHMwtLkREVAzDC1UbxsbGCAoKgkajQVBQEIMLERGViMe8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLwQERGRrDC8EBERkaxUOLwcPnwYffv2hbOzMxQKBfbu3Vusz7lz59CvXz/Y2NjAwsICAQEBuHbtmj7qJSIiolquwuFFo9GgZcuWWLNmTYnLL1++jI4dO8Lb2xvx8fE4deoU5syZAzMzs+culoiIiKjCN2bs1asXevXqVery9957D71798aSJUukNk9Pz2erjoiIiOgJer2rdGFhIf773/9i5syZ6NmzJ3777Td4eHhg1qxZCA0NLfFncnNzkZubKz3OyMgAAGi1Wmi1Wn2WRzJQ9JrztSeqfTj/a7eKvO56DS93795FVlYWFi1ahI8++giLFy/GwYMHMXDgQMTFxSEoKKjYzyxcuBARERHF2mNiYqBWq/VZHslIbGysoUsgIgPh/K+dsrOzy91XIYQQz7oihUKBPXv2SFtVbt68iQYNGuCVV17Bjh07pH79+vWDhYUFdu7cWWyMkra8uLq64t69e7C2tn7W0kimtFotYmNj0b17dyiVSkOXQ0RViPO/dsvIyEC9evWQnp7+1O9/vW55qVevHkxMTODj46PT3qxZM/z8888l/oxKpYJKpSrWrlQq+eatxfj6E9VenP+1U0Vec71e58XU1BQBAQG4cOGCTvvFixfh5uamz1URERFRLVXhLS9ZWVm4dOmS9Dg1NRUnT56Era0tGjZsiBkzZmDo0KEIDAxEcHAwDh48iO+//x7x8fH6rJuIiIhqqQqHl2PHjiE4OFh6PHXqVADAyJEjsXXrVgwYMADr1q3DwoULER4ejqZNm+Lbb79Fx44d9Vc1ERER1VoVDi+dO3fG047xHTNmDMaMGfPMRRERERGVhvc2IiIiIllheCEiIiJZYXghIiIiWWF4ISIiIllheCEiIiJZYXghIiIiWWF4ISIiIllheCEiIiJZYXihaqOgoAAJCQk4fPgwEhISUFBQYOiSiKiKcP5TRTC8ULUQFRUFLy8vdO/eHZGRkejevTu8vLwQFRVl6NKIqJJx/lNFMbyQwUVFRSEsLAx+fn5ITEzEzp07kZiYCD8/P4SFhfEDjKgG4/ynZ6EQT7tRURXLyMiAjY0N0tPTYW1tbehyqJIVFBTAy8sLfn5+2Lt3LwoKChAdHY3evXvD2NgYoaGhOH36NFJSUmBsbGzocolIjzj/6XEV+f7nlhcyqMTERFy5cgWzZ8+GkZHu29HIyAizZs1CamoqEhMTDVQhEVUWzn96VgwvZFC3bt0CADRv3rzE5UXtRf2IqObg/KdnxfBCBuXk5AQAOH36dInLi9qL+hFRzcH5T8+K4YUMqlOnTnB3d8eCBQtQWFios6ywsBALFy6Eh4cHOnXqZKAKiaiycP7Ts2J4IYMyNjbG8uXLsX//foSGhiIpKQk5OTlISkpCaGgo9u/fj2XLlvFgPaIaiPOfnhXPNqJqISoqCtOmTcOVK1ekNg8PDyxbtgwDBw40XGFEVOk4/wmo2Pc/wwtVGwUFBYiLi8OBAwfQq1cvBAcH8y8uolqC858q8v1vUkU1ET2VsbExgoKCoNFoEBQUxA8uolqE858qgse8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLxQtVFQUICEhAQcPnwYCQkJKCgoMHRJRFRF8vLy8Omnn2LDhg349NNPkZeXZ+iSqBrj7QGoWijp3ibu7u5Yvnw5721CVMPNnDkTK1asQH5+vtRmYmKCKVOmYMmSJQasjKpSRb7/K7zl5fDhw+jbty+cnZ2hUCiwd+/eUvu+/fbbUCgUWLlyZUVXQ7VIVFQUwsLC4Ofnh8TEROzcuROJiYnw8/NDWFgYoqKiDF0iEVWSmTNnYunSpbCzs8O6deuwZcsWrFu3DnZ2dli6dClmzpxp6BKpGqpweNFoNGjZsiXWrFlTZr89e/YgKSkJzs7Oz1wc1XwFBQWYNm0a+vTpg71796Jt27YwNzdH27ZtsXfvXvTp0wfTp0/nLiSiGigvLw8rVqyAg4MDbty4gTFjxqBu3boYM2YMbty4AQcHB6xYsYK7kKiYCt+YsVevXujVq1eZff766y9MnDgRP/zwA0JCQsrsm5ubi9zcXOlxRkYGAECr1UKr1Va0PJKZhIQEXLlyBdu3b0dBQYH0mhf9f8aMGQgMDERcXByCgoIMWSoR6dmqVauQn5+PiIgICCF05r9SqcTcuXMxbtw4rFq1CuHh4QaulipbRb7z9X5X6cLCQrz22muYMWMGfH19n9p/4cKFiIiIKNYeExMDtVqt7/Komjl8+DAA4MaNG7h//77UHhsbCwDIyckBABw4cAAajabqCySiSvPTTz8BAFQqFaKjo6X2ovlvZmYm9fPy8qr6AqlKZWdnl7uv3sPL4sWLYWJiUu6UPGvWLEydOlV6nJGRAVdXV/To0YMH7NYCFhYWiIyMhIuLC9q2bQutVovY2Fh0794dSqUSSUlJAB5t8eOWF6Ka5dKlS4iOjkZubi569+5dbP5v2rQJANClSxf07t3bwNVSZSva81Ieeg0vx48fxyeffIITJ05AoVCU62dUKhVUKlWxdqVSCaVSqc/yqBoKDg6Gu7s7lixZonPwt1KphLGxMZYuXQoPDw8EBwfD2NjYcIUSkd5NnDgR7777LubOnYuxY8dKn/lKpRIKhQIREREwMTHBxIkT+X1QC1TkNdbrdV4SExNx9+5dNGzYECYmJjAxMcHVq1cxbdo0uLu763NVVEMYGxtj+fLl2L9/P0JDQ5GUlIScnBwkJSUhNDQU+/fvx7JlyxhciGogU1NTTJkyBXfu3IGLiws2bdqEtLQ0bNq0CS4uLrhz5w6mTJkCU1NTQ5dK1Yxet7y89tpr6Natm05bz5498dprr2H06NH6XBXVIAMHDsTu3bsxbdo0BAYGSu0eHh7YvXs3r/NCVIMVXcdlxYoVGDdunNRuYmKCGTNm8DovVKIKh5esrCxcunRJepyamoqTJ0/C1tYWDRs2hJ2dnU5/pVIJR0dHNG3a9PmrpRpr4MCB6N+/P+Li4nDgwAH06tWLu4qIaoklS5bgo48+wqpVq/DTTz+hS5cumDhxIre4UKkqHF6OHTuG4OBg6XHRwbYjR47E1q1b9VYY1T7GxsYICgqCRqNBUFAQgwtRLWJqaorw8HB4eXmhd+/ePMaFylTh8NK5c2dU5I4Cj1/unYiIiOh58caMREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9UbeTk5CA8PBzz5s1DeHg4cnJyDF0SEVURzn+qCIWoyOVyq0BGRgZsbGyQnp4Oa2trQ5dDVSQ0NBT79u0r1t6/f3/s3bu36gsioirD+U9Axb7/ueWFDK7og8vU1BQzZ87E2rVrMXPmTJiammLfvn0IDQ01dIlEVEk4/+lZcMsLGVROTg7UajVMTU2RmZkJhUKB6Oho9O7dG0IIWFlZIS8vD9nZ2TA3Nzd0uUSkR5z/9DhueSHZmDFjBoBHdyc3NTXVWWZqaorJkyfr9COimoPzn54VwwsZVEpKCgDgjTfeKHH52LFjdfoRUc3B+U/PiuGFDKpx48YAgE2bNpW4fPPmzTr9iKjm4PynZ8VjXsiguM+bqPbi/KfH8ZgXkg1zc3P0798feXl5sLKywuzZs/HXX39h9uzZ0gdX//79+cFFVANx/tOz4pYXqhZ4nQei2ovzn4CKff8zvFC1kZOTg6lTpyIpKQkvvfQSIiMj+RcXUS3B+U8MLyRbWq1W2uetVCoNXQ4RVSHO/9qNx7wQERFRjcXwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8ELVRkFBARISEnD48GEkJCSgoKDA0CURURXh/KeKqHB4OXz4MPr27QtnZ2coFAqd+05otVq888478PPzg4WFBZydnfH666/j5s2b+qyZaqCoqCh4eXmhe/fuiIyMRPfu3eHl5YWoqChDl0ZElYzznyqqwuFFo9GgZcuWWLNmTbFl2dnZOHHiBObMmYMTJ04gKioKFy5cQL9+/fRSLNVMUVFRCAsLg5+fHxITE7Fz504kJibCz88PYWFh/AAjqsE4/+lZPNe9jRQKBfbs2YPQ0NBS+yQnJ6NNmza4evUqGjZs+NQxeW+j2qWgoABeXl7w8/PD3r17UVBQIN3bxNjYGKGhoTh9+jRSUlJgbGxs6HKJSI84/+lxFfn+N6nsYtLT06FQKFCnTp0Sl+fm5iI3N1d6nJGRAeDRLiitVlvZ5ZGBJSQk4MqVK9i+fTsKCgqk17zo/zNmzEBgYCDi4uIQFBRkyFKJSM84/+lxFfnOr9Tw8s8//+Cdd97BK6+8UmqKWrhwISIiIoq1x8TEQK1WV2Z5VA0cPnwYAHDjxg3cv39fao+NjQUA5OTkAAAOHDgAjUZT9QUSUaXh/KfHZWdnl7tvpYUXrVaLIUOGQAiBtWvXltpv1qxZmDp1qvQ4IyMDrq6u6NGjB3cb1QIWFhaIjIyEi4sL2rZtC61Wi9jYWHTv3h1KpRJJSUkAgF69evEvL6IahvOfHle056U8KiW8FAWXq1ev4qeffiozhKhUKqhUqmLtSqUSSqWyMsqjaiQ4OBju7u5YsmSJzplrSqUSxsbGWLp0KTw8PBAcHMx93kQ1DOc/Pa4i3/l6v85LUXBJSUnBjz/+CDs7O32vgmoQY2NjLF++HPv370doaCiSkpKQk5ODpKQkhIaGYv/+/Vi2bBk/uIhqIM5/elYV3vKSlZWFS5cuSY9TU1Nx8uRJ2NrawsnJCWFhYThx4gT279+PgoIC3L59GwBga2sLU1NT/VVONcbAgQOxe/duTJs2DYGBgVK7h4cHdu/ejYEDBxqwOiKqTJz/9CwqfKp0fHw8goODi7WPHDkS8+bNg4eHR4k/FxcXh86dOz91fJ4qXXsVFBQgLi4OBw4cQK9evbipmKgW4fynSj1VunPnzigr7zzHZWOoljM2NkZQUBA0Gg2CgoL4wUVUi3D+U0Xw3kZEREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9UbWRlZWHQoEGYNGkSBg0ahKysLEOXRERVJC0tDa1atcJrr72GVq1aIS0tzdAlUTVW4dsDEFWGNm3aIDk5WXp89epVWFlZISAgAEePHjVgZURU2RwdHXHnzh3p8dmzZ2FnZwcHBwfp5r5Ej+OWFzK4ouCiUCgwYsQIrFixAiNGjIBCoUBycjLatGlj6BKJqJI8Hlzatm2LiIgItG3bFgBw584dODo6GrI8qqYqfFfpysa7StcuWVlZsLKygkKhQHZ2NoyNjREdHY3evXujoKAAarUaQghkZmbC0tLS0OUSkR6lpaXBzs4OAJCZmQmVSiXN/9zcXFhZWQEA7t+/D1tbW0OWSlWgIt//3PJCBvXaa68BAEaMGAEzMzOdZWZmZnj11Vd1+hFRzREUFAQAeOmll4r9cWJpaSltdS3qR1SE4YUM6vLlywCA6dOnl7h86tSpOv2IqOa4efMmAODjjz8ucfn8+fN1+hEVYXghg/L09AQALFu2rMTlkZGROv2IqOZwdnYGALz33nslLv/ggw90+hEV4TEvZFA85oWo9uIxL/Q4HvNCsmFpaYmAgAAIIaBWqzFq1ChcvnwZo0aNkoJLQEAAgwtRDWRrawsHBwcAgJWVFTp06IATJ06gQ4cOUnBxcHBgcKFiuOWFqoUnr/NShNd5Iar5nrzOSxFe56V24ZYXkp2jR48iMzMTffv2hZubG/r27YvMzEwGF6Ja4Pbt27h//z58fHxgZWUFHx8f3L9/n8GFSsUtL1StaLVaaZ+3Uqk0dDlEVIU4/2s3bnkhIiKiGovhhYiIiGSF4YWIiIhkheGFiIiIZIXhhYiIiGSF4YWIiIhkheGFiIiIZIXhhYiIiGSF4YWqjdu3b8PV1RWDBw+Gq6srr65JVItkZWVh0KBBmDRpEgYNGoSsrCxDl0TVWIXDy+HDh9G3b184OztDoVBg7969OsuFEPjggw/g5OQEc3NzdOvWDSkpKfqql2ooCwsLODk54c6dO9Bqtbhz5w6cnJxgYWFh6NKIqJK1adMGVlZW+P7773H16lV8//33sLKyQps2bQxdGlVTFQ4vGo0GLVu2xJo1a0pcvmTJEnz66adYt24dfv31V1hYWKBnz574559/nrtYqpksLCyQnZ0NAHB3d8f06dPh7u4OAMjOzmaAIarBim7KqlAoMGLECKxYsQIjRoyAQqFAcnIyAwyV6LnubaRQKLBnzx6EhoYCeLTVxdnZGdOmTcP06dMBAOnp6XBwcMDWrVsxbNiwp47JexvVLrdv34aTkxMA4MGDB7CwsJDubaLRaFC3bl0AwK1bt+Do6GjIUolIz7KysmBlZQWFQoHs7GwYGxtL87+goABqtRpCCGRmZsLS0tLQ5VIlq8j3v4k+V5yamorbt2+jW7duUpuNjQ3atm2LX375pcTwkpubi9zcXOlxRkYGgEc36NJqtfosj6qhVq1aAXi0xcXCwkJ6zbVaLSwsLODm5oarV6+iVatWuH79ugErJSJ9e/XVVwEAw4cPh7Gxsc78VyqVeOWVV7Bjxw68+uqr+Pbbbw1ZKlWBinzn6zW8FB1g6eDgoNPu4OBQ6sGXCxcuRERERLH2mJgYqNVqfZZH1VBaWhoAICwsDNHR0VJ7bGwsAGDAgAFYuXIl0tLSdJYTkfydOnUKAODv71/i/Pf398eOHTtw6tQpzv9aoOjwgfLQa3h5FrNmzcLUqVOlxxkZGXB1dUWPHj2426gWsLW1xZ07d7B7924sWLAAWq0WsbGx6N69O5RKJSZNmiT16927t4GrJSJ92rx5M65evYrjx49j/Pjxxeb/qFGjAAAtWrTg/K8Fiva8lIdew0vRMQlFZ4oUuXPnjrR74EkqlQoqlapYu1KphFKp1Gd5VA2dPHkSTk5OuHLlCjQajXRwrlKphEajwdWrV6V+fD8Q1Sw7duyAlZUVvvzyS2zcuFGa40qlEgUFBdi5c6fUj/O/5qvIa6zX67x4eHjA0dERhw4dktoyMjLw66+/ol27dvpcFdUQjo6O0u7BunXronHjxoiPj0fjxo2lg3XVajUP1iWqgSwtLREQEAAhBNRqNUaNGoXLly9j1KhR0sG6AQEBPFiXiqnw2UZZWVm4dOkSAOCFF15AZGQkgoODYWtri4YNG2Lx4sVYtGgRtm3bBg8PD8yZMwenTp3C2bNnYWZm9tTxebZR7fT46dKPU6vV0Gg0BqiIiKpK0enSTwoICMDRo0cNUBEZQqWebXTs2DEEBwdLj4uOVxk5ciS2bt2KmTNnQqPR4F//+hcePnyIjh074uDBg+UKLlR7aTQa3L59G61atUJaWhpsbW1x8uRJbnEhqgWOHj2KrKwsvPrqqzh16hRatGiBHTt2cIsLleq5rvNSGbjlpXbTarXSdR64j5uoduH8r90q8v3PexsRERGRrDC8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGs6PWu0kTP4+zZs/Dz80NhYSGMjIzwxx9/wMfHx9BlEVEVSE9PR69evZCSkoLGjRvjwIEDsLGxMXRZVE0xvFC1oFAodB4XFhbC19cXAFDN7mBBRHrm5eWFy5cvS4/v3buHOnXqwNPTU7oRMNHjuNuIDO7x4KJUKhEWFqZzX5Mngw0R1RyPB5eePXti0aJF6NmzJwDg8uXL8PLyMmR5VE0xvJBBnT17Vvr39evXodFoMGLECGg0Gly/fr3EfkRUM6Snp0vBRaPR4Pvvv4e3tze+//57aDQaAI8CTHp6uiHLpGqI4YUMys/PD8CjLS4uLi46y1xcXKQtMEX9iKjmCAkJAQC8/PLLUKvVOsvUajV69Oih04+oCMMLGVRhYSEA4N133y1x+ZQpU3T6EVHNce3aNQDA3LlzS1z+/vvv6/QjKsLwQgZlZPToLbho0aISl69YsUKnHxHVHA0bNgQARERElLj8o48+0ulHVITfCGRQf/zxBwBAq9Xixo0bOstu3LgBrVar04+Iao7//ve/AICDBw8iOztbZ1l2djZiYmJ0+hEVYXghg3r8Oi6urq6wsLDAli1bYGFhAVdX1xL7EVHNYGNjA09PTwCAhYUFQkJCcObMGYSEhMDCwgIA4Onpyeu9UDEKUc0uopGRkQEbGxukp6fD2tra0OVQFSnrdOhq9hYlIj178jovRXidl9qlIt//3PJC1YIQAmfOnJGObTEyMsKZM2cYXIhqgUuXLuHhw4do164d6tWrh3bt2uHhw4cMLlQqbnmhakWr1SI6Ohq9e/fWuVAdEdV8nP+1G7e8EBERUY3F8EJERESywvBCREREssLwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8EJERESyYmLoAoiKXLt2Db6+vtBoNLCwsMCZM2d4N1kiIipG71teCgoKMGfOHHh4eMDc3Byenp748MMPeZl3KpNSqYSbmxuysrIghEBWVhbc3Nx4lU0iIipG71teFi9ejLVr12Lbtm3w9fXFsWPHMHr0aNjY2CA8PFzfq6MaQKlUIj8/HwBga2uLIUOGYNeuXUhLS0N+fj6USiW0Wq2BqyQioupC71te/ve//6F///4ICQmBu7s7wsLC0KNHDxw9elTfq6Ia4Nq1a1Jw+fvvv3H79m28/PLLuH37Nv7++28AQH5+Pq5du2bIMomIqBrR+5aX9u3bY8OGDbh48SKaNGmC33//HT///DMiIyNL7J+bm4vc3FzpcUZGBoBHN+jiX9s1n6+vL4BHW1xsbGyk11yr1cLGxga2trZIS0uDr68v0tLSDFkqET2H7OxsXLhwocw+Go0GSUlJsLa2hoWFxVPHbNq0KdRqtb5KJAOryHe+3sPLu+++i4yMDHh7e8PY2BgFBQX4+OOPMXz48BL7L1y4EBEREcXaY2Ji+KasBTQaDQBgyJAhiI6OltpjY2MBAAMHDsSmTZug0Wh0lhORvFy+fBnTpk0rV99FixaVq9/y5cvh6en5PGVRNZKdnV3uvgqh5yNpv/rqK8yYMQNLly6Fr68vTp48icmTJyMyMhIjR44s1r+kLS+urq64d+/eU2+JTfJna2uLrKws2Nra4vbt29BqtYiNjUX37t2hVCrh6OiItLQ0WFpacssLkYyVZ8vLpUuXMG/ePMybNw9eXl5PHZNbXmqWjIwM1KtXD+np6U/9/tf7lpcZM2bg3XffxbBhwwAAfn5+uHr1KhYuXFhieFGpVFCpVMXalUolzzSpBc6cOQM3NzekpaUhPT0dNjY2AB69/unp6VJgOXPmDN8PRDJmY2ODNm3alNnH3NwcarUafn5+8PPzq6LKqLqoyGe83g/Yzc7OhpGR7rDGxsYoLCzU96qoBmjYsCFMTB5laHt7ezg6OmL//v1wdHSEvb09AMDExITXeyEiIonet7z07dsXH3/8MRo2bAhfX1/89ttviIyMxJgxY/S9KqohtFqtdLp0WloaNm3aJC0zMTHhgdtERKRD71teVq1ahbCwMIwbNw7NmjXD9OnT8dZbb+HDDz/U96qoBtFqtbh69SosLS2hUChgaWmJq1evMrgQEVExet/yYmVlhZUrV2LlypX6HppquIYNGyItLQ3R0dHo3bs3j3EhIqIS8caMREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCt6v6s0UWmys7Nx/vz5MvtoNBokJSXB1tYWFhYWTx3T29sbarVaXyUSEZEMMLxQlTl//jz8/f3L1XfRokXl6nf8+HG8+OKLz1MWERHJDMMLVRlvb28cP368zD4pKSmYM2cOPvzwQzRu3LhcYxIRUe3C8EJVRq1WP3UriVKphFqtho+PD/z8/KqoMiIikhMesEtERESywvBCREREssLwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8EJERESywvBCREREssLwQkRERLLC8EJERESyUinh5a+//sKIESNgZ2cHc3Nz+Pn54dixY5WxKiIiIqplTPQ94IMHD9ChQwcEBwfjwIEDsLe3R0pKCurWravvVREREVEtpPfwsnjxYri6umLLli1Sm4eHh75XQ0RERLWU3sPLd999h549e2Lw4MFISEhAgwYNMG7cOLz55psl9s/NzUVubq70OCMjAwCg1Wqh1Wr1XR5Vc/n5+dL/+foT1S6c/7VbRV5zvYeXP//8E2vXrsXUqVMxe/ZsJCcnIzw8HKamphg5cmSx/gsXLkRERESx9piYGKjVan2XR9XczZs3AQBJSUm4du2agashoqrE+V+7ZWdnl7uvQggh9LlyU1NTtG7dGv/73/+ktvDwcCQnJ+OXX34p1r+kLS+urq64d+8erK2t9VkaycDp06cxevRobNmyBc2bNzd0OURUhTj/a7eMjAzUq1cP6enpT/3+1/uWFycnJ/j4+Oi0NWvWDN9++22J/VUqFVQqVbF2pVIJpVKp7/KomjMxMZH+z9efqHbh/K/dKvKa6/1U6Q4dOuDChQs6bRcvXoSbm5u+V0VERES1kN7Dy5QpU5CUlIQFCxbg0qVL2LFjBzZs2IDx48fre1VERERUC+k9vAQEBGDPnj3YuXMnmjdvjg8//BArV67E8OHD9b0qIiIiqoX0fswLAPTp0wd9+vSpjKGJiIioluO9jYiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYqPbwsWrQICoUCkydPruxVERERUS1QqeElOTkZ69evR4sWLSpzNURERFSLVFp4ycrKwvDhw7Fx40bUrVu3slZDREREtYxJZQ08fvx4hISEoFu3bvjoo49K7Zebm4vc3FzpcUZGBgBAq9VCq9VWVnmkZ9euXUN2dvZzj3Pp0iWd/+uDWq1Gw4YN9TYeEeni/Cd9qMh3fqWEl6+++gonTpxAcnLyU/suXLgQERERxdpjYmKgVqsrozzSs/v37+PTTz/V65glvSeeR3h4OOzs7PQ6JhFx/pP+VCQA6z28XL9+HZMmTUJsbCzMzMye2n/WrFmYOnWq9DgjIwOurq7o0aMHrK2t9V0eVYLz588DAObPnw8PD4/nGkuj0SAmJgY9evSAhYXFc9eWmpqKDz74AAEBAfD29n7u8YhIF+c/6UvRnpfy0Ht4OX78OO7evYsXX3xRaisoKMDhw4exevVq5ObmwtjYWFqmUqmgUqmKjaNUKqFUKvVdHlUCE5NHb6PGjRujWbNmzzWWVqvFnTt34O/vr5fXv6g2ExMTvp+IKgHnP+lLRV4jvYeXrl274o8//tBpGz16NLy9vfHOO+/oBBciIiKiitJ7eLGyskLz5s112iwsLGBnZ1esnYiIiKiieIVdIiIikpVKO1X6cfHx8VWxGiIiIqoFuOWFiIiIZIXhhYiIiGSF4YWIiIhkheGFiIiIZIXhhYiIiGSF4YWIiIhkheGFiIiIZIXhhYiIiGSF4YWIiIhkheGFiIiIZIXhhYiIiGSF4YWIiIhkpUpuzEg1W0FBAerVq4fMzEz8/fffzzVWfn4+tFot7t27BxOT5397ZmZmol69eigoKHjusYiIqHpgeKHnlp2djbCwMJw4cQInTpzQy5j79u3TyzgAEBYWhuzsbL2NR0REhsXwQs9NrVZj9+7dWLBgATw8PJ5rrPz8fBw5cgQdOnTQy5aX1NRUzJ49Gx07dnzusYiIqHpgeKHnZmxsjHv37sHKygr29vbPNZZWq4VSqUS9evWgVCqfu7Z79+7h3r17MDY2fu6xiIioeuABu0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkKwwvREREJCsML0RERCQrDC9EREQkK3oPLwsXLkRAQACsrKxQv359hIaG4sKFC/peDREREdVSeg8vCQkJGD9+PJKSkhAbGwutVosePXpAo9Hoe1VERERUC5noe8CDBw/qPN66dSvq16+P48ePIzAwUN+rIyIiolpG7+HlSenp6QAAW1vbEpfn5uYiNzdXepyRkQEA0Gq10Gq1lV0e6UFWVhYA4PTp08jPz3+usTQaDX7//Xc4ODjAwsLiuWtLTU0FAOTn5/P9RFQJcnNzUa9ePTx8+BC3bt16rrGK5unt27dhYvL8X08PHz5EvXr1kJuby/kvAxV5jRRCCFFZhRQWFqJfv354+PAhfv755xL7zJs3DxEREcXad+zYAbVaXVmlkR4dP34c3333naHLKFN4eDjs7OwMXQZRjXPz5k0oFApDl1EmIQScnZ0NXQY9RXZ2Nl599VWkp6fD2tq6zL6VGl7+/e9/48CBA/j555/h4uJSYp+Stry4urri3r17Ty2eqoeHDx8iPj4e7u7uMDMze66xLl26hIiICMydOxdeXl56qU+tVqNhw4Z6GYuIdJ05cwbTp0/Hhx9+CHd39+caKz8/H7/++ivatm2rly0vV65cwZw5c7Bs2TL4+vo+93hUuTIyMlCvXr1yhZdK2200YcIE7N+/H4cPHy41uACASqWCSqUq1q5UKqFUKiurPNIje3t7DB48WK9jenl5wc/PT69jEpH+qVQq3Lt3D3Xq1IGTk9NzjaXVaqFUKuHo6KiXz/+HDx/i3r17UKlU/D6RgYq8RnoPL0IITJw4EXv27EF8fDw8PDz0vQoiIiKqxfQeXsaPH48dO3Zg3759sLKywu3btwEANjY2MDc31/fqiIiIqJbR+3Ve1q5di/T0dHTu3BlOTk7Sf19//bW+V0VERES1UKXsNiIiIiKqLLy3EREREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJCsMLERERyYreb8xIVJrs7GycP3++zD4pKSnIzs7G2bNnodVqnzqmt7c31Gq1vkokogr6559/AADnzp0rs19OTg5SU1PL7JOfn4+TJ0/in3/+gYnJ07+ePDw8YG5uXuryP//886ljkDwxvFCVOX/+PPz9/cvVd9iwYeXqd/z4cbz44ovPUxYRPYeiQDJ//vwy+2VnZyMlJUWv627cuHG5/njhHzg1D8MLVRlvb28cP368zD4ajQbR0dHo3bs3LCwsyjUmERlOcHAwgEdbQczMzErtV5EtL61atdLLlhfgUXBxc3N76lgkLwwvVGXUavVTt5JotVqkpaXhpZdeglKprKLKiOhZ1a1bFwMHDixX3/LMfzMzM/Tu3Zvzn8rEA3aJiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVhheiIiISFYYXoiIiEhWGF6IiIhIVqrdXaWFEACAjIwMA1dChqDVapGdnY2MjAzeVZaoluH8r92KvveLckBZql14yczMBAC4uroauBIiIiKqapmZmbCxsSmzj0KUJ+JUocLCQty8eRNWVlZQKBSGLoeqWEZGBlxdXXH9+nVYW1sbuhwiqkKc/7WbEAKZmZlwdnaGkVHZR7VUuy0vRkZGcHFxMXQZZGDW1tb88CKqpTj/a6+nbXEpwgN2iYiISFYYXoiIiEhWGF6oWlGpVJg7dy5UKpWhSyGiKsb5T+VV7Q7YJSIiIioLt7wQERGRrDC8EBERkawwvBAREZGsMLxQpRg1ahRCQ0PL7NO5c2dMnjy5SuohourhypUrUCgUOHnyZKl94uPjoVAo8PDhwyqri+Sl2l2kjmqPqKgo3r+EiIpp3749bt26Ve4LllHtw/BCBmNra2voEoioGjI1NYWjo6Ohy6BqjLuNCAcPHkTHjh1Rp04d2NnZoU+fPrh8+TKA/9/Eu2vXLnTq1Anm5uYICAjAxYsXkZycjNatW8PS0hK9evXC33//XWzsiIgI2Nvbw9raGm+//Tby8vKkZU/uNrp16xZCQkJgbm4ODw8P7NixA+7u7li5cqVOLY9vbn748CEUCgXi4+OltoSEBLRp0wYqlQpOTk549913kZ+fLy1/fMwirVq1wrx58wA8ur/GvHnz0LBhQ6hUKjg7OyM8PPzZfrlEBvK097lCocCmTZswYMAAqNVqNG7cGN99953Ut6CgAGPHjoWHhwfMzc3RtGlTfPLJJzrjFe0eXrBgARwcHFCnTh3Mnz8f+fn5mDFjBmxtbeHi4oItW7YUq+/8+fNo3749zMzM0Lx5cyQkJEjLStpttHHjRri6ukKtVmPAgAGIjIxEnTp1itXyuMmTJ6Nz587S49zcXISHh6N+/fowMzNDx44dkZycLC3funWrzpgAsHfvXp377P3+++8IDg6GlZUVrK2t4e/vj2PHjhV7flS5GF4IGo0GU6dOxbFjx3Do0CEYGRlhwIABKCwslPrMnTsX77//Pk6cOAETExO8+uqrmDlzJj755BMkJibi0qVL+OCDD3TGPXToEM6dO4f4+Hjs3LkTUVFRiIiIKLWO119/HTdv3kR8fDy+/fZbbNiwAXfv3q3Qc/nrr7/Qu3dvBAQE4Pfff8fatWuxefNmfPTRR+Ue49tvv8WKFSuwfv16pKSkYO/evfDz86tQHURyEBERgSFDhuDUqVPo3bs3hg8fjrS0NACPbpLr4uKCb775BmfPnsUHH3yA2bNnY9euXTpj/PTTT7h58yYOHz6MyMhIzJ07F3369EHdunXx66+/4u2338Zbb72FGzdu6PzcjBkzMG3aNPz2229o164d+vbti/v375dY55EjR/D2229j0qRJOHnyJLp3746PP/64ws935syZ+Pbbb7Ft2zacOHECXl5e6Nmzp/Scy2P48OFwcXFBcnIyjh8/jnfffZe7vw1BED3h77//FgDEH3/8IVJTUwUAsWnTJmn5zp07BQBx6NAhqW3hwoWiadOm0uORI0cKW1tbodFopLa1a9cKS0tLUVBQIIQQIigoSEyaNEkIIcS5c+cEAJGcnCz1T0lJEQDEihUrhBBCquW3336T+jx48EAAEHFxcUIIIWbPni2aNm0qCgsLpT5r1qzRWa+bm5s0ZpGWLVuKuXPnCiGEWL58uWjSpInIy8ur2C+OqBp52vscgHj//felZVlZWQKAOHDgQKljjh8/XgwaNEh6PHLkSOHm5ibNLSGEaNq0qejUqZP0OD8/X1hYWIidO3cKIf5/Hi9atEjqo9VqhYuLi1i8eLEQQoi4uDgBQDx48EAIIcTQoUNFSEiITi3Dhw8XNjY2OrX0799fp8+kSZNEUFCQ9PyUSqX48ssvpeV5eXnC2dlZLFmyRAghxJYtW3TGFEKIPXv2iMe/Kq2srMTWrVtL/R1R1eCWF0JKSgpeeeUVNGrUCNbW1nB3dwcAXLt2TerTokUL6d8ODg4AoLM1wsHBodhWkpYtW0KtVkuP27Vrh6ysLFy/fr1YDRcuXICJiQlefPFFqc3Lywt169at0HM5d+4c2rVrp7OZt0OHDsjKyir2l19pBg8ejJycHDRq1Ahvvvkm9uzZo7PbiaimeHxeW1hYwNraWmcer1mzBv7+/rC3t4elpSU2bNig87kAAL6+vjAy+v+vEgcHB53PBmNjY9jZ2RX7fGjXrp30bxMTE7Ru3Rrnzp0rsc4LFy6gTZs2Om1PPn6ay5cvQ6vVokOHDlKbUqlEmzZtSl1vSaZOnYo33ngD3bp1w6JFi6Rd7FS1GF4Iffv2RVpaGjZu3Ihff/0Vv/76KwDoHJ/y+GbRomDwZNvju5kqQ9EHpHjsjhZarfaZxhFP3BXj8XFcXV1x4cIFfPbZZzA3N8e4ceMQGBj4TOsiMpSnvc8BFNvd8fg8/uqrrzB9+nSMHTsWMTExOHnyJEaPHq3zuVDaGGWNW1nK83z1Mca8efNw5swZhISE4KeffoKPjw/27NnzbEXTM2N4qeXu37+PCxcu4P3330fXrl3RrFkzPHjwQC9j//7778jJyZEeJyUlwdLSEq6ursX6Nm3aFPn5+fjtt9+ktkuXLunUYm9vD+DRgb1FnrxWRLNmzfDLL7/ofAAdOXIEVlZWcHFxkcZ5fIyMjAykpqbqjGNubo6+ffvi008/RXx8PH755Rf88ccfFXn6RAZVnvd5WY4cOYL27dtj3LhxeOGFF+Dl5aXXrQxJSUnSv/Pz83H8+HE0a9asxL5NmzbVObAWQLHHTz5fQPfzwdPTE6ampjhy5IjUptVqkZycDB8fH2mMzMxMaDSaEsco0qRJE0yZMgUxMTEYOHBgiQckU+VieKnl6tatCzs7O2zYsAGXLl3CTz/9hKlTp+pl7Ly8PIwdOxZnz55FdHQ05s6diwkTJuhsYi7i7e2Nbt264V//+heOHj2K3377Df/6179gbm4ubekxNzfHSy+9hEWLFuHcuXNISEjA+++/rzPOuHHjcP36dUycOBHnz5/Hvn37MHfuXEydOlVab5cuXbB9+3YkJibijz/+wMiRI2FsbCyNsXXrVmzevBmnT5/Gn3/+iS+++ALm5uZwc3PTy++FqCo87X3+NI0bN8axY8fwww8/4OLFi5gzZ06xwPA81qxZgz179uD8+fMYP348Hjx4gDFjxpTYd+LEiYiOjkZkZCRSUlKwfv16HDhwQGf3cJcuXXDs2DH85z//QUpKCubOnYvTp09Lyy0sLPDvf/8bM2bMwMGDB3H27Fm8+eabyM7OxtixYwEAbdu2hVqtxuzZs3H58mXs2LEDW7dulcbIycnBhAkTEB8fj6tXr+LIkSNITk4uNXRR5WF4qeWMjIzw1Vdf4fjx42jevDmmTJmCpUuX6mXsrl27onHjxggMDMTQoUPRr18/6TTNkvznP/+Bg4MDAgMDMWDAALz55puwsrKCmZmZ1Ofzzz9Hfn4+/P39MXny5GJnETVo0ADR0dE4evQoWrZsibfffhtjx47VCTmzZs1CUFAQ+vTpg5CQEISGhsLT01NaXqdOHWzcuBEdOnRAixYt8OOPP+L777+HnZ2dXn4vRFXhae/zp3nrrbcwcOBADB06FG3btsX9+/cxbtw4vdW3aNEiLFq0CC1btsTPP/+M7777DvXq1Suxb4cOHbBu3TpERkaiZcuWOHjwIKZMmaLz2dCzZ0/MmTMHM2fOREBAADIzM/H6668XW+egQYPw2muv4cUXX8SlS5fwww8/SMfW2dra4osvvkB0dDT8/Pywc+dOnc8sY2Nj3L9/H6+//jqaNGmCIUOGoFevXmWeRUmVQyGe3MFHVE3cuHEDrq6u+PHHH9G1a1dDl0NE1cibb76J8+fPIzEx0dClkAHwCrtUbfz000/IysqCn58fbt26hZkzZ8Ld3R2BgYGGLo2IDGzZsmXo3r07LCwscODAAWzbtg2fffaZocsiA2F4oWpDq9Vi9uzZ+PPPP2FlZYX27dvjyy+/5AWgiAhHjx7FkiVLkJmZiUaNGuHTTz/FG2+8YeiyyEC424iIiIhkhQfsEhERkawwvBAREZGsMLwQERGRrDC8EBERkawwvBAREZGsMLwQUbXSuXNnTJ48WXrs7u6OlStXlvkz8+bNQ6tWrSq1LiKqPhheiKhEt2/fxsSJE9GoUSOoVCq4urqib9++OHToUJXWkZycjH/961/SY4VCgb179+r0mT59epXXRUSGw4vUEVExV65cQYcOHVCnTh0sXboUfn5+0Gq1+OGHHzB+/HicP3++ymopupt4WSwtLWFpaVkF1RBRdcAtL0RUzLhx46BQKHD06FEMGjQITZo0ga+vL6ZOnYqkpCQAwLVr19C/f39YWlrC2toaQ4YMwZ07d6QxinblbN++He7u7rCxscGwYcOQmZkp9dFoNHj99ddhaWkJJycnLF++vFgtj+82cnd3BwAMGDAACoVCevzkbqPCwkLMnz8fLi4uUKlUaNWqFQ4ePCgtv3LlChQKBaKiohAcHAy1Wo2WLVvil19+0dNvkIgqE8MLEelIS0vDwYMHMX78eFhYWBRbXqdOHRQWFqJ///5IS0tDQkICYmNj8eeff2Lo0KE6fS9fvoy9e/di//792L9/PxISErBo0SJp+YwZM5CQkIB9+/YhJiYG8fHxOHHiRKm1JScnAwC2bNmCW7duSY+f9Mknn2D58uVYtmwZTp06hZ49e6Jfv35ISUnR6ffee+9h+vTpOHnyJJo0aYJXXnkF+fn55f5dEZFhcLcREem4dOkShBDw9vYutc+hQ4fwxx9/IDU1Fa6urgCA//znP/D19UVycjICAgIAPNoCsnXrVlhZWQEAXnvtNRw6dAgff/wxsrKysHnzZnzxxRfSXcO3bdsGFxeXUtdbtAupTp06cHR0LLXfsmXL8M4772DYsGEAgMWLFyMuLg4rV67EmjVrpH7Tp09HSEgIACAiIgK+vr64dOlSmc+diAyPW16ISEd5bnd27tw5uLq6SsEFAHx8fFCnTh2cO3dOanN3d5eCCwA4OTnh7t27AB5tlcnLy0Pbtm2l5ba2tmjatOlz1Z+RkYGbN2+iQ4cOOu0dOnTQqQ0AWrRooVMbAKk+Iqq+GF6ISEfjxo2hUCj0clDuk3cEVygUKCwsfO5x9eXx+hQKBQBUq/qIqGQML0Skw9bWFj179sSaNWug0WiKLX/48CGaNWuG69ev4/r161L72bNn8fDhQ/j4+JRrPZ6enlAqlfj111+ltgcPHuDixYtl/pxSqURBQUGpy62treHs7IwjR47otB85cqTctRFR9cZjXoiomDVr1qBDhw5o06YN5s+fjxYtWiA/Px+xsbFYu3Ytzp49Cz8/PwwfPhwrV65Efn4+xo0bh6CgILRu3bpc67C0tMTYsWMxY8YM2NnZoX79+njvvfdgZFT231Tu7u44dOgQOnToAJVKhbp16xbrM2PGDMydOxeenp5o1aoVtmzZgpMnT+LLL798pt8HEVUvDC9EVEyjRo1w4sQJfPzxx5g2bRpu3boFe3t7+Pv7Y+3atVAoFNi3bx8mTpyIwMBAGBkZ4eWXX8aqVasqtJ6lS5ciKysLffv2hZWVFaZNm4b09PQyf2b58uWYOnUqNm7ciAYNGuDKlSvF+oSHhyM9PR3Tpk3D3bt34ePjg++++w6NGzeuUH1EVD0pRHmOziMiIiKqJnjMCxEREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJCsMLERERyQrDCxEREckKwwsRERHJyv8BDXnT2rgS9+oAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "alternative_hypotheses = {metric: ALTERNATIVE_HYPOTHESIS_GREATER for metric in metrics}\n",
    "for algorithm in results:\n",
    "  statistical_analysis_for_subjectwise_averages(results[algorithm], alternative_hypotheses,  [], stest_kind=TEST_KIND_PAIRED)\n",
    "\n",
    "for metric in metrics:\n",
    "    for algorithm in results:\n",
    "        plt.figure()\n",
    "        results[algorithm].boxplot(column=metric, by=CONDITION)\n",
    "        plt.title(f'{algorithm} {metric}')\n",
    "        plt.suptitle('')\n",
    "        plt.show()"
   ]
  }
 ],
 "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}