Kinect Capture.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import tensorflow as tf\n",
    "%matplotlib inline\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = 'emotional database/motion capture/'\n",
    "files = []\n",
    "# r=root, d=directories, f = files\n",
    "for r, d, f in os.walk(path):\n",
    "    for file in f:\n",
    "        if '.txt' in file:\n",
    "            files.append(os.path.join(r, file))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>gender</th>\n",
       "      <th>gender_no</th>\n",
       "      <th>output</th>\n",
       "      <th>expression_index</th>\n",
       "      <th>video_name</th>\n",
       "      <th>start_time_in_sec</th>\n",
       "      <th>end_time_in_sec</th>\n",
       "      <th>start_exp</th>\n",
       "      <th>end_exp</th>\n",
       "      <th>text_file</th>\n",
       "      <th>kinect_start_frame</th>\n",
       "      <th>kinect_end_frame</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>F</td>\n",
       "      <td>3</td>\n",
       "      <td>An</td>\n",
       "      <td>1</td>\n",
       "      <td>927_0216_01.MP4</td>\n",
       "      <td>5.356700</td>\n",
       "      <td>9.481139</td>\n",
       "      <td>161</td>\n",
       "      <td>284</td>\n",
       "      <td>20170902_092359_00.txt</td>\n",
       "      <td>217</td>\n",
       "      <td>312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>F</td>\n",
       "      <td>3</td>\n",
       "      <td>An</td>\n",
       "      <td>2</td>\n",
       "      <td>927_0216_01.MP4</td>\n",
       "      <td>9.883585</td>\n",
       "      <td>14.903150</td>\n",
       "      <td>296</td>\n",
       "      <td>447</td>\n",
       "      <td>20170902_092359_00.txt</td>\n",
       "      <td>322</td>\n",
       "      <td>466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>F</td>\n",
       "      <td>3</td>\n",
       "      <td>An</td>\n",
       "      <td>3</td>\n",
       "      <td>927_0216_01.MP4</td>\n",
       "      <td>14.903150</td>\n",
       "      <td>19.427206</td>\n",
       "      <td>447</td>\n",
       "      <td>582</td>\n",
       "      <td>20170902_092359_00.txt</td>\n",
       "      <td>466</td>\n",
       "      <td>564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>F</td>\n",
       "      <td>3</td>\n",
       "      <td>An</td>\n",
       "      <td>4</td>\n",
       "      <td>927_0216_01.MP4</td>\n",
       "      <td>19.427206</td>\n",
       "      <td>25.077029</td>\n",
       "      <td>582</td>\n",
       "      <td>752</td>\n",
       "      <td>20170902_092359_00.txt</td>\n",
       "      <td>564</td>\n",
       "      <td>699</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>F</td>\n",
       "      <td>3</td>\n",
       "      <td>An</td>\n",
       "      <td>5</td>\n",
       "      <td>927_0216_01.MP4</td>\n",
       "      <td>25.077029</td>\n",
       "      <td>29.981168</td>\n",
       "      <td>752</td>\n",
       "      <td>899</td>\n",
       "      <td>20170902_092359_00.txt</td>\n",
       "      <td>699</td>\n",
       "      <td>828</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  gender  gender_no output  expression_index       video_name  \\\n",
       "1      F          3     An                 1  927_0216_01.MP4   \n",
       "2      F          3     An                 2  927_0216_01.MP4   \n",
       "3      F          3     An                 3  927_0216_01.MP4   \n",
       "4      F          3     An                 4  927_0216_01.MP4   \n",
       "5      F          3     An                 5  927_0216_01.MP4   \n",
       "\n",
       "   start_time_in_sec  end_time_in_sec  start_exp  end_exp  \\\n",
       "1           5.356700         9.481139        161      284   \n",
       "2           9.883585        14.903150        296      447   \n",
       "3          14.903150        19.427206        447      582   \n",
       "4          19.427206        25.077029        582      752   \n",
       "5          25.077029        29.981168        752      899   \n",
       "\n",
       "                text_file  kinect_start_frame  kinect_end_frame  \n",
       "1  20170902_092359_00.txt                 217               312  \n",
       "2  20170902_092359_00.txt                 322               466  \n",
       "3  20170902_092359_00.txt                 466               564  \n",
       "4  20170902_092359_00.txt                 564               699  \n",
       "5  20170902_092359_00.txt                 699               828  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "descriptors = pd.read_csv('Descriptors.csv', index_col=0)\n",
    "descriptors.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['emotional database/motion capture/20170902_085505_00.txt',\n",
       " 'emotional database/motion capture/20170902_085608_00.txt',\n",
       " 'emotional database/motion capture/20170902_085656_00.txt',\n",
       " 'emotional database/motion capture/20170902_085743_00.txt',\n",
       " 'emotional database/motion capture/20170902_085853_00.txt',\n",
       " 'emotional database/motion capture/20170902_090011_00.txt',\n",
       " 'emotional database/motion capture/20170902_090109_00.txt',\n",
       " 'emotional database/motion capture/20170902_092011_00.txt',\n",
       " 'emotional database/motion capture/20170902_092058_00.txt',\n",
       " 'emotional database/motion capture/20170902_092208_00.txt',\n",
       " 'emotional database/motion capture/20170902_092303_00.txt',\n",
       " 'emotional database/motion capture/20170902_092359_00.txt',\n",
       " 'emotional database/motion capture/20170902_092442_00.txt',\n",
       " 'emotional database/motion capture/20170902_092555_00.txt',\n",
       " 'emotional database/motion capture/20170902_093004_00.txt',\n",
       " 'emotional database/motion capture/20170902_093051_00.txt',\n",
       " 'emotional database/motion capture/20170902_093140_00.txt',\n",
       " 'emotional database/motion capture/20170902_093226_00.txt',\n",
       " 'emotional database/motion capture/20170902_093314_00.txt',\n",
       " 'emotional database/motion capture/20170902_093418_00.txt',\n",
       " 'emotional database/motion capture/20170902_093508_00.txt',\n",
       " 'emotional database/motion capture/20170902_094636_00.txt',\n",
       " 'emotional database/motion capture/20170902_094731_00.txt',\n",
       " 'emotional database/motion capture/20170902_094816_00.txt',\n",
       " 'emotional database/motion capture/20170902_094918_00.txt',\n",
       " 'emotional database/motion capture/20170902_094955_00.txt',\n",
       " 'emotional database/motion capture/20170902_095043_00.txt',\n",
       " 'emotional database/motion capture/20170902_095123_00.txt',\n",
       " 'emotional database/motion capture/20170902_095224_00.txt',\n",
       " 'emotional database/motion capture/20170902_095310_00.txt',\n",
       " 'emotional database/motion capture/20170902_095400_00.txt',\n",
       " 'emotional database/motion capture/20170902_095444_00.txt',\n",
       " 'emotional database/motion capture/20170902_095552_00.txt',\n",
       " 'emotional database/motion capture/20170902_095658_00.txt',\n",
       " 'emotional database/motion capture/20170902_095745_00.txt',\n",
       " 'emotional database/motion capture/20170902_095938_00.txt',\n",
       " 'emotional database/motion capture/20170902_100021_00.txt',\n",
       " 'emotional database/motion capture/20170902_100059_00.txt',\n",
       " 'emotional database/motion capture/20170902_100135_00.txt',\n",
       " 'emotional database/motion capture/20170902_100211_00.txt',\n",
       " 'emotional database/motion capture/20170902_100245_00.txt',\n",
       " 'emotional database/motion capture/20170902_100415_00.txt',\n",
       " 'emotional database/motion capture/20170902_100631_00.txt',\n",
       " 'emotional database/motion capture/20170902_100709_00.txt',\n",
       " 'emotional database/motion capture/20170902_100800_00.txt',\n",
       " 'emotional database/motion capture/20170902_100846_00.txt',\n",
       " 'emotional database/motion capture/20170902_100936_00.txt',\n",
       " 'emotional database/motion capture/20170902_101011_00.txt',\n",
       " 'emotional database/motion capture/20170902_101102_00.txt',\n",
       " 'emotional database/motion capture/20170902_113912_00.txt',\n",
       " 'emotional database/motion capture/20170902_114004_00.txt',\n",
       " 'emotional database/motion capture/20170902_114059_00.txt',\n",
       " 'emotional database/motion capture/20170902_114141_00.txt',\n",
       " 'emotional database/motion capture/20170902_114239_00.txt',\n",
       " 'emotional database/motion capture/20170902_114316_00.txt',\n",
       " 'emotional database/motion capture/20170902_114427_00.txt',\n",
       " 'emotional database/motion capture/20170902_114727_00.txt',\n",
       " 'emotional database/motion capture/20170902_114900_00.txt',\n",
       " 'emotional database/motion capture/20170902_115022_00.txt',\n",
       " 'emotional database/motion capture/20170902_115116_00.txt',\n",
       " 'emotional database/motion capture/20170902_115212_00.txt',\n",
       " 'emotional database/motion capture/20170902_115317_00.txt',\n",
       " 'emotional database/motion capture/20170902_115419_00.txt']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>frameTime</th>\n",
       "      <th>bodyIndex</th>\n",
       "      <th>SpineBase_positionX</th>\n",
       "      <th>SpineBase_positionY</th>\n",
       "      <th>SpineBase_positionZ</th>\n",
       "      <th>SpineBase_rotationX</th>\n",
       "      <th>SpineBase_rotationY</th>\n",
       "      <th>SpineBase_rotationZ</th>\n",
       "      <th>SpineMid_positionX</th>\n",
       "      <th>SpineMid_positionY</th>\n",
       "      <th>...</th>\n",
       "      <th>HandTipRight_rotationX</th>\n",
       "      <th>HandTipRight_rotationY</th>\n",
       "      <th>HandTipRight_rotationZ</th>\n",
       "      <th>ThumbRight_positionX</th>\n",
       "      <th>ThumbRight_positionY</th>\n",
       "      <th>ThumbRight_positionZ</th>\n",
       "      <th>ThumbRight_rotationX</th>\n",
       "      <th>ThumbRight_rotationY</th>\n",
       "      <th>ThumbRight_rotationZ</th>\n",
       "      <th>Unnamed: 152</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1234</td>\n",
       "      <td>0</td>\n",
       "      <td>0.062298</td>\n",
       "      <td>0.230842</td>\n",
       "      <td>2.540962</td>\n",
       "      <td>358.7676</td>\n",
       "      <td>180.1466</td>\n",
       "      <td>2.819737</td>\n",
       "      <td>0.077674</td>\n",
       "      <td>0.542595</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.505001</td>\n",
       "      <td>1.357066</td>\n",
       "      <td>2.628572</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1266</td>\n",
       "      <td>0</td>\n",
       "      <td>0.069238</td>\n",
       "      <td>0.257058</td>\n",
       "      <td>2.526453</td>\n",
       "      <td>356.7902</td>\n",
       "      <td>179.9677</td>\n",
       "      <td>1.979240</td>\n",
       "      <td>0.079333</td>\n",
       "      <td>0.548986</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.473728</td>\n",
       "      <td>1.338728</td>\n",
       "      <td>2.621750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1334</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084557</td>\n",
       "      <td>0.248516</td>\n",
       "      <td>2.483606</td>\n",
       "      <td>351.4843</td>\n",
       "      <td>183.0456</td>\n",
       "      <td>359.412200</td>\n",
       "      <td>0.083828</td>\n",
       "      <td>0.551884</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.421183</td>\n",
       "      <td>1.339403</td>\n",
       "      <td>2.615883</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1366</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084818</td>\n",
       "      <td>0.249397</td>\n",
       "      <td>2.483649</td>\n",
       "      <td>352.0697</td>\n",
       "      <td>182.5708</td>\n",
       "      <td>359.807800</td>\n",
       "      <td>0.085690</td>\n",
       "      <td>0.553738</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.408477</td>\n",
       "      <td>1.418415</td>\n",
       "      <td>2.645500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1399</td>\n",
       "      <td>0</td>\n",
       "      <td>0.085442</td>\n",
       "      <td>0.250219</td>\n",
       "      <td>2.483902</td>\n",
       "      <td>352.3281</td>\n",
       "      <td>182.3243</td>\n",
       "      <td>0.070354</td>\n",
       "      <td>0.087480</td>\n",
       "      <td>0.554349</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.373999</td>\n",
       "      <td>1.373415</td>\n",
       "      <td>2.632500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 153 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   frameTime  bodyIndex  SpineBase_positionX  SpineBase_positionY  \\\n",
       "0       1234          0             0.062298             0.230842   \n",
       "1       1266          0             0.069238             0.257058   \n",
       "2       1334          0             0.084557             0.248516   \n",
       "3       1366          0             0.084818             0.249397   \n",
       "4       1399          0             0.085442             0.250219   \n",
       "\n",
       "   SpineBase_positionZ  SpineBase_rotationX  SpineBase_rotationY  \\\n",
       "0             2.540962             358.7676             180.1466   \n",
       "1             2.526453             356.7902             179.9677   \n",
       "2             2.483606             351.4843             183.0456   \n",
       "3             2.483649             352.0697             182.5708   \n",
       "4             2.483902             352.3281             182.3243   \n",
       "\n",
       "   SpineBase_rotationZ  SpineMid_positionX  SpineMid_positionY      ...       \\\n",
       "0             2.819737            0.077674            0.542595      ...        \n",
       "1             1.979240            0.079333            0.548986      ...        \n",
       "2           359.412200            0.083828            0.551884      ...        \n",
       "3           359.807800            0.085690            0.553738      ...        \n",
       "4             0.070354            0.087480            0.554349      ...        \n",
       "\n",
       "   HandTipRight_rotationX  HandTipRight_rotationY  HandTipRight_rotationZ  \\\n",
       "0                       0                       0                       0   \n",
       "1                       0                       0                       0   \n",
       "2                       0                       0                       0   \n",
       "3                       0                       0                       0   \n",
       "4                       0                       0                       0   \n",
       "\n",
       "   ThumbRight_positionX  ThumbRight_positionY  ThumbRight_positionZ  \\\n",
       "0              0.505001              1.357066              2.628572   \n",
       "1              0.473728              1.338728              2.621750   \n",
       "2              0.421183              1.339403              2.615883   \n",
       "3              0.408477              1.418415              2.645500   \n",
       "4              0.373999              1.373415              2.632500   \n",
       "\n",
       "   ThumbRight_rotationX  ThumbRight_rotationY  ThumbRight_rotationZ  \\\n",
       "0                     0                     0                     0   \n",
       "1                     0                     0                     0   \n",
       "2                     0                     0                     0   \n",
       "3                     0                     0                     0   \n",
       "4                     0                     0                     0   \n",
       "\n",
       "   Unnamed: 152  \n",
       "0           NaN  \n",
       "1           NaN  \n",
       "2           NaN  \n",
       "3           NaN  \n",
       "4           NaN  \n",
       "\n",
       "[5 rows x 153 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('emotional database/motion capture/20170902_085505_00.txt', sep=';')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['frameTime', 'bodyIndex', 'SpineBase_positionX', 'SpineBase_positionY',\n",
       "       'SpineBase_positionZ', 'SpineBase_rotationX', 'SpineBase_rotationY',\n",
       "       'SpineBase_rotationZ', 'SpineMid_positionX', 'SpineMid_positionY',\n",
       "       ...\n",
       "       'HandTipRight_rotationX', 'HandTipRight_rotationY',\n",
       "       'HandTipRight_rotationZ', 'ThumbRight_positionX',\n",
       "       'ThumbRight_positionY', 'ThumbRight_positionZ', 'ThumbRight_rotationX',\n",
       "       'ThumbRight_rotationY', 'ThumbRight_rotationZ', 'Unnamed: 152'],\n",
       "      dtype='object', length=153)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Returns a numpy array\n",
    "def load_file(file):\n",
    "    temp_df = pd.read_csv(file, sep=';')\n",
    "    textfile = file[34:]\n",
    "    output_value = descriptors.loc[descriptors['text_file']==textfile]['output'][:1].values[0]\n",
    "    #video_name = descriptors.loc[descriptors['text_file']==textfile]['video_name'][:1].values[0]\n",
    "    gender = descriptors.loc[descriptors['text_file']==textfile]['gender'][:1].values[0]\n",
    "    #temp_df['textfile'] = textfile\n",
    "    #temp_df['output'] = output_value\n",
    "    #temp_df['video_name'] = video_name\n",
    "    if gender == 'F':\n",
    "        temp_df['gender'] = 1\n",
    "    else:\n",
    "        temp_df['gender'] = 0\n",
    "    temp_df.drop(['Unnamed: 152'], axis=1, inplace=True)\n",
    "    return temp_df.values, output_value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(array([[1.234000e+03, 0.000000e+00, 6.229840e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [1.266000e+03, 0.000000e+00, 6.923762e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [1.334000e+03, 0.000000e+00, 8.455718e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       ...,\n",
      "       [4.060000e+04, 0.000000e+00, 9.428389e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [4.066700e+04, 0.000000e+00, 9.430516e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [4.070000e+04, 0.000000e+00, 9.472756e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00]]), 'Ne')\n"
     ]
    }
   ],
   "source": [
    "print(load_file('emotional database/motion capture/20170902_085505_00.txt'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(array([[6.990000e+02, 0.000000e+00, 8.576407e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [7.660000e+02, 0.000000e+00, 8.575481e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [8.340000e+02, 0.000000e+00, 8.578444e-02, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       ...,\n",
      "       [4.066600e+04, 0.000000e+00, 1.023175e-01, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [4.069900e+04, 0.000000e+00, 1.029394e-01, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00],\n",
      "       [4.076600e+04, 0.000000e+00, 1.033070e-01, ..., 0.000000e+00,\n",
      "        0.000000e+00, 0.000000e+00]]), 'Sa')\n"
     ]
    }
   ],
   "source": [
    "print(load_file('emotional database/motion capture/20170902_085608_00.txt'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "shapes = []\n",
    "Y = []\n",
    "for name in files:\n",
    "    data, t = load_file(name)\n",
    "    shapes.append(data.shape[0])\n",
    "    Y.append(t)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Replacing the emotions with the following:\n",
    "\n",
    "<li> 0 - Neutral state (Ne)</li>\n",
    "<li> 1 - Sadness (Sa)</li>\n",
    "<li> 2 - Surprise (Su)</li>\n",
    "<li> 3 - Fear (Fe)</li>\n",
    "<li> 4 - Anger (An)</li>\n",
    "<li> 5 - Disgust (Di)</li>\n",
    "<li> 6 - Happiness (Ha)</li>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "index = 0 \n",
    "for element in Y:\n",
    "    if element == 'Ne':\n",
    "        Y[index] = 0\n",
    "    elif element == 'Sa':\n",
    "        Y[index] = 1\n",
    "    elif element == 'Su':\n",
    "        Y[index] = 2\n",
    "    elif element == 'Fe':\n",
    "        Y[index] = 3\n",
    "    elif element == 'An':\n",
    "        Y[index] = 4\n",
    "    elif element == 'Di':\n",
    "        Y[index] = 5\n",
    "    elif element == 'Ha':\n",
    "        Y[index] = 6\n",
    "    index += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1758\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.utils import to_categorical\n",
    "\n",
    "maxlen = max(shapes)\n",
    "print(maxlen)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_group(filenames, prefix=''):\n",
    "    loaded = list()\n",
    "    for name in filenames:\n",
    "        data, temp = load_file(name)\n",
    "        #print('The name is:', name, data.shape)\n",
    "        zeros_data = np.zeros((max(shapes)-data.shape[0], 153))\n",
    "        data = np.concatenate((zeros_data, data), axis=0)\n",
    "        #print('Now the shape is:', name, data.shape)\n",
    "        loaded.append(data)\n",
    "        shapes.append(data.shape[0])\n",
    "    loaded = np.stack(loaded)\n",
    "    return loaded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(63, 1758, 153) (63, 7)\n"
     ]
    }
   ],
   "source": [
    "X = load_group(files)\n",
    "\n",
    "Y = np.asarray(Y).reshape((63,1))\n",
    "Y = to_categorical(Y)\n",
    "print(X.shape, Y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.1, random_state = 42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense, Dropout, LSTM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def evaluate_model(trainX, trainy, testX, testy):\n",
    "    verbose = 1\n",
    "    epochs = 100\n",
    "    n_timesteps, n_features, n_outputs = trainX.shape[1], trainX.shape[2], trainy.shape[1]\n",
    "    model = Sequential()\n",
    "    model.add(LSTM(32, input_shape=(n_timesteps, n_features)))\n",
    "    #model.add(Dropout(0.5))\n",
    "    model.add(Dense(16, activation='relu'))\n",
    "    model.add(Dense(n_outputs, activation='softmax'))\n",
    "    model.compile(loss='categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])\n",
    "    model.fit(trainX, trainy, epochs=epochs, verbose=verbose)\n",
    "    _, accuracy = model.evaluate(testX, testy, verbose=verbose)\n",
    "    return accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/100\n",
      "56/56 [==============================] - 7s 134ms/sample - loss: 2.0835 - accuracy: 0.1071\n",
      "Epoch 2/100\n",
      "56/56 [==============================] - 5s 82ms/sample - loss: 2.0654 - accuracy: 0.1071\n",
      "Epoch 3/100\n",
      "56/56 [==============================] - 5s 86ms/sample - loss: 2.0468 - accuracy: 0.1071\n",
      "Epoch 4/100\n",
      "56/56 [==============================] - 5s 95ms/sample - loss: 2.0366 - accuracy: 0.1071\n",
      "Epoch 5/100\n",
      "56/56 [==============================] - 5s 97ms/sample - loss: 2.0282 - accuracy: 0.1250\n",
      "Epoch 6/100\n",
      "56/56 [==============================] - 5s 98ms/sample - loss: 2.0216 - accuracy: 0.1250\n",
      "Epoch 7/100\n",
      "56/56 [==============================] - 6s 99ms/sample - loss: 2.0130 - accuracy: 0.1429\n",
      "Epoch 8/100\n",
      "56/56 [==============================] - 6s 102ms/sample - loss: 2.0066 - accuracy: 0.1607\n",
      "Epoch 9/100\n",
      "56/56 [==============================] - 6s 101ms/sample - loss: 1.9994 - accuracy: 0.1250\n",
      "Epoch 10/100\n",
      "56/56 [==============================] - 6s 101ms/sample - loss: 1.9922 - accuracy: 0.1250\n",
      "Epoch 11/100\n",
      "56/56 [==============================] - 6s 102ms/sample - loss: 1.9869 - accuracy: 0.1250\n",
      "Epoch 12/100\n",
      "56/56 [==============================] - 7s 131ms/sample - loss: 1.9830 - accuracy: 0.1250\n",
      "Epoch 13/100\n",
      "56/56 [==============================] - 8s 140ms/sample - loss: 1.9751 - accuracy: 0.1250\n",
      "Epoch 14/100\n",
      "56/56 [==============================] - 8s 135ms/sample - loss: 1.9713 - accuracy: 0.1250\n",
      "Epoch 15/100\n",
      "56/56 [==============================] - 8s 146ms/sample - loss: 1.9687 - accuracy: 0.1429\n",
      "Epoch 16/100\n",
      "56/56 [==============================] - 8s 137ms/sample - loss: 1.9657 - accuracy: 0.1429\n",
      "Epoch 17/100\n",
      "56/56 [==============================] - 7s 116ms/sample - loss: 1.9610 - accuracy: 0.1607\n",
      "Epoch 18/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.9574 - accuracy: 0.1607\n",
      "Epoch 19/100\n",
      "56/56 [==============================] - 6s 104ms/sample - loss: 1.9543 - accuracy: 0.1607\n",
      "Epoch 20/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9520 - accuracy: 0.1607\n",
      "Epoch 21/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.9489 - accuracy: 0.1607\n",
      "Epoch 22/100\n",
      "56/56 [==============================] - 6s 104ms/sample - loss: 1.9459 - accuracy: 0.1607\n",
      "Epoch 23/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9434 - accuracy: 0.1607\n",
      "Epoch 24/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9402 - accuracy: 0.1607\n",
      "Epoch 25/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9378 - accuracy: 0.1607\n",
      "Epoch 26/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9345 - accuracy: 0.1607\n",
      "Epoch 27/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9336 - accuracy: 0.1607\n",
      "Epoch 28/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9295 - accuracy: 0.1607\n",
      "Epoch 29/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9308 - accuracy: 0.1607\n",
      "Epoch 30/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9247 - accuracy: 0.1607\n",
      "Epoch 31/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.9273 - accuracy: 0.1607\n",
      "Epoch 32/100\n",
      "56/56 [==============================] - 6s 108ms/sample - loss: 1.9249 - accuracy: 0.1607\n",
      "Epoch 33/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9216 - accuracy: 0.1607\n",
      "Epoch 34/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9176 - accuracy: 0.1786\n",
      "Epoch 35/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9142 - accuracy: 0.1786\n",
      "Epoch 36/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9207 - accuracy: 0.1607\n",
      "Epoch 37/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9106 - accuracy: 0.1786\n",
      "Epoch 38/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9066 - accuracy: 0.1786\n",
      "Epoch 39/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.9085 - accuracy: 0.1607\n",
      "Epoch 40/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9041 - accuracy: 0.1607\n",
      "Epoch 41/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9110 - accuracy: 0.1786\n",
      "Epoch 42/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.9123 - accuracy: 0.1786\n",
      "Epoch 43/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.9096 - accuracy: 0.1786\n",
      "Epoch 44/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9078 - accuracy: 0.1786\n",
      "Epoch 45/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.9002 - accuracy: 0.2143\n",
      "Epoch 46/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.9043 - accuracy: 0.1964\n",
      "Epoch 47/100\n",
      "56/56 [==============================] - 6s 111ms/sample - loss: 1.8956 - accuracy: 0.2143\n",
      "Epoch 48/100\n",
      "56/56 [==============================] - 6s 109ms/sample - loss: 1.8973 - accuracy: 0.2143\n",
      "Epoch 49/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8989 - accuracy: 0.2143\n",
      "Epoch 50/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8953 - accuracy: 0.2143\n",
      "Epoch 51/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8918 - accuracy: 0.2143\n",
      "Epoch 52/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8926 - accuracy: 0.2143\n",
      "Epoch 53/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8921 - accuracy: 0.1964\n",
      "Epoch 54/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8933 - accuracy: 0.1964\n",
      "Epoch 55/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8924 - accuracy: 0.1964\n",
      "Epoch 56/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8915 - accuracy: 0.1964\n",
      "Epoch 57/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8903 - accuracy: 0.1964\n",
      "Epoch 58/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8886 - accuracy: 0.1964\n",
      "Epoch 59/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8864 - accuracy: 0.2143\n",
      "Epoch 60/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8860 - accuracy: 0.2143\n",
      "Epoch 61/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8857 - accuracy: 0.2143\n",
      "Epoch 62/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8852 - accuracy: 0.2143\n",
      "Epoch 63/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8835 - accuracy: 0.1964\n",
      "Epoch 64/100\n",
      "56/56 [==============================] - 6s 105ms/sample - loss: 1.8806 - accuracy: 0.2321\n",
      "Epoch 65/100\n",
      "56/56 [==============================] - 6s 110ms/sample - loss: 1.9007 - accuracy: 0.2321\n",
      "Epoch 66/100\n",
      "56/56 [==============================] - 6s 108ms/sample - loss: 1.8794 - accuracy: 0.2321\n",
      "Epoch 67/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8743 - accuracy: 0.2857\n",
      "Epoch 68/100\n",
      "56/56 [==============================] - 6s 111ms/sample - loss: 1.8826 - accuracy: 0.2321\n",
      "Epoch 69/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.8841 - accuracy: 0.2321\n",
      "Epoch 70/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.8843 - accuracy: 0.2679\n",
      "Epoch 71/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8880 - accuracy: 0.2321\n",
      "Epoch 72/100\n",
      "56/56 [==============================] - 6s 109ms/sample - loss: 1.8834 - accuracy: 0.2500\n",
      "Epoch 73/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8797 - accuracy: 0.2500\n",
      "Epoch 74/100\n",
      "56/56 [==============================] - 6s 108ms/sample - loss: 1.8794 - accuracy: 0.2500\n",
      "Epoch 75/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8797 - accuracy: 0.2500\n",
      "Epoch 76/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8793 - accuracy: 0.2500\n",
      "Epoch 77/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8783 - accuracy: 0.2500\n",
      "Epoch 78/100\n",
      "56/56 [==============================] - 6s 108ms/sample - loss: 1.8773 - accuracy: 0.2500\n",
      "Epoch 79/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8765 - accuracy: 0.2500\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 80/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8759 - accuracy: 0.2500\n",
      "Epoch 81/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8751 - accuracy: 0.2500\n",
      "Epoch 82/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8749 - accuracy: 0.2500\n",
      "Epoch 83/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8742 - accuracy: 0.2321\n",
      "Epoch 84/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8739 - accuracy: 0.2321\n",
      "Epoch 85/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8734 - accuracy: 0.2500\n",
      "Epoch 86/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8726 - accuracy: 0.2500\n",
      "Epoch 87/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8721 - accuracy: 0.2500\n",
      "Epoch 88/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8719 - accuracy: 0.2500\n",
      "Epoch 89/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8717 - accuracy: 0.2500\n",
      "Epoch 90/100\n",
      "56/56 [==============================] - 6s 116ms/sample - loss: 1.8717 - accuracy: 0.2500\n",
      "Epoch 91/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8710 - accuracy: 0.2500\n",
      "Epoch 92/100\n",
      "56/56 [==============================] - 6s 108ms/sample - loss: 1.8713 - accuracy: 0.2500\n",
      "Epoch 93/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8704 - accuracy: 0.2500\n",
      "Epoch 94/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8702 - accuracy: 0.2500\n",
      "Epoch 95/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8699 - accuracy: 0.2500\n",
      "Epoch 96/100\n",
      "56/56 [==============================] - 6s 107ms/sample - loss: 1.8696 - accuracy: 0.2500\n",
      "Epoch 97/100\n",
      "56/56 [==============================] - 6s 110ms/sample - loss: 1.8693 - accuracy: 0.2500\n",
      "Epoch 98/100\n",
      "56/56 [==============================] - 6s 112ms/sample - loss: 1.8689 - accuracy: 0.2500\n",
      "Epoch 99/100\n",
      "56/56 [==============================] - 6s 110ms/sample - loss: 1.8685 - accuracy: 0.2500\n",
      "Epoch 100/100\n",
      "56/56 [==============================] - 6s 106ms/sample - loss: 1.8680 - accuracy: 0.2500\n",
      "7/7 [==============================] - 0s 60ms/sample - loss: 2.2385 - accuracy: 0.0000e+00\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "evaluate_model(X_train, Y_train, X_test, Y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "20170902_115419_00.txt Ha 927_0282_01.MP4 F\n"
     ]
    }
   ],
   "source": [
    "df = pd.DataFrame()\n",
    "for file in files:\n",
    "    temp_df = pd.read_csv(file, sep=';')\n",
    "    textfile = file[34:]\n",
    "    output_value = descriptors.loc[descriptors['text_file']==textfile]['output'][:1].values[0]\n",
    "    video_name = descriptors.loc[descriptors['text_file']==textfile]['video_name'][:1].values[0]\n",
    "    gender = descriptors.loc[descriptors['text_file']==textfile]['gender'][:1].values[0]\n",
    "    temp_df['textfile'] = textfile\n",
    "    temp_df['output'] = output_value\n",
    "    temp_df['video_name'] = video_name\n",
    "    temp_df['gender'] = gender\n",
    "    df = df.append(temp_df, sort=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "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>frameTime</th>\n",
       "      <th>bodyIndex</th>\n",
       "      <th>SpineBase_positionX</th>\n",
       "      <th>SpineBase_positionY</th>\n",
       "      <th>SpineBase_positionZ</th>\n",
       "      <th>SpineBase_rotationX</th>\n",
       "      <th>SpineBase_rotationY</th>\n",
       "      <th>SpineBase_rotationZ</th>\n",
       "      <th>SpineMid_positionX</th>\n",
       "      <th>SpineMid_positionY</th>\n",
       "      <th>...</th>\n",
       "      <th>ThumbRight_positionY</th>\n",
       "      <th>ThumbRight_positionZ</th>\n",
       "      <th>ThumbRight_rotationX</th>\n",
       "      <th>ThumbRight_rotationY</th>\n",
       "      <th>ThumbRight_rotationZ</th>\n",
       "      <th>Unnamed: 152</th>\n",
       "      <th>textfile</th>\n",
       "      <th>output</th>\n",
       "      <th>video_name</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1234</td>\n",
       "      <td>0</td>\n",
       "      <td>0.062298</td>\n",
       "      <td>0.230842</td>\n",
       "      <td>2.540962</td>\n",
       "      <td>358.7676</td>\n",
       "      <td>180.1466</td>\n",
       "      <td>2.819737</td>\n",
       "      <td>0.077674</td>\n",
       "      <td>0.542595</td>\n",
       "      <td>...</td>\n",
       "      <td>1.357066</td>\n",
       "      <td>2.628572</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1266</td>\n",
       "      <td>0</td>\n",
       "      <td>0.069238</td>\n",
       "      <td>0.257058</td>\n",
       "      <td>2.526453</td>\n",
       "      <td>356.7902</td>\n",
       "      <td>179.9677</td>\n",
       "      <td>1.979240</td>\n",
       "      <td>0.079333</td>\n",
       "      <td>0.548986</td>\n",
       "      <td>...</td>\n",
       "      <td>1.338728</td>\n",
       "      <td>2.621750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1334</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084557</td>\n",
       "      <td>0.248516</td>\n",
       "      <td>2.483606</td>\n",
       "      <td>351.4843</td>\n",
       "      <td>183.0456</td>\n",
       "      <td>359.412200</td>\n",
       "      <td>0.083828</td>\n",
       "      <td>0.551884</td>\n",
       "      <td>...</td>\n",
       "      <td>1.339403</td>\n",
       "      <td>2.615883</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1366</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084818</td>\n",
       "      <td>0.249397</td>\n",
       "      <td>2.483649</td>\n",
       "      <td>352.0697</td>\n",
       "      <td>182.5708</td>\n",
       "      <td>359.807800</td>\n",
       "      <td>0.085690</td>\n",
       "      <td>0.553738</td>\n",
       "      <td>...</td>\n",
       "      <td>1.418415</td>\n",
       "      <td>2.645500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1399</td>\n",
       "      <td>0</td>\n",
       "      <td>0.085442</td>\n",
       "      <td>0.250219</td>\n",
       "      <td>2.483902</td>\n",
       "      <td>352.3281</td>\n",
       "      <td>182.3243</td>\n",
       "      <td>0.070354</td>\n",
       "      <td>0.087480</td>\n",
       "      <td>0.554349</td>\n",
       "      <td>...</td>\n",
       "      <td>1.373415</td>\n",
       "      <td>2.632500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 157 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   frameTime  bodyIndex  SpineBase_positionX  SpineBase_positionY  \\\n",
       "0       1234          0             0.062298             0.230842   \n",
       "1       1266          0             0.069238             0.257058   \n",
       "2       1334          0             0.084557             0.248516   \n",
       "3       1366          0             0.084818             0.249397   \n",
       "4       1399          0             0.085442             0.250219   \n",
       "\n",
       "   SpineBase_positionZ  SpineBase_rotationX  SpineBase_rotationY  \\\n",
       "0             2.540962             358.7676             180.1466   \n",
       "1             2.526453             356.7902             179.9677   \n",
       "2             2.483606             351.4843             183.0456   \n",
       "3             2.483649             352.0697             182.5708   \n",
       "4             2.483902             352.3281             182.3243   \n",
       "\n",
       "   SpineBase_rotationZ  SpineMid_positionX  SpineMid_positionY   ...    \\\n",
       "0             2.819737            0.077674            0.542595   ...     \n",
       "1             1.979240            0.079333            0.548986   ...     \n",
       "2           359.412200            0.083828            0.551884   ...     \n",
       "3           359.807800            0.085690            0.553738   ...     \n",
       "4             0.070354            0.087480            0.554349   ...     \n",
       "\n",
       "   ThumbRight_positionY  ThumbRight_positionZ  ThumbRight_rotationX  \\\n",
       "0              1.357066              2.628572                     0   \n",
       "1              1.338728              2.621750                     0   \n",
       "2              1.339403              2.615883                     0   \n",
       "3              1.418415              2.645500                     0   \n",
       "4              1.373415              2.632500                     0   \n",
       "\n",
       "   ThumbRight_rotationY  ThumbRight_rotationZ  Unnamed: 152  \\\n",
       "0                     0                     0           NaN   \n",
       "1                     0                     0           NaN   \n",
       "2                     0                     0           NaN   \n",
       "3                     0                     0           NaN   \n",
       "4                     0                     0           NaN   \n",
       "\n",
       "                 textfile  output       video_name  gender  \n",
       "0  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "1  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "2  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "3  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "4  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "\n",
       "[5 rows x 157 columns]"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(columns=['Unnamed: 152'], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('Motion_capture.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('Motion_capture.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 68101 entries, 0 to 68100\n",
      "Columns: 157 entries, Unnamed: 0 to gender\n",
      "dtypes: float64(129), int64(24), object(4)\n",
      "memory usage: 81.6+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x25490febac8>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x=\"output\", data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x254914f5b38>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x=\"output\", hue=\"gender\", data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x25491573128>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x=\"gender\", data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>frameTime</th>\n",
       "      <th>bodyIndex</th>\n",
       "      <th>SpineBase_positionX</th>\n",
       "      <th>SpineBase_positionY</th>\n",
       "      <th>SpineBase_positionZ</th>\n",
       "      <th>SpineBase_rotationX</th>\n",
       "      <th>SpineBase_rotationY</th>\n",
       "      <th>SpineBase_rotationZ</th>\n",
       "      <th>SpineMid_positionX</th>\n",
       "      <th>SpineMid_positionY</th>\n",
       "      <th>...</th>\n",
       "      <th>ThumbRight_positionX</th>\n",
       "      <th>ThumbRight_positionY</th>\n",
       "      <th>ThumbRight_positionZ</th>\n",
       "      <th>ThumbRight_rotationX</th>\n",
       "      <th>ThumbRight_rotationY</th>\n",
       "      <th>ThumbRight_rotationZ</th>\n",
       "      <th>textfile</th>\n",
       "      <th>output</th>\n",
       "      <th>video_name</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1234</td>\n",
       "      <td>0</td>\n",
       "      <td>0.062298</td>\n",
       "      <td>0.230842</td>\n",
       "      <td>2.540962</td>\n",
       "      <td>358.7676</td>\n",
       "      <td>180.1466</td>\n",
       "      <td>2.819737</td>\n",
       "      <td>0.077674</td>\n",
       "      <td>0.542595</td>\n",
       "      <td>...</td>\n",
       "      <td>0.505001</td>\n",
       "      <td>1.357066</td>\n",
       "      <td>2.628572</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1266</td>\n",
       "      <td>0</td>\n",
       "      <td>0.069238</td>\n",
       "      <td>0.257058</td>\n",
       "      <td>2.526453</td>\n",
       "      <td>356.7902</td>\n",
       "      <td>179.9677</td>\n",
       "      <td>1.979240</td>\n",
       "      <td>0.079333</td>\n",
       "      <td>0.548986</td>\n",
       "      <td>...</td>\n",
       "      <td>0.473728</td>\n",
       "      <td>1.338728</td>\n",
       "      <td>2.621750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1334</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084557</td>\n",
       "      <td>0.248516</td>\n",
       "      <td>2.483606</td>\n",
       "      <td>351.4843</td>\n",
       "      <td>183.0456</td>\n",
       "      <td>359.412200</td>\n",
       "      <td>0.083828</td>\n",
       "      <td>0.551884</td>\n",
       "      <td>...</td>\n",
       "      <td>0.421183</td>\n",
       "      <td>1.339403</td>\n",
       "      <td>2.615883</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1366</td>\n",
       "      <td>0</td>\n",
       "      <td>0.084818</td>\n",
       "      <td>0.249397</td>\n",
       "      <td>2.483649</td>\n",
       "      <td>352.0697</td>\n",
       "      <td>182.5708</td>\n",
       "      <td>359.807800</td>\n",
       "      <td>0.085690</td>\n",
       "      <td>0.553738</td>\n",
       "      <td>...</td>\n",
       "      <td>0.408477</td>\n",
       "      <td>1.418415</td>\n",
       "      <td>2.645500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1399</td>\n",
       "      <td>0</td>\n",
       "      <td>0.085442</td>\n",
       "      <td>0.250219</td>\n",
       "      <td>2.483902</td>\n",
       "      <td>352.3281</td>\n",
       "      <td>182.3243</td>\n",
       "      <td>0.070354</td>\n",
       "      <td>0.087480</td>\n",
       "      <td>0.554349</td>\n",
       "      <td>...</td>\n",
       "      <td>0.373999</td>\n",
       "      <td>1.373415</td>\n",
       "      <td>2.632500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20170902_085505_00.txt</td>\n",
       "      <td>Ne</td>\n",
       "      <td>927_0196_01.MP4</td>\n",
       "      <td>M</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 156 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   frameTime  bodyIndex  SpineBase_positionX  SpineBase_positionY  \\\n",
       "0       1234          0             0.062298             0.230842   \n",
       "1       1266          0             0.069238             0.257058   \n",
       "2       1334          0             0.084557             0.248516   \n",
       "3       1366          0             0.084818             0.249397   \n",
       "4       1399          0             0.085442             0.250219   \n",
       "\n",
       "   SpineBase_positionZ  SpineBase_rotationX  SpineBase_rotationY  \\\n",
       "0             2.540962             358.7676             180.1466   \n",
       "1             2.526453             356.7902             179.9677   \n",
       "2             2.483606             351.4843             183.0456   \n",
       "3             2.483649             352.0697             182.5708   \n",
       "4             2.483902             352.3281             182.3243   \n",
       "\n",
       "   SpineBase_rotationZ  SpineMid_positionX  SpineMid_positionY   ...    \\\n",
       "0             2.819737            0.077674            0.542595   ...     \n",
       "1             1.979240            0.079333            0.548986   ...     \n",
       "2           359.412200            0.083828            0.551884   ...     \n",
       "3           359.807800            0.085690            0.553738   ...     \n",
       "4             0.070354            0.087480            0.554349   ...     \n",
       "\n",
       "   ThumbRight_positionX  ThumbRight_positionY  ThumbRight_positionZ  \\\n",
       "0              0.505001              1.357066              2.628572   \n",
       "1              0.473728              1.338728              2.621750   \n",
       "2              0.421183              1.339403              2.615883   \n",
       "3              0.408477              1.418415              2.645500   \n",
       "4              0.373999              1.373415              2.632500   \n",
       "\n",
       "   ThumbRight_rotationX  ThumbRight_rotationY  ThumbRight_rotationZ  \\\n",
       "0                     0                     0                     0   \n",
       "1                     0                     0                     0   \n",
       "2                     0                     0                     0   \n",
       "3                     0                     0                     0   \n",
       "4                     0                     0                     0   \n",
       "\n",
       "                 textfile  output       video_name  gender  \n",
       "0  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "1  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "2  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "3  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "4  20170902_085505_00.txt      Ne  927_0196_01.MP4       M  \n",
       "\n",
       "[5 rows x 156 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 68101 entries, 0 to 68100\n",
      "Columns: 156 entries, frameTime to gender\n",
      "dtypes: float64(129), int64(23), object(4)\n",
      "memory usage: 81.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>frameTime</th>\n",
       "      <th>bodyIndex</th>\n",
       "      <th>SpineBase_positionX</th>\n",
       "      <th>SpineBase_positionY</th>\n",
       "      <th>SpineBase_positionZ</th>\n",
       "      <th>SpineBase_rotationX</th>\n",
       "      <th>SpineBase_rotationY</th>\n",
       "      <th>SpineBase_rotationZ</th>\n",
       "      <th>SpineMid_positionX</th>\n",
       "      <th>SpineMid_positionY</th>\n",
       "      <th>...</th>\n",
       "      <th>HandTipRight_positionZ</th>\n",
       "      <th>HandTipRight_rotationX</th>\n",
       "      <th>HandTipRight_rotationY</th>\n",
       "      <th>HandTipRight_rotationZ</th>\n",
       "      <th>ThumbRight_positionX</th>\n",
       "      <th>ThumbRight_positionY</th>\n",
       "      <th>ThumbRight_positionZ</th>\n",
       "      <th>ThumbRight_rotationX</th>\n",
       "      <th>ThumbRight_rotationY</th>\n",
       "      <th>ThumbRight_rotationZ</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.0</td>\n",
       "      <td>68101.0</td>\n",
       "      <td>68101.0</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.000000</td>\n",
       "      <td>68101.0</td>\n",
       "      <td>68101.0</td>\n",
       "      <td>68101.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>23795.040704</td>\n",
       "      <td>0.548068</td>\n",
       "      <td>0.075381</td>\n",
       "      <td>0.071375</td>\n",
       "      <td>2.846934</td>\n",
       "      <td>160.366392</td>\n",
       "      <td>182.287124</td>\n",
       "      <td>244.587691</td>\n",
       "      <td>0.069708</td>\n",
       "      <td>0.371071</td>\n",
       "      <td>...</td>\n",
       "      <td>2.686957</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.235022</td>\n",
       "      <td>0.165853</td>\n",
       "      <td>2.689732</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>14330.625262</td>\n",
       "      <td>1.212417</td>\n",
       "      <td>0.127782</td>\n",
       "      <td>0.076835</td>\n",
       "      <td>0.215083</td>\n",
       "      <td>175.053612</td>\n",
       "      <td>9.277310</td>\n",
       "      <td>165.792220</td>\n",
       "      <td>0.133636</td>\n",
       "      <td>0.088251</td>\n",
       "      <td>...</td>\n",
       "      <td>0.216331</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.189756</td>\n",
       "      <td>0.231388</td>\n",
       "      <td>0.212288</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>667.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.521609</td>\n",
       "      <td>-1.265361</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.005686</td>\n",
       "      <td>38.651870</td>\n",
       "      <td>-0.005711</td>\n",
       "      <td>-0.541466</td>\n",
       "      <td>-1.011956</td>\n",
       "      <td>...</td>\n",
       "      <td>0.291140</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.683795</td>\n",
       "      <td>-1.150637</td>\n",
       "      <td>0.231914</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>11900.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.058093</td>\n",
       "      <td>0.022591</td>\n",
       "      <td>2.678133</td>\n",
       "      <td>2.001868</td>\n",
       "      <td>179.871600</td>\n",
       "      <td>2.508938</td>\n",
       "      <td>0.051926</td>\n",
       "      <td>0.320332</td>\n",
       "      <td>...</td>\n",
       "      <td>2.541406</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.150399</td>\n",
       "      <td>0.001163</td>\n",
       "      <td>2.543833</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>22800.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.096567</td>\n",
       "      <td>0.077503</td>\n",
       "      <td>2.814031</td>\n",
       "      <td>10.710430</td>\n",
       "      <td>182.723900</td>\n",
       "      <td>356.946000</td>\n",
       "      <td>0.094269</td>\n",
       "      <td>0.359206</td>\n",
       "      <td>...</td>\n",
       "      <td>2.663486</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.270697</td>\n",
       "      <td>0.096575</td>\n",
       "      <td>2.671648</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>33832.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.130497</td>\n",
       "      <td>0.130945</td>\n",
       "      <td>2.991473</td>\n",
       "      <td>357.095200</td>\n",
       "      <td>185.790100</td>\n",
       "      <td>358.986200</td>\n",
       "      <td>0.126267</td>\n",
       "      <td>0.454923</td>\n",
       "      <td>...</td>\n",
       "      <td>2.815593</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.337466</td>\n",
       "      <td>0.255656</td>\n",
       "      <td>2.808400</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>70600.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.357695</td>\n",
       "      <td>0.405219</td>\n",
       "      <td>3.557597</td>\n",
       "      <td>359.994100</td>\n",
       "      <td>248.212300</td>\n",
       "      <td>359.994200</td>\n",
       "      <td>1.347992</td>\n",
       "      <td>0.708656</td>\n",
       "      <td>...</td>\n",
       "      <td>3.727729</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.508312</td>\n",
       "      <td>1.425420</td>\n",
       "      <td>3.709944</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 152 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          frameTime     bodyIndex  SpineBase_positionX  SpineBase_positionY  \\\n",
       "count  68101.000000  68101.000000         68101.000000         68101.000000   \n",
       "mean   23795.040704      0.548068             0.075381             0.071375   \n",
       "std    14330.625262      1.212417             0.127782             0.076835   \n",
       "min      667.000000      0.000000            -0.521609            -1.265361   \n",
       "25%    11900.000000      0.000000             0.058093             0.022591   \n",
       "50%    22800.000000      0.000000             0.096567             0.077503   \n",
       "75%    33832.000000      0.000000             0.130497             0.130945   \n",
       "max    70600.000000      4.000000             1.357695             0.405219   \n",
       "\n",
       "       SpineBase_positionZ  SpineBase_rotationX  SpineBase_rotationY  \\\n",
       "count         68101.000000         68101.000000         68101.000000   \n",
       "mean              2.846934           160.366392           182.287124   \n",
       "std               0.215083           175.053612             9.277310   \n",
       "min               0.000000            -0.005686            38.651870   \n",
       "25%               2.678133             2.001868           179.871600   \n",
       "50%               2.814031            10.710430           182.723900   \n",
       "75%               2.991473           357.095200           185.790100   \n",
       "max               3.557597           359.994100           248.212300   \n",
       "\n",
       "       SpineBase_rotationZ  SpineMid_positionX  SpineMid_positionY  \\\n",
       "count         68101.000000        68101.000000        68101.000000   \n",
       "mean            244.587691            0.069708            0.371071   \n",
       "std             165.792220            0.133636            0.088251   \n",
       "min              -0.005711           -0.541466           -1.011956   \n",
       "25%               2.508938            0.051926            0.320332   \n",
       "50%             356.946000            0.094269            0.359206   \n",
       "75%             358.986200            0.126267            0.454923   \n",
       "max             359.994200            1.347992            0.708656   \n",
       "\n",
       "               ...           HandTipRight_positionZ  HandTipRight_rotationX  \\\n",
       "count          ...                     68101.000000                 68101.0   \n",
       "mean           ...                         2.686957                     0.0   \n",
       "std            ...                         0.216331                     0.0   \n",
       "min            ...                         0.291140                     0.0   \n",
       "25%            ...                         2.541406                     0.0   \n",
       "50%            ...                         2.663486                     0.0   \n",
       "75%            ...                         2.815593                     0.0   \n",
       "max            ...                         3.727729                     0.0   \n",
       "\n",
       "       HandTipRight_rotationY  HandTipRight_rotationZ  ThumbRight_positionX  \\\n",
       "count                 68101.0                 68101.0          68101.000000   \n",
       "mean                      0.0                     0.0              0.235022   \n",
       "std                       0.0                     0.0              0.189756   \n",
       "min                       0.0                     0.0             -0.683795   \n",
       "25%                       0.0                     0.0              0.150399   \n",
       "50%                       0.0                     0.0              0.270697   \n",
       "75%                       0.0                     0.0              0.337466   \n",
       "max                       0.0                     0.0              1.508312   \n",
       "\n",
       "       ThumbRight_positionY  ThumbRight_positionZ  ThumbRight_rotationX  \\\n",
       "count          68101.000000          68101.000000               68101.0   \n",
       "mean               0.165853              2.689732                   0.0   \n",
       "std                0.231388              0.212288                   0.0   \n",
       "min               -1.150637              0.231914                   0.0   \n",
       "25%                0.001163              2.543833                   0.0   \n",
       "50%                0.096575              2.671648                   0.0   \n",
       "75%                0.255656              2.808400                   0.0   \n",
       "max                1.425420              3.709944                   0.0   \n",
       "\n",
       "       ThumbRight_rotationY  ThumbRight_rotationZ  \n",
       "count               68101.0               68101.0  \n",
       "mean                    0.0                   0.0  \n",
       "std                     0.0                   0.0  \n",
       "min                     0.0                   0.0  \n",
       "25%                     0.0                   0.0  \n",
       "50%                     0.0                   0.0  \n",
       "75%                     0.0                   0.0  \n",
       "max                     0.0                   0.0  \n",
       "\n",
       "[8 rows x 152 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}