{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Filtering the data for the LSTM: removes all the rows, where we used the revert button, when the participant performed a wrong gesture\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from multiprocessing import Pool, cpu_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>8351</th>\n",
       "      <td>2</td>\n",
       "      <td>1553594010364</td>\n",
       "      <td>1</td>\n",
       "      <td>510</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8352</th>\n",
       "      <td>2</td>\n",
       "      <td>1553594010414</td>\n",
       "      <td>1</td>\n",
       "      <td>510</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8353</th>\n",
       "      <td>2</td>\n",
       "      <td>1553594010445</td>\n",
       "      <td>1</td>\n",
       "      <td>510</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8354</th>\n",
       "      <td>2</td>\n",
       "      <td>1553594010485</td>\n",
       "      <td>1</td>\n",
       "      <td>510</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8355</th>\n",
       "      <td>2</td>\n",
       "      <td>1553594010525</td>\n",
       "      <td>1</td>\n",
       "      <td>510</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      userID      Timestamp  Current_Task  Task_amount  TaskID  VersionID  \\\n",
       "8351       2  1553594010364             1          510      28          2   \n",
       "8352       2  1553594010414             1          510      28          2   \n",
       "8353       2  1553594010445             1          510      28          2   \n",
       "8354       2  1553594010485             1          510      28          2   \n",
       "8355       2  1553594010525             1          510      28          2   \n",
       "\n",
       "      RepetitionID  Actual_Data  Is_Pause  \\\n",
       "8351             0         True     False   \n",
       "8352             0         True     False   \n",
       "8353             0         True     False   \n",
       "8354             0         True     False   \n",
       "8355             0         True     False   \n",
       "\n",
       "                                                  Image  \n",
       "8351  [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...  \n",
       "8352  [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...  \n",
       "8353  [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...  \n",
       "8354  [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...  \n",
       "8355  [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, ...  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dfAll = pd.read_pickle(\"DataStudyEvaluation/AllData.pkl\")\n",
    "df_actual = dfAll[(dfAll.Actual_Data == True) & (dfAll.Is_Pause == False)]\n",
    "df_actual.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df_actual.userID.unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "all: 608084, actual data: 495142\n"
     ]
    }
   ],
   "source": [
    "print(\"all: %s, actual data: %s\" % (len(dfAll), len(df_actual)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 23.3 s, sys: 3.08 s, total: 26.3 s\n",
      "Wall time: 26 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "# filter out all gestures, where the revert button was pressed during the study and the gestrue was repeated\n",
    "def is_max(df):\n",
    "    df_temp = df.copy(deep=True)\n",
    "    max_version = df_temp.RepetitionID.max()\n",
    "    df_temp[\"IsMax\"] = np.where(df_temp.RepetitionID == max_version, True, False)\n",
    "    df_temp[\"MaxRepetition\"] = [max_version] * len(df_temp)\n",
    "    return df_temp\n",
    "\n",
    "df_filtered = df_actual.copy(deep=True)\n",
    "df_grp = df_filtered.groupby([df_filtered.userID, df_filtered.TaskID, df_filtered.VersionID])\n",
    "pool = Pool(cpu_count() - 1)\n",
    "result_lst = pool.map(is_max, [grp for name, grp in df_grp])\n",
    "df_filtered = pd.concat(result_lst)\n",
    "df_filtered = df_filtered[df_filtered.IsMax == True]\n",
    "pool.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_filtered.to_pickle(\"DataStudyEvaluation/df_lstm.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "actual: 495142, filtered data: 457271\n"
     ]
    }
   ],
   "source": [
    "print(\"actual: %s, filtered data: %s\" % (len(df_actual), len(df_filtered)))"
   ]
  }
 ],
 "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
}