{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# Exploratory data analysis \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Based on assignment 3 <br>\n",
    "<font color = red >This Demo and the attached files from course PSYO/NESC 3505 Neural Data Science, at Dalhousie University. You should not disseminate, distribute or copy. </font>\n",
    "<br><font color = red >I am NOT post inappropriate or copyrighted content, advertise or promote outside products or organizations </font>\n",
    "<br>© Copyright 2020.PSYO/NESC 3505 FAll 2020 https://dalpsychneuro.github.io/NESC_3505_textbook/intro.html\n",
    "<br>**For demonstration purposes only**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Background\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "> Flanker Data\n",
    "We'll be working with data from a similar flanker experiment as we used in Assignment 2. However, in Assignment 2 we gave you a \"sanitized\" version of the data, where we had done a bit of clean-up to extract just the information we wanted you to work with. In this assignment you'll get experience starting with the raw data and extracting the necessary information yourself.\n",
    "\n",
    "--PSYO 3505 Fall 2019 Assignment 2 cell1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Read file and check it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "First of all we need input and examine the data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "subjects = ['001_2015_05_22_11_30',\n",
    "            '002_2015_05_25_14_36',\n",
    "            '003_2015_05_28_14_09'\n",
    "           ]\n",
    "\n",
    "in_file = subjects[0]+'/'+subjects[0]+'_data.txt'\n",
    "\n",
    "#input to data_frame\n",
    "df = pd.read_csv(in_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "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>id\\tyear\\tmonth\\tday\\thour\\tminute\\tgender\\tage\\thandedness\\twait\\tblock\\ttrial\\ttarget_location\\ttarget\\tflankers\\trt\\tresponse\\terror\\tpre_target_response\\tITI_response\\ttarget_on_error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  id\\tyear\\tmonth\\tday\\thour\\tminute\\tgender\\tage\\thandedness\\twait\\tblock\\ttrial\\ttarget_location\\ttarget\\tflankers\\trt\\tresponse\\terror\\tpre_target_response\\tITI_response\\ttarget_on_error\n",
       "0  001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...                                                                                                                                         \n",
       "1  001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...                                                                                                                                         \n",
       "2  001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...                                                                                                                                         \n",
       "3  001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...                                                                                                                                         \n",
       "4  001\\t2015\\t05\\t22\\t11\\t30\\tm\\t25\\tr\\t3.24\\tpra...                                                                                                                                         "
      ]
     },
     "execution_count": 7,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "looks like not very well, we need add escape character. Typically, I prefer read csv file directly and then check the head."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "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>id</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>minute</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>handedness</th>\n",
       "      <th>wait</th>\n",
       "      <th>...</th>\n",
       "      <th>trial</th>\n",
       "      <th>target_location</th>\n",
       "      <th>target</th>\n",
       "      <th>flankers</th>\n",
       "      <th>rt</th>\n",
       "      <th>response</th>\n",
       "      <th>error</th>\n",
       "      <th>pre_target_response</th>\n",
       "      <th>ITI_response</th>\n",
       "      <th>target_on_error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.240</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>left</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.240</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>right</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.550</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.240</td>\n",
       "      <td>...</td>\n",
       "      <td>3</td>\n",
       "      <td>up</td>\n",
       "      <td>white</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.565</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.240</td>\n",
       "      <td>...</td>\n",
       "      <td>4</td>\n",
       "      <td>up</td>\n",
       "      <td>black</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.453</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.240</td>\n",
       "      <td>...</td>\n",
       "      <td>5</td>\n",
       "      <td>down</td>\n",
       "      <td>black</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.442</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>left</td>\n",
       "      <td>white</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.349</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>188</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>29</td>\n",
       "      <td>right</td>\n",
       "      <td>white</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.371</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>189</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>30</td>\n",
       "      <td>up</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.549</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>31</td>\n",
       "      <td>left</td>\n",
       "      <td>white</td>\n",
       "      <td>neutral</td>\n",
       "      <td>0.463</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>191</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>32</td>\n",
       "      <td>right</td>\n",
       "      <td>black</td>\n",
       "      <td>neutral</td>\n",
       "      <td>0.430</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>192 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     id  year  month  day  hour  minute gender  age handedness   wait  ...  \\\n",
       "0     1  2015      5   22    11      30      m   25          r  3.240  ...   \n",
       "1     1  2015      5   22    11      30      m   25          r  3.240  ...   \n",
       "2     1  2015      5   22    11      30      m   25          r  3.240  ...   \n",
       "3     1  2015      5   22    11      30      m   25          r  3.240  ...   \n",
       "4     1  2015      5   22    11      30      m   25          r  3.240  ...   \n",
       "..   ..   ...    ...  ...   ...     ...    ...  ...        ...    ...  ...   \n",
       "187   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "188   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "189   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "190   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "191   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "\n",
       "    trial  target_location target     flankers     rt  response error  \\\n",
       "0       1             left  black  incongruent    NaN       NaN   NaN   \n",
       "1       2            right  black  incongruent  0.550     black  True   \n",
       "2       3               up  white  incongruent  0.565     white  True   \n",
       "3       4               up  black    congruent  0.453     black  True   \n",
       "4       5             down  black    congruent  0.442     black  True   \n",
       "..    ...              ...    ...          ...    ...       ...   ...   \n",
       "187    28             left  white    congruent  0.349     white  True   \n",
       "188    29            right  white    congruent  0.371     white  True   \n",
       "189    30               up  black  incongruent  0.549     black  True   \n",
       "190    31             left  white      neutral  0.463     white  True   \n",
       "191    32            right  black      neutral  0.430     black  True   \n",
       "\n",
       "    pre_target_response  ITI_response  target_on_error  \n",
       "0                 False         False            0.023  \n",
       "1                 False         False            0.023  \n",
       "2                 False         False            0.024  \n",
       "3                 False         False            0.024  \n",
       "4                 False         False            0.023  \n",
       "..                  ...           ...              ...  \n",
       "187               False         False            0.024  \n",
       "188               False         False            0.023  \n",
       "189               False         False            0.023  \n",
       "190               False         False            0.023  \n",
       "191               False         False            0.023  \n",
       "\n",
       "[192 rows x 21 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(in_file,sep = '\\t')\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "look at the head and tail again \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "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>id</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>minute</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>handedness</th>\n",
       "      <th>wait</th>\n",
       "      <th>...</th>\n",
       "      <th>trial</th>\n",
       "      <th>target_location</th>\n",
       "      <th>target</th>\n",
       "      <th>flankers</th>\n",
       "      <th>rt</th>\n",
       "      <th>response</th>\n",
       "      <th>error</th>\n",
       "      <th>pre_target_response</th>\n",
       "      <th>ITI_response</th>\n",
       "      <th>target_on_error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.24</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>left</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.24</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>right</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.550</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.24</td>\n",
       "      <td>...</td>\n",
       "      <td>3</td>\n",
       "      <td>up</td>\n",
       "      <td>white</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.565</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.24</td>\n",
       "      <td>...</td>\n",
       "      <td>4</td>\n",
       "      <td>up</td>\n",
       "      <td>black</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.453</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>3.24</td>\n",
       "      <td>...</td>\n",
       "      <td>5</td>\n",
       "      <td>down</td>\n",
       "      <td>black</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.442</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  year  month  day  hour  minute gender  age handedness  wait  ... trial  \\\n",
       "0   1  2015      5   22    11      30      m   25          r  3.24  ...     1   \n",
       "1   1  2015      5   22    11      30      m   25          r  3.24  ...     2   \n",
       "2   1  2015      5   22    11      30      m   25          r  3.24  ...     3   \n",
       "3   1  2015      5   22    11      30      m   25          r  3.24  ...     4   \n",
       "4   1  2015      5   22    11      30      m   25          r  3.24  ...     5   \n",
       "\n",
       "   target_location target     flankers     rt  response error  \\\n",
       "0             left  black  incongruent    NaN       NaN   NaN   \n",
       "1            right  black  incongruent  0.550     black  True   \n",
       "2               up  white  incongruent  0.565     white  True   \n",
       "3               up  black    congruent  0.453     black  True   \n",
       "4             down  black    congruent  0.442     black  True   \n",
       "\n",
       "  pre_target_response  ITI_response  target_on_error  \n",
       "0               False         False            0.023  \n",
       "1               False         False            0.023  \n",
       "2               False         False            0.024  \n",
       "3               False         False            0.024  \n",
       "4               False         False            0.023  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "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>id</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>hour</th>\n",
       "      <th>minute</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>handedness</th>\n",
       "      <th>wait</th>\n",
       "      <th>...</th>\n",
       "      <th>trial</th>\n",
       "      <th>target_location</th>\n",
       "      <th>target</th>\n",
       "      <th>flankers</th>\n",
       "      <th>rt</th>\n",
       "      <th>response</th>\n",
       "      <th>error</th>\n",
       "      <th>pre_target_response</th>\n",
       "      <th>ITI_response</th>\n",
       "      <th>target_on_error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>187</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>left</td>\n",
       "      <td>white</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.349</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>188</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>29</td>\n",
       "      <td>right</td>\n",
       "      <td>white</td>\n",
       "      <td>congruent</td>\n",
       "      <td>0.371</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>189</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>30</td>\n",
       "      <td>up</td>\n",
       "      <td>black</td>\n",
       "      <td>incongruent</td>\n",
       "      <td>0.549</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>31</td>\n",
       "      <td>left</td>\n",
       "      <td>white</td>\n",
       "      <td>neutral</td>\n",
       "      <td>0.463</td>\n",
       "      <td>white</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>191</th>\n",
       "      <td>1</td>\n",
       "      <td>2015</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>r</td>\n",
       "      <td>1.627</td>\n",
       "      <td>...</td>\n",
       "      <td>32</td>\n",
       "      <td>right</td>\n",
       "      <td>black</td>\n",
       "      <td>neutral</td>\n",
       "      <td>0.430</td>\n",
       "      <td>black</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>0.023</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     id  year  month  day  hour  minute gender  age handedness   wait  ...  \\\n",
       "187   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "188   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "189   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "190   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "191   1  2015      5   22    11      30      m   25          r  1.627  ...   \n",
       "\n",
       "    trial  target_location target     flankers     rt  response error  \\\n",
       "187    28             left  white    congruent  0.349     white  True   \n",
       "188    29            right  white    congruent  0.371     white  True   \n",
       "189    30               up  black  incongruent  0.549     black  True   \n",
       "190    31             left  white      neutral  0.463     white  True   \n",
       "191    32            right  black      neutral  0.430     black  True   \n",
       "\n",
       "    pre_target_response  ITI_response  target_on_error  \n",
       "187               False         False            0.024  \n",
       "188               False         False            0.023  \n",
       "189               False         False            0.023  \n",
       "190               False         False            0.023  \n",
       "191               False         False            0.023  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Then we check have missing value "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "id                     0\n",
      "year                   0\n",
      "month                  0\n",
      "day                    0\n",
      "hour                   0\n",
      "minute                 0\n",
      "gender                 0\n",
      "age                    0\n",
      "handedness             0\n",
      "wait                   0\n",
      "block                  0\n",
      "trial                  0\n",
      "target_location        0\n",
      "target                 0\n",
      "flankers               0\n",
      "rt                     2\n",
      "response               2\n",
      "error                  2\n",
      "pre_target_response    0\n",
      "ITI_response           0\n",
      "target_on_error        0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(pd.isna(df).sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Data cleaning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Obviously, we need to remove missing data by appling \n",
    "```\n",
    ".dropna() method\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "id                     0\n",
      "year                   0\n",
      "month                  0\n",
      "day                    0\n",
      "hour                   0\n",
      "minute                 0\n",
      "gender                 0\n",
      "age                    0\n",
      "handedness             0\n",
      "wait                   0\n",
      "block                  0\n",
      "trial                  0\n",
      "target_location        0\n",
      "target                 0\n",
      "flankers               0\n",
      "rt                     0\n",
      "response               0\n",
      "error                  0\n",
      "pre_target_response    0\n",
      "ITI_response           0\n",
      "target_on_error        0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df = df.dropna()\n",
    "print(pd.isna(df).sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "This experiment has ‘practice’, the main idea is giving participants a chance to figure out the experiment. But we do not need it in our EDA. Not all experiments have ‘practice’ . "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "value = df['block']\n",
    "print(value.unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['1' '2' '3' '4' '5']\n"
     ]
    }
   ],
   "source": [
    "df = df[df.block!='practice']\n",
    "value = df['block']\n",
    "print(value.unique())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Then we found ‘rt’ column is not milliseconds and need to convert"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "32     0.528\n",
       "33     0.419\n",
       "34     0.514\n",
       "35     0.406\n",
       "36     0.502\n",
       "       ...  \n",
       "187    0.349\n",
       "188    0.371\n",
       "189    0.549\n",
       "190    0.463\n",
       "191    0.430\n",
       "Name: rt, Length: 160, dtype: float64"
      ]
     },
     "execution_count": 20,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['rt']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "32     528.0\n",
      "33     419.0\n",
      "34     514.0\n",
      "35     406.0\n",
      "36     502.0\n",
      "       ...  \n",
      "187    349.0\n",
      "188    371.0\n",
      "189    549.0\n",
      "190    463.0\n",
      "191    430.0\n",
      "Name: rt, Length: 160, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "df['rt'] = df['rt']*1000\n",
    "print(df['rt'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "‘rt’ is our interested variable, but In most behavioural studies, RTs are not normally distributed, so we need to Examining the RT distribution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    160.00000\n",
       "mean     465.16875\n",
       "std      101.47170\n",
       "min      314.00000\n",
       "25%      392.25000\n",
       "50%      454.00000\n",
       "75%      505.25000\n",
       "max      845.00000\n",
       "Name: rt, dtype: float64"
      ]
     },
     "execution_count": 22,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['rt'].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "plot a histogram of RTs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 23,
     "metadata": {
      "image/png": {
       "height": 411,
       "width": 717
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['rt'].plot(kind='hist')\n",
    "\n",
    "# add a solid line at the median and dashed lines at the 25th and 75th percentiles (done for you)\n",
    "plt.axvline(df['rt'].describe()['25%'], 0, 1, color='turquoise', linestyle='--')\n",
    "plt.axvline(df['rt'].median(), 0, 1, color='cyan', linestyle='-')\n",
    "plt.axvline(df['rt'].describe()['75%'], 0, 1, color='turquoise', linestyle='--')\n",
    "\n",
    "# Rememebr to use plt.show() to see your plots (often they show anyway, but with some garbagy text at the top)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Analyzing relationships between variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "According to above figure, the histogram look not follow normal distribution, Looks like right skewed. Because the data sets have low ‘high value\n",
    "<br> check the cdf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 25,
     "metadata": {
      "image/png": {
       "height": 411,
       "width": 720
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['rt'].plot(kind = 'hist',cumulative = True, density =True)\n",
    "# add a dashed oragne line at the median\n",
    "plt.axvline(df['rt'].describe()['25%'], 0, 1, color='turquoise', linestyle='--')\n",
    "plt.axvline(df['rt'].median(), 0, 1, color='cyan', linestyle='-')\n",
    "plt.axvline(df['rt'].describe()['75%'], 0, 1, color='turquoise', linestyle='--')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "How should we do in this situation. The course tells me :\n",
    "<br>\n",
    ">While the skew in the RT data makes sense, for the reasons described above, it's problematic when running statistics on the data. This is because many conventional statistical tests, like t-tests and ANOVAs, assume that the data are normally distributed. Using skewed data can cause unreliable results.\n",
    "<br>\n",
    "<br>\n",
    "For this reason, many researchers apply some transformation to RTs to make their distribution more normal (statistically normal, that is). A common one is to take the logarithm of the RT values: log(RT)log(RT); another is to take the inverse: 1/RT.\n",
    "\n",
    "\n",
    "---PSYO 3505 Fall 2019 Assignment 2 cell40\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "So, for log(RT)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 26,
     "metadata": {
      "image/png": {
       "height": 411,
       "width": 717
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# log-transform the rt data (done for you) \n",
    "df['logrt'] = np.log(df['rt'])\n",
    "\n",
    "# put your plotting code here\n",
    "# YOUR CODE HERE\n",
    "df['logrt'].plot(kind='hist')\n",
    "\n",
    "# add a solid line at the median and dashed lines at the 25th and 75th percentiles (done for you)\n",
    "plt.axvline(df['logrt'].describe()['25%'], 0, 1, color='turquoise', linestyle='--')\n",
    "plt.axvline(df['logrt'].median(), 0, 1, color='cyan', linestyle='-')\n",
    "plt.axvline(df['logrt'].describe()['75%'], 0, 1, color='turquoise', linestyle='--')\n",
    "\n",
    "# Rememebr to use plt.show() to see your plots (often they show anyway, but with some garbagy text at the top)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "inverse: $1/RT$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 27,
     "metadata": {
      "image/png": {
       "height": 411,
       "width": 727
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['invrt'] = 1/(df['rt'])\n",
    "\n",
    "df['invrt'].plot(kind='hist')\n",
    "# add a solid line at the median and dashed lines at the 25th and 75th percentiles (done for you)\n",
    "plt.axvline(df['invrt'].describe()['25%'], 0, 1, color='turquoise', linestyle='--')\n",
    "plt.axvline(df['invrt'].median(), 0, 1, color='cyan', linestyle='-')\n",
    "plt.axvline(df['invrt'].describe()['75%'], 0, 1, color='turquoise', linestyle='--')\n",
    "\n",
    "# Rememebr to use plt.show() to see your plots (often they show anyway, but with some garbagy text at the top)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "After that, we want to explore the data will be on errors and reaction times (RTs).\n",
    ">Recall that these data are from a \"flanker\" experiment in which participants had to respond with a left or right button press, depending on whether the target (centre) arrow pointed left or right. The target arrow was flanked with two arrows on either side that were either congruent (pointed in same direction) or incongruent (opposite direction).\n",
    "\n",
    "---PSYO 3505 Fall 2019 Assignment 2 cell48\n",
    "\n",
    "```{tip} You can found more information about flanker experiment in this article 'Flanker and Simon effects interact at the response selection stage'\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "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>rt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>flankers</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>congruent</th>\n",
       "      <td>452.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>incongruent</th>\n",
       "      <td>466.05</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 rt\n",
       "flankers           \n",
       "congruent    452.60\n",
       "incongruent  466.05"
      ]
     },
     "execution_count": 28,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rt_mean = df.groupby(by = 'flankers')[['rt','error']].agg('mean')\n",
    "rt_mean = rt_mean.drop('neutral')\n",
    "rt_mean"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Generate a table for accuracy (the error column)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "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>Correct</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>flankers</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>congruent</th>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>incongruent</th>\n",
       "      <td>34</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Correct\n",
       "flankers            \n",
       "congruent         40\n",
       "incongruent       34"
      ]
     },
     "execution_count": 29,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "correct = df.groupby(by = 'flankers')[['error']].agg('sum')\n",
    "correct.columns = ['Correct']\n",
    "correct = correct.drop('neutral')\n",
    "correct"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    " showing the accuracy rate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "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>Accuracy</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>flankers</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>congruent</th>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>incongruent</th>\n",
       "      <td>0.85</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Accuracy\n",
       "flankers             \n",
       "congruent        1.00\n",
       "incongruent      0.85"
      ]
     },
     "execution_count": 30,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total= df.groupby(by = 'flankers')[['error']].agg('count')\n",
    "correct = df.groupby(by = 'flankers')[['error']].agg('sum')\n",
    "number = correct[:2]/total[:2]\n",
    "number.columns = ['Accuracy']\n",
    "number"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Plot box plots of the log-transformed RT data (logrt) for each flanker conditio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 31,
     "metadata": {
      "image/png": {
       "height": 426,
       "width": 706
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "execution_count": 31,
     "metadata": {
      "image/png": {
       "height": 426,
       "width": 706
      },
      "needs_background": "light"
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "boxplot1 = df.loc[df['flankers']=='congruent','logrt'].plot(kind = 'box',title = 'Congruent')\n",
    "plt.show()\n",
    "boxplot2 = df.loc[df['flankers']=='incongruent','logrt'].plot(kind = 'box',title = 'Incongruent')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Interpretation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    " Basis of EDA, I can say incongruent flankers would lead to slower and less accurate responses. according to the participant results, the congruent condition has 100% accuracy and 452.60 (mean) response time. Incongruent condition has 85% accuracy and 466.05 (mean) response time."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "So far, we end EDA methods (basic). \n",
    "<br>\n",
    "<br>\n",
    "Through this assignment, I learned the basic steps of data analysis. Especially,EDA methods:\n",
    "<br> Read files\n",
    "<br> Data cleaning\n",
    "<br> Analyzing relationships between variables\n",
    "<br> Visualization\n",
    "<br> Interpretation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## References\n",
    "\n",
    "[1] [NESC 3505 Neural Data Science, at Dalhousie University. Textbook](https://dalpsychneuro.github.io/NESC_3505_textbook/intro.html)\n",
    "<br>\n",
    "[2] NESC 3505 Neural Data Science, at Dalhousie University. Assignment 3\n",
    "<br>\n",
    "[3] [An Extensive Step by Step Guide to Exploratory Data Analysis](https://towardsdatascience.com/an-extensive-guide-to-exploratory-data-analysis-ddd99a03199e)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Based on assignment 3 <br>\n",
    "<font color = red >This Demo and the attached files from course PSYO/NESC 3505 Neural Data Science, at Dalhousie University. You should not disseminate, distribute or copy. </font>\n",
    "<br><font color = red >I am NOT post inappropriate or copyrighted content, advertise or promote outside products or organizations </font>\n",
    "<br>© Copyright 2020.PSYO/NESC 3505 FAll 2020 https://dalpsychneuro.github.io/NESC_3505_textbook/intro.html\n",
    "<br>**For demonstration purposes only**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (system-wide)",
   "language": "python",
   "metadata": {
    "cocalc": {
     "description": "Python 3 programming language",
     "priority": 100,
     "url": "https://www.python.org/"
    }
   },
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}