{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cEr06C20L8WK"
   },
   "source": [
    "# Introduction to Python  \n",
    "\n",
    "## Pandas Intro\n",
    "\n",
    "Some examples from [here](https://towardsdatascience.com/40-examples-to-master-pandas-c69d058f434e)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "WmxnkxF8L8WL"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "Vv-0YZfBL8WP"
   },
   "outputs": [],
   "source": [
    "datapath = \"../Data/\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "1F6OvLAcL8WR"
   },
   "source": [
    "## Pandas Data Structures: [Series](https://pandas.pydata.org/pandas-docs/stable/reference/series.html)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "JryIewnkL8WS",
    "outputId": "a06421dc-4c4a-4ebc-ac41-dc3e87eebed3"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     4\n",
       "1    12\n",
       "2    -5\n",
       "3     3\n",
       "4     5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj = pd.Series([4, 12, -5, 3, 5])\n",
    "obj"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "#dir(obj)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exporting to Numpy array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "r9li9Ii-L8WU",
    "outputId": "e63fde87-980d-4b2b-b26e-bfb3c1acaf59"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 4, 12, -5,  3,  5])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj.values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Examining the index object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "wjI6Wts0L8WX",
    "outputId": "c4980045-c9b8-4a0b-bc85-a87dd7d99e39"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RangeIndex(start=0, stop=5, step=1)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj.index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Redefining the index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "yHqJC6b8L8WZ",
    "outputId": "a9373822-231c-4c2d-9241-9a4c6edb0cd1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Bob        4\n",
       "Steve     12\n",
       "Jeff      -5\n",
       "Ryan       3\n",
       "Fernie     5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj.index = ['Bob', 'Steve', 'Jeff', 'Ryan', 'Fernie']\n",
    "obj"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating series and passing the inidex as parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "jI-k8rRGL8Wc",
    "outputId": "4f37ef09-5899-486c-fdbe-b80cf2663242"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "d    4\n",
       "b    7\n",
       "a   -5\n",
       "c    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj2 = pd.Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])\n",
    "obj2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Slicing and accessing elements in the series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj2['c']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "u8e_SNzcL8Wj",
    "outputId": "4ddd882c-d8bc-4d21-ff39-66e76ba47e4b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "c    3\n",
       "a   -5\n",
       "d    4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj2[['c', 'a', 'd']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Slicing using boolean expressions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "2Q-BkxadL8Wm",
    "outputId": "15badfe1-934c-4b24-a151-247bcd4971e1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   -5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj2[obj2 < 0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Scalar operations with the series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "LhjvPFD8L8Wo",
    "outputId": "b37a6c1f-5a8f-46bc-cdab-0e3faaba1bfa"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "d     8\n",
       "b    14\n",
       "a   -10\n",
       "c     6\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj2 * 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "51z3zmZYL8Ws",
    "outputId": "12b72973-26a1-450f-952d-f27c5d1c11dc"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "d      54.598150\n",
       "b    1096.633158\n",
       "a       0.006738\n",
       "c      20.085537\n",
       "dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.exp(obj2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating Series from dictionaries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "CoqYtDi2L8Wu",
    "outputId": "81291bfc-271b-4c77-eacd-406338fd1e88"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Ohio      35000\n",
       "Texas     71000\n",
       "Oregon    16000\n",
       "Utah       5000\n",
       "dtype: int64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}\n",
    "obj3 = pd.Series(sdata)\n",
    "obj3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "U3ldGKqTL8Wx",
    "outputId": "eb244782-419e-44e8-f216-1a000c3779d7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California        NaN\n",
       "Ohio          35000.0\n",
       "Oregon        16000.0\n",
       "Texas         71000.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "states = ['California', 'Ohio', 'Oregon', 'Texas']\n",
    "\n",
    "obj4 = pd.Series(sdata, index=states)\n",
    "obj4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "isnull() and notnull() methods"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "FGYJqsm8L8Wz",
    "outputId": "a45c5aa6-a07e-449b-e416-1fd7138006b2"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California     True\n",
       "Ohio          False\n",
       "Oregon        False\n",
       "Texas         False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(obj4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "RZrJBBM-L8W2",
    "outputId": "08a78774-20bb-473e-ba38-3c68b1a3db98"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California    False\n",
       "Ohio           True\n",
       "Oregon         True\n",
       "Texas          True\n",
       "dtype: bool"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.notnull(obj4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "id": "6pWvwb46L8W8",
    "outputId": "5471c51a-de44-4e99-d746-e88aa00d4a28"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California         NaN\n",
       "Ohio           70000.0\n",
       "Oregon         32000.0\n",
       "Texas         142000.0\n",
       "Utah            5010.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj3.add(obj4, fill_value=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "id": "d6_O2TahL8W-",
    "outputId": "cbc3d183-f1dd-4f76-dac8-9a635910bc09"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "State\n",
       "California        NaN\n",
       "Ohio          35000.0\n",
       "Oregon        16000.0\n",
       "Texas         71000.0\n",
       "Name: Population, dtype: float64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obj4.name = 'Population'\n",
    "obj4.index.name = 'State'\n",
    "obj4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pandas Data Structures: [Date Time Range](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.date_range.html)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Specify start and end, with the default daily frequency."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2018-01-01', '2018-01-02', '2018-01-03', '2018-01-04',\n",
       "               '2018-01-05', '2018-01-06', '2018-01-07', '2018-01-08'],\n",
       "              dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts_idx1 = pd.date_range(start='1/1/2018', end='1/08/2018')\n",
    "ts_idx1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Specify start and periods, the number of periods (days)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2016-01-01', '2016-01-02', '2016-01-03', '2016-01-04',\n",
       "               '2016-01-05', '2016-01-06', '2016-01-07', '2016-01-08',\n",
       "               '2016-01-09', '2016-01-10'],\n",
       "              dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts_idx2 = pd.date_range(\"20160101\", periods=10, freq='D')\n",
    "ts_idx2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Specify end and periods, the number of periods (days)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2017-12-25', '2017-12-26', '2017-12-27', '2017-12-28',\n",
       "               '2017-12-29', '2017-12-30', '2017-12-31', '2018-01-01'],\n",
       "              dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts_idx3 = pd.date_range(end='1/1/2018', periods=8)\n",
    "ts_idx3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Specify start, end, and periods; the frequency is generated automatically (linearly spaced)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2018-04-24 00:00:00', '2018-04-25 12:00:00',\n",
       "               '2018-04-27 00:00:00'],\n",
       "              dtype='datetime64[ns]', freq=None)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts_idx4 = pd.date_range(start='2018-04-24', end='2018-04-27', periods=3)\n",
    "ts_idx4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2018-01-31', '2018-02-28', '2018-03-31', '2018-04-30',\n",
       "               '2018-05-31'],\n",
       "              dtype='datetime64[ns]', freq='M')"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='1/1/2018', periods=5, freq='M')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2018-01-31', '2018-04-30', '2018-07-31', '2018-10-31',\n",
       "               '2019-01-31'],\n",
       "              dtype='datetime64[ns]', freq='3M')"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='1/1/2018', periods=5, freq='3M')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2018-01-01 00:00:00+00:00', '2018-01-02 00:00:00+00:00',\n",
       "               '2018-01-03 00:00:00+00:00', '2018-01-04 00:00:00+00:00',\n",
       "               '2018-01-05 00:00:00+00:00'],\n",
       "              dtype='datetime64[ns, Europe/Lisbon]', freq='D')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='1/1/2018', periods=5, tz='Europe/Lisbon')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04'], dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='2017-01-01', end='2017-01-04', inclusive=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03'], dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='2017-01-01', end='2017-01-04', inclusive='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2017-01-02', '2017-01-03', '2017-01-04'], dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.date_range(start='2017-01-01', end='2017-01-04', inclusive='right')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "VSkGDQr5L8XA"
   },
   "source": [
    "## Pandas Data Structures: [Dataframe](https://pandas.pydata.org/pandas-docs/stable/reference/frame.html)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating Dataframe from a dictionary of lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "JJBQnbqDL8XA",
    "outputId": "7b6e7083-65ae-471f-ac54-1e19dd42f896"
   },
   "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>state</th>\n",
       "      <th>year</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>2000</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>2001</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>2002</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2001</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2002</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    state  year  pop\n",
       "0    Ohio  2000  1.5\n",
       "1    Ohio  2001  1.7\n",
       "2    Ohio  2002  3.6\n",
       "3  Nevada  2001  2.4\n",
       "4  Nevada  2002  2.9"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],\n",
    "        'year': [2000, 2001, 2002, 2001, 2002],\n",
    "        'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}\n",
    "\n",
    "frame = pd.DataFrame(data)\n",
    "frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "#dir(frame)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n"
     ]
    }
   ],
   "source": [
    "print(type(frame))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n"
     ]
    }
   ],
   "source": [
    "print(type(frame['state']))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Specifying the names of columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "GlmmkIaQL8XC",
    "outputId": "fccf280c-9a02-4bf1-f9ec-70e022c6d442"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year   state  pop\n",
       "0  2000    Ohio  1.5\n",
       "1  2001    Ohio  1.7\n",
       "2  2002    Ohio  3.6\n",
       "3  2001  Nevada  2.4\n",
       "4  2002  Nevada  2.9"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = pd.DataFrame(data, columns=['year', 'state', 'pop'])\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Making a column as the index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "id": "dHHFSDK5L8XE"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      year   state  pop\n",
       "year                   \n",
       "2000  2000    Ohio  1.5\n",
       "2001  2001    Ohio  1.7\n",
       "2002  2002    Ohio  3.6\n",
       "2001  2001  Nevada  2.4\n",
       "2002  2002  Nevada  2.9"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.set_index('year', inplace=True, drop=False)\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dropping a column"
   ]
  },
  {
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2000    Ohio  1.5\n",
       "2001    Ohio  1.7\n",
       "2002    Ohio  3.6\n",
       "2001  Nevada  2.4\n",
       "2002  Nevada  2.9"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.drop('year', axis=1, inplace=True)\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dropping one or some lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "id": "_m00ehvGL8XH",
    "outputId": "a292d2bf-dcf5-4fb5-ced4-60b34cd172d4"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2000    Ohio  1.5\n",
       "2001    Ohio  1.7\n",
       "2002    Ohio  3.6\n",
       "2001  Nevada  2.4\n",
       "2002  Nevada  2.9"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.drop(2000, axis=0, inplace=False)\n",
    "d"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "id": "AdSUXcgwL8XJ",
    "outputId": "6b161b59-0870-4cb0-cee9-e533d51b65df"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2001    Ohio  1.7\n",
       "2002    Ohio  3.6\n",
       "2001  Nevada  2.4\n",
       "2002  Nevada  2.9"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.drop(2000, axis=0, inplace=True)\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Slicing by column / index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year\n",
       "2001    1.7\n",
       "2002    3.6\n",
       "2001    2.4\n",
       "2002    2.9\n",
       "Name: pop, dtype: float64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d['pop']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year\n",
       "2001    1.7\n",
       "2002    3.6\n",
       "2001    2.4\n",
       "2002    2.9\n",
       "Name: pop, dtype: float64"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.loc[:,'pop']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2001    Ohio  1.7\n",
       "2001  Nevada  2.4"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.loc[2001]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2001    Ohio  1.7\n",
       "2001  Nevada  2.4\n",
       "2002    Ohio  3.6\n",
       "2002  Nevada  2.9"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.loc[[2001,2002], [\"state\", \"pop\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      pop\n",
       "year     \n",
       "2001  1.7\n",
       "2002  3.6"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.iloc[[0,1],[1]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2001    Ohio  1.7\n",
       "2002    Ohio  3.6\n",
       "2001  Nevada  2.4"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.iloc[0:3,[0,1]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Accessing index and columns objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([2001, 2002, 2001, 2002], dtype='int64', name='year')"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "id": "1bEokh0LL8XZ",
    "outputId": "fcba92bf-2184-4542-80d3-457b1ee8b365"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['state', 'pop'], dtype='object')"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using alternate notation to access columns as a property"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "id": "6ehEuDNOL8Xb",
    "outputId": "98660696-6174-4d3c-8084-ff3c967af7c4"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year\n",
       "2001      Ohio\n",
       "2002      Ohio\n",
       "2001    Nevada\n",
       "2002    Nevada\n",
       "Name: state, dtype: object"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d['state']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "id": "8fwIym5IL8Xe",
    "outputId": "77ca9eb7-91d7-49f9-9c8a-b13b625c6dc2"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year\n",
       "2001      Ohio\n",
       "2002      Ohio\n",
       "2001    Nevada\n",
       "2002    Nevada\n",
       "Name: state, dtype: object"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d.state"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Slicing with boolean conditions (&, |, ==, !=)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       state  pop\n",
       "year             \n",
       "2001    Ohio  1.7\n",
       "2002    Ohio  3.6\n",
       "2001  Nevada  2.4"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = d[(d[\"state\"] != 'Nevada') | (d.index != 2002)]\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating Dataframes from existing structures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "id": "pHmbuPv5L8XK",
    "outputId": "9dbd2851-aae4-46e0-8571-02b02ab410b2"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop debt\n",
       "one    2000    Ohio  1.5  NaN\n",
       "two    2001    Ohio  1.7  NaN\n",
       "three  2002    Ohio  3.6  NaN\n",
       "four   2001  Nevada  2.4  NaN\n",
       "five   2002  Nevada  2.9  NaN"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2 = pd.DataFrame(data, \n",
    "                      columns=['year', 'state', 'pop', 'debt'],\n",
    "                      index=['one', 'two', 'three', 'four', 'five'])\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating new column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "id": "dUocNBSbL8XN",
    "outputId": "abe4c48e-142a-4162-fde8-b4db4b63b3e6"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "      <th>new</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop debt  new\n",
       "one    2000    Ohio  1.5  NaN   13\n",
       "two    2001    Ohio  1.7  NaN   13\n",
       "three  2002    Ohio  3.6  NaN   13\n",
       "four   2001  Nevada  2.4  NaN   13\n",
       "five   2002  Nevada  2.9  NaN   13"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2['new'] = 13\n",
    "frame2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "id": "-jAr37_vL8XT",
    "outputId": "ac4f4191-3cfb-46f9-b2ac-0c0e2de61805"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year     2002\n",
       "state    Ohio\n",
       "pop       3.6\n",
       "debt      NaN\n",
       "new        13\n",
       "Name: three, dtype: object"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2.loc['three']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.6"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2.loc['three', 'pop']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "id": "thLPV8M9L8XV",
    "outputId": "a87def93-007b-475b-9277-3fa007e792ac"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year     2002\n",
       "state    Ohio\n",
       "pop       3.6\n",
       "debt      NaN\n",
       "new        13\n",
       "Name: three, dtype: object"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2.iloc[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Ohio'"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2.iloc[2,1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "id": "oriaA7V8L8Xx",
    "outputId": "a23d458f-b216-4a7f-f0ae-d68d0cdaffc3"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2000     NaN   1.5"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop = {'Nevada': {2001: 2.4, 2002: 2.9},'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}\n",
    "\n",
    "frame3 = pd.DataFrame(pop)\n",
    "frame3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "id": "1IznlSKvL8Xi",
    "outputId": "69d179ef-9fd5-4653-df34-5ca596eab8ed"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "      <th>new</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>16.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>16.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>16.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>16.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>16.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt  new\n",
       "one    2000    Ohio  1.5  16.5   13\n",
       "two    2001    Ohio  1.7  16.5   13\n",
       "three  2002    Ohio  3.6  16.5   13\n",
       "four   2001  Nevada  2.4  16.5   13\n",
       "five   2002  Nevada  2.9  16.5   13"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2['debt'] = 16.5\n",
    "frame2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "id": "V3opjIPvL8Xk",
    "outputId": "e45c75dd-9c6a-4240-ceca-0185f443f86a"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "      <th>new</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>1.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>2.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>3.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>4.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt  new\n",
       "one    2000    Ohio  1.5   0.0   13\n",
       "two    2001    Ohio  1.7   1.0   13\n",
       "three  2002    Ohio  3.6   2.0   13\n",
       "four   2001  Nevada  2.4   3.0   13\n",
       "five   2002  Nevada  2.9   4.0   13"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2['debt'] = np.arange(5.)\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating a column from a series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "id": "xmPu8JO7L8Xm",
    "outputId": "f74a2fa9-c4fe-4f8b-9d11-abcc4215743a"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "      <th>new</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>-1.2</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>-1.5</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>-1.7</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt  new\n",
       "one    2000    Ohio  1.5   NaN   13\n",
       "two    2001    Ohio  1.7  -1.2   13\n",
       "three  2002    Ohio  3.6   NaN   13\n",
       "four   2001  Nevada  2.4  -1.5   13\n",
       "five   2002  Nevada  2.9  -1.7   13"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val = pd.Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])\n",
    "\n",
    "frame2['debt'] = val\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating a column from a bolean expression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "id": "B9qiCoeqL8Xo",
    "outputId": "9def766d-748d-4a61-e232-49518874f7a8"
   },
   "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>state</th>\n",
       "      <th>pop</th>\n",
       "      <th>debt</th>\n",
       "      <th>new</th>\n",
       "      <th>eastern</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>one</th>\n",
       "      <td>2000</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>-1.2</td>\n",
       "      <td>13</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>NaN</td>\n",
       "      <td>13</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>-1.5</td>\n",
       "      <td>13</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>-1.7</td>\n",
       "      <td>13</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt  new  eastern\n",
       "one    2000    Ohio  1.5   NaN   13     True\n",
       "two    2001    Ohio  1.7  -1.2   13     True\n",
       "three  2002    Ohio  3.6   NaN   13     True\n",
       "four   2001  Nevada  2.4  -1.5   13    False\n",
       "five   2002  Nevada  2.9  -1.7   13    False"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2['eastern'] = frame2.state == 'Ohio'\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Deleting a column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "id": "Pstsb7rTL8Xq",
    "outputId": "6ba15086-1cd2-49d3-a2fa-507418b722f8"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['year', 'state', 'pop', 'debt', 'new'], dtype='object')"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "del frame2['eastern']\n",
    "frame2.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "id": "7CTgyP5bL8X7",
    "outputId": "bcf2e719-8dc6-43e3-bc11-7448dbf2a7ff"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2003</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2003     NaN   NaN"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(pop, index=[2001, 2002, 2003])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "id": "I9IZWJZML8X_",
    "outputId": "7d04cda7-166f-4273-9b75-e59cdee02ab5"
   },
   "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>Ohio</th>\n",
       "      <th>Nevada</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>1.7</td>\n",
       "      <td>2.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>3.6</td>\n",
       "      <td>2.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Ohio  Nevada\n",
       "2001   1.7     2.4\n",
       "2002   3.6     2.9"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pdata = {'Ohio': frame3['Ohio'][:-1],'Nevada': frame3['Nevada'][:2]}\n",
    "pd.DataFrame(pdata)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "id": "Rz0Y8hCkL8YB",
    "outputId": "aaeed6d6-1d33-4056-ebc8-738053b44311"
   },
   "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>state</th>\n",
       "      <th>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "state  Nevada  Ohio\n",
       "year               \n",
       "2001      2.4   1.7\n",
       "2002      2.9   3.6\n",
       "2000      NaN   1.5"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame3.index.name = 'year'\n",
    "frame3.columns.name = 'state'\n",
    "frame3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "id": "1TFUFB4AL8YE",
    "outputId": "b673bbd5-fc17-4807-f52d-2fa781fc79fe"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2000     NaN   1.5"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pop = {'Nevada': {2001: 2.4, 2002: 2.9},'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}\n",
    "frame4 = pd.DataFrame(pop)\n",
    "frame4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "id": "zJWgEm7zL8YF",
    "outputId": "8260ccc7-6032-4f1d-fec2-b49f22c237d1"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>2.0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2000     2.0   1.5"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame4.loc[2000,'Nevada'] = 2\n",
    "frame4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "id": "iZToNmINL8YH",
    "outputId": "326e15ae-2fee-4666-d8cd-4f6290342429"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>2.0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>2.0</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2000     2.0   1.5\n",
       "2001     2.4  32.0\n",
       "2002     2.9  32.0\n",
       "2000     2.0  32.0"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame5 = pd.concat([frame4, frame4], axis=0)\n",
    "frame5.iloc[3:,1] = 32\n",
    "frame5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "id": "eVth2N0_L8YJ",
    "outputId": "0bd36e9c-581c-4bab-9141-4a5fa558124f"
   },
   "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>Nevada</th>\n",
       "      <th>Ohio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2001</th>\n",
       "      <td>2.4</td>\n",
       "      <td>1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002</th>\n",
       "      <td>2.9</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000</th>\n",
       "      <td>2.0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Nevada  Ohio\n",
       "2001     2.4   1.7\n",
       "2002     2.9   3.6\n",
       "2000     2.0   1.5"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame5.drop_duplicates(['Nevada'], inplace=True)\n",
    "frame5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2016-01-01', '2016-01-02', '2016-01-03', '2016-01-04',\n",
       "               '2016-01-05', '2016-01-06', '2016-01-07', '2016-01-08',\n",
       "               '2016-01-09', '2016-01-10'],\n",
       "              dtype='datetime64[ns]', freq='D')"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dates = pd.date_range(\"20160101\", periods=10, freq='D')\n",
    "dates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "id": "pCUFSR3ML8YL"
   },
   "outputs": [],
   "source": [
    "data = np.random.random((10,3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {
    "id": "eX-2uqSsL8YR",
    "outputId": "e69d1950-84f6-455d-fbe2-0df36edb29b1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.3940105 , 0.16598653, 0.32306814],\n",
       "       [0.46469848, 0.12793369, 0.23421117],\n",
       "       [0.58451733, 0.82838421, 0.74140121],\n",
       "       [0.51013677, 0.9891163 , 0.91843721],\n",
       "       [0.37910817, 0.34414402, 0.3448779 ],\n",
       "       [0.9496902 , 0.27825066, 0.21221705],\n",
       "       [0.06240444, 0.77187425, 0.06477811],\n",
       "       [0.13257664, 0.70945323, 0.09441618],\n",
       "       [0.0072288 , 0.83029155, 0.15235712],\n",
       "       [0.1302358 , 0.72444933, 0.67439275]])"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "id": "SvDpOoEYL8YV",
    "outputId": "49779dd1-3142-4e38-c0ca-187e32d59929"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.394010</td>\n",
       "      <td>0.165987</td>\n",
       "      <td>0.323068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.278251</td>\n",
       "      <td>0.212217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>0.132577</td>\n",
       "      <td>0.709453</td>\n",
       "      <td>0.094416</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.830292</td>\n",
       "      <td>0.152357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.130236</td>\n",
       "      <td>0.724449</td>\n",
       "      <td>0.674393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-01  0.394010  0.165987  0.323068\n",
       "2016-01-02  0.464698  0.127934  0.234211\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-05  0.379108  0.344144  0.344878\n",
       "2016-01-06  0.949690  0.278251  0.212217\n",
       "2016-01-07  0.062404  0.771874  0.064778\n",
       "2016-01-08  0.132577  0.709453  0.094416\n",
       "2016-01-09  0.007229  0.830292  0.152357\n",
       "2016-01-10  0.130236  0.724449  0.674393"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "column_names = ['Column1', 'Column2', 'Column3']\n",
    "df = pd.DataFrame(data, index=dates, columns=column_names)\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "id": "zFJZeaMQL8Ya",
    "outputId": "92460c5c-a8dc-4b5f-fe1c-52133be01365"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-02  0.464698  0.127934  0.234211\n",
       "2016-01-03  0.584517  0.828384  0.741401"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[1:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "id": "45hwfY72L8Yc",
    "outputId": "8b30a088-d247-459c-ed20-cedb12c99326"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.278251</td>\n",
       "      <td>0.212217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-05  0.379108  0.344144  0.344878\n",
       "2016-01-06  0.949690  0.278251  0.212217\n",
       "2016-01-07  0.062404  0.771874  0.064778"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['20160104':'20160107']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2016-01-01    0.165987\n",
       "2016-01-02    0.127934\n",
       "2016-01-03    0.828384\n",
       "2016-01-04    0.989116\n",
       "2016-01-05    0.344144\n",
       "2016-01-06    0.278251\n",
       "2016-01-07    0.771874\n",
       "2016-01-08    0.709453\n",
       "2016-01-09    0.830292\n",
       "2016-01-10    0.724449\n",
       "Freq: D, Name: Column2, dtype: float64"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['2016-01-01':'2016-01-11','Column2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "id": "QsuCiRzuL8YX",
    "outputId": "b1f271e6-7e4e-4b99-ae8a-d25405d48145"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2016-01-01    0.165987\n",
       "2016-01-02    0.127934\n",
       "2016-01-03    0.828384\n",
       "2016-01-04    0.989116\n",
       "2016-01-05    0.344144\n",
       "2016-01-06    0.278251\n",
       "2016-01-07    0.771874\n",
       "2016-01-08    0.709453\n",
       "2016-01-09    0.830292\n",
       "2016-01-10    0.724449\n",
       "Freq: D, Name: Column2, dtype: float64"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.iloc[0:11,1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {
    "id": "v9yt82jyL8Yf",
    "outputId": "6a0feefb-a6cb-407c-c5cb-591b584dee94"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-05  0.379108  0.344144  0.344878"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df.index > '20160102') & (df.index < '20160106')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "id": "LFGw7iv4L8Yh",
    "outputId": "5f27335e-8e65-4758-82a2-2c0462b4ed70"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.830292</td>\n",
       "      <td>0.152357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.130236</td>\n",
       "      <td>0.724449</td>\n",
       "      <td>0.674393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-07  0.062404  0.771874  0.064778\n",
       "2016-01-09  0.007229  0.830292  0.152357\n",
       "2016-01-10  0.130236  0.724449  0.674393"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.query('(Column1 < Column2) & (Column1 < Column3)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {
    "id": "WMF0I3X5L8Yi",
    "outputId": "162717d9-1062-467b-d09f-9c6e9f024822"
   },
   "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>Column1</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.394010</td>\n",
       "      <td>0.323068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column3\n",
       "2016-01-01  0.394010  0.323068\n",
       "2016-01-02  0.464698  0.234211"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['20160101':'20160102',['Column1','Column3']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {
    "id": "gjt7LI1IL8Yn",
    "outputId": "db9bf1ca-30db-4d4c-f8a6-0ceca7ceec2c"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2\n",
       "2016-01-04  0.510137  0.989116\n",
       "2016-01-05  0.379108  0.344144"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.iloc[3:5, 0:2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {
    "id": "xOOyyU33L8Yl",
    "outputId": "cebf0c4c-8046-461b-aa71-b9f39d3eff3b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 10 entries, 2016-01-01 to 2016-01-10\n",
      "Freq: D\n",
      "Data columns (total 3 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   Column1  10 non-null     float64\n",
      " 1   Column2  10 non-null     float64\n",
      " 2   Column3  10 non-null     float64\n",
      "dtypes: float64(3)\n",
      "memory usage: 620.0 bytes\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {
    "id": "p7yej71hL8Yr",
    "outputId": "35a5cfd0-eecf-4111-d6fc-7fe57058567c"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.361461</td>\n",
       "      <td>0.576988</td>\n",
       "      <td>0.376016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.288804</td>\n",
       "      <td>0.314204</td>\n",
       "      <td>0.296958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.130821</td>\n",
       "      <td>0.294724</td>\n",
       "      <td>0.167322</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.386559</td>\n",
       "      <td>0.716951</td>\n",
       "      <td>0.278640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.498777</td>\n",
       "      <td>0.814257</td>\n",
       "      <td>0.592014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Column1    Column2    Column3\n",
       "count  10.000000  10.000000  10.000000\n",
       "mean    0.361461   0.576988   0.376016\n",
       "std     0.288804   0.314204   0.296958\n",
       "min     0.007229   0.127934   0.064778\n",
       "25%     0.130821   0.294724   0.167322\n",
       "50%     0.386559   0.716951   0.278640\n",
       "75%     0.498777   0.814257   0.592014\n",
       "max     0.949690   0.989116   0.918437"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {
    "id": "F5Dk5Je-L8Yv",
    "outputId": "bbdc29a5-2759-4558-c686-d963066a8ca2"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.394010</td>\n",
       "      <td>0.165987</td>\n",
       "      <td>0.323068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.278251</td>\n",
       "      <td>0.212217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>0.132577</td>\n",
       "      <td>0.709453</td>\n",
       "      <td>0.094416</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.830292</td>\n",
       "      <td>0.152357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.130236</td>\n",
       "      <td>0.724449</td>\n",
       "      <td>0.674393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-01  0.394010  0.165987  0.323068\n",
       "2016-01-02  0.464698  0.127934  0.234211\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-05  0.379108  0.344144  0.344878\n",
       "2016-01-06  0.949690  0.278251  0.212217\n",
       "2016-01-07  0.062404  0.771874  0.064778\n",
       "2016-01-08  0.132577  0.709453  0.094416\n",
       "2016-01-09  0.007229  0.830292  0.152357\n",
       "2016-01-10  0.130236  0.724449  0.674393"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sort_index(axis=0, ascending=True,) # inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {
    "id": "ZdzzGZMpL8Yw",
    "outputId": "92c40e02-85a3-4d56-fcb6-e939500c43fa"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.394010</td>\n",
       "      <td>0.165987</td>\n",
       "      <td>0.323068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.278251</td>\n",
       "      <td>0.212217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>0.132577</td>\n",
       "      <td>0.709453</td>\n",
       "      <td>0.094416</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.830292</td>\n",
       "      <td>0.152357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.130236</td>\n",
       "      <td>0.724449</td>\n",
       "      <td>0.674393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-01  0.394010  0.165987  0.323068\n",
       "2016-01-02  0.464698  0.127934  0.234211\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-04  0.510137  0.989116  0.918437\n",
       "2016-01-05  0.379108  0.344144  0.344878\n",
       "2016-01-06  0.949690  0.278251  0.212217\n",
       "2016-01-07  0.062404  0.771874  0.064778\n",
       "2016-01-08  0.132577  0.709453  0.094416\n",
       "2016-01-09  0.007229  0.830292  0.152357\n",
       "2016-01-10  0.130236  0.724449  0.674393"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[sorted(df.columns)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {
    "id": "5RW7CbCQL8Yz",
    "outputId": "0383cf8f-2de9-4239-a48b-dac3a105f9be"
   },
   "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>Column1</th>\n",
       "      <th>Column2</th>\n",
       "      <th>Column3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.464698</td>\n",
       "      <td>0.127934</td>\n",
       "      <td>0.234211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.394010</td>\n",
       "      <td>0.165987</td>\n",
       "      <td>0.323068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.278251</td>\n",
       "      <td>0.212217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.379108</td>\n",
       "      <td>0.344144</td>\n",
       "      <td>0.344878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>0.132577</td>\n",
       "      <td>0.709453</td>\n",
       "      <td>0.094416</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.130236</td>\n",
       "      <td>0.724449</td>\n",
       "      <td>0.674393</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.062404</td>\n",
       "      <td>0.771874</td>\n",
       "      <td>0.064778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.584517</td>\n",
       "      <td>0.828384</td>\n",
       "      <td>0.741401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.007229</td>\n",
       "      <td>0.830292</td>\n",
       "      <td>0.152357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.510137</td>\n",
       "      <td>0.989116</td>\n",
       "      <td>0.918437</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Column1   Column2   Column3\n",
       "2016-01-02  0.464698  0.127934  0.234211\n",
       "2016-01-01  0.394010  0.165987  0.323068\n",
       "2016-01-06  0.949690  0.278251  0.212217\n",
       "2016-01-05  0.379108  0.344144  0.344878\n",
       "2016-01-08  0.132577  0.709453  0.094416\n",
       "2016-01-10  0.130236  0.724449  0.674393\n",
       "2016-01-07  0.062404  0.771874  0.064778\n",
       "2016-01-03  0.584517  0.828384  0.741401\n",
       "2016-01-09  0.007229  0.830292  0.152357\n",
       "2016-01-04  0.510137  0.989116  0.918437"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sort_values(by='Column2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {
    "id": "yGX8iYskL8Y2"
   },
   "outputs": [],
   "source": [
    "dates1 = pd.date_range(\"20160101\", periods=6)\n",
    "data1 = np.random.random((6,2))\n",
    "column_names1 = ['ColumnA', 'ColumnB']\n",
    "\n",
    "dates2 = pd.date_range(\"20160104\", periods=7)\n",
    "data2 = np.random.random((7,2))\n",
    "column_names2 = ['ColumnC', 'ColumnD']\n",
    "\n",
    "df1 = pd.DataFrame(data1, index=dates1, columns=column_names1)\n",
    "df2 = pd.DataFrame(data2, index=dates2, columns=column_names2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {
    "id": "FdexPwrQL8Y4",
    "outputId": "ae9b61a2-4a09-4696-c0b9-9ad2479682ad"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB\n",
       "2016-01-01  0.961191  0.214906\n",
       "2016-01-02  0.562981  0.602063\n",
       "2016-01-03  0.583841  0.367577\n",
       "2016-01-04  0.562917  0.712821\n",
       "2016-01-05  0.794997  0.518708\n",
       "2016-01-06  0.946344  0.972193"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {
    "id": "yOJ_bMBRL8Y5",
    "outputId": "b14eb2f3-19d9-4698-c924-cfde04f2bc18"
   },
   "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>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>0.427601</td>\n",
       "      <td>0.153653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>0.945375</td>\n",
       "      <td>0.084841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>0.630937</td>\n",
       "      <td>0.256707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>0.017057</td>\n",
       "      <td>0.316170</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnC   ColumnD\n",
       "2016-01-04  0.017940  0.876961\n",
       "2016-01-05  0.309962  0.768632\n",
       "2016-01-06  0.273469  0.435210\n",
       "2016-01-07  0.427601  0.153653\n",
       "2016-01-08  0.945375  0.084841\n",
       "2016-01-09  0.630937  0.256707\n",
       "2016-01-10  0.017057  0.316170"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {
    "id": "jymASUXyL8Y6",
    "outputId": "73ca0b63-be54-4ddd-9597-01dcc5e0b216"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD\n",
       "2016-01-01  0.961191  0.214906       NaN       NaN\n",
       "2016-01-02  0.562981  0.602063       NaN       NaN\n",
       "2016-01-03  0.583841  0.367577       NaN       NaN\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.join.html\n",
    "df1.join(df2, how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {
    "id": "dwi5DcXdL8Y-",
    "outputId": "fb77c0dc-4b65-492a-95c8-c5685982c1b9"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.427601</td>\n",
       "      <td>0.153653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.945375</td>\n",
       "      <td>0.084841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.630937</td>\n",
       "      <td>0.256707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.017057</td>\n",
       "      <td>0.316170</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210\n",
       "2016-01-07       NaN       NaN  0.427601  0.153653\n",
       "2016-01-08       NaN       NaN  0.945375  0.084841\n",
       "2016-01-09       NaN       NaN  0.630937  0.256707\n",
       "2016-01-10       NaN       NaN  0.017057  0.316170"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.join(df2, how='right')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {
    "id": "LehqC2xKL8Y_",
    "outputId": "da540f4b-9ee8-49e9-a2fe-18c5939f1b32"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-07</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.427601</td>\n",
       "      <td>0.153653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-08</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.945375</td>\n",
       "      <td>0.084841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-09</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.630937</td>\n",
       "      <td>0.256707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-10</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.017057</td>\n",
       "      <td>0.316170</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD\n",
       "2016-01-01  0.961191  0.214906       NaN       NaN\n",
       "2016-01-02  0.562981  0.602063       NaN       NaN\n",
       "2016-01-03  0.583841  0.367577       NaN       NaN\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210\n",
       "2016-01-07       NaN       NaN  0.427601  0.153653\n",
       "2016-01-08       NaN       NaN  0.945375  0.084841\n",
       "2016-01-09       NaN       NaN  0.630937  0.256707\n",
       "2016-01-10       NaN       NaN  0.017057  0.316170"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.join(df2, how='outer')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {
    "id": "BnxIHD1wL8ZA",
    "outputId": "a02abc4f-beec-4741-cbc1-179168bafadf"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.join(df2, how='inner')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {
    "id": "ypYiciNsL8ZC",
    "outputId": "8ea83eee-e408-4fa2-fb6a-709be802654a"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "      <th>ColumnA_df2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "      <td>1.562917</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "      <td>1.794997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "      <td>1.946344</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD  ColumnA_df2\n",
       "2016-01-01  0.961191  0.214906       NaN       NaN          NaN\n",
       "2016-01-02  0.562981  0.602063       NaN       NaN          NaN\n",
       "2016-01-03  0.583841  0.367577       NaN       NaN          NaN\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961     1.562917\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632     1.794997\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210     1.946344"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2['ColumnA'] = df1.ColumnA+1   #Example when columns have the same name\n",
    "\n",
    "df1.join(df2, how='left', rsuffix='_df2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {
    "id": "VKWLYtQyL8ZD"
   },
   "outputs": [],
   "source": [
    "del df2['ColumnA']\n",
    "df3 = df1.join(df2)\n",
    "\n",
    "# add a column to df to group on\n",
    "df3['ProfitLoss'] = pd.Series(['Profit', \n",
    "                               'Loss', \n",
    "                               'Profit', \n",
    "                               'Same', \n",
    "                               'Profit', \n",
    "                               'Loss', \n",
    "                               'Profit', \n",
    "                               'Profit', \n",
    "                               'Same', \n",
    "                               'Loss'], index=dates)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {
    "id": "tVryLR1kL8ZF"
   },
   "outputs": [],
   "source": [
    "df3['Student'] = pd.Series(['Alex',\n",
    "                            'Alex',\n",
    "                            'Alex',\n",
    "                            'Marcos',\n",
    "                            'Hannah',\n",
    "                            'Hannah',\n",
    "                            'Marcos',\n",
    "                            'Hannah',\n",
    "                            'Hannah',\n",
    "                            'Barbara'], index=dates)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {
    "id": "q9vjZfwcL8ZG",
    "outputId": "50e5fb5e-fb40-469a-f4a2-3758b12b7039"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "      <th>ProfitLoss</th>\n",
       "      <th>Student</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "      <td>Same</td>\n",
       "      <td>Marcos</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD ProfitLoss Student\n",
       "2016-01-01  0.961191  0.214906       NaN       NaN     Profit    Alex\n",
       "2016-01-02  0.562981  0.602063       NaN       NaN       Loss    Alex\n",
       "2016-01-03  0.583841  0.367577       NaN       NaN     Profit    Alex\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961       Same  Marcos\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632     Profit  Hannah\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210       Loss  Hannah"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {
    "id": "aQ5xKKMWL8ZI",
    "outputId": "993632fa-1ffe-46bd-97b1-492300cc1dc0"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ProfitLoss</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Loss</th>\n",
       "      <td>0.754662</td>\n",
       "      <td>0.787128</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Profit</th>\n",
       "      <td>0.780010</td>\n",
       "      <td>0.367064</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Same</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD\n",
       "ProfitLoss                                        \n",
       "Loss        0.754662  0.787128  0.273469  0.435210\n",
       "Profit      0.780010  0.367064  0.309962  0.768632\n",
       "Same        0.562917  0.712821  0.017940  0.876961"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grupos = df3.groupby('ProfitLoss')#.mean()\n",
    "grupos.mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Verifying Python's ordering heuristics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {
    "id": "bbIbVPYVL8ZJ",
    "outputId": "7af165bc-e886-4aa8-b1c0-f3950152ba1f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'name2'"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(['name1', 'name2', 'Name3'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {
    "id": "lW_LdufBL8ZK",
    "outputId": "930a5e51-ec3f-444b-8124-9de6bba0a0e9"
   },
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Student</th>\n",
       "      <th>ProfitLoss</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Alex</th>\n",
       "      <th>Loss</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Profit</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Hannah</th>\n",
       "      <th>Loss</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Profit</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Marcos</th>\n",
       "      <th>Same</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     ColumnA   ColumnB   ColumnC   ColumnD\n",
       "Student ProfitLoss                                        \n",
       "Alex    Loss        0.562981  0.602063       NaN       NaN\n",
       "        Profit      0.961191  0.367577       NaN       NaN\n",
       "Hannah  Loss        0.946344  0.972193  0.273469  0.435210\n",
       "        Profit      0.794997  0.518708  0.309962  0.768632\n",
       "Marcos  Same        0.562917  0.712821  0.017940  0.876961"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4 = df3.groupby(['Student','ProfitLoss']).max()\n",
    "df4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {
    "id": "Fer2LHsrL8ZM",
    "outputId": "adbc1636-4d72-4b0a-bc3c-814812976fe0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Alex', 'Alex', 'Hannah', 'Hannah', 'Marcos'], dtype='object', name='Student')"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4.index.get_level_values('Student')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {
    "id": "aUM-BJMYL8ZN",
    "outputId": "f992ff24-9751-40bd-ebd4-e0f9e948f1e8"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7949966854120388"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4.loc[('Hannah','Profit'), 'ColumnA']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [Pandas Useful Functions](https://pandas.pydata.org/pandas-docs/stable/reference/general_functions.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "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>ColumnA</th>\n",
       "      <th>ColumnB</th>\n",
       "      <th>ColumnC</th>\n",
       "      <th>ColumnD</th>\n",
       "      <th>ProfitLoss</th>\n",
       "      <th>Student</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016-01-01</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.214906</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-02</th>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-03</th>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Alex</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-04</th>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.017940</td>\n",
       "      <td>0.876961</td>\n",
       "      <td>Same</td>\n",
       "      <td>Marcos</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-05</th>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.768632</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-01-06</th>\n",
       "      <td>0.946344</td>\n",
       "      <td>0.972193</td>\n",
       "      <td>0.273469</td>\n",
       "      <td>0.435210</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ColumnA   ColumnB   ColumnC   ColumnD ProfitLoss Student\n",
       "2016-01-01  0.961191  0.214906       NaN       NaN     Profit    Alex\n",
       "2016-01-02  0.562981  0.602063       NaN       NaN       Loss    Alex\n",
       "2016-01-03  0.583841  0.367577       NaN       NaN     Profit    Alex\n",
       "2016-01-04  0.562917  0.712821  0.017940  0.876961       Same  Marcos\n",
       "2016-01-05  0.794997  0.518708  0.309962  0.768632     Profit  Hannah\n",
       "2016-01-06  0.946344  0.972193  0.273469  0.435210       Loss  Hannah"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Transpose"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "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>2016-01-01</th>\n",
       "      <th>2016-01-02</th>\n",
       "      <th>2016-01-03</th>\n",
       "      <th>2016-01-04</th>\n",
       "      <th>2016-01-05</th>\n",
       "      <th>2016-01-06</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ColumnA</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.946344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnB</th>\n",
       "      <td>0.214906</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.972193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnC</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.01794</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.273469</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnD</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.876961</td>\n",
       "      <td>0.768632</td>\n",
       "      <td>0.43521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ProfitLoss</th>\n",
       "      <td>Profit</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Same</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Student</th>\n",
       "      <td>Alex</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Marcos</td>\n",
       "      <td>Hannah</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           2016-01-01 2016-01-02 2016-01-03 2016-01-04 2016-01-05 2016-01-06\n",
       "ColumnA      0.961191   0.562981   0.583841   0.562917   0.794997   0.946344\n",
       "ColumnB      0.214906   0.602063   0.367577   0.712821   0.518708   0.972193\n",
       "ColumnC           NaN        NaN        NaN    0.01794   0.309962   0.273469\n",
       "ColumnD           NaN        NaN        NaN   0.876961   0.768632    0.43521\n",
       "ProfitLoss     Profit       Loss     Profit       Same     Profit       Loss\n",
       "Student          Alex       Alex       Alex     Marcos     Hannah     Hannah"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "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>2016-01-01</th>\n",
       "      <th>2016-01-02</th>\n",
       "      <th>2016-01-03</th>\n",
       "      <th>2016-01-04</th>\n",
       "      <th>2016-01-05</th>\n",
       "      <th>2016-01-06</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ColumnA</th>\n",
       "      <td>0.961191</td>\n",
       "      <td>0.562981</td>\n",
       "      <td>0.583841</td>\n",
       "      <td>0.562917</td>\n",
       "      <td>0.794997</td>\n",
       "      <td>0.946344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnB</th>\n",
       "      <td>0.214906</td>\n",
       "      <td>0.602063</td>\n",
       "      <td>0.367577</td>\n",
       "      <td>0.712821</td>\n",
       "      <td>0.518708</td>\n",
       "      <td>0.972193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnC</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.01794</td>\n",
       "      <td>0.309962</td>\n",
       "      <td>0.273469</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ColumnD</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.876961</td>\n",
       "      <td>0.768632</td>\n",
       "      <td>0.43521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ProfitLoss</th>\n",
       "      <td>Profit</td>\n",
       "      <td>Loss</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Same</td>\n",
       "      <td>Profit</td>\n",
       "      <td>Loss</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Student</th>\n",
       "      <td>Alex</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Marcos</td>\n",
       "      <td>Hannah</td>\n",
       "      <td>Hannah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           2016-01-01 2016-01-02 2016-01-03 2016-01-04 2016-01-05 2016-01-06\n",
       "ColumnA      0.961191   0.562981   0.583841   0.562917   0.794997   0.946344\n",
       "ColumnB      0.214906   0.602063   0.367577   0.712821   0.518708   0.972193\n",
       "ColumnC           NaN        NaN        NaN    0.01794   0.309962   0.273469\n",
       "ColumnD           NaN        NaN        NaN   0.876961   0.768632    0.43521\n",
       "ProfitLoss     Profit       Loss     Profit       Same     Profit       Loss\n",
       "Student          Alex       Alex       Alex     Marcos     Hannah     Hannah"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.transpose()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [idmin & idmax](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.idxmax.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Timestamp('2016-01-01 00:00:00', freq='D')"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3['ColumnA'].idxmax()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ColumnA       0.961191\n",
       "ColumnB       0.214906\n",
       "ColumnC            NaN\n",
       "ColumnD            NaN\n",
       "ProfitLoss      Profit\n",
       "Student           Alex\n",
       "Name: 2016-01-01 00:00:00, dtype: object"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.loc[df3['ColumnA'].idxmax()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9611911784461947"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max(df3['ColumnA'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Timestamp('2016-01-04 00:00:00', freq='D')"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3['ColumnA'].idxmin()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ColumnA       0.562917\n",
       "ColumnB       0.712821\n",
       "ColumnC        0.01794\n",
       "ColumnD       0.876961\n",
       "ProfitLoss        Same\n",
       "Student         Marcos\n",
       "Name: 2016-01-04 00:00:00, dtype: object"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.loc[df3['ColumnA'].idxmin()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5629166477301453"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min(df3['ColumnA'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [Not Equal - ne](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.ne.html)  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     False\n",
       "1     False\n",
       "2     False\n",
       "3     False\n",
       "4     False\n",
       "5     False\n",
       "6      True\n",
       "7      True\n",
       "8      True\n",
       "9      True\n",
       "10     True\n",
       "11     True\n",
       "12     True\n",
       "Name: x, dtype: bool"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame()\n",
    "df['x'] = [0,0,0,0,0,0,1,2,3,4,5,6,7]\n",
    "\n",
    "df['x'].ne(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Nsmallest  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    0\n",
       "2    0\n",
       "Name: x, dtype: int64"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['x'].nsmallest(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   x\n",
       "0  0\n",
       "1  0\n",
       "2  0"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.nsmallest(3, 'x')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Nlargest  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12    7\n",
       "11    6\n",
       "10    5\n",
       "Name: x, dtype: int64"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['x'].nlargest(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    x\n",
       "12  7\n",
       "11  6\n",
       "10  5"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.nlargest(3, 'x')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Is in  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       x\n",
       "0   True\n",
       "1   True\n",
       "2   True\n",
       "3   True\n",
       "4   True\n",
       "5   True\n",
       "6  False\n",
       "7   True\n",
       "8  False\n",
       "9  False"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isin([0,2]).head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      x\n",
       "0   0.0\n",
       "1   0.0\n",
       "2   0.0\n",
       "3   0.0\n",
       "4   0.0\n",
       "5   0.0\n",
       "6   NaN\n",
       "7   2.0\n",
       "8   NaN\n",
       "9   NaN\n",
       "10  NaN\n",
       "11  NaN\n",
       "12  NaN"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.isin([0,2])] #.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      x\n",
       "6   1.0\n",
       "8   3.0\n",
       "9   4.0\n",
       "10  5.0\n",
       "11  6.0\n",
       "12  7.0"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[~df.isin([0,2])].dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "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>Test</th>\n",
       "      <th>Student</th>\n",
       "      <th>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 1</td>\n",
       "      <td>54</td>\n",
       "      <td>75</td>\n",
       "      <td>66</td>\n",
       "      <td>99</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 2</td>\n",
       "      <td>29</td>\n",
       "      <td>91</td>\n",
       "      <td>96</td>\n",
       "      <td>69</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 3</td>\n",
       "      <td>28</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>33</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 4</td>\n",
       "      <td>29</td>\n",
       "      <td>23</td>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 5</td>\n",
       "      <td>40</td>\n",
       "      <td>71</td>\n",
       "      <td>45</td>\n",
       "      <td>42</td>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Test    Student  Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "0   T2  Student 1     54       75         66       99                32\n",
       "1   T2  Student 2     29       91         96       69                58\n",
       "2   T1  Student 3     28       10         22       33                25\n",
       "3   T2  Student 4     29       23         41        0                42\n",
       "4   T3  Student 5     40       71         45       42                87"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create a test dataframe\n",
    "# Untidy dataframe\n",
    "# x : Subjects\n",
    "# y : Student names\n",
    "\n",
    "marks = pd.DataFrame(np.random.randint(0, 100, size = (20,5)), \n",
    "                     columns = ['Maths', 'Physics','Chemistry', 'Biology', 'Computer_Science'])\n",
    "\n",
    "marks['Student'] = ['Student ' + str(i) for i in range(1,21)]\n",
    "marks['Test'] = np.random.choice(['T1', 'T2', 'T3'], size=len(marks))\n",
    "marks = marks[['Test','Student','Maths', 'Physics','Chemistry', 'Biology', 'Computer_Science']]\n",
    "\n",
    "display(marks.head())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [Agg](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.agg.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "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>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>sum</th>\n",
       "      <td>994.0</td>\n",
       "      <td>1084.0</td>\n",
       "      <td>818.0</td>\n",
       "      <td>1121.00</td>\n",
       "      <td>999.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>11.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>49.7</td>\n",
       "      <td>54.2</td>\n",
       "      <td>40.9</td>\n",
       "      <td>56.05</td>\n",
       "      <td>49.95</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "sum   994.0   1084.0      818.0  1121.00            999.00\n",
       "min     5.0      0.0        0.0     0.00             11.00\n",
       "mean   49.7     54.2       40.9    56.05             49.95"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "marks[['Maths', 'Physics','Chemistry', 'Biology', 'Computer_Science']].agg(['sum', 'min', 'mean'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Group By"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "grouped = marks.groupby('Test')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "T1\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>Test</th>\n",
       "      <th>Student</th>\n",
       "      <th>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 3</td>\n",
       "      <td>28</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>33</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 6</td>\n",
       "      <td>43</td>\n",
       "      <td>50</td>\n",
       "      <td>48</td>\n",
       "      <td>95</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 7</td>\n",
       "      <td>99</td>\n",
       "      <td>97</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 11</td>\n",
       "      <td>85</td>\n",
       "      <td>3</td>\n",
       "      <td>95</td>\n",
       "      <td>50</td>\n",
       "      <td>55</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 12</td>\n",
       "      <td>97</td>\n",
       "      <td>93</td>\n",
       "      <td>22</td>\n",
       "      <td>63</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Test     Student  Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "2    T1   Student 3     28       10         22       33                25\n",
       "5    T1   Student 6     43       50         48       95                71\n",
       "6    T1   Student 7     99       97          0       12                73\n",
       "10   T1  Student 11     85        3         95       50                55\n",
       "11   T1  Student 12     97       93         22       63                30"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "T2\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>Test</th>\n",
       "      <th>Student</th>\n",
       "      <th>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 1</td>\n",
       "      <td>54</td>\n",
       "      <td>75</td>\n",
       "      <td>66</td>\n",
       "      <td>99</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 2</td>\n",
       "      <td>29</td>\n",
       "      <td>91</td>\n",
       "      <td>96</td>\n",
       "      <td>69</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 4</td>\n",
       "      <td>29</td>\n",
       "      <td>23</td>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 8</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>72</td>\n",
       "      <td>75</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 10</td>\n",
       "      <td>15</td>\n",
       "      <td>94</td>\n",
       "      <td>55</td>\n",
       "      <td>69</td>\n",
       "      <td>45</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Test     Student  Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "0   T2   Student 1     54       75         66       99                32\n",
       "1   T2   Student 2     29       91         96       69                58\n",
       "3   T2   Student 4     29       23         41        0                42\n",
       "7   T2   Student 8     17        0         72       75                17\n",
       "9   T2  Student 10     15       94         55       69                45"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "T3\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>Test</th>\n",
       "      <th>Student</th>\n",
       "      <th>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 5</td>\n",
       "      <td>40</td>\n",
       "      <td>71</td>\n",
       "      <td>45</td>\n",
       "      <td>42</td>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 9</td>\n",
       "      <td>75</td>\n",
       "      <td>23</td>\n",
       "      <td>1</td>\n",
       "      <td>65</td>\n",
       "      <td>38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 13</td>\n",
       "      <td>92</td>\n",
       "      <td>88</td>\n",
       "      <td>58</td>\n",
       "      <td>18</td>\n",
       "      <td>54</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Test     Student  Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "4    T3   Student 5     40       71         45       42                87\n",
       "8    T3   Student 9     75       23          1       65                38\n",
       "12   T3  Student 13     92       88         58       18                54"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for group in grouped:\n",
    "    print(group[0])\n",
    "    display(group[1].head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Test\n",
       "T1    55.111111\n",
       "T2    36.375000\n",
       "T3    69.000000\n",
       "Name: Maths, dtype: float64"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped['Maths'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  Test  Student\n",
      "0   T1        9\n",
      "1   T2        8\n",
      "2   T3        3\n"
     ]
    }
   ],
   "source": [
    "grouped2 = grouped.agg({\"Student\": \"nunique\"})\n",
    "grouped2 = grouped2.reset_index()\n",
    "print(grouped2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Pivot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {
    "id": "h7UmJLl8L8Xs",
    "outputId": "7c07a5fa-bbc7-4e52-c64f-b30109932018"
   },
   "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>Student</th>\n",
       "      <th>Student 1</th>\n",
       "      <th>Student 10</th>\n",
       "      <th>Student 11</th>\n",
       "      <th>Student 12</th>\n",
       "      <th>Student 13</th>\n",
       "      <th>Student 14</th>\n",
       "      <th>Student 15</th>\n",
       "      <th>Student 16</th>\n",
       "      <th>Student 17</th>\n",
       "      <th>Student 18</th>\n",
       "      <th>Student 19</th>\n",
       "      <th>Student 2</th>\n",
       "      <th>Student 20</th>\n",
       "      <th>Student 3</th>\n",
       "      <th>Student 4</th>\n",
       "      <th>Student 5</th>\n",
       "      <th>Student 6</th>\n",
       "      <th>Student 7</th>\n",
       "      <th>Student 8</th>\n",
       "      <th>Student 9</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Test</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>T1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>95.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>43.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>53.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>48.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>T2</th>\n",
       "      <td>66.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>31.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>96.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>41.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>72.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>T3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>58.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>45.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Student  Student 1  Student 10  Student 11  Student 12  Student 13  \\\n",
       "Test                                                                 \n",
       "T1             NaN         NaN        95.0        22.0         NaN   \n",
       "T2            66.0        55.0         NaN         NaN         NaN   \n",
       "T3             NaN         NaN         NaN         NaN        58.0   \n",
       "\n",
       "Student  Student 14  Student 15  Student 16  Student 17  Student 18  \\\n",
       "Test                                                                  \n",
       "T1              NaN         NaN        43.0         4.0        14.0   \n",
       "T2             31.0        25.0         NaN         NaN         NaN   \n",
       "T3              NaN         NaN         NaN         NaN         NaN   \n",
       "\n",
       "Student  Student 19  Student 2  Student 20  Student 3  Student 4  Student 5  \\\n",
       "Test                                                                          \n",
       "T1             53.0        NaN         NaN       22.0        NaN        NaN   \n",
       "T2              NaN       96.0        27.0        NaN       41.0        NaN   \n",
       "T3              NaN        NaN         NaN        NaN        NaN       45.0   \n",
       "\n",
       "Student  Student 6  Student 7  Student 8  Student 9  \n",
       "Test                                                 \n",
       "T1            48.0        0.0        NaN        NaN  \n",
       "T2             NaN        NaN       72.0        NaN  \n",
       "T3             NaN        NaN        NaN        1.0  "
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pivot = marks.pivot(index='Test', columns='Student', values='Chemistry') \n",
    "pivot.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [Melt](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.melt.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "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>Test</th>\n",
       "      <th>Student</th>\n",
       "      <th>Maths</th>\n",
       "      <th>Physics</th>\n",
       "      <th>Chemistry</th>\n",
       "      <th>Biology</th>\n",
       "      <th>Computer_Science</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 1</td>\n",
       "      <td>54</td>\n",
       "      <td>75</td>\n",
       "      <td>66</td>\n",
       "      <td>99</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 2</td>\n",
       "      <td>29</td>\n",
       "      <td>91</td>\n",
       "      <td>96</td>\n",
       "      <td>69</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 3</td>\n",
       "      <td>28</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>33</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 4</td>\n",
       "      <td>29</td>\n",
       "      <td>23</td>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 5</td>\n",
       "      <td>40</td>\n",
       "      <td>71</td>\n",
       "      <td>45</td>\n",
       "      <td>42</td>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 6</td>\n",
       "      <td>43</td>\n",
       "      <td>50</td>\n",
       "      <td>48</td>\n",
       "      <td>95</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>T1</td>\n",
       "      <td>Student 7</td>\n",
       "      <td>99</td>\n",
       "      <td>97</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 8</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>72</td>\n",
       "      <td>75</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>T3</td>\n",
       "      <td>Student 9</td>\n",
       "      <td>75</td>\n",
       "      <td>23</td>\n",
       "      <td>1</td>\n",
       "      <td>65</td>\n",
       "      <td>38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>T2</td>\n",
       "      <td>Student 10</td>\n",
       "      <td>15</td>\n",
       "      <td>94</td>\n",
       "      <td>55</td>\n",
       "      <td>69</td>\n",
       "      <td>45</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Test     Student  Maths  Physics  Chemistry  Biology  Computer_Science\n",
       "0   T2   Student 1     54       75         66       99                32\n",
       "1   T2   Student 2     29       91         96       69                58\n",
       "2   T1   Student 3     28       10         22       33                25\n",
       "3   T2   Student 4     29       23         41        0                42\n",
       "4   T3   Student 5     40       71         45       42                87\n",
       "5   T1   Student 6     43       50         48       95                71\n",
       "6   T1   Student 7     99       97          0       12                73\n",
       "7   T2   Student 8     17        0         72       75                17\n",
       "8   T3   Student 9     75       23          1       65                38\n",
       "9   T2  Student 10     15       94         55       69                45"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "marks.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "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>Student</th>\n",
       "      <th>variable</th>\n",
       "      <th>Frequency</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>110</th>\n",
       "      <td>Student 11</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>55</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>111</th>\n",
       "      <td>Student 12</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112</th>\n",
       "      <td>Student 13</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113</th>\n",
       "      <td>Student 14</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>114</th>\n",
       "      <td>Student 15</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>Student 16</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>Student 17</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>Student 18</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>Student 19</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>79</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>Student 20</td>\n",
       "      <td>Computer_Science</td>\n",
       "      <td>98</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Student          variable Frequency\n",
       "110  Student 11  Computer_Science        55\n",
       "111  Student 12  Computer_Science        30\n",
       "112  Student 13  Computer_Science        54\n",
       "113  Student 14  Computer_Science        74\n",
       "114  Student 15  Computer_Science        11\n",
       "115  Student 16  Computer_Science        61\n",
       "116  Student 17  Computer_Science        18\n",
       "117  Student 18  Computer_Science        31\n",
       "118  Student 19  Computer_Science        79\n",
       "119  Student 20  Computer_Science        98"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tidy = pd.melt(marks, id_vars = 'Student', value_name = 'Frequency')\n",
    "tidy.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 120 entries, 0 to 119\n",
      "Data columns (total 3 columns):\n",
      " #   Column     Non-Null Count  Dtype \n",
      "---  ------     --------------  ----- \n",
      " 0   Student    120 non-null    object\n",
      " 1   variable   120 non-null    object\n",
      " 2   Frequency  120 non-null    object\n",
      "dtypes: object(3)\n",
      "memory usage: 2.9+ KB\n"
     ]
    }
   ],
   "source": [
    "tidy.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "15_Pandas_Basics.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}