{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## This notebook creates one dataframe from all participants data\n",
    "## It also removes 1% of the data as this is corrupted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "from scipy.odr import *\n",
    "from scipy.stats import *\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import os\n",
    "import time\n",
    "import matplotlib.pyplot as plt\n",
    "import ast\n",
    "from multiprocessing import Pool, cpu_count\n",
    "\n",
    "import scipy\n",
    "\n",
    "from IPython import display\n",
    "from matplotlib.patches import Rectangle\n",
    "\n",
    "from sklearn.metrics import mean_squared_error\n",
    "import json\n",
    "\n",
    "import scipy.stats as st\n",
    "from sklearn.metrics import r2_score\n",
    "\n",
    "\n",
    "from matplotlib import cm\n",
    "from mpl_toolkits.mplot3d import axes3d\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import copy\n",
    "\n",
    "from sklearn.model_selection import LeaveOneOut, LeavePOut\n",
    "\n",
    "from multiprocessing import Pool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def cast_to_int(row):\n",
    "    try:\n",
    "        return np.array([a if float(a) >= 0 else 0 for a in row[2:-1]], dtype=np.uint8)\n",
    "    except Exception as e:\n",
    "        return None\n",
    "    \n",
    "def load_csv(file):\n",
    "    temp_df = pd.read_csv(file, delimiter=\";\")\n",
    "    temp_df.Image = temp_df.Image.str.split(',')\n",
    "    temp_df.Image = temp_df.Image.apply(cast_to_int)\n",
    "    return temp_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['DataStudyEvaluation/2_studyData.csv', 'DataStudyEvaluation/12_studyData.csv', 'DataStudyEvaluation/5_studyData.csv', 'DataStudyEvaluation/1_studyData.csv', 'DataStudyEvaluation/10_studyData.csv', 'DataStudyEvaluation/6_studyData.csv', 'DataStudyEvaluation/3_studyData.csv', 'DataStudyEvaluation/7_studyData.csv', 'DataStudyEvaluation/8_studyData.csv', 'DataStudyEvaluation/9_studyData.csv', 'DataStudyEvaluation/11_studyData.csv', 'DataStudyEvaluation/4_studyData.csv']\n",
      "CPU times: user 1.35 s, sys: 786 ms, total: 2.14 s\n",
      "Wall time: 1min 43s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "pool = Pool(cpu_count() - 2)\n",
    "data_files = [\"DataStudyEvaluation/%s\" % file for file in os.listdir(\"DataStudyEvaluation\") if file.endswith(\".csv\") and \"studyData\" in file]\n",
    "print(data_files)\n",
    "df_lst = pool.map(load_csv, data_files)\n",
    "dfAll = pd.concat(df_lst)\n",
    "pool.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "608084"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = dfAll[dfAll.Image.notnull()]\n",
    "df = df[df.userID != \"userID\"]\n",
    "df.userID = pd.to_numeric(df.userID)\n",
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "loaded 610816 values\n",
      "removed 2732 values (thats 0.447%)\n",
      "new df has size 608084\n"
     ]
    }
   ],
   "source": [
    "print(\"loaded %s values\" % len(dfAll))\n",
    "print(\"removed %s values (thats %s%%)\" % (len(dfAll) - len(df), round((len(dfAll) - len(df)) / len(dfAll) * 100, 3)))\n",
    "print(\"new df has size %s\" % len(df))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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 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>userID</th>\n",
       "      <th>Timestamp</th>\n",
       "      <th>Current_Task</th>\n",
       "      <th>Task_amount</th>\n",
       "      <th>TaskID</th>\n",
       "      <th>VersionID</th>\n",
       "      <th>RepetitionID</th>\n",
       "      <th>Actual_Data</th>\n",
       "      <th>Is_Pause</th>\n",
       "      <th>Image</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>1553593631562</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>false</td>\n",
       "      <td>false</td>\n",
       "      <td>[3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 2, 1, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1553593631595</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>false</td>\n",
       "      <td>false</td>\n",
       "      <td>[3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1553593631634</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>false</td>\n",
       "      <td>false</td>\n",
       "      <td>[3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>1553593631676</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>false</td>\n",
       "      <td>false</td>\n",
       "      <td>[3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>1553593631716</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>false</td>\n",
       "      <td>false</td>\n",
       "      <td>[3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   userID      Timestamp Current_Task Task_amount TaskID VersionID  \\\n",
       "0       2  1553593631562            0          34      0         0   \n",
       "1       2  1553593631595            0          34      0         0   \n",
       "2       2  1553593631634            0          34      0         0   \n",
       "3       2  1553593631676            0          34      0         0   \n",
       "4       2  1553593631716            0          34      0         0   \n",
       "\n",
       "  RepetitionID Actual_Data Is_Pause  \\\n",
       "0            0       false    false   \n",
       "1            0       false    false   \n",
       "2            0       false    false   \n",
       "3            0       false    false   \n",
       "4            0       false    false   \n",
       "\n",
       "                                               Image  \n",
       "0  [3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 2, 1, 0, 0, ...  \n",
       "1  [3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...  \n",
       "2  [3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...  \n",
       "3  [3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...  \n",
       "4  [3, 3, 3, 2, 0, 0, 1, 0, 0, 0, 1, 222, 0, 0, 0...  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 2, 12,  5,  1, 10,  6,  3,  7,  8,  9, 11,  4])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.userID.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.userID = pd.to_numeric(df.userID)\n",
    "df.TaskID = pd.to_numeric(df.TaskID)\n",
    "df.VersionID = pd.to_numeric(df.VersionID)\n",
    "df.Timestamp = pd.to_numeric(df.Timestamp)\n",
    "df.Current_Task = pd.to_numeric(df.Current_Task)\n",
    "df.Task_amount = pd.to_numeric(df.Task_amount)\n",
    "df.RepetitionID = pd.to_numeric(df.RepetitionID)\n",
    "df.loc[df.Actual_Data == \"false\", \"Actual_Data\"] = False\n",
    "df.loc[df.Actual_Data == \"true\", \"Actual_Data\"] = True\n",
    "df.loc[df.Is_Pause == \"false\", \"Is_Pause\"] = False\n",
    "df.loc[df.Is_Pause == \"true\", \"Is_Pause\"] = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_pickle(\"DataStudyEvaluation/AllData.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}