{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Reading Data into Pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# conventional way to import pandas\n",
    "import pandas as pd "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read CSV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read data from csv file \n",
    "corona = pd.read_csv(\"../data/covid-19_cleaned_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>Province/State</th>\n",
       "      <th>Country/Region</th>\n",
       "      <th>Lat</th>\n",
       "      <th>Long</th>\n",
       "      <th>Date</th>\n",
       "      <th>Confirmed</th>\n",
       "      <th>Deaths</th>\n",
       "      <th>Recovered</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>Thailand</td>\n",
       "      <td>Thailand</td>\n",
       "      <td>15.0000</td>\n",
       "      <td>101.0000</td>\n",
       "      <td>2020-01-22</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Japan</td>\n",
       "      <td>36.0000</td>\n",
       "      <td>138.0000</td>\n",
       "      <td>2020-01-22</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>Singapore</td>\n",
       "      <td>Singapore</td>\n",
       "      <td>1.2833</td>\n",
       "      <td>103.8333</td>\n",
       "      <td>2020-01-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>Nepal</td>\n",
       "      <td>Nepal</td>\n",
       "      <td>28.1667</td>\n",
       "      <td>84.2500</td>\n",
       "      <td>2020-01-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Malaysia</td>\n",
       "      <td>Malaysia</td>\n",
       "      <td>2.5000</td>\n",
       "      <td>112.5000</td>\n",
       "      <td>2020-01-22</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Province/State Country/Region      Lat      Long        Date  Confirmed  \\\n",
       "0       Thailand       Thailand  15.0000  101.0000  2020-01-22          2   \n",
       "1          Japan          Japan  36.0000  138.0000  2020-01-22          2   \n",
       "2      Singapore      Singapore   1.2833  103.8333  2020-01-22          0   \n",
       "3          Nepal          Nepal  28.1667   84.2500  2020-01-22          0   \n",
       "4       Malaysia       Malaysia   2.5000  112.5000  2020-01-22          0   \n",
       "\n",
       "   Deaths  Recovered  \n",
       "0       0          0  \n",
       "1       0          0  \n",
       "2       0          0  \n",
       "3       0          0  \n",
       "4       0          0  "
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Examine first few rows \n",
    "corona.head() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read Excel Sheet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read data from excel file \n",
    "movies = pd.read_excel(\"../data/movies.xls\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "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>Title</th>\n",
       "      <th>Year</th>\n",
       "      <th>Genres</th>\n",
       "      <th>Language</th>\n",
       "      <th>Country</th>\n",
       "      <th>Content Rating</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Aspect Ratio</th>\n",
       "      <th>Budget</th>\n",
       "      <th>Gross Earnings</th>\n",
       "      <th>...</th>\n",
       "      <th>Facebook Likes - Actor 1</th>\n",
       "      <th>Facebook Likes - Actor 2</th>\n",
       "      <th>Facebook Likes - Actor 3</th>\n",
       "      <th>Facebook Likes - cast Total</th>\n",
       "      <th>Facebook likes - Movie</th>\n",
       "      <th>Facenumber in posters</th>\n",
       "      <th>User Votes</th>\n",
       "      <th>Reviews by Users</th>\n",
       "      <th>Reviews by Crtiics</th>\n",
       "      <th>IMDB Score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>Intolerance: Love's Struggle Throughout the Ages</td>\n",
       "      <td>1916</td>\n",
       "      <td>Drama|History|War</td>\n",
       "      <td>NaN</td>\n",
       "      <td>USA</td>\n",
       "      <td>Not Rated</td>\n",
       "      <td>123</td>\n",
       "      <td>1.33</td>\n",
       "      <td>385907.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>436</td>\n",
       "      <td>22</td>\n",
       "      <td>9.0</td>\n",
       "      <td>481</td>\n",
       "      <td>691</td>\n",
       "      <td>1</td>\n",
       "      <td>10718</td>\n",
       "      <td>88</td>\n",
       "      <td>69.0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>Over the Hill to the Poorhouse</td>\n",
       "      <td>1920</td>\n",
       "      <td>Crime|Drama</td>\n",
       "      <td>NaN</td>\n",
       "      <td>USA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>110</td>\n",
       "      <td>1.33</td>\n",
       "      <td>100000.0</td>\n",
       "      <td>3000000.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>The Big Parade</td>\n",
       "      <td>1925</td>\n",
       "      <td>Drama|Romance|War</td>\n",
       "      <td>NaN</td>\n",
       "      <td>USA</td>\n",
       "      <td>Not Rated</td>\n",
       "      <td>151</td>\n",
       "      <td>1.33</td>\n",
       "      <td>245000.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>81</td>\n",
       "      <td>12</td>\n",
       "      <td>6.0</td>\n",
       "      <td>108</td>\n",
       "      <td>226</td>\n",
       "      <td>0</td>\n",
       "      <td>4849</td>\n",
       "      <td>45</td>\n",
       "      <td>48.0</td>\n",
       "      <td>8.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>Metropolis</td>\n",
       "      <td>1927</td>\n",
       "      <td>Drama|Sci-Fi</td>\n",
       "      <td>German</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Not Rated</td>\n",
       "      <td>145</td>\n",
       "      <td>1.33</td>\n",
       "      <td>6000000.0</td>\n",
       "      <td>26435.0</td>\n",
       "      <td>...</td>\n",
       "      <td>136</td>\n",
       "      <td>23</td>\n",
       "      <td>18.0</td>\n",
       "      <td>203</td>\n",
       "      <td>12000</td>\n",
       "      <td>1</td>\n",
       "      <td>111841</td>\n",
       "      <td>413</td>\n",
       "      <td>260.0</td>\n",
       "      <td>8.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Pandora's Box</td>\n",
       "      <td>1929</td>\n",
       "      <td>Crime|Drama|Romance</td>\n",
       "      <td>German</td>\n",
       "      <td>Germany</td>\n",
       "      <td>Not Rated</td>\n",
       "      <td>110</td>\n",
       "      <td>1.33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9950.0</td>\n",
       "      <td>...</td>\n",
       "      <td>426</td>\n",
       "      <td>20</td>\n",
       "      <td>3.0</td>\n",
       "      <td>455</td>\n",
       "      <td>926</td>\n",
       "      <td>1</td>\n",
       "      <td>7431</td>\n",
       "      <td>84</td>\n",
       "      <td>71.0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               Title  Year  \\\n",
       "0  Intolerance: Love's Struggle Throughout the Ages   1916   \n",
       "1                    Over the Hill to the Poorhouse   1920   \n",
       "2                                    The Big Parade   1925   \n",
       "3                                        Metropolis   1927   \n",
       "4                                     Pandora's Box   1929   \n",
       "\n",
       "                Genres Language  Country Content Rating  Duration  \\\n",
       "0    Drama|History|War      NaN      USA      Not Rated       123   \n",
       "1          Crime|Drama      NaN      USA            NaN       110   \n",
       "2    Drama|Romance|War      NaN      USA      Not Rated       151   \n",
       "3         Drama|Sci-Fi   German  Germany      Not Rated       145   \n",
       "4  Crime|Drama|Romance   German  Germany      Not Rated       110   \n",
       "\n",
       "   Aspect Ratio     Budget  Gross Earnings  ... Facebook Likes - Actor 1  \\\n",
       "0          1.33   385907.0             NaN  ...                      436   \n",
       "1          1.33   100000.0       3000000.0  ...                        2   \n",
       "2          1.33   245000.0             NaN  ...                       81   \n",
       "3          1.33  6000000.0         26435.0  ...                      136   \n",
       "4          1.33        NaN          9950.0  ...                      426   \n",
       "\n",
       "  Facebook Likes - Actor 2 Facebook Likes - Actor 3  \\\n",
       "0                       22                      9.0   \n",
       "1                        2                      0.0   \n",
       "2                       12                      6.0   \n",
       "3                       23                     18.0   \n",
       "4                       20                      3.0   \n",
       "\n",
       "  Facebook Likes - cast Total  Facebook likes - Movie  Facenumber in posters  \\\n",
       "0                         481                     691                      1   \n",
       "1                           4                       0                      1   \n",
       "2                         108                     226                      0   \n",
       "3                         203                   12000                      1   \n",
       "4                         455                     926                      1   \n",
       "\n",
       "   User Votes  Reviews by Users  Reviews by Crtiics  IMDB Score  \n",
       "0       10718                88                69.0         8.0  \n",
       "1           5                 1                 1.0         4.8  \n",
       "2        4849                45                48.0         8.3  \n",
       "3      111841               413               260.0         8.3  \n",
       "4        7431                84                71.0         8.0  \n",
       "\n",
       "[5 rows x 25 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine first few rows \n",
    "movies.head() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read Multiple Excel Sheets "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xlrd \n",
    "# Import xlsx file and store each sheet in to a df list\n",
    "xl_file = pd.ExcelFile(\"../data/data.xls\",)\n",
    "# Dictionary comprehension\n",
    "dfs = {sheet_name: xl_file.parse(sheet_name) for sheet_name in xl_file.sheet_names}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data from each sheet can be accessed via key\n",
    "keylist = list(dfs.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2020-03-13-03-30',\n",
       " '2020-03-13-00-00',\n",
       " '2020-03-12-22-00',\n",
       " '2020-03-12-21-30',\n",
       " '2020-03-12-21-00',\n",
       " '2020-03-12-20-00',\n",
       " '2020-03-12-18-30',\n",
       " '2020-03-12-17-00',\n",
       " '2020-03-12-15-30']"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Examine the sheet name \n",
    "keylist[1:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>Province/State</th>\n",
       "      <th>Country/Region</th>\n",
       "      <th>Last Update</th>\n",
       "      <th>Confirmed</th>\n",
       "      <th>Deaths</th>\n",
       "      <th>Recovered</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>Hubei</td>\n",
       "      <td>Mainland China</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>67786</td>\n",
       "      <td>3062</td>\n",
       "      <td>51553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>Guangdong</td>\n",
       "      <td>Mainland China</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1356</td>\n",
       "      <td>8</td>\n",
       "      <td>1296</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>Zhejiang</td>\n",
       "      <td>Mainland China</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1215</td>\n",
       "      <td>1</td>\n",
       "      <td>1209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>Shandong</td>\n",
       "      <td>Mainland China</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>760</td>\n",
       "      <td>7</td>\n",
       "      <td>739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Henan</td>\n",
       "      <td>Mainland China</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1273</td>\n",
       "      <td>22</td>\n",
       "      <td>1249</td>\n",
       "    </tr>\n",
       "    <tr>\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",
       "      <td>216</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mongolia</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>217</td>\n",
       "      <td>NaN</td>\n",
       "      <td>St. Barth</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>218</td>\n",
       "      <td>NaN</td>\n",
       "      <td>St. Vincent Grenadines</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>219</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Togo</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>220</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Trinidad and Tobago</td>\n",
       "      <td>3/13/2020 06:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>221 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Province/State          Country/Region      Last Update  Confirmed  \\\n",
       "0            Hubei          Mainland China  3/13/2020 06:00      67786   \n",
       "1        Guangdong          Mainland China  3/13/2020 06:00       1356   \n",
       "2         Zhejiang          Mainland China  3/13/2020 06:00       1215   \n",
       "3         Shandong          Mainland China  3/13/2020 06:00        760   \n",
       "4            Henan          Mainland China  3/13/2020 06:00       1273   \n",
       "..             ...                     ...              ...        ...   \n",
       "216            NaN                Mongolia  3/13/2020 06:00          1   \n",
       "217            NaN               St. Barth  3/13/2020 06:00          1   \n",
       "218            NaN  St. Vincent Grenadines  3/13/2020 06:00          1   \n",
       "219            NaN                    Togo  3/13/2020 06:00          1   \n",
       "220            NaN     Trinidad and Tobago  3/13/2020 06:00          1   \n",
       "\n",
       "     Deaths  Recovered  \n",
       "0      3062      51553  \n",
       "1         8       1296  \n",
       "2         1       1209  \n",
       "3         7        739  \n",
       "4        22       1249  \n",
       "..      ...        ...  \n",
       "216       0          0  \n",
       "217       0          0  \n",
       "218       0          0  \n",
       "219       0          0  \n",
       "220       0          0  \n",
       "\n",
       "[221 rows x 6 columns]"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Accessing first sheet\n",
    "dfs[keylist[0]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## From URL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read a dataset of Chipotle orders directly from a URL and store the results in a DataFrame \n",
    "orders = pd.read_table('http://bit.ly/chiporders')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>order_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>item_name</th>\n",
       "      <th>choice_description</th>\n",
       "      <th>item_price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips and Fresh Tomato Salsa</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$2.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Izze</td>\n",
       "      <td>[Clementine]</td>\n",
       "      <td>$3.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Nantucket Nectar</td>\n",
       "      <td>[Apple]</td>\n",
       "      <td>$3.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips and Tomatillo-Green Chili Salsa</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$2.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>Chicken Bowl</td>\n",
       "      <td>[Tomatillo-Red Chili Salsa (Hot), [Black Beans...</td>\n",
       "      <td>$16.98</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   order_id  quantity                              item_name  \\\n",
       "0         1         1           Chips and Fresh Tomato Salsa   \n",
       "1         1         1                                   Izze   \n",
       "2         1         1                       Nantucket Nectar   \n",
       "3         1         1  Chips and Tomatillo-Green Chili Salsa   \n",
       "4         2         2                           Chicken Bowl   \n",
       "\n",
       "                                  choice_description item_price  \n",
       "0                                                NaN     $2.39   \n",
       "1                                       [Clementine]     $3.39   \n",
       "2                                            [Apple]     $3.39   \n",
       "3                                                NaN     $2.39   \n",
       "4  [Tomatillo-Red Chili Salsa (Hot), [Black Beans...    $16.98   "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine the first 5 rows \n",
    "orders.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>order_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>item_name</th>\n",
       "      <th>choice_description</th>\n",
       "      <th>item_price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>4617</td>\n",
       "      <td>1833</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Black Beans, Sour ...</td>\n",
       "      <td>$11.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4618</td>\n",
       "      <td>1833</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Sour Cream, Cheese...</td>\n",
       "      <td>$11.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4619</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Pinto...</td>\n",
       "      <td>$11.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4620</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Lettu...</td>\n",
       "      <td>$8.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4621</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Pinto...</td>\n",
       "      <td>$8.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      order_id  quantity           item_name  \\\n",
       "4617      1833         1       Steak Burrito   \n",
       "4618      1833         1       Steak Burrito   \n",
       "4619      1834         1  Chicken Salad Bowl   \n",
       "4620      1834         1  Chicken Salad Bowl   \n",
       "4621      1834         1  Chicken Salad Bowl   \n",
       "\n",
       "                                     choice_description item_price  \n",
       "4617  [Fresh Tomato Salsa, [Rice, Black Beans, Sour ...    $11.75   \n",
       "4618  [Fresh Tomato Salsa, [Rice, Sour Cream, Cheese...    $11.75   \n",
       "4619  [Fresh Tomato Salsa, [Fajita Vegetables, Pinto...    $11.25   \n",
       "4620  [Fresh Tomato Salsa, [Fajita Vegetables, Lettu...     $8.75   \n",
       "4621  [Fresh Tomato Salsa, [Fajita Vegetables, Pinto...     $8.75   "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine the last 5 rows \n",
    "orders.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>order_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>item_name</th>\n",
       "      <th>choice_description</th>\n",
       "      <th>item_price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips and Fresh Tomato Salsa</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$2.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Izze</td>\n",
       "      <td>[Clementine]</td>\n",
       "      <td>$3.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Nantucket Nectar</td>\n",
       "      <td>[Apple]</td>\n",
       "      <td>$3.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips and Tomatillo-Green Chili Salsa</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$2.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>Chicken Bowl</td>\n",
       "      <td>[Tomatillo-Red Chili Salsa (Hot), [Black Beans...</td>\n",
       "      <td>$16.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa (Mild), [Rice, Cheese, Sou...</td>\n",
       "      <td>$10.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Side of Chips</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$1.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Tomatillo Red Chili Salsa, [Fajita Vegetables...</td>\n",
       "      <td>$11.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Soft Tacos</td>\n",
       "      <td>[Tomatillo Green Chili Salsa, [Pinto Beans, Ch...</td>\n",
       "      <td>$9.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Black Beans, Pinto...</td>\n",
       "      <td>$9.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   order_id  quantity                              item_name  \\\n",
       "0         1         1           Chips and Fresh Tomato Salsa   \n",
       "1         1         1                                   Izze   \n",
       "2         1         1                       Nantucket Nectar   \n",
       "3         1         1  Chips and Tomatillo-Green Chili Salsa   \n",
       "4         2         2                           Chicken Bowl   \n",
       "5         3         1                           Chicken Bowl   \n",
       "6         3         1                          Side of Chips   \n",
       "7         4         1                          Steak Burrito   \n",
       "8         4         1                       Steak Soft Tacos   \n",
       "9         5         1                          Steak Burrito   \n",
       "\n",
       "                                  choice_description item_price  \n",
       "0                                                NaN     $2.39   \n",
       "1                                       [Clementine]     $3.39   \n",
       "2                                            [Apple]     $3.39   \n",
       "3                                                NaN     $2.39   \n",
       "4  [Tomatillo-Red Chili Salsa (Hot), [Black Beans...    $16.98   \n",
       "5  [Fresh Tomato Salsa (Mild), [Rice, Cheese, Sou...    $10.98   \n",
       "6                                                NaN     $1.69   \n",
       "7  [Tomatillo Red Chili Salsa, [Fajita Vegetables...    $11.75   \n",
       "8  [Tomatillo Green Chili Salsa, [Pinto Beans, Ch...     $9.25   \n",
       "9  [Fresh Tomato Salsa, [Rice, Black Beans, Pinto...     $9.25   "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine the first `n` number of rows\n",
    "orders.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>order_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>item_name</th>\n",
       "      <th>choice_description</th>\n",
       "      <th>item_price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>4612</td>\n",
       "      <td>1831</td>\n",
       "      <td>1</td>\n",
       "      <td>Carnitas Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Rice,...</td>\n",
       "      <td>$9.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4613</td>\n",
       "      <td>1831</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$2.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4614</td>\n",
       "      <td>1831</td>\n",
       "      <td>1</td>\n",
       "      <td>Bottled Water</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$1.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4615</td>\n",
       "      <td>1832</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Soft Tacos</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Cheese, Sour Cream]]</td>\n",
       "      <td>$8.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4616</td>\n",
       "      <td>1832</td>\n",
       "      <td>1</td>\n",
       "      <td>Chips and Guacamole</td>\n",
       "      <td>NaN</td>\n",
       "      <td>$4.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4617</td>\n",
       "      <td>1833</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Black Beans, Sour ...</td>\n",
       "      <td>$11.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4618</td>\n",
       "      <td>1833</td>\n",
       "      <td>1</td>\n",
       "      <td>Steak Burrito</td>\n",
       "      <td>[Fresh Tomato Salsa, [Rice, Sour Cream, Cheese...</td>\n",
       "      <td>$11.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4619</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Pinto...</td>\n",
       "      <td>$11.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4620</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Lettu...</td>\n",
       "      <td>$8.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4621</td>\n",
       "      <td>1834</td>\n",
       "      <td>1</td>\n",
       "      <td>Chicken Salad Bowl</td>\n",
       "      <td>[Fresh Tomato Salsa, [Fajita Vegetables, Pinto...</td>\n",
       "      <td>$8.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      order_id  quantity            item_name  \\\n",
       "4612      1831         1        Carnitas Bowl   \n",
       "4613      1831         1                Chips   \n",
       "4614      1831         1        Bottled Water   \n",
       "4615      1832         1   Chicken Soft Tacos   \n",
       "4616      1832         1  Chips and Guacamole   \n",
       "4617      1833         1        Steak Burrito   \n",
       "4618      1833         1        Steak Burrito   \n",
       "4619      1834         1   Chicken Salad Bowl   \n",
       "4620      1834         1   Chicken Salad Bowl   \n",
       "4621      1834         1   Chicken Salad Bowl   \n",
       "\n",
       "                                     choice_description item_price  \n",
       "4612  [Fresh Tomato Salsa, [Fajita Vegetables, Rice,...     $9.25   \n",
       "4613                                                NaN     $2.15   \n",
       "4614                                                NaN     $1.50   \n",
       "4615   [Fresh Tomato Salsa, [Rice, Cheese, Sour Cream]]     $8.75   \n",
       "4616                                                NaN     $4.45   \n",
       "4617  [Fresh Tomato Salsa, [Rice, Black Beans, Sour ...    $11.75   \n",
       "4618  [Fresh Tomato Salsa, [Rice, Sour Cream, Cheese...    $11.75   \n",
       "4619  [Fresh Tomato Salsa, [Fajita Vegetables, Pinto...    $11.25   \n",
       "4620  [Fresh Tomato Salsa, [Fajita Vegetables, Lettu...     $8.75   \n",
       "4621  [Fresh Tomato Salsa, [Fajita Vegetables, Pinto...     $8.75   "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine the last `n` number of rows\n",
    "orders.tail(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modify Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read a dataset of movie reviewers (modifying the default parameter values for read_table)\n",
    "users = pd.read_table('http://bit.ly//movieusers')"
   ]
  },
  {
   "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>1|24|M|technician|85711</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2|53|F|other|94043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>3|23|M|writer|32067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>4|24|M|technician|43537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>5|33|F|other|15213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>6|42|M|executive|98101</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   1|24|M|technician|85711\n",
       "0       2|53|F|other|94043\n",
       "1      3|23|M|writer|32067\n",
       "2  4|24|M|technician|43537\n",
       "3       5|33|F|other|15213\n",
       "4   6|42|M|executive|98101"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine the first 5 rows \n",
    "users.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# DataFrame looks ugly. let's modify the default parameter for read_table \n",
    "user_cols = ['user_id', 'age', 'gender', 'occupation', 'zip_code']\n",
    "users = pd.read_table('http://bit.ly//movieusers', sep='|' , header=None, names=user_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>occupation</th>\n",
       "      <th>zip_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>M</td>\n",
       "      <td>technician</td>\n",
       "      <td>85711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>53</td>\n",
       "      <td>F</td>\n",
       "      <td>other</td>\n",
       "      <td>94043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>23</td>\n",
       "      <td>M</td>\n",
       "      <td>writer</td>\n",
       "      <td>32067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>24</td>\n",
       "      <td>M</td>\n",
       "      <td>technician</td>\n",
       "      <td>43537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>33</td>\n",
       "      <td>F</td>\n",
       "      <td>other</td>\n",
       "      <td>15213</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   user_id  age gender  occupation zip_code\n",
       "0        1   24      M  technician    85711\n",
       "1        2   53      F       other    94043\n",
       "2        3   23      M      writer    32067\n",
       "3        4   24      M  technician    43537\n",
       "4        5   33      F       other    15213"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# now take a look at modified dataset\n",
    "users.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read Biological Data(.txt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read text/csv data into pandas \n",
    "chrom = pd.read_csv(\"../data/Encode_HMM_data.txt\", delimiter=\"\\t\", header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>chr1</td>\n",
       "      <td>10000</td>\n",
       "      <td>10600</td>\n",
       "      <td>15_Repetitive/CNV</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>10000</td>\n",
       "      <td>10600</td>\n",
       "      <td>245,245,245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>chr1</td>\n",
       "      <td>10600</td>\n",
       "      <td>11137</td>\n",
       "      <td>13_Heterochrom/lo</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>10600</td>\n",
       "      <td>11137</td>\n",
       "      <td>245,245,245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>chr1</td>\n",
       "      <td>11137</td>\n",
       "      <td>11737</td>\n",
       "      <td>8_Insulator</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11137</td>\n",
       "      <td>11737</td>\n",
       "      <td>10,190,254</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>chr1</td>\n",
       "      <td>11737</td>\n",
       "      <td>11937</td>\n",
       "      <td>11_Weak_Txn</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11737</td>\n",
       "      <td>11937</td>\n",
       "      <td>153,255,102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>chr1</td>\n",
       "      <td>11937</td>\n",
       "      <td>12137</td>\n",
       "      <td>7_Weak_Enhancer</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11937</td>\n",
       "      <td>12137</td>\n",
       "      <td>255,252,4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      0      1      2                  3  4  5      6      7            8\n",
       "0  chr1  10000  10600  15_Repetitive/CNV  0  .  10000  10600  245,245,245\n",
       "1  chr1  10600  11137  13_Heterochrom/lo  0  .  10600  11137  245,245,245\n",
       "2  chr1  11137  11737        8_Insulator  0  .  11137  11737   10,190,254\n",
       "3  chr1  11737  11937        11_Weak_Txn  0  .  11737  11937  153,255,102\n",
       "4  chr1  11937  12137    7_Weak_Enhancer  0  .  11937  12137    255,252,4"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Examine first few rows \n",
    "chrom.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# it's not much better to see. so we have to modify this dataset\n",
    "cols_name = ['chrom', 'start', 'stop', 'type']\n",
    "chrom = pd.read_csv(\"../data/Encode_HMM_data.txt\", delimiter=\"\\t\", header=None, names=cols_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>chrom</th>\n",
       "      <th>start</th>\n",
       "      <th>stop</th>\n",
       "      <th>type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td rowspan=\"5\" valign=\"top\">chr1</td>\n",
       "      <td>10000</td>\n",
       "      <td>10600</td>\n",
       "      <td>15_Repetitive/CNV</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>10000</td>\n",
       "      <td>10600</td>\n",
       "      <td>245,245,245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10600</td>\n",
       "      <td>11137</td>\n",
       "      <td>13_Heterochrom/lo</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>10600</td>\n",
       "      <td>11137</td>\n",
       "      <td>245,245,245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11137</td>\n",
       "      <td>11737</td>\n",
       "      <td>8_Insulator</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11137</td>\n",
       "      <td>11737</td>\n",
       "      <td>10,190,254</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11737</td>\n",
       "      <td>11937</td>\n",
       "      <td>11_Weak_Txn</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11737</td>\n",
       "      <td>11937</td>\n",
       "      <td>153,255,102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11937</td>\n",
       "      <td>12137</td>\n",
       "      <td>7_Weak_Enhancer</td>\n",
       "      <td>0</td>\n",
       "      <td>.</td>\n",
       "      <td>11937</td>\n",
       "      <td>12137</td>\n",
       "      <td>255,252,4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     chrom  start   stop         type\n",
       "chr1 10000 10600 15_Repetitive/CNV 0     .  10000  10600  245,245,245\n",
       "     10600 11137 13_Heterochrom/lo 0     .  10600  11137  245,245,245\n",
       "     11137 11737 8_Insulator       0     .  11137  11737   10,190,254\n",
       "     11737 11937 11_Weak_Txn       0     .  11737  11937  153,255,102\n",
       "     11937 12137 7_Weak_Enhancer   0     .  11937  12137    255,252,4"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# now examine first few rows \n",
    "chrom.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read Biological Data(.tsv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "pokemon = pd.read_csv(\"../data/pokemon.tsv\", sep=\"\\t\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "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>Number</th>\n",
       "      <th>Name</th>\n",
       "      <th>Type_1</th>\n",
       "      <th>Type_2</th>\n",
       "      <th>Total</th>\n",
       "      <th>HP</th>\n",
       "      <th>Attack</th>\n",
       "      <th>Defense</th>\n",
       "      <th>Sp_Atk</th>\n",
       "      <th>Sp_Def</th>\n",
       "      <th>...</th>\n",
       "      <th>Color</th>\n",
       "      <th>hasGender</th>\n",
       "      <th>Pr_Male</th>\n",
       "      <th>Egg_Group_1</th>\n",
       "      <th>Egg_Group_2</th>\n",
       "      <th>hasMegaEvolution</th>\n",
       "      <th>Height_m</th>\n",
       "      <th>Weight_kg</th>\n",
       "      <th>Catch_Rate</th>\n",
       "      <th>Body_Style</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Bulbasaur</td>\n",
       "      <td>Grass</td>\n",
       "      <td>Poison</td>\n",
       "      <td>318</td>\n",
       "      <td>45</td>\n",
       "      <td>49</td>\n",
       "      <td>49</td>\n",
       "      <td>65</td>\n",
       "      <td>65</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>True</td>\n",
       "      <td>0.875</td>\n",
       "      <td>Monster</td>\n",
       "      <td>Grass</td>\n",
       "      <td>False</td>\n",
       "      <td>0.71</td>\n",
       "      <td>6.9</td>\n",
       "      <td>45</td>\n",
       "      <td>quadruped</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Ivysaur</td>\n",
       "      <td>Grass</td>\n",
       "      <td>Poison</td>\n",
       "      <td>405</td>\n",
       "      <td>60</td>\n",
       "      <td>62</td>\n",
       "      <td>63</td>\n",
       "      <td>80</td>\n",
       "      <td>80</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>True</td>\n",
       "      <td>0.875</td>\n",
       "      <td>Monster</td>\n",
       "      <td>Grass</td>\n",
       "      <td>False</td>\n",
       "      <td>0.99</td>\n",
       "      <td>13.0</td>\n",
       "      <td>45</td>\n",
       "      <td>quadruped</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>Venusaur</td>\n",
       "      <td>Grass</td>\n",
       "      <td>Poison</td>\n",
       "      <td>525</td>\n",
       "      <td>80</td>\n",
       "      <td>82</td>\n",
       "      <td>83</td>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>True</td>\n",
       "      <td>0.875</td>\n",
       "      <td>Monster</td>\n",
       "      <td>Grass</td>\n",
       "      <td>True</td>\n",
       "      <td>2.01</td>\n",
       "      <td>100.0</td>\n",
       "      <td>45</td>\n",
       "      <td>quadruped</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>Charmander</td>\n",
       "      <td>Fire</td>\n",
       "      <td>NaN</td>\n",
       "      <td>309</td>\n",
       "      <td>39</td>\n",
       "      <td>52</td>\n",
       "      <td>43</td>\n",
       "      <td>60</td>\n",
       "      <td>50</td>\n",
       "      <td>...</td>\n",
       "      <td>Red</td>\n",
       "      <td>True</td>\n",
       "      <td>0.875</td>\n",
       "      <td>Monster</td>\n",
       "      <td>Dragon</td>\n",
       "      <td>False</td>\n",
       "      <td>0.61</td>\n",
       "      <td>8.5</td>\n",
       "      <td>45</td>\n",
       "      <td>bipedal_tailed</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>Charmeleon</td>\n",
       "      <td>Fire</td>\n",
       "      <td>NaN</td>\n",
       "      <td>405</td>\n",
       "      <td>58</td>\n",
       "      <td>64</td>\n",
       "      <td>58</td>\n",
       "      <td>80</td>\n",
       "      <td>65</td>\n",
       "      <td>...</td>\n",
       "      <td>Red</td>\n",
       "      <td>True</td>\n",
       "      <td>0.875</td>\n",
       "      <td>Monster</td>\n",
       "      <td>Dragon</td>\n",
       "      <td>False</td>\n",
       "      <td>1.09</td>\n",
       "      <td>19.0</td>\n",
       "      <td>45</td>\n",
       "      <td>bipedal_tailed</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Number        Name Type_1  Type_2  Total  HP  Attack  Defense  Sp_Atk  \\\n",
       "0       1   Bulbasaur  Grass  Poison    318  45      49       49      65   \n",
       "1       2     Ivysaur  Grass  Poison    405  60      62       63      80   \n",
       "2       3    Venusaur  Grass  Poison    525  80      82       83     100   \n",
       "3       4  Charmander   Fire     NaN    309  39      52       43      60   \n",
       "4       5  Charmeleon   Fire     NaN    405  58      64       58      80   \n",
       "\n",
       "   Sp_Def  ...  Color  hasGender  Pr_Male Egg_Group_1  Egg_Group_2  \\\n",
       "0      65  ...  Green       True    0.875     Monster        Grass   \n",
       "1      80  ...  Green       True    0.875     Monster        Grass   \n",
       "2     100  ...  Green       True    0.875     Monster        Grass   \n",
       "3      50  ...    Red       True    0.875     Monster       Dragon   \n",
       "4      65  ...    Red       True    0.875     Monster       Dragon   \n",
       "\n",
       "   hasMegaEvolution Height_m Weight_kg  Catch_Rate      Body_Style  \n",
       "0             False     0.71       6.9          45       quadruped  \n",
       "1             False     0.99      13.0          45       quadruped  \n",
       "2              True     2.01     100.0          45       quadruped  \n",
       "3             False     0.61       8.5          45  bipedal_tailed  \n",
       "4             False     1.09      19.0          45  bipedal_tailed  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pokemon.head() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read HTML Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read HTML data from web \n",
    "url = 'https://www.fdic.gov/bank/individual/failed/banklist.html'\n",
    "data = pd.io.html.read_html(url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "list"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check type \n",
    "type(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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>Bank Name</th>\n",
       "      <th>City</th>\n",
       "      <th>ST</th>\n",
       "      <th>CERT</th>\n",
       "      <th>Acquiring Institution</th>\n",
       "      <th>Closing Date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>The First State Bank</td>\n",
       "      <td>Barboursville</td>\n",
       "      <td>WV</td>\n",
       "      <td>14361</td>\n",
       "      <td>MVB Bank, Inc.</td>\n",
       "      <td>April 3, 2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>Ericson State Bank</td>\n",
       "      <td>Ericson</td>\n",
       "      <td>NE</td>\n",
       "      <td>18265</td>\n",
       "      <td>Farmers and Merchants Bank</td>\n",
       "      <td>February 14, 2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>City National Bank of New Jersey</td>\n",
       "      <td>Newark</td>\n",
       "      <td>NJ</td>\n",
       "      <td>21111</td>\n",
       "      <td>Industrial Bank</td>\n",
       "      <td>November 1, 2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>Resolute Bank</td>\n",
       "      <td>Maumee</td>\n",
       "      <td>OH</td>\n",
       "      <td>58317</td>\n",
       "      <td>Buckeye State Bank</td>\n",
       "      <td>October 25, 2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Louisa Community Bank</td>\n",
       "      <td>Louisa</td>\n",
       "      <td>KY</td>\n",
       "      <td>58112</td>\n",
       "      <td>Kentucky Farmers Bank Corporation</td>\n",
       "      <td>October 25, 2019</td>\n",
       "    </tr>\n",
       "    <tr>\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",
       "      <td>556</td>\n",
       "      <td>Superior Bank, FSB</td>\n",
       "      <td>Hinsdale</td>\n",
       "      <td>IL</td>\n",
       "      <td>32646</td>\n",
       "      <td>Superior Federal, FSB</td>\n",
       "      <td>July 27, 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>557</td>\n",
       "      <td>Malta National Bank</td>\n",
       "      <td>Malta</td>\n",
       "      <td>OH</td>\n",
       "      <td>6629</td>\n",
       "      <td>North Valley Bank</td>\n",
       "      <td>May 3, 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>558</td>\n",
       "      <td>First Alliance Bank &amp; Trust Co.</td>\n",
       "      <td>Manchester</td>\n",
       "      <td>NH</td>\n",
       "      <td>34264</td>\n",
       "      <td>Southern New Hampshire Bank &amp; Trust</td>\n",
       "      <td>February 2, 2001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>559</td>\n",
       "      <td>National State Bank of Metropolis</td>\n",
       "      <td>Metropolis</td>\n",
       "      <td>IL</td>\n",
       "      <td>3815</td>\n",
       "      <td>Banterra Bank of Marion</td>\n",
       "      <td>December 14, 2000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>560</td>\n",
       "      <td>Bank of Honolulu</td>\n",
       "      <td>Honolulu</td>\n",
       "      <td>HI</td>\n",
       "      <td>21029</td>\n",
       "      <td>Bank of the Orient</td>\n",
       "      <td>October 13, 2000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>561 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                             Bank Name           City  ST   CERT  \\\n",
       "0                 The First State Bank  Barboursville  WV  14361   \n",
       "1                   Ericson State Bank        Ericson  NE  18265   \n",
       "2     City National Bank of New Jersey         Newark  NJ  21111   \n",
       "3                        Resolute Bank         Maumee  OH  58317   \n",
       "4                Louisa Community Bank         Louisa  KY  58112   \n",
       "..                                 ...            ...  ..    ...   \n",
       "556                 Superior Bank, FSB       Hinsdale  IL  32646   \n",
       "557                Malta National Bank          Malta  OH   6629   \n",
       "558    First Alliance Bank & Trust Co.     Manchester  NH  34264   \n",
       "559  National State Bank of Metropolis     Metropolis  IL   3815   \n",
       "560                   Bank of Honolulu       Honolulu  HI  21029   \n",
       "\n",
       "                   Acquiring Institution       Closing Date  \n",
       "0                         MVB Bank, Inc.      April 3, 2020  \n",
       "1             Farmers and Merchants Bank  February 14, 2020  \n",
       "2                        Industrial Bank   November 1, 2019  \n",
       "3                     Buckeye State Bank   October 25, 2019  \n",
       "4      Kentucky Farmers Bank Corporation   October 25, 2019  \n",
       "..                                   ...                ...  \n",
       "556                Superior Federal, FSB      July 27, 2001  \n",
       "557                    North Valley Bank        May 3, 2001  \n",
       "558  Southern New Hampshire Bank & Trust   February 2, 2001  \n",
       "559              Banterra Bank of Marion  December 14, 2000  \n",
       "560                   Bank of the Orient   October 13, 2000  \n",
       "\n",
       "[561 rows x 6 columns]"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# access data \n",
    "data[0]"
   ]
  }
 ],
 "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": "3.7.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}