exercises_solutions.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>.container { width:90% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Usual inputs\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import pylab as plt\n",
    "\n",
    "%matplotlib inline\n",
    "\n",
    "from IPython.display import Image, display\n",
    "\n",
    "#Make the notebook wider\n",
    "from IPython.core.display import display, HTML \n",
    "display(HTML(\"<style>.container { width:90% !important; }</style>\"))\n",
    "\n",
    "\n",
    "sns.set(font_scale=1.2)#make fonts 20% larger\n",
    "sns.set_style(\"whitegrid\")#white background\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# In class 0: Read and plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read file \"data/world_bank_data.tsv\" \n",
    "df = pd.read_csv(\"data/world_bank_data.tsv\",sep=\"\\t\")\n",
    "\n",
    "#Keep Italy and Sweden, and years 2005 and 2010 (more on this later in the day)\n",
    "df_subset = df.loc[(df[\"Country\"].isin([\"ES\",\"DE\"])) & (df[\"Year\"].isin([2005,2010]))]\n",
    "\n",
    "#Show the head (first 5 lines)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Create a scatter plot of green area vs co2_pc for teh dataframe df_subset with the following characteristix:\n",
    "#should be square (aspect=1)\n",
    "#4 inches of height\n",
    "#dots should be 100 points wide\n",
    "\n",
    "sns.relplot(x=\"GREEN_AREA_PC\", y=\"CO2_PC\",hue=\"Country\", data=df_subset, kind=\"scatter\", \n",
    "                aspect=1,height=4,s=100)\n",
    "\n",
    "#Make the x axis in log scale\n",
    "plt.xscale(\"log\")\n",
    "\n",
    "# Add better (more descriptive) lables\n",
    "plt.xlabel(\"Green area per capita\")\n",
    "plt.ylabel(\"CO2 per capita\")\n",
    "\n",
    "#Remove the vertical lines, keeping only the horizontal ones\n",
    "plt.gca().grid(axis='x') \n",
    "\n",
    "#Save the figure with the name \"figures/myexample.pdf\"\n",
    "plt.savefig(\"figures/myexample.pdf\") "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 1: CONCAT\n",
    "Concat df1 and df2"
   ]
  },
  {
   "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>year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2002</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count\n",
       "0  2001      2\n",
       "1  2002      3"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2003</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2004</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count\n",
       "0  2003      4\n",
       "1  2004      3"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2002</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2003</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2004</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count\n",
       "0  2001      2\n",
       "1  2002      3\n",
       "0  2003      4\n",
       "1  2004      3"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([[2001,2],[2002,3]],columns=[\"year\",\"count\"])\n",
    "df2 = pd.DataFrame([[2003,4],[2004,3]],columns=[\"year\",\"count\"])\n",
    "display(df1)\n",
    "display(df2)\n",
    "\n",
    "#Concat both files and shiw the resulting table\n",
    "df = pd.concat([df1,df2])\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 2: MERGE INNER (default)\n",
    "Inner (default) merge df1 and df2"
   ]
  },
  {
   "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>year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2002</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count\n",
       "0  2001      2\n",
       "1  2002      3"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>place</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>Mexico</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2003</td>\n",
       "      <td>China</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year   place\n",
       "0  2001  Mexico\n",
       "1  2003   China"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>count</th>\n",
       "      <th>place</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2</td>\n",
       "      <td>Mexico</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count   place\n",
       "0  2001      2  Mexico"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([[2001,2],[2002,3]],columns=[\"year\",\"count\"])\n",
    "df2 = pd.DataFrame([[2001,\"Mexico\"],[2003,\"China\"]],columns=[\"year\",\"place\"])\n",
    "display(df1)\n",
    "display(df2)\n",
    "\n",
    "#Inner merge both files and show the resulting table\n",
    "df = pd.merge(df1,df2) #on=\"year\" and how=\"inner\" are optional\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 3: MERGE OUTER \n",
    "Outer merge df1 and df2"
   ]
  },
  {
   "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>year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2002</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count\n",
       "0  2001      2\n",
       "1  2002      3"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>place</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>Mexico</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2003</td>\n",
       "      <td>China</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year   place\n",
       "0  2001  Mexico\n",
       "1  2003   China"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>year</th>\n",
       "      <th>count</th>\n",
       "      <th>place</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>2.0</td>\n",
       "      <td>Mexico</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2002</td>\n",
       "      <td>3.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2003</td>\n",
       "      <td>NaN</td>\n",
       "      <td>China</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year  count   place\n",
       "0  2001    2.0  Mexico\n",
       "1  2002    3.0     NaN\n",
       "2  2003    NaN   China"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([[2001,2],[2002,3]],columns=[\"year\",\"count\"])\n",
    "df2 = pd.DataFrame([[2001,\"Mexico\"],[2003,\"China\"]],columns=[\"year\",\"place\"])\n",
    "display(df1)\n",
    "display(df2)\n",
    "\n",
    "#Outer merge both files  and show the resulting table\n",
    "df = pd.merge(df1,df2,how=\"outer\")\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 4: MELT\n",
    "This dataset has variables in the column names, you'll need to melt it to have a nice, tidy dataset"
   ]
  },
  {
   "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>place</th>\n",
       "      <th>2000</th>\n",
       "      <th>2001</th>\n",
       "      <th>2002</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>China</td>\n",
       "      <td>22</td>\n",
       "      <td>12</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    place  2000  2001  2002\n",
       "0  Mexico     2     3     4\n",
       "1   China    22    12     3"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([[\"Mexico\",2,3,4],[\"China\",22,12,3]],columns=[\"place\",\"2000\",\"2001\",\"2002\"])\n",
    "df1\n"
   ]
  },
  {
   "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>place</th>\n",
       "      <th>Year</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>China</td>\n",
       "      <td>2000</td>\n",
       "      <td>22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2001</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>China</td>\n",
       "      <td>2001</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2002</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>China</td>\n",
       "      <td>2002</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    place  Year  count\n",
       "0  Mexico  2000      2\n",
       "1   China  2000     22\n",
       "2  Mexico  2001      3\n",
       "3   China  2001     12\n",
       "4  Mexico  2002      4\n",
       "5   China  2002      3"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Variables present in columns already\n",
    "variables_already_presents = [\"place\"]\n",
    "\n",
    "#Variables to combine in on\n",
    "columns_combine = [\"2000\",\"2001\",\"2002\"]\n",
    "\n",
    "#Fix\n",
    "melted_df1 = pd.melt(df1,id_vars=variables_already_presents,\n",
    "           value_vars=columns_combine,\n",
    "           var_name=\"Year\",\n",
    "           value_name=\"count\")\n",
    "\n",
    "#Convert the Year variable to numeric\n",
    "melted_df1[\"Year\"]  = melted_df1[\"Year\"].astype(int)\n",
    "\n",
    "#Print\n",
    "melted_df1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 5: PIVOT\n",
    "This dataset has several variables in one column, you'll need to pivot it to have a nice, tidy dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>place</th>\n",
       "      <th>year</th>\n",
       "      <th>variable</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>temperature</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2001</td>\n",
       "      <td>temperature</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2002</td>\n",
       "      <td>temperature</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>humidity</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>humidity</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>humidity</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    place  year     variable value\n",
       "0  Mexico  2000  temperature    25\n",
       "1  Mexico  2001  temperature    30\n",
       "2  Mexico  2002  temperature    35\n",
       "3  Mexico  2000     humidity    25\n",
       "4  Mexico  2000     humidity    25\n",
       "5  Mexico  2000     humidity    25"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame([[\"Mexico\",2000,\"temperature\",\"25\"],[\"Mexico\",2001,\"temperature\",\"30\"],[\"Mexico\",2002,\"temperature\",\"35\"],\n",
    "                    [\"Mexico\",2000,\"humidity\",\"25\"],[\"Mexico\",2000,\"humidity\",\"25\"],[\"Mexico\",2000,\"humidity\",\"25\"]],\n",
    "                   columns=[\"place\",\"year\",\"variable\",\"value\"])\n",
    "df1"
   ]
  },
  {
   "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>variable</th>\n",
       "      <th>place</th>\n",
       "      <th>year</th>\n",
       "      <th>humidity</th>\n",
       "      <th>temperature</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2000</td>\n",
       "      <td>25.0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2001</td>\n",
       "      <td>NaN</td>\n",
       "      <td>30.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>2002</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "variable   place  year  humidity  temperature\n",
       "0         Mexico  2000      25.0         25.0\n",
       "1         Mexico  2001       NaN         30.0\n",
       "2         Mexico  2002       NaN         35.0"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1[\"value\"] = df1[\"value\"].astype(int)\n",
    "\n",
    "#Columns already present\n",
    "variables_already_present = [\"place\",\"year\"]\n",
    "\n",
    "#Column with the variables\n",
    "column_to_split = [\"variable\"]\n",
    "\n",
    "#Column with the values\n",
    "column_with_values = \"value\"\n",
    "\n",
    "#Fix\n",
    "pivoted_df1 = df1.pivot_table(column_with_values,\n",
    "               variables_already_present,\n",
    "               column_to_split).reset_index()\n",
    "\n",
    "pivoted_df1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 6: SCATTER + logarithmic variables\n",
    "The file \"data/revenue_marketCap.csv\" has data on revenue and market capitalization for US publicly listed companies\n",
    "- Read the file\n",
    "- Plot the distributions of revenue and marketCap (sns.distplot())\n",
    "- Transform the variables (take the log10)\n",
    "- Fix the infinity values\n",
    "- Make a scatter plot of Revenue vs MarketCap by Exchange"
   ]
  },
  {
   "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>Revenue</th>\n",
       "      <th>MarketCap</th>\n",
       "      <th>Exchange</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7500000.0</td>\n",
       "      <td>13123024.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7500000.0</td>\n",
       "      <td>16739323.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>350000.0</td>\n",
       "      <td>43392.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>350000.0</td>\n",
       "      <td>26674.0</td>\n",
       "      <td>NASDAQ National Market</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>93750.0</td>\n",
       "      <td>48840.0</td>\n",
       "      <td>NASDAQ National Market</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Revenue   MarketCap                        Exchange\n",
       "0  7500000.0  13123024.0  New York Stock Exchange (NYSE)\n",
       "1  7500000.0  16739323.0  New York Stock Exchange (NYSE)\n",
       "2   350000.0     43392.0  New York Stock Exchange (NYSE)\n",
       "3   350000.0     26674.0          NASDAQ National Market\n",
       "4    93750.0     48840.0          NASDAQ National Market"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Read the file\n",
    "us_listed = pd.read_csv(\"./data/revenue_marketCap.csv\",sep=\"\\t\")\n",
    "us_listed.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frequency')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Plot the distributions of revenue and marketcap and label the plots\n",
    "#Take a look at http://seaborn.pydata.org/generated/seaborn.distplot.html\n",
    "sns.distplot(us_listed[\"Revenue\"])\n",
    "sns.distplot(us_listed[\"MarketCap\"])\n",
    "plt.xlabel(\"dollars\")\n",
    "plt.ylabel(\"Frequency\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.7/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log10\n",
      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n",
      "/opt/anaconda3/lib/python3.7/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: invalid value encountered in log10\n",
      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n"
     ]
    }
   ],
   "source": [
    "#TRansform both variables\n",
    "us_listed[\"log_Revenue\"] = np.log10(us_listed[\"Revenue\"])\n",
    "us_listed[\"log_MarketCap\"] = np.log10(us_listed[\"MarketCap\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Fix the infinity values\n",
    "us_listed = us_listed.replace([np.inf,-np.inf],np.nan)#log(0) = infinity, we're basically discarding the rows with 0 dollars\n",
    "us_listed = us_listed.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda/anaconda3/lib/python3.5/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n",
      "/opt/anaconda/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6499: MatplotlibDeprecationWarning: \n",
      "The 'normed' kwarg was deprecated in Matplotlib 2.1 and will be removed in 3.1. Use 'density' instead.\n",
      "  alternative=\"'density'\", removal=\"3.1\")\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frequency')"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Plot the distributions of revenue and marketcap and label the plots\n",
    "#Take a look at http://seaborn.pydata.org/generated/seaborn.distplot.html\n",
    "sns.distplot(us_listed[\"log_Revenue\"])\n",
    "sns.distplot(us_listed[\"log_MarketCap\"])\n",
    "plt.xlabel(\"dollars\")\n",
    "plt.ylabel(\"Frequency\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda/anaconda3/lib/python3.5/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f71d4882f98>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.regplot(x=\"log_Revenue\",y=\"log_MarketCap\",data=us_listed)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## In class 7: GROUPBY stock market exchange  and calculate descriptive statistics\n",
    "- Summary statisics (describe)\n",
    "- Correlation matrix (corr)\n",
    "- Median value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.7/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log10\n",
      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n",
      "/opt/anaconda3/lib/python3.7/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: invalid value encountered in log10\n",
      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n"
     ]
    },
    {
     "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>Revenue</th>\n",
       "      <th>MarketCap</th>\n",
       "      <th>Exchange</th>\n",
       "      <th>log_Revenue</th>\n",
       "      <th>log_MarketCap</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7500000.0</td>\n",
       "      <td>13123024.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "      <td>6.875061</td>\n",
       "      <td>7.118034</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7500000.0</td>\n",
       "      <td>16739323.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "      <td>6.875061</td>\n",
       "      <td>7.223738</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>350000.0</td>\n",
       "      <td>43392.0</td>\n",
       "      <td>New York Stock Exchange (NYSE)</td>\n",
       "      <td>5.544068</td>\n",
       "      <td>4.637410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>350000.0</td>\n",
       "      <td>26674.0</td>\n",
       "      <td>NASDAQ National Market</td>\n",
       "      <td>5.544068</td>\n",
       "      <td>4.426088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>93750.0</td>\n",
       "      <td>48840.0</td>\n",
       "      <td>NASDAQ National Market</td>\n",
       "      <td>4.971971</td>\n",
       "      <td>4.688776</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Revenue   MarketCap                        Exchange  log_Revenue  \\\n",
       "0  7500000.0  13123024.0  New York Stock Exchange (NYSE)     6.875061   \n",
       "1  7500000.0  16739323.0  New York Stock Exchange (NYSE)     6.875061   \n",
       "2   350000.0     43392.0  New York Stock Exchange (NYSE)     5.544068   \n",
       "3   350000.0     26674.0          NASDAQ National Market     5.544068   \n",
       "4    93750.0     48840.0          NASDAQ National Market     4.971971   \n",
       "\n",
       "   log_MarketCap  \n",
       "0       7.118034  \n",
       "1       7.223738  \n",
       "2       4.637410  \n",
       "3       4.426088  \n",
       "4       4.688776  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Read the file\n",
    "us_listed = pd.read_csv(\"./data/revenue_marketCap.csv\",sep=\"\\t\")\n",
    "#TRansform both variables\n",
    "us_listed[\"log_Revenue\"] = np.log10(us_listed[\"Revenue\"])\n",
    "us_listed[\"log_MarketCap\"] = np.log10(us_listed[\"MarketCap\"])\n",
    "us_listed.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">Revenue</th>\n",
       "      <th colspan=\"2\" halign=\"left\">MarketCap</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">log_Revenue</th>\n",
       "      <th colspan=\"8\" halign=\"left\">log_MarketCap</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exchange</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>NASDAQ National Market</th>\n",
       "      <td>2122.0</td>\n",
       "      <td>1.404546e+06</td>\n",
       "      <td>8.175416e+06</td>\n",
       "      <td>-37572.0</td>\n",
       "      <td>28950.75</td>\n",
       "      <td>139238.0</td>\n",
       "      <td>625615.0</td>\n",
       "      <td>233715000.0</td>\n",
       "      <td>2122.0</td>\n",
       "      <td>3.061470e+06</td>\n",
       "      <td>...</td>\n",
       "      <td>5.798579</td>\n",
       "      <td>8.368687</td>\n",
       "      <td>2122.0</td>\n",
       "      <td>-inf</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-inf</td>\n",
       "      <td>4.909845</td>\n",
       "      <td>5.463476</td>\n",
       "      <td>6.045597</td>\n",
       "      <td>8.740094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NASDAQ/NMS (Global Market)</th>\n",
       "      <td>1.0</td>\n",
       "      <td>7.813000e+03</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7813.0</td>\n",
       "      <td>7813.00</td>\n",
       "      <td>7813.0</td>\n",
       "      <td>7813.0</td>\n",
       "      <td>7813.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>...</td>\n",
       "      <td>3.892818</td>\n",
       "      <td>3.892818</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NYSE ARCA</th>\n",
       "      <td>1.0</td>\n",
       "      <td>6.576340e+05</td>\n",
       "      <td>NaN</td>\n",
       "      <td>657634.0</td>\n",
       "      <td>657634.00</td>\n",
       "      <td>657634.0</td>\n",
       "      <td>657634.0</td>\n",
       "      <td>657634.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.117250e+05</td>\n",
       "      <td>...</td>\n",
       "      <td>5.817984</td>\n",
       "      <td>5.817984</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.852312</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.852312</td>\n",
       "      <td>5.852312</td>\n",
       "      <td>5.852312</td>\n",
       "      <td>5.852312</td>\n",
       "      <td>5.852312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NYSE MKT</th>\n",
       "      <td>201.0</td>\n",
       "      <td>1.446127e+05</td>\n",
       "      <td>4.813782e+05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6164.00</td>\n",
       "      <td>26832.0</td>\n",
       "      <td>99121.0</td>\n",
       "      <td>5594000.0</td>\n",
       "      <td>201.0</td>\n",
       "      <td>2.211391e+05</td>\n",
       "      <td>...</td>\n",
       "      <td>4.996166</td>\n",
       "      <td>6.747722</td>\n",
       "      <td>201.0</td>\n",
       "      <td>4.722250</td>\n",
       "      <td>0.663085</td>\n",
       "      <td>3.024896</td>\n",
       "      <td>4.272491</td>\n",
       "      <td>4.647197</td>\n",
       "      <td>5.158456</td>\n",
       "      <td>6.887473</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>New York Stock Exchange (NYSE)</th>\n",
       "      <td>1512.0</td>\n",
       "      <td>6.809412e+06</td>\n",
       "      <td>2.124570e+07</td>\n",
       "      <td>0.0</td>\n",
       "      <td>535898.75</td>\n",
       "      <td>1638175.0</td>\n",
       "      <td>4930506.0</td>\n",
       "      <td>482130000.0</td>\n",
       "      <td>1512.0</td>\n",
       "      <td>1.007483e+07</td>\n",
       "      <td>...</td>\n",
       "      <td>6.692889</td>\n",
       "      <td>8.683164</td>\n",
       "      <td>1512.0</td>\n",
       "      <td>-inf</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-inf</td>\n",
       "      <td>5.871473</td>\n",
       "      <td>6.360792</td>\n",
       "      <td>6.864110</td>\n",
       "      <td>8.571984</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                               Revenue                                        \\\n",
       "                                 count          mean           std       min   \n",
       "Exchange                                                                       \n",
       "NASDAQ National Market          2122.0  1.404546e+06  8.175416e+06  -37572.0   \n",
       "NASDAQ/NMS (Global Market)         1.0  7.813000e+03           NaN    7813.0   \n",
       "NYSE ARCA                          1.0  6.576340e+05           NaN  657634.0   \n",
       "NYSE MKT                         201.0  1.446127e+05  4.813782e+05       0.0   \n",
       "New York Stock Exchange (NYSE)  1512.0  6.809412e+06  2.124570e+07       0.0   \n",
       "\n",
       "                                                                              \\\n",
       "                                      25%        50%        75%          max   \n",
       "Exchange                                                                       \n",
       "NASDAQ National Market           28950.75   139238.0   625615.0  233715000.0   \n",
       "NASDAQ/NMS (Global Market)        7813.00     7813.0     7813.0       7813.0   \n",
       "NYSE ARCA                       657634.00   657634.0   657634.0     657634.0   \n",
       "NYSE MKT                          6164.00    26832.0    99121.0    5594000.0   \n",
       "New York Stock Exchange (NYSE)  535898.75  1638175.0  4930506.0  482130000.0   \n",
       "\n",
       "                               MarketCap                ... log_Revenue  \\\n",
       "                                   count          mean  ...         75%   \n",
       "Exchange                                                ...               \n",
       "NASDAQ National Market            2122.0  3.061470e+06  ...    5.798579   \n",
       "NASDAQ/NMS (Global Market)           1.0  1.000000e+00  ...    3.892818   \n",
       "NYSE ARCA                            1.0  7.117250e+05  ...    5.817984   \n",
       "NYSE MKT                           201.0  2.211391e+05  ...    4.996166   \n",
       "New York Stock Exchange (NYSE)    1512.0  1.007483e+07  ...    6.692889   \n",
       "\n",
       "                                         log_MarketCap                      \\\n",
       "                                     max         count      mean       std   \n",
       "Exchange                                                                     \n",
       "NASDAQ National Market          8.368687        2122.0      -inf       NaN   \n",
       "NASDAQ/NMS (Global Market)      3.892818           1.0  0.000000       NaN   \n",
       "NYSE ARCA                       5.817984           1.0  5.852312       NaN   \n",
       "NYSE MKT                        6.747722         201.0  4.722250  0.663085   \n",
       "New York Stock Exchange (NYSE)  8.683164        1512.0      -inf       NaN   \n",
       "\n",
       "                                                                        \\\n",
       "                                     min       25%       50%       75%   \n",
       "Exchange                                                                 \n",
       "NASDAQ National Market              -inf  4.909845  5.463476  6.045597   \n",
       "NASDAQ/NMS (Global Market)      0.000000  0.000000  0.000000  0.000000   \n",
       "NYSE ARCA                       5.852312  5.852312  5.852312  5.852312   \n",
       "NYSE MKT                        3.024896  4.272491  4.647197  5.158456   \n",
       "New York Stock Exchange (NYSE)      -inf  5.871473  6.360792  6.864110   \n",
       "\n",
       "                                          \n",
       "                                     max  \n",
       "Exchange                                  \n",
       "NASDAQ National Market          8.740094  \n",
       "NASDAQ/NMS (Global Market)      0.000000  \n",
       "NYSE ARCA                       5.852312  \n",
       "NYSE MKT                        6.887473  \n",
       "New York Stock Exchange (NYSE)  8.571984  \n",
       "\n",
       "[5 rows x 32 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Groupby by \"Exchange\" and describe\n",
    "us_listed.groupby(\"Exchange\").describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>Revenue</th>\n",
       "      <th>MarketCap</th>\n",
       "      <th>log_Revenue</th>\n",
       "      <th>log_MarketCap</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exchange</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>NASDAQ National Market</th>\n",
       "      <td>139238.0</td>\n",
       "      <td>290721.0</td>\n",
       "      <td>5.155878</td>\n",
       "      <td>5.463476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NASDAQ/NMS (Global Market)</th>\n",
       "      <td>7813.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.892818</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NYSE ARCA</th>\n",
       "      <td>657634.0</td>\n",
       "      <td>711725.0</td>\n",
       "      <td>5.817984</td>\n",
       "      <td>5.852312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NYSE MKT</th>\n",
       "      <td>26832.0</td>\n",
       "      <td>44381.0</td>\n",
       "      <td>4.428653</td>\n",
       "      <td>4.647197</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>New York Stock Exchange (NYSE)</th>\n",
       "      <td>1638175.0</td>\n",
       "      <td>2295049.0</td>\n",
       "      <td>6.214360</td>\n",
       "      <td>6.360792</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  Revenue  MarketCap  log_Revenue  \\\n",
       "Exchange                                                            \n",
       "NASDAQ National Market           139238.0   290721.0     5.155878   \n",
       "NASDAQ/NMS (Global Market)         7813.0        1.0     3.892818   \n",
       "NYSE ARCA                        657634.0   711725.0     5.817984   \n",
       "NYSE MKT                          26832.0    44381.0     4.428653   \n",
       "New York Stock Exchange (NYSE)  1638175.0  2295049.0     6.214360   \n",
       "\n",
       "                                log_MarketCap  \n",
       "Exchange                                       \n",
       "NASDAQ National Market               5.463476  \n",
       "NASDAQ/NMS (Global Market)           0.000000  \n",
       "NYSE ARCA                            5.852312  \n",
       "NYSE MKT                             4.647197  \n",
       "New York Stock Exchange (NYSE)       6.360792  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Groupby by \"Exchange\" and get median\n",
    "us_listed.groupby(\"Exchange\").median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>Revenue</th>\n",
       "      <th>MarketCap</th>\n",
       "      <th>log_Revenue</th>\n",
       "      <th>log_MarketCap</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exchange</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">NASDAQ National Market</th>\n",
       "      <th>Revenue</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.830759</td>\n",
       "      <td>0.337475</td>\n",
       "      <td>0.345935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MarketCap</th>\n",
       "      <td>0.830759</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.279043</td>\n",
       "      <td>0.366109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_Revenue</th>\n",
       "      <td>0.337475</td>\n",
       "      <td>0.279043</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.696848</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_MarketCap</th>\n",
       "      <td>0.345935</td>\n",
       "      <td>0.366109</td>\n",
       "      <td>0.696848</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">NASDAQ/NMS (Global Market)</th>\n",
       "      <th>Revenue</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MarketCap</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_Revenue</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_MarketCap</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">NYSE ARCA</th>\n",
       "      <th>Revenue</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MarketCap</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_Revenue</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_MarketCap</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">NYSE MKT</th>\n",
       "      <th>Revenue</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.334245</td>\n",
       "      <td>0.478076</td>\n",
       "      <td>0.323326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MarketCap</th>\n",
       "      <td>0.334245</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.217016</td>\n",
       "      <td>0.597283</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_Revenue</th>\n",
       "      <td>0.478076</td>\n",
       "      <td>0.217016</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.331110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_MarketCap</th>\n",
       "      <td>0.323326</td>\n",
       "      <td>0.597283</td>\n",
       "      <td>0.331110</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">New York Stock Exchange (NYSE)</th>\n",
       "      <th>Revenue</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.685314</td>\n",
       "      <td>0.531785</td>\n",
       "      <td>0.437152</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MarketCap</th>\n",
       "      <td>0.685314</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.502688</td>\n",
       "      <td>0.582415</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_Revenue</th>\n",
       "      <td>0.531785</td>\n",
       "      <td>0.502688</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.750138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_MarketCap</th>\n",
       "      <td>0.437152</td>\n",
       "      <td>0.582415</td>\n",
       "      <td>0.750138</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               Revenue  MarketCap  \\\n",
       "Exchange                                                            \n",
       "NASDAQ National Market         Revenue        1.000000   0.830759   \n",
       "                               MarketCap      0.830759   1.000000   \n",
       "                               log_Revenue    0.337475   0.279043   \n",
       "                               log_MarketCap  0.345935   0.366109   \n",
       "NASDAQ/NMS (Global Market)     Revenue             NaN        NaN   \n",
       "                               MarketCap           NaN        NaN   \n",
       "                               log_Revenue         NaN        NaN   \n",
       "                               log_MarketCap       NaN        NaN   \n",
       "NYSE ARCA                      Revenue             NaN        NaN   \n",
       "                               MarketCap           NaN        NaN   \n",
       "                               log_Revenue         NaN        NaN   \n",
       "                               log_MarketCap       NaN        NaN   \n",
       "NYSE MKT                       Revenue        1.000000   0.334245   \n",
       "                               MarketCap      0.334245   1.000000   \n",
       "                               log_Revenue    0.478076   0.217016   \n",
       "                               log_MarketCap  0.323326   0.597283   \n",
       "New York Stock Exchange (NYSE) Revenue        1.000000   0.685314   \n",
       "                               MarketCap      0.685314   1.000000   \n",
       "                               log_Revenue    0.531785   0.502688   \n",
       "                               log_MarketCap  0.437152   0.582415   \n",
       "\n",
       "                                              log_Revenue  log_MarketCap  \n",
       "Exchange                                                                  \n",
       "NASDAQ National Market         Revenue           0.337475       0.345935  \n",
       "                               MarketCap         0.279043       0.366109  \n",
       "                               log_Revenue       1.000000       0.696848  \n",
       "                               log_MarketCap     0.696848       1.000000  \n",
       "NASDAQ/NMS (Global Market)     Revenue                NaN            NaN  \n",
       "                               MarketCap              NaN            NaN  \n",
       "                               log_Revenue            NaN            NaN  \n",
       "                               log_MarketCap          NaN            NaN  \n",
       "NYSE ARCA                      Revenue                NaN            NaN  \n",
       "                               MarketCap              NaN            NaN  \n",
       "                               log_Revenue            NaN            NaN  \n",
       "                               log_MarketCap          NaN            NaN  \n",
       "NYSE MKT                       Revenue           0.478076       0.323326  \n",
       "                               MarketCap         0.217016       0.597283  \n",
       "                               log_Revenue       1.000000       0.331110  \n",
       "                               log_MarketCap     0.331110       1.000000  \n",
       "New York Stock Exchange (NYSE) Revenue           0.531785       0.437152  \n",
       "                               MarketCap         0.502688       0.582415  \n",
       "                               log_Revenue       1.000000       0.750138  \n",
       "                               log_MarketCap     0.750138       1.000000  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Groupby by \"Exchange\" and get correlation matrixes\n",
    "us_listed.groupby(\"Exchange\").corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}