{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "86d2536c",
   "metadata": {},
   "source": [
    "# Combine information across tables: joins and anti-joins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b6f949f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d2a4eab",
   "metadata": {},
   "source": [
    "# \"Load\" some experimental data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a9450803",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response\n",
       "0         312           A1           0.12     LEFT\n",
       "1         312           A2           0.37     LEFT\n",
       "2         312           C2           0.68     LEFT\n",
       "3         711           A1           4.01    RIGHT\n",
       "4         711           A2           0.44     LEFT\n",
       "5         313           A1           0.07    RIGHT\n",
       "6         313           B1           0.08    RIGHT\n",
       "7         712           A2           3.29     LEFT\n",
       "8         314           A2           0.29     LEFT\n",
       "9         714           B2           3.32    RIGHT\n",
       "10        314           B1           0.14    RIGHT\n",
       "11        314           C2           0.73    RIGHT\n",
       "12        713           B1           5.74     LEFT"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.DataFrame(\n",
    "    data=[\n",
    "        ['312', 'A1', 0.12, 'LEFT'],\n",
    "        ['312', 'A2', 0.37, 'LEFT'],\n",
    "        ['312', 'C2', 0.68, 'LEFT'],\n",
    "        ['711', 'A1', 4.01, 'RIGHT'],\n",
    "        ['711', 'A2', 0.44, 'LEFT'],\n",
    "        ['313', 'A1', 0.07, 'RIGHT'],\n",
    "        ['313', 'B1', 0.08, 'RIGHT'],\n",
    "        ['712', 'A2', 3.29, 'LEFT'],\n",
    "        ['314', 'A2', 0.29, 'LEFT'],\n",
    "        ['714', 'B2', 3.32, 'RIGHT'],\n",
    "        ['314', 'B1', 0.14, 'RIGHT'],\n",
    "        ['314', 'C2', 0.73, 'RIGHT'],\n",
    "        ['713', 'B1', 5.74, 'LEFT'],\n",
    "    ],\n",
    "    columns=['subject_id', 'condition_id', 'response_time', 'response'],\n",
    ")\n",
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7e8b09b",
   "metadata": {},
   "source": [
    "Each experiment belongs to one experimental condition, but the parameters of each condition are not in the table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "455471d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "condition_to_orientation = {\n",
    "    'A1': 0,\n",
    "    'A2': 0,\n",
    "    'B1': 45,\n",
    "    'B2': 45,\n",
    "    'C1': 90,\n",
    "}\n",
    "\n",
    "condition_to_duration = {\n",
    "    'A1': 0.1,\n",
    "    'A2': 0.01,\n",
    "    'B1': 0.1,\n",
    "    'B2': 0.01,\n",
    "    'C1': 0.2,\n",
    "}\n",
    "\n",
    "condition_to_surround = {\n",
    "    'A1': 'FULL',\n",
    "    'A2': 'NONE',\n",
    "    'B1': 'NONE',\n",
    "    'B2': 'FULL',\n",
    "    'C1': 'FULL',\n",
    "}\n",
    "\n",
    "\n",
    "condition_to_stimulus_type = {\n",
    "    'A1': 'LINES',\n",
    "    'A2': 'DOTS',\n",
    "    'B1': 'PLAID',\n",
    "    'B2': 'PLAID',\n",
    "    'C1': 'WIGGLES',\n",
    "}\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ccfd7e7",
   "metadata": {},
   "source": [
    "# Manually adding the condition parameters to the table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cc32110c",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_with_properties = data.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c322a9af",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     A1\n",
       "1     A2\n",
       "2     C2\n",
       "3     A1\n",
       "4     A2\n",
       "5     A1\n",
       "6     B1\n",
       "7     A2\n",
       "8     A2\n",
       "9     B2\n",
       "10    B1\n",
       "11    C2\n",
       "12    B1\n",
       "Name: condition_id, dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_with_properties['condition_id']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0dbee78b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      0.0\n",
       "1      0.0\n",
       "2      NaN\n",
       "3      0.0\n",
       "4      0.0\n",
       "5      0.0\n",
       "6     45.0\n",
       "7      0.0\n",
       "8      0.0\n",
       "9     45.0\n",
       "10    45.0\n",
       "11     NaN\n",
       "12    45.0\n",
       "Name: condition_id, dtype: float64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_with_properties['condition_id'].map(condition_to_orientation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3fb3e3af",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_with_properties['orientation'] = data_with_properties['condition_id'].map(condition_to_orientation)\n",
    "data_with_properties['duration'] = data_with_properties['condition_id'].map(condition_to_duration)\n",
    "data_with_properties['surround'] = data_with_properties['condition_id'].map(condition_to_surround)\n",
    "data_with_properties['stimulus_type'] = data_with_properties['condition_id'].map(condition_to_stimulus_type)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "995eff91",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>orientation</th>\n",
       "      <th>duration</th>\n",
       "      <th>surround</th>\n",
       "      <th>stimulus_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45.0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>FULL</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>45.0</td>\n",
       "      <td>0.10</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response  orientation  duration  \\\n",
       "0         312           A1           0.12     LEFT          0.0      0.10   \n",
       "1         312           A2           0.37     LEFT          0.0      0.01   \n",
       "2         312           C2           0.68     LEFT          NaN       NaN   \n",
       "3         711           A1           4.01    RIGHT          0.0      0.10   \n",
       "4         711           A2           0.44     LEFT          0.0      0.01   \n",
       "5         313           A1           0.07    RIGHT          0.0      0.10   \n",
       "6         313           B1           0.08    RIGHT         45.0      0.10   \n",
       "7         712           A2           3.29     LEFT          0.0      0.01   \n",
       "8         314           A2           0.29     LEFT          0.0      0.01   \n",
       "9         714           B2           3.32    RIGHT         45.0      0.01   \n",
       "10        314           B1           0.14    RIGHT         45.0      0.10   \n",
       "11        314           C2           0.73    RIGHT          NaN       NaN   \n",
       "12        713           B1           5.74     LEFT         45.0      0.10   \n",
       "\n",
       "   surround stimulus_type  \n",
       "0      FULL         LINES  \n",
       "1      NONE          DOTS  \n",
       "2       NaN           NaN  \n",
       "3      FULL         LINES  \n",
       "4      NONE          DOTS  \n",
       "5      FULL         LINES  \n",
       "6      NONE         PLAID  \n",
       "7      NONE          DOTS  \n",
       "8      NONE          DOTS  \n",
       "9      FULL         PLAID  \n",
       "10     NONE         PLAID  \n",
       "11      NaN           NaN  \n",
       "12     NONE         PLAID  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_with_properties"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d6e71b13",
   "metadata": {},
   "source": [
    "# Using a join operation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d9835d7c",
   "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>orientation</th>\n",
       "      <th>duration</th>\n",
       "      <th>surround</th>\n",
       "      <th>stimulus_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A2</th>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B1</th>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B2</th>\n",
       "      <td>45</td>\n",
       "      <td>0.01</td>\n",
       "      <td>FULL</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C1</th>\n",
       "      <td>90</td>\n",
       "      <td>0.2</td>\n",
       "      <td>FULL</td>\n",
       "      <td>WIGGLES</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   orientation duration surround stimulus_type\n",
       "A1           0      0.1     FULL         LINES\n",
       "A2           0     0.01     NONE          DOTS\n",
       "B1          45      0.1     NONE         PLAID\n",
       "B2          45     0.01     FULL         PLAID\n",
       "C1          90      0.2     FULL       WIGGLES"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Often, this is done using a spreadsheet\n",
    "condition_properties = pd.DataFrame(\n",
    "    [condition_to_orientation, condition_to_duration, condition_to_surround, condition_to_stimulus_type],\n",
    "    index=['orientation', 'duration', 'surround', 'stimulus_type'],\n",
    ").T\n",
    "condition_properties"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a9087876",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>orientation</th>\n",
       "      <th>duration</th>\n",
       "      <th>surround</th>\n",
       "      <th>stimulus_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.01</td>\n",
       "      <td>FULL</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response orientation duration  \\\n",
       "0         312           A1           0.12     LEFT           0      0.1   \n",
       "3         711           A1           4.01    RIGHT           0      0.1   \n",
       "5         313           A1           0.07    RIGHT           0      0.1   \n",
       "1         312           A2           0.37     LEFT           0     0.01   \n",
       "4         711           A2           0.44     LEFT           0     0.01   \n",
       "7         712           A2           3.29     LEFT           0     0.01   \n",
       "8         314           A2           0.29     LEFT           0     0.01   \n",
       "6         313           B1           0.08    RIGHT          45      0.1   \n",
       "10        314           B1           0.14    RIGHT          45      0.1   \n",
       "12        713           B1           5.74     LEFT          45      0.1   \n",
       "9         714           B2           3.32    RIGHT          45     0.01   \n",
       "\n",
       "   surround stimulus_type  \n",
       "0      FULL         LINES  \n",
       "3      FULL         LINES  \n",
       "5      FULL         LINES  \n",
       "1      NONE          DOTS  \n",
       "4      NONE          DOTS  \n",
       "7      NONE          DOTS  \n",
       "8      NONE          DOTS  \n",
       "6      NONE         PLAID  \n",
       "10     NONE         PLAID  \n",
       "12     NONE         PLAID  \n",
       "9      FULL         PLAID  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.merge(condition_properties, left_on='condition_id', right_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "61cb65be",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>orientation</th>\n",
       "      <th>duration</th>\n",
       "      <th>surround</th>\n",
       "      <th>stimulus_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.01</td>\n",
       "      <td>FULL</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response orientation duration  \\\n",
       "0         312           A1           0.12     LEFT           0      0.1   \n",
       "1         312           A2           0.37     LEFT           0     0.01   \n",
       "2         312           C2           0.68     LEFT         NaN      NaN   \n",
       "3         711           A1           4.01    RIGHT           0      0.1   \n",
       "4         711           A2           0.44     LEFT           0     0.01   \n",
       "5         313           A1           0.07    RIGHT           0      0.1   \n",
       "6         313           B1           0.08    RIGHT          45      0.1   \n",
       "7         712           A2           3.29     LEFT           0     0.01   \n",
       "8         314           A2           0.29     LEFT           0     0.01   \n",
       "9         714           B2           3.32    RIGHT          45     0.01   \n",
       "10        314           B1           0.14    RIGHT          45      0.1   \n",
       "11        314           C2           0.73    RIGHT         NaN      NaN   \n",
       "12        713           B1           5.74     LEFT          45      0.1   \n",
       "\n",
       "   surround stimulus_type  \n",
       "0      FULL         LINES  \n",
       "1      NONE          DOTS  \n",
       "2       NaN           NaN  \n",
       "3      FULL         LINES  \n",
       "4      NONE          DOTS  \n",
       "5      FULL         LINES  \n",
       "6      NONE         PLAID  \n",
       "7      NONE          DOTS  \n",
       "8      NONE          DOTS  \n",
       "9      FULL         PLAID  \n",
       "10     NONE         PLAID  \n",
       "11      NaN           NaN  \n",
       "12     NONE         PLAID  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.merge(condition_properties, left_on='condition_id', right_index=True, how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7b4d23df",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>orientation</th>\n",
       "      <th>duration</th>\n",
       "      <th>surround</th>\n",
       "      <th>stimulus_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0.0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3.0</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5.0</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>FULL</td>\n",
       "      <td>LINES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.0</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4.0</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7.0</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8.0</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>0</td>\n",
       "      <td>0.01</td>\n",
       "      <td>NONE</td>\n",
       "      <td>DOTS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2.0</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11.0</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6.0</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10.0</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12.0</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.1</td>\n",
       "      <td>NONE</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9.0</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>45</td>\n",
       "      <td>0.01</td>\n",
       "      <td>FULL</td>\n",
       "      <td>PLAID</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NaN</th>\n",
       "      <td>NaN</td>\n",
       "      <td>C1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>90</td>\n",
       "      <td>0.2</td>\n",
       "      <td>FULL</td>\n",
       "      <td>WIGGLES</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     subject_id condition_id  response_time response orientation duration  \\\n",
       "0.0         312           A1           0.12     LEFT           0      0.1   \n",
       "3.0         711           A1           4.01    RIGHT           0      0.1   \n",
       "5.0         313           A1           0.07    RIGHT           0      0.1   \n",
       "1.0         312           A2           0.37     LEFT           0     0.01   \n",
       "4.0         711           A2           0.44     LEFT           0     0.01   \n",
       "7.0         712           A2           3.29     LEFT           0     0.01   \n",
       "8.0         314           A2           0.29     LEFT           0     0.01   \n",
       "2.0         312           C2           0.68     LEFT         NaN      NaN   \n",
       "11.0        314           C2           0.73    RIGHT         NaN      NaN   \n",
       "6.0         313           B1           0.08    RIGHT          45      0.1   \n",
       "10.0        314           B1           0.14    RIGHT          45      0.1   \n",
       "12.0        713           B1           5.74     LEFT          45      0.1   \n",
       "9.0         714           B2           3.32    RIGHT          45     0.01   \n",
       "NaN         NaN           C1            NaN      NaN          90      0.2   \n",
       "\n",
       "     surround stimulus_type  \n",
       "0.0      FULL         LINES  \n",
       "3.0      FULL         LINES  \n",
       "5.0      FULL         LINES  \n",
       "1.0      NONE          DOTS  \n",
       "4.0      NONE          DOTS  \n",
       "7.0      NONE          DOTS  \n",
       "8.0      NONE          DOTS  \n",
       "2.0       NaN           NaN  \n",
       "11.0      NaN           NaN  \n",
       "6.0      NONE         PLAID  \n",
       "10.0     NONE         PLAID  \n",
       "12.0     NONE         PLAID  \n",
       "9.0      FULL         PLAID  \n",
       "NaN      FULL       WIGGLES  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.merge(condition_properties, left_on='condition_id', right_index=True, how='outer')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cba9534f",
   "metadata": {},
   "source": [
    "# Anti-join: filter out unwanted data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "1cb2bbdb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# We are given a list of subjects that are outliers and should be disregarded in the analysis\n",
    "outliers = pd.DataFrame([['711'], ['712'], ['713'], ['714'], ['888']], columns=['subject_id'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e2e627d5",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id condition_id  response_time response\n",
       "0        711           A1           4.01    RIGHT\n",
       "1        711           A2           0.44     LEFT\n",
       "2        712           A2           3.29     LEFT\n",
       "3        714           B2           3.32    RIGHT\n",
       "4        713           B1           5.74     LEFT"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.merge(outliers, on='subject_id')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "eb809fe0",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>_merge</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>711</td>\n",
       "      <td>A1</td>\n",
       "      <td>4.01</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>711</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.44</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>712</td>\n",
       "      <td>A2</td>\n",
       "      <td>3.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>714</td>\n",
       "      <td>B2</td>\n",
       "      <td>3.32</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>713</td>\n",
       "      <td>B1</td>\n",
       "      <td>5.74</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>888</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>right_only</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response      _merge\n",
       "0         312           A1           0.12     LEFT   left_only\n",
       "1         312           A2           0.37     LEFT   left_only\n",
       "2         312           C2           0.68     LEFT   left_only\n",
       "3         711           A1           4.01    RIGHT        both\n",
       "4         711           A2           0.44     LEFT        both\n",
       "5         313           A1           0.07    RIGHT   left_only\n",
       "6         313           B1           0.08    RIGHT   left_only\n",
       "7         712           A2           3.29     LEFT        both\n",
       "8         314           A2           0.29     LEFT   left_only\n",
       "9         314           B1           0.14    RIGHT   left_only\n",
       "10        314           C2           0.73    RIGHT   left_only\n",
       "11        714           B2           3.32    RIGHT        both\n",
       "12        713           B1           5.74     LEFT        both\n",
       "13        888          NaN            NaN      NaN  right_only"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.merge(outliers, on='subject_id', how='outer', indicator=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6fdb696e",
   "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>subject_id</th>\n",
       "      <th>condition_id</th>\n",
       "      <th>response_time</th>\n",
       "      <th>response</th>\n",
       "      <th>_merge</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>312</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.12</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>312</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.68</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>313</td>\n",
       "      <td>A1</td>\n",
       "      <td>0.07</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>313</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.08</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>314</td>\n",
       "      <td>A2</td>\n",
       "      <td>0.29</td>\n",
       "      <td>LEFT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>314</td>\n",
       "      <td>B1</td>\n",
       "      <td>0.14</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>314</td>\n",
       "      <td>C2</td>\n",
       "      <td>0.73</td>\n",
       "      <td>RIGHT</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id condition_id  response_time response     _merge\n",
       "0         312           A1           0.12     LEFT  left_only\n",
       "1         312           A2           0.37     LEFT  left_only\n",
       "2         312           C2           0.68     LEFT  left_only\n",
       "5         313           A1           0.07    RIGHT  left_only\n",
       "6         313           B1           0.08    RIGHT  left_only\n",
       "8         314           A2           0.29     LEFT  left_only\n",
       "9         314           B1           0.14    RIGHT  left_only\n",
       "10        314           C2           0.73    RIGHT  left_only"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp = data.merge(outliers, on='subject_id', how='outer', indicator=True)\n",
    "data_without_outliers = temp[temp['_merge'] == 'left_only']\n",
    "data_without_outliers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c3e6baa",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}