{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pandas import DataFrame\n",
    "from numpy import random"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 1: Tufte Style Box+Whiskers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "      <th>E</th>\n",
       "      <th>F</th>\n",
       "      <th>G</th>\n",
       "      <th>H</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.816951</td>\n",
       "      <td>4.354197</td>\n",
       "      <td>5.014316</td>\n",
       "      <td>4.944332</td>\n",
       "      <td>5.268459</td>\n",
       "      <td>4.127929</td>\n",
       "      <td>4.495678</td>\n",
       "      <td>6.285195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.140925</td>\n",
       "      <td>5.384016</td>\n",
       "      <td>4.585007</td>\n",
       "      <td>5.698897</td>\n",
       "      <td>3.753989</td>\n",
       "      <td>4.385816</td>\n",
       "      <td>5.595906</td>\n",
       "      <td>5.910020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.973697</td>\n",
       "      <td>4.270081</td>\n",
       "      <td>5.344023</td>\n",
       "      <td>6.379101</td>\n",
       "      <td>6.241163</td>\n",
       "      <td>4.133344</td>\n",
       "      <td>6.699746</td>\n",
       "      <td>3.925451</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.723197</td>\n",
       "      <td>5.890564</td>\n",
       "      <td>4.528252</td>\n",
       "      <td>6.288667</td>\n",
       "      <td>4.873346</td>\n",
       "      <td>5.236624</td>\n",
       "      <td>5.074247</td>\n",
       "      <td>5.054928</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.319266</td>\n",
       "      <td>4.843160</td>\n",
       "      <td>5.366703</td>\n",
       "      <td>4.274235</td>\n",
       "      <td>3.926008</td>\n",
       "      <td>4.957835</td>\n",
       "      <td>7.711974</td>\n",
       "      <td>4.995974</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4.795188</td>\n",
       "      <td>5.731934</td>\n",
       "      <td>3.759910</td>\n",
       "      <td>4.874946</td>\n",
       "      <td>3.977707</td>\n",
       "      <td>4.284435</td>\n",
       "      <td>5.820949</td>\n",
       "      <td>6.194236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.130495</td>\n",
       "      <td>1.754058</td>\n",
       "      <td>4.924919</td>\n",
       "      <td>5.250145</td>\n",
       "      <td>5.244639</td>\n",
       "      <td>5.101537</td>\n",
       "      <td>6.141814</td>\n",
       "      <td>5.193609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5.104017</td>\n",
       "      <td>5.400567</td>\n",
       "      <td>4.318200</td>\n",
       "      <td>4.306453</td>\n",
       "      <td>6.280427</td>\n",
       "      <td>6.555387</td>\n",
       "      <td>6.585680</td>\n",
       "      <td>4.189265</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.030186</td>\n",
       "      <td>5.208992</td>\n",
       "      <td>4.528060</td>\n",
       "      <td>5.024145</td>\n",
       "      <td>4.610665</td>\n",
       "      <td>3.610316</td>\n",
       "      <td>3.984090</td>\n",
       "      <td>4.892341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.961964</td>\n",
       "      <td>5.812331</td>\n",
       "      <td>3.388120</td>\n",
       "      <td>6.822580</td>\n",
       "      <td>5.383096</td>\n",
       "      <td>2.459424</td>\n",
       "      <td>6.806711</td>\n",
       "      <td>5.510672</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>5.478655</td>\n",
       "      <td>5.567332</td>\n",
       "      <td>4.066557</td>\n",
       "      <td>6.074857</td>\n",
       "      <td>6.760632</td>\n",
       "      <td>5.683561</td>\n",
       "      <td>6.237218</td>\n",
       "      <td>2.985190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>4.261113</td>\n",
       "      <td>7.166819</td>\n",
       "      <td>5.423207</td>\n",
       "      <td>6.093811</td>\n",
       "      <td>4.994752</td>\n",
       "      <td>4.670659</td>\n",
       "      <td>5.987789</td>\n",
       "      <td>2.215282</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>5.201085</td>\n",
       "      <td>4.851406</td>\n",
       "      <td>4.682030</td>\n",
       "      <td>3.602403</td>\n",
       "      <td>4.634048</td>\n",
       "      <td>4.589244</td>\n",
       "      <td>4.543679</td>\n",
       "      <td>4.680432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>4.312412</td>\n",
       "      <td>6.617821</td>\n",
       "      <td>5.172933</td>\n",
       "      <td>4.243390</td>\n",
       "      <td>3.866812</td>\n",
       "      <td>5.568476</td>\n",
       "      <td>3.870093</td>\n",
       "      <td>6.613179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>4.265170</td>\n",
       "      <td>5.080882</td>\n",
       "      <td>3.595370</td>\n",
       "      <td>3.391088</td>\n",
       "      <td>3.928088</td>\n",
       "      <td>5.606241</td>\n",
       "      <td>4.995347</td>\n",
       "      <td>4.873159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>3.112553</td>\n",
       "      <td>4.018332</td>\n",
       "      <td>5.450781</td>\n",
       "      <td>4.662063</td>\n",
       "      <td>3.935943</td>\n",
       "      <td>4.965459</td>\n",
       "      <td>5.582554</td>\n",
       "      <td>6.837429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>5.369033</td>\n",
       "      <td>5.311757</td>\n",
       "      <td>4.306653</td>\n",
       "      <td>5.185948</td>\n",
       "      <td>4.138951</td>\n",
       "      <td>5.972153</td>\n",
       "      <td>5.839915</td>\n",
       "      <td>3.526673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>4.497646</td>\n",
       "      <td>4.407245</td>\n",
       "      <td>5.702950</td>\n",
       "      <td>4.794317</td>\n",
       "      <td>5.983328</td>\n",
       "      <td>6.257530</td>\n",
       "      <td>7.155495</td>\n",
       "      <td>4.816282</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>4.818714</td>\n",
       "      <td>3.246948</td>\n",
       "      <td>4.630178</td>\n",
       "      <td>3.395023</td>\n",
       "      <td>3.886652</td>\n",
       "      <td>5.151510</td>\n",
       "      <td>6.368907</td>\n",
       "      <td>1.870367</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>5.871599</td>\n",
       "      <td>4.733323</td>\n",
       "      <td>4.987047</td>\n",
       "      <td>5.165873</td>\n",
       "      <td>4.668263</td>\n",
       "      <td>3.479415</td>\n",
       "      <td>5.938720</td>\n",
       "      <td>6.275684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>6.354728</td>\n",
       "      <td>4.036087</td>\n",
       "      <td>5.009182</td>\n",
       "      <td>6.595682</td>\n",
       "      <td>5.356226</td>\n",
       "      <td>5.269646</td>\n",
       "      <td>4.548096</td>\n",
       "      <td>4.632888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>4.784111</td>\n",
       "      <td>6.358432</td>\n",
       "      <td>7.049450</td>\n",
       "      <td>3.907292</td>\n",
       "      <td>5.436143</td>\n",
       "      <td>4.328879</td>\n",
       "      <td>4.688403</td>\n",
       "      <td>6.334957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>4.149367</td>\n",
       "      <td>3.926702</td>\n",
       "      <td>4.340054</td>\n",
       "      <td>4.543143</td>\n",
       "      <td>3.998085</td>\n",
       "      <td>4.542539</td>\n",
       "      <td>6.307795</td>\n",
       "      <td>4.257889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>6.109732</td>\n",
       "      <td>5.541091</td>\n",
       "      <td>5.142267</td>\n",
       "      <td>4.134215</td>\n",
       "      <td>5.360157</td>\n",
       "      <td>4.848468</td>\n",
       "      <td>3.314067</td>\n",
       "      <td>5.714349</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>4.398707</td>\n",
       "      <td>4.526739</td>\n",
       "      <td>4.448023</td>\n",
       "      <td>4.110701</td>\n",
       "      <td>6.140705</td>\n",
       "      <td>3.683653</td>\n",
       "      <td>4.941240</td>\n",
       "      <td>4.754220</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           A         B         C         D         E         F         G  \\\n",
       "0   5.816951  4.354197  5.014316  4.944332  5.268459  4.127929  4.495678   \n",
       "1   5.140925  5.384016  4.585007  5.698897  3.753989  4.385816  5.595906   \n",
       "2   3.973697  4.270081  5.344023  6.379101  6.241163  4.133344  6.699746   \n",
       "3   5.723197  5.890564  4.528252  6.288667  4.873346  5.236624  5.074247   \n",
       "4   5.319266  4.843160  5.366703  4.274235  3.926008  4.957835  7.711974   \n",
       "5   4.795188  5.731934  3.759910  4.874946  3.977707  4.284435  5.820949   \n",
       "6   6.130495  1.754058  4.924919  5.250145  5.244639  5.101537  6.141814   \n",
       "7   5.104017  5.400567  4.318200  4.306453  6.280427  6.555387  6.585680   \n",
       "8   6.030186  5.208992  4.528060  5.024145  4.610665  3.610316  3.984090   \n",
       "9   4.961964  5.812331  3.388120  6.822580  5.383096  2.459424  6.806711   \n",
       "10  5.478655  5.567332  4.066557  6.074857  6.760632  5.683561  6.237218   \n",
       "11  4.261113  7.166819  5.423207  6.093811  4.994752  4.670659  5.987789   \n",
       "12  5.201085  4.851406  4.682030  3.602403  4.634048  4.589244  4.543679   \n",
       "13  4.312412  6.617821  5.172933  4.243390  3.866812  5.568476  3.870093   \n",
       "14  4.265170  5.080882  3.595370  3.391088  3.928088  5.606241  4.995347   \n",
       "15  3.112553  4.018332  5.450781  4.662063  3.935943  4.965459  5.582554   \n",
       "16  5.369033  5.311757  4.306653  5.185948  4.138951  5.972153  5.839915   \n",
       "17  4.497646  4.407245  5.702950  4.794317  5.983328  6.257530  7.155495   \n",
       "18  4.818714  3.246948  4.630178  3.395023  3.886652  5.151510  6.368907   \n",
       "19  5.871599  4.733323  4.987047  5.165873  4.668263  3.479415  5.938720   \n",
       "20  6.354728  4.036087  5.009182  6.595682  5.356226  5.269646  4.548096   \n",
       "21  4.784111  6.358432  7.049450  3.907292  5.436143  4.328879  4.688403   \n",
       "22  4.149367  3.926702  4.340054  4.543143  3.998085  4.542539  6.307795   \n",
       "23  6.109732  5.541091  5.142267  4.134215  5.360157  4.848468  3.314067   \n",
       "24  4.398707  4.526739  4.448023  4.110701  6.140705  3.683653  4.941240   \n",
       "\n",
       "           H  \n",
       "0   6.285195  \n",
       "1   5.910020  \n",
       "2   3.925451  \n",
       "3   5.054928  \n",
       "4   4.995974  \n",
       "5   6.194236  \n",
       "6   5.193609  \n",
       "7   4.189265  \n",
       "8   4.892341  \n",
       "9   5.510672  \n",
       "10  2.985190  \n",
       "11  2.215282  \n",
       "12  4.680432  \n",
       "13  6.613179  \n",
       "14  4.873159  \n",
       "15  6.837429  \n",
       "16  3.526673  \n",
       "17  4.816282  \n",
       "18  1.870367  \n",
       "19  6.275684  \n",
       "20  4.632888  \n",
       "21  6.334957  \n",
       "22  4.257889  \n",
       "23  5.714349  \n",
       "24  4.754220  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = DataFrame(random.normal(5, 1, size=(25,8)), columns=list(\"ABCDEFGH\"))\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    5.039220\n",
       "B    4.961633\n",
       "C    4.790568\n",
       "D    4.950532\n",
       "E    4.905931\n",
       "F    4.778803\n",
       "G    5.569445\n",
       "H    4.901587\n",
       "dtype: float64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.mean(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib\n",
    "from matplotlib import pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "matplotlib.rcParams[\"font.size\"] = 16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plt.subplots()[1]\n",
    "ax.spines['right'].set_visible(False)\n",
    "ax.spines['top'].set_visible(False)\n",
    "\n",
    "plt.xlabel(\"X label here\")\n",
    "plt.ylabel(\"Y label here\")\n",
    "\n",
    "ax.set_xlim(0.5, len(df.columns)+0.5)\n",
    "ax.set_ylim(0, 8)\n",
    "ax.set_xticklabels(list(df.columns))\n",
    "ax.set_xticks(range(1, len(df.columns)+1))\n",
    "\n",
    "for i, col in enumerate(df.columns):\n",
    "    s = df[col]\n",
    "    \n",
    "    # mean\n",
    "    x = i+1\n",
    "    y = s.quantile(0.5)\n",
    "    ax.plot(x, y, 'ro')\n",
    "    \n",
    "    y1 = s.quantile(0.75)\n",
    "    y2 = s.quantile(1)\n",
    "    ax.plot((x, x), (y1, y2), 'k')\n",
    "    \n",
    "    y1 = s.quantile(0)\n",
    "    y2 = s.quantile(0.25)\n",
    "    ax.plot((x, x), (y1, y2), 'k')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 2: Std Dev Ranges"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfs = []\n",
    "\n",
    "for i in range(5):\n",
    "    df = DataFrame()\n",
    "    df[\"x\"] = list(range(4))\n",
    "    df[\"A\"] = df[\"x\"] + random.normal(size=4) * 0.2\n",
    "    df[\"B\"] = 2 + random.normal(size=4) * 0.3\n",
    "    df[\"trial\"] = i\n",
    "    dfs.append(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>x</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>trial</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>-0.250173</td>\n",
       "      <td>1.576447</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.061277</td>\n",
       "      <td>2.089403</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1.668585</td>\n",
       "      <td>1.485925</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>2.769240</td>\n",
       "      <td>1.733016</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0.025520</td>\n",
       "      <td>1.886120</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.267888</td>\n",
       "      <td>1.809673</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2.083532</td>\n",
       "      <td>1.878483</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>2.870992</td>\n",
       "      <td>2.597568</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0.296073</td>\n",
       "      <td>1.694059</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.188875</td>\n",
       "      <td>2.432131</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2.036837</td>\n",
       "      <td>1.819796</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>2.783269</td>\n",
       "      <td>2.108234</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>-0.004710</td>\n",
       "      <td>2.115809</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.068703</td>\n",
       "      <td>1.467082</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2.193544</td>\n",
       "      <td>2.041147</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3.337262</td>\n",
       "      <td>1.778743</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>-0.233613</td>\n",
       "      <td>2.250526</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.142650</td>\n",
       "      <td>1.996993</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1.748166</td>\n",
       "      <td>2.321381</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>2.760914</td>\n",
       "      <td>2.105326</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   x         A         B  trial\n",
       "0  0 -0.250173  1.576447      0\n",
       "1  1  1.061277  2.089403      0\n",
       "2  2  1.668585  1.485925      0\n",
       "3  3  2.769240  1.733016      0\n",
       "0  0  0.025520  1.886120      1\n",
       "1  1  1.267888  1.809673      1\n",
       "2  2  2.083532  1.878483      1\n",
       "3  3  2.870992  2.597568      1\n",
       "0  0  0.296073  1.694059      2\n",
       "1  1  1.188875  2.432131      2\n",
       "2  2  2.036837  1.819796      2\n",
       "3  3  2.783269  2.108234      2\n",
       "0  0 -0.004710  2.115809      3\n",
       "1  1  1.068703  1.467082      3\n",
       "2  2  2.193544  2.041147      3\n",
       "3  3  3.337262  1.778743      3\n",
       "0  0 -0.233613  2.250526      4\n",
       "1  1  1.142650  1.996993      4\n",
       "2  2  1.748166  2.321381      4\n",
       "3  3  2.760914  2.105326      4"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.concat(dfs)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>trial</th>\n",
       "      <th>x</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">0</th>\n",
       "      <th>0</th>\n",
       "      <td>-0.250173</td>\n",
       "      <td>1.576447</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.061277</td>\n",
       "      <td>2.089403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.668585</td>\n",
       "      <td>1.485925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.769240</td>\n",
       "      <td>1.733016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>0.025520</td>\n",
       "      <td>1.886120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.267888</td>\n",
       "      <td>1.809673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.083532</td>\n",
       "      <td>1.878483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.870992</td>\n",
       "      <td>2.597568</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">2</th>\n",
       "      <th>0</th>\n",
       "      <td>0.296073</td>\n",
       "      <td>1.694059</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.188875</td>\n",
       "      <td>2.432131</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.036837</td>\n",
       "      <td>1.819796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.783269</td>\n",
       "      <td>2.108234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">3</th>\n",
       "      <th>0</th>\n",
       "      <td>-0.004710</td>\n",
       "      <td>2.115809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.068703</td>\n",
       "      <td>1.467082</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.193544</td>\n",
       "      <td>2.041147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.337262</td>\n",
       "      <td>1.778743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">4</th>\n",
       "      <th>0</th>\n",
       "      <td>-0.233613</td>\n",
       "      <td>2.250526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.142650</td>\n",
       "      <td>1.996993</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.748166</td>\n",
       "      <td>2.321381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.760914</td>\n",
       "      <td>2.105326</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                A         B\n",
       "trial x                    \n",
       "0     0 -0.250173  1.576447\n",
       "      1  1.061277  2.089403\n",
       "      2  1.668585  1.485925\n",
       "      3  2.769240  1.733016\n",
       "1     0  0.025520  1.886120\n",
       "      1  1.267888  1.809673\n",
       "      2  2.083532  1.878483\n",
       "      3  2.870992  2.597568\n",
       "2     0  0.296073  1.694059\n",
       "      1  1.188875  2.432131\n",
       "      2  2.036837  1.819796\n",
       "      3  2.783269  2.108234\n",
       "3     0 -0.004710  2.115809\n",
       "      1  1.068703  1.467082\n",
       "      2  2.193544  2.041147\n",
       "      3  3.337262  1.778743\n",
       "4     0 -0.233613  2.250526\n",
       "      1  1.142650  1.996993\n",
       "      2  1.748166  2.321381\n",
       "      3  2.760914  2.105326"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.set_index([\"trial\", \"x\"])\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "trial  x\n",
       "0      0    0.663137\n",
       "       1    1.575340\n",
       "       2    1.577255\n",
       "       3    2.251128\n",
       "1      0    0.955820\n",
       "       1    1.538780\n",
       "       2    1.981007\n",
       "       3    2.734280\n",
       "2      0    0.995066\n",
       "       1    1.810503\n",
       "       2    1.928317\n",
       "       3    2.445751\n",
       "3      0    1.055549\n",
       "       1    1.267893\n",
       "       2    2.117345\n",
       "       3    2.558002\n",
       "4      0    1.008456\n",
       "       1    1.569822\n",
       "       2    2.034773\n",
       "       3    2.433120\n",
       "dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.mean(axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1.490742\n",
       "B    1.959393\n",
       "dtype: float64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.mean(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>x</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.033381</td>\n",
       "      <td>1.904592</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.145879</td>\n",
       "      <td>1.959057</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.946133</td>\n",
       "      <td>1.909347</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.904335</td>\n",
       "      <td>2.064577</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          A         B\n",
       "x                    \n",
       "0 -0.033381  1.904592\n",
       "1  1.145879  1.959057\n",
       "2  1.946133  1.909347\n",
       "3  2.904335  2.064577"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean = df.mean(level=1)\n",
    "mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>x</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.223564</td>\n",
       "      <td>0.281348</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.086398</td>\n",
       "      <td>0.355873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.226131</td>\n",
       "      <td>0.306350</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.245975</td>\n",
       "      <td>0.346150</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          A         B\n",
       "x                    \n",
       "0  0.223564  0.281348\n",
       "1  0.086398  0.355873\n",
       "2  0.226131  0.306350\n",
       "3  0.245975  0.346150"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "std = df.std(level=1)\n",
    "std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = None\n",
    "colors = [\"black\", \"gray\"]\n",
    "for col in reversed(df.columns):\n",
    "    ax = mean[col].plot.line(color=colors.pop(0), ax=ax)\n",
    "    plt.fill_between(mean.index, mean[col]-std[col], mean[col]+std[col],\n",
    "                     color='black', alpha=0.1)\n",
    "    \n",
    "ax.legend(frameon=False, ncol=2)\n",
    "ax.set_xlabel(\"x label here\")\n",
    "ax.set_ylabel(\"y label here\")\n",
    "ax.spines['right'].set_visible(False)\n",
    "ax.spines['top'].set_visible(False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}