workbook_su_ol.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Workbook for Eye Tracking Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Basics\n",
    "import numpy as np\n",
    "import os\n",
    "import math\n",
    "\n",
    "# Data processing\n",
    "import pandas as pd\n",
    "import awkward as ak\n",
    "\n",
    "# ML\n",
    "import sklearn\n",
    "\n",
    "# Misc\n",
    "from pathlib import Path\n",
    "import pyarrow as pa\n",
    "import urllib.request"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import users and their score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Imports the user score information\n",
    "user_data = pd.read_csv(r\"data\\scores_WtG_PrePost.csv\", delimiter=\",\", usecols=[\"User\", \"Pre score\", \"Post score\", \"Difference\", \"Group cat\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Defines my directory with the user data\n",
    "user_dir = r'data\\with ET'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Filters and drops non-relevant users\n",
    "to_drop = []\n",
    "for i, cat in enumerate(user_data[\"Group cat\"]):\n",
    "    if math.isnan(cat):\n",
    "        to_drop.append(i)\n",
    "user_data = user_data.drop(to_drop)\n",
    "user_data = user_data.reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Filters and drops users with no directory\n",
    "not_existing_names = []\n",
    "for i, user in enumerate(user_data[\"User\"]):\n",
    "    if not os.path.isdir(user_dir + '/' + user):\n",
    "        not_existing_names.append(i)\n",
    "user_data = user_data.drop(not_existing_names)\n",
    "user_data = user_data.reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Convert to awkward array\n",
    "array_user = ak.zip(dict(user_data))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import Eye Tracking data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Creates dictionary with all the files for one user\n",
    "file_names = {}\n",
    "for user in user_data[\"User\"]:\n",
    "    #print(user)\n",
    "    available_files = []\n",
    "    available_files_temp = os.listdir(user_dir + '/' + user)\n",
    "    for file in available_files_temp:\n",
    "        if \"graph01-ET_planning\" in file:\n",
    "            available_files.append(file)\n",
    "    # print(available_files)\n",
    "    file_names[user] = available_files\n",
    "#file_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Read each CSV file for one user, stored for each attempt\n",
    "df_attempt1 = []\n",
    "df_attempt2 = []\n",
    "attempt2_mask = []\n",
    "for user in user_data['User']:\n",
    "    files = file_names[user]\n",
    "    if len(files) == 2:\n",
    "        attempt2_mask.append(True)\n",
    "        df_attempt1.append(pd.read_csv(user_dir + '/' + user + '/' + files[0], delimiter=\"\t\", usecols=[\"eyeDataTimestamp\", \"gazePointAOI_target_x\", \"gazePointAOI_target_y\"]))\n",
    "        df_attempt2.append(pd.read_csv(user_dir + '/' + user + '/' + files[1], delimiter=\"\t\", usecols=[\"eyeDataTimestamp\", \"gazePointAOI_target_x\", \"gazePointAOI_target_y\"]))\n",
    "    elif len(files) == 1:\n",
    "        attempt2_mask.append(False)\n",
    "        df_attempt1.append(pd.read_csv(user_dir + '/' + user + '/' + files[0], delimiter=\"\t\", usecols=[\"eyeDataTimestamp\", \"gazePointAOI_target_x\", \"gazePointAOI_target_y\"]))\n",
    "        df_attempt2.append(pd.read_csv(user_dir + '/' + user + '/' + files[0], delimiter=\"\t\", usecols=[\"eyeDataTimestamp\", \"gazePointAOI_target_x\", \"gazePointAOI_target_y\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Add delta t list\n",
    "for attempt in [df_attempt1, df_attempt2]:\n",
    "    for i in range(len(attempt)):\n",
    "        temp_delta_t_list = []\n",
    "        for j in range(len(attempt[i][\"eyeDataTimestamp\"]) - 1):\n",
    "            temp_delta_t_list.append(attempt[i][\"eyeDataTimestamp\"][j+1] - attempt[i][\"eyeDataTimestamp\"][j])\n",
    "        temp_delta_t_list.append(np.mean(temp_delta_t_list))\n",
    "        attempt[i][\"deltaTimestamp\"] = temp_delta_t_list\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "tags": []