01-03-2016-rrfd-pandas-intro.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pandas import Series, DataFrame\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[-10.          -8.94736842  -7.89473684  -6.84210526  -5.78947368\n",
      "  -4.73684211  -3.68421053  -2.63157895  -1.57894737  -0.52631579\n",
      "   0.52631579   1.57894737   2.63157895   3.68421053   4.73684211\n",
      "   5.78947368   6.84210526   7.89473684   8.94736842  10.        ]\n"
     ]
    }
   ],
   "source": [
    "line = np.linspace(-10, 10, num=20)\n",
    "print line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    -10.000000\n",
      "1     -8.947368\n",
      "2     -7.894737\n",
      "3     -6.842105\n",
      "4     -5.789474\n",
      "5     -4.736842\n",
      "6     -3.684211\n",
      "7     -2.631579\n",
      "8     -1.578947\n",
      "9     -0.526316\n",
      "10     0.526316\n",
      "11     1.578947\n",
      "12     2.631579\n",
      "13     3.684211\n",
      "14     4.736842\n",
      "15     5.789474\n",
      "16     6.842105\n",
      "17     7.894737\n",
      "18     8.947368\n",
      "19    10.000000\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Series gives a numerical value to each element of the array\n",
    "line_series = Series(line)\n",
    "print line_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[-10.          -8.94736842  -7.89473684  -6.84210526  -5.78947368\n",
      "  -4.73684211  -3.68421053  -2.63157895  -1.57894737  -0.52631579\n",
      "   0.52631579   1.57894737   2.63157895   3.68421053   4.73684211\n",
      "   5.78947368   6.84210526   7.89473684   8.94736842  10.        ] \n",
      "\n",
      "Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,\n",
      "            19],\n",
      "           dtype='int64')\n"
     ]
    }
   ],
   "source": [
    "# Notice how the index numbers are different from the values.\n",
    "# Index is the \"indexed\" number while the value is the corresponding value\n",
    "# linked to the index\n",
    "\n",
    "print line_series.values, \"\\n\"\n",
    "print line_series.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1   -8.947368\n",
       "3   -6.842105\n",
       "5   -4.736842\n",
       "dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get a group of numbers\n",
    "# Notice the double [[]]\n",
    "line_series[[1, 3, 5]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5     -4.736842\n",
       "6     -3.684211\n",
       "7     -2.631579\n",
       "8     -1.578947\n",
       "9     -0.526316\n",
       "10     0.526316\n",
       "11     1.578947\n",
       "12     2.631579\n",
       "13     3.684211\n",
       "14     4.736842\n",
       "15     5.789474\n",
       "16     6.842105\n",
       "17     7.894737\n",
       "18     8.947368\n",
       "19    10.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get values > -5\n",
    "line_series[line_series > -5]\n",
    "\n",
    "# Notice how it gives the index value as well"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    -20.000000\n",
       "1    -17.894737\n",
       "2    -15.789474\n",
       "3    -13.684211\n",
       "4    -11.578947\n",
       "5     -9.473684\n",
       "6     -7.368421\n",
       "7     -5.263158\n",
       "8     -3.157895\n",
       "9     -1.052632\n",
       "10     1.052632\n",
       "11     3.157895\n",
       "12     5.263158\n",
       "13     7.368421\n",
       "14     9.473684\n",
       "15    11.578947\n",
       "16    13.684211\n",
       "17    15.789474\n",
       "18    17.894737\n",
       "19    20.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# You can also manipulate the  values\n",
    "line_series * 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    -10.000000\n",
      "1     -8.947368\n",
      "2     -7.894737\n",
      "3     -6.842105\n",
      "4     -5.789474\n",
      "5     -4.736842\n",
      "6     -3.684211\n",
      "7     -2.631579\n",
      "8     -1.578947\n",
      "9     -0.526316\n",
      "10     0.526316\n",
      "11     1.578947\n",
      "12     2.631579\n",
      "13     3.684211\n",
      "14     4.736842\n",
      "15     5.789474\n",
      "16     6.842105\n",
      "17     7.894737\n",
      "18     8.947368\n",
      "19    10.000000\n",
      "dtype: float64 \n",
      "0         0.000045\n",
      "1         0.000130\n",
      "2         0.000373\n",
      "3         0.001068\n",
      "4         0.003060\n",
      "5         0.008766\n",
      "6         0.025117\n",
      "7         0.071965\n",
      "8         0.206192\n",
      "9         0.590778\n",
      "10        1.692685\n",
      "11        4.849848\n",
      "12       13.895693\n",
      "13       39.813678\n",
      "14      114.073401\n",
      "15      326.840958\n",
      "16      936.458553\n",
      "17     2683.123399\n",
      "18     7687.634601\n",
      "19    22026.465795\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "# Create an exponential funciton\n",
    "np.exp(line_series)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1\n",
       "b    2\n",
       "c    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# You can also turn a dictionary into a series\n",
    "dict_1 = {'a': 1, 'b': 2, 'c': 3}\n",
    "dict_series = Series(dict_1)\n",
    "dict_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(dict_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    False\n",
       "b    False\n",
       "c    False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(dict_series)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice how pandas handles the two differently. Once with the dictionary the other with a series."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a     2\n",
       "b     4\n",
       "c     6\n",
       "d   NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# You cannot add dict, but you can add series\n",
    "dict_2 = {'a': 1, 'b': 2, 'c': 3, 'd': 4}\n",
    "dict_series_2 = Series(dict_2)\n",
    "dict_series + dict_series_2 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "dict_series.name = \"TestName\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1\n",
       "b    2\n",
       "c    3\n",
       "Name: TestName, dtype: int64"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Now lets label the indexs\n",
    "dict_series.index.name = \"Index Test Name\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index Test Name\n",
       "a    1\n",
       "b    2\n",
       "c    3\n",
       "Name: TestName, dtype: int64"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "first     1\n",
       "second    2\n",
       "third     3\n",
       "Name: TestName, dtype: int64"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now lets rename the indexes\n",
    "dict_series.index = [\"first\", \"second\", \"third\"]\n",
    "dict_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pop</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.0</td>\n",
       "      <td>VA</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.1</td>\n",
       "      <td>VA</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.2</td>\n",
       "      <td>VA</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>MD</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.1</td>\n",
       "      <td>MD</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   pop state  year\n",
       "0  5.0    VA  2012\n",
       "1  5.1    VA  2013\n",
       "2  5.2    VA  2014\n",
       "3  4.0    MD  2014\n",
       "4  4.1    MD  2015"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now we're going to be looking at some data frames\n",
    "\n",
    "data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
    "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
    "          'pop' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
    "\n",
    "df_1 = DataFrame(data_1)\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\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>2012</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2015</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year state  pop\n",
       "0  2012    VA  5.0\n",
       "1  2013    VA  5.1\n",
       "2  2014    VA  5.2\n",
       "3  2014    MD  4.0\n",
       "4  2015    MD  4.1"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# If you want to create the DF with a different order to the columns\n",
    "df_2 = DataFrame(data_1, columns = ['year', 'state', 'pop'])\n",
    "df_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\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>unempl</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2015</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year state  pop unempl\n",
       "0  2012    VA  5.0    NaN\n",
       "1  2013    VA  5.1    NaN\n",
       "2  2014    VA  5.2    NaN\n",
       "3  2014    MD  4.0    NaN\n",
       "4  2015    MD  4.1    NaN"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# What if you want to add another col to the DF which has no data\n",
    "df_3 = DataFrame(data_1, columns = ['year', 'state', 'pop', 'unempl'])\n",
    "df_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    2012\n",
      "1    2013\n",
      "2    2014\n",
      "3    2014\n",
      "4    2015\n",
      "Name: year, dtype: int64 0    5.0\n",
      "1    5.1\n",
      "2    5.2\n",
      "3    4.0\n",
      "4    4.1\n",
      "Name: pop, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# You can return the column values with dot location or bracket location\n",
    "print df_3.year, df_3['pop']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year      2014\n",
       "state       VA\n",
       "pop        5.2\n",
       "unempl     NaN\n",
       "Name: 2, dtype: object"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# You can find the row data by using the .ix operator\n",
    "df_3.ix[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\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>unempl</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2015</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year state  pop  unempl\n",
       "0  2012    VA  5.0       0\n",
       "1  2013    VA  5.1       1\n",
       "2  2014    VA  5.2       2\n",
       "3  2014    MD  4.0       3\n",
       "4  2015    MD  4.1       4"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now you can update the NaN colum\n",
    "df_3['unempl'] = np.arange(5)\n",
    "df_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\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>unempl</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014</td>\n",
       "      <td>VA</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2015</td>\n",
       "      <td>MD</td>\n",
       "      <td>4.1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year state  pop  unempl\n",
       "0  2012    VA  5.0       0\n",
       "1  2013    VA  5.1       1\n",
       "2  2014    VA  5.2       2\n",
       "3  2014    MD  4.0       3\n",
       "4  2015    MD  4.1       4"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Lets create a duplicate column\n",
    "df_3['dup'] = df_3['state']\n",
    "del df_3['dup']\n",
    "df_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       MD   VA\n",
       "2013  NaN  5.1\n",
       "2014  4.0  5.2\n",
       "2015  4.1  NaN"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# DataFrame will will fill in the blanks\n",
    "# Notice how 2013 only has one entry, so does 2015\n",
    "pop = {'VA' : {2013 : 5.1, 2014 : 5.2},\n",
    "       'MD' : {2014 : 4.0, 2015 : 4.1}}\n",
    "df_4 = DataFrame(pop)\n",
    "df_4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>MD</th>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>VA</th>\n",
       "      <td>5.1</td>\n",
       "      <td>5.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    2013  2014  2015\n",
       "MD   NaN   4.0   4.1\n",
       "VA   5.1   5.2   NaN"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# You can also transpose the DF\n",
    "df_4.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years    MD   VA\n",
       "States          \n",
       "2013    NaN  5.1\n",
       "2014    4.0  5.2\n",
       "2015    4.1  NaN"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4.columns.name = \"Years\"\n",
    "df_4.index.name = \"States\"\n",
    "df_4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ nan,  5.1],\n",
       "       [ 4. ,  5.2],\n",
       "       [ 4.1,  nan]])"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2012, 'VA', 5.0, 0],\n",
       "       [2013, 'VA', 5.1, 1],\n",
       "       [2014, 'VA', 5.2, 2],\n",
       "       [2014, 'MD', 4.0, 3],\n",
       "       [2015, 'MD', 4.1, 4]], dtype=object)"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_3.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years    MD   VA\n",
       "States          \n",
       "2013    NaN  5.1\n",
       "2014    4.0  5.2\n",
       "2015    4.1  NaN"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4.reindex(list(range(2013,2016)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years    MD\n",
       "States     \n",
       "2013    NaN\n",
       "2014    4.0\n",
       "2015    4.1"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4.drop('VA', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years   MD   VA\n",
       "States         \n",
       "2014     4  5.2"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# If you want to see which cell of a column meets a certain standard\n",
    "df_4[df_4['MD'] == 4.0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years      MD     VA\n",
       "States              \n",
       "2013    False   True\n",
       "2014    False   True\n",
       "2015     True  False"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Shows a scalar comparison\n",
    "df_4 >= 4.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years    MD   VA\n",
       "States          \n",
       "2013    NaN  5.1\n",
       "2014    NaN  5.2\n",
       "2015    4.1  NaN"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Or you can show the actual vales amd the NaN\n",
    "df_4[df_4 >= 4.1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>4.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years    MD   VA\n",
       "States          \n",
       "2013    NaN  5.1\n",
       "2014    4.0  5.2\n",
       "2015    4.1  NaN"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Years</th>\n",
       "      <th>MD</th>\n",
       "      <th>VA</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>States</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>5.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Years   MD   VA\n",
       "States         \n",
       "2013   NaN  5.1"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_4.ix[df_4.VA < 5.2]\n",
    "\n",
    "# Notice how the NaN are gone"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1.764052\n",
       "b    0.400157\n",
       "c    0.978738\n",
       "d    2.240893\n",
       "e    1.867558\n",
       "dtype: float64"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remember a series is different from a dataframe\n",
    "\n",
    "np.random.seed(0)\n",
    "ser_6 = Series(np.random.randn(5), index = ['a', 'b', 'c', 'd', 'e'])\n",
    "ser_6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1.624345\n",
       "c   -0.611756\n",
       "e   -0.528172\n",
       "f   -1.072969\n",
       "g    0.865408\n",
       "dtype: float64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.seed(1)\n",
    "ser_7 = Series(np.random.randn(5), index = ['a', 'c', 'e', 'f', 'g'])\n",
    "ser_7"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    3.388398\n",
       "b         NaN\n",
       "c    0.366982\n",
       "d         NaN\n",
       "e    1.339386\n",
       "f         NaN\n",
       "g         NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser_6 + ser_7"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    3.388398\n",
       "b    0.400157\n",
       "c    0.366982\n",
       "d    2.240893\n",
       "e    1.339386\n",
       "f   -1.072969\n",
       "g    0.865408\n",
       "dtype: float64"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Set a fill value instead of NaN for indices that do not overlap:\n",
    "# The fill_value adds extra digits to the indicies that do not overlap\n",
    "ser_6.add(ser_7, fill_value=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.771321</td>\n",
       "      <td>0.020752</td>\n",
       "      <td>0.633648</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.748804</td>\n",
       "      <td>0.498507</td>\n",
       "      <td>0.224797</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.198063</td>\n",
       "      <td>0.760531</td>\n",
       "      <td>0.169111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          a         b         c\n",
       "0  0.771321  0.020752  0.633648\n",
       "1  0.748804  0.498507  0.224797\n",
       "2  0.198063  0.760531  0.169111"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.seed(10)\n",
    "# reshape() --> Gives a new shape to an array without changing its data.\n",
    "df_8 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
    "                 columns=['a', 'b', 'c'])\n",
    "df_8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.180270</td>\n",
       "      <td>0.019475</td>\n",
       "      <td>0.463219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.724934</td>\n",
       "      <td>0.420204</td>\n",
       "      <td>0.485427</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.012781</td>\n",
       "      <td>0.487372</td>\n",
       "      <td>0.941807</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          b         c         d\n",
       "0  0.180270  0.019475  0.463219\n",
       "1  0.724934  0.420204  0.485427\n",
       "2  0.012781  0.487372  0.941807"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.seed(11)\n",
    "# reshape() --> Gives a new shape to an array without changing its data.\n",
    "df_9 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
    "                 columns=['b', 'c', 'd'])\n",
    "df_9"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>0.201022</td>\n",
       "      <td>0.653123</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.223441</td>\n",
       "      <td>0.645000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>0.773312</td>\n",
       "      <td>0.656482</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    a         b         c   d\n",
       "0 NaN  0.201022  0.653123 NaN\n",
       "1 NaN  1.223441  0.645000 NaN\n",
       "2 NaN  0.773312  0.656482 NaN"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_8 + df_9"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.771321</td>\n",
       "      <td>0.201022</td>\n",
       "      <td>0.653123</td>\n",
       "      <td>0.463219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.748804</td>\n",
       "      <td>1.223441</td>\n",
       "      <td>0.645000</td>\n",
       "      <td>0.485427</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.198063</td>\n",
       "      <td>0.773312</td>\n",
       "      <td>0.656482</td>\n",
       "      <td>0.941807</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          a         b         c         d\n",
       "0  0.771321  0.201022  0.653123  0.463219\n",
       "1  0.748804  1.223441  0.645000  0.485427\n",
       "2  0.198063  0.773312  0.656482  0.941807"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_10 = df_8.add(df_9, fill_value = 0)\n",
    "df_10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# The dataFrame now becomes a series\n",
    "df_10_1 = df_10.ix[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.022517</td>\n",
       "      <td>1.022419</td>\n",
       "      <td>-0.008123</td>\n",
       "      <td>0.022209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.573258</td>\n",
       "      <td>0.572290</td>\n",
       "      <td>0.003359</td>\n",
       "      <td>0.478588</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          a         b         c         d\n",
       "0  0.000000  0.000000  0.000000  0.000000\n",
       "1 -0.022517  1.022419 -0.008123  0.022209\n",
       "2 -0.573258  0.572290  0.003359  0.478588"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_10 - df_10_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    100\n",
       "1    200\n",
       "2    300\n",
       "dtype: int64"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# If you want a Series - not at DF - simply write out Series()\n",
    "ser_10 = Series([100, 200, 300])\n",
    "ser_10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-99.228679</td>\n",
       "      <td>-99.798978</td>\n",
       "      <td>-99.346877</td>\n",
       "      <td>-99.536781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-199.251196</td>\n",
       "      <td>-198.776559</td>\n",
       "      <td>-199.355000</td>\n",
       "      <td>-199.514573</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-299.801937</td>\n",
       "      <td>-299.226688</td>\n",
       "      <td>-299.343518</td>\n",
       "      <td>-299.058193</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            a           b           c           d\n",
       "0  -99.228679  -99.798978  -99.346877  -99.536781\n",
       "1 -199.251196 -198.776559 -199.355000 -199.514573\n",
       "2 -299.801937 -299.226688 -299.343518 -299.058193"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remember you can remove a scaler from the DF\n",
    "df_10.sub(ser_10, axis = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.771321</td>\n",
       "      <td>0.201022</td>\n",
       "      <td>0.653123</td>\n",
       "      <td>0.463219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.748804</td>\n",
       "      <td>1.223441</td>\n",
       "      <td>0.645000</td>\n",
       "      <td>0.485427</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.198063</td>\n",
       "      <td>0.773312</td>\n",
       "      <td>0.656482</td>\n",
       "      <td>0.941807</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          a         b         c         d\n",
       "0  0.771321  0.201022  0.653123  0.463219\n",
       "1  0.748804  1.223441  0.645000  0.485427\n",
       "2  0.198063  0.773312  0.656482  0.941807"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_11 = np.abs(df_10)\n",
    "df_11"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    0.573258\n",
       "b    1.022419\n",
       "c    0.011482\n",
       "d    0.478588\n",
       "dtype: float64"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "func_1 = lambda x: x.max() - x.min()\n",
    "df_11.apply(func_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   -1.228679\n",
       "b   -0.776559\n",
       "c   -1.343518\n",
       "d   -1.058193\n",
       "dtype: float64"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "func_2 = lambda x: x.max() - 2\n",
    "df_11.apply(func_2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice how the lambda function takes in the DF and returns a series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.198063</td>\n",
       "      <td>0.201022</td>\n",
       "      <td>0.645000</td>\n",
       "      <td>0.463219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>0.771321</td>\n",
       "      <td>1.223441</td>\n",
       "      <td>0.656482</td>\n",
       "      <td>0.941807</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            a         b         c         d\n",
       "min  0.198063  0.201022  0.645000  0.463219\n",
       "max  0.771321  1.223441  0.656482  0.941807"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "func_3 = lambda x: Series([x.min(), x.max()], index = ['min', 'max'])\n",
    "df_11.apply(func_3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.7713</td>\n",
       "      <td>0.2010</td>\n",
       "      <td>0.6531</td>\n",
       "      <td>0.4632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.7488</td>\n",
       "      <td>1.2234</td>\n",
       "      <td>0.6450</td>\n",
       "      <td>0.4854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.1981</td>\n",
       "      <td>0.7733</td>\n",
       "      <td>0.6565</td>\n",
       "      <td>0.9418</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        a       b       c       d\n",
       "0  0.7713  0.2010  0.6531  0.4632\n",
       "1  0.7488  1.2234  0.6450  0.4854\n",
       "2  0.1981  0.7733  0.6565  0.9418"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Remember to reduce the number of decimal places you map the functions\n",
    "# to .3f or .2f or .xf\n",
    "\n",
    "# This is also applymap() --> works on a element-wise basis on a DataFrame\n",
    "func_4 = lambda x: '%.4f' %x\n",
    "df_11.applymap(func_4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0.7713\n",
       "1    0.7488\n",
       "2    0.1981\n",
       "Name: a, dtype: object"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now if you just want to run it on a series, you use map()\n",
    "\n",
    "#map() --> works element-wise on a Series\n",
    "df_11['a'].map(func_4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    100\n",
       "1    200\n",
       "2    300\n",
       "dtype: int64"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser_10.sort_index()\n",
    "\n",
    "# You can sort by the index value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    100\n",
       "1    200\n",
       "2    300\n",
       "dtype: int64"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser_10.sort_values()\n",
    "\n",
    "# You can sort by the values in the cell"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>second</th>\n",
       "      <th>first</th>\n",
       "      <th>fifth</th>\n",
       "      <th>fourth</th>\n",
       "      <th>third</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "      <td>8</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>10</td>\n",
       "      <td>11</td>\n",
       "      <td>12</td>\n",
       "      <td>13</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>f</th>\n",
       "      <td>15</td>\n",
       "      <td>16</td>\n",
       "      <td>17</td>\n",
       "      <td>18</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>e</th>\n",
       "      <td>20</td>\n",
       "      <td>21</td>\n",
       "      <td>22</td>\n",
       "      <td>23</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   second  first  fifth  fourth  third\n",
       "b       0      1      2       3      4\n",
       "a       5      6      7       8      9\n",
       "d      10     11     12      13     14\n",
       "f      15     16     17      18     19\n",
       "e      20     21     22      23     24"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_rd = DataFrame(np.arange(25).reshape((5,5)), index = ['b','a','d','f','e'],\n",
    "                 columns=['second', 'first', 'fifth', 'fourth', 'third'])\n",
    "df_rd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>second</th>\n",
       "      <th>first</th>\n",
       "      <th>fifth</th>\n",
       "      <th>fourth</th>\n",
       "      <th>third</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "      <td>8</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>10</td>\n",
       "      <td>11</td>\n",
       "      <td>12</td>\n",
       "      <td>13</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>e</th>\n",
       "      <td>20</td>\n",
       "      <td>21</td>\n",
       "      <td>22</td>\n",
       "      <td>23</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>f</th>\n",
       "      <td>15</td>\n",
       "      <td>16</td>\n",
       "      <td>17</td>\n",
       "      <td>18</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   second  first  fifth  fourth  third\n",
       "a       5      6      7       8      9\n",
       "b       0      1      2       3      4\n",
       "d      10     11     12      13     14\n",
       "e      20     21     22      23     24\n",
       "f      15     16     17      18     19"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sort_index --> axis (index, columns to direct sorting), ascending)\n",
    "# axis = 0 is Y\n",
    "df_rd.sort_index(axis=0, ascending = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>fifth</th>\n",
       "      <th>first</th>\n",
       "      <th>fourth</th>\n",
       "      <th>second</th>\n",
       "      <th>third</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>7</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>12</td>\n",
       "      <td>11</td>\n",
       "      <td>13</td>\n",
       "      <td>10</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>f</th>\n",
       "      <td>17</td>\n",
       "      <td>16</td>\n",
       "      <td>18</td>\n",
       "      <td>15</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>e</th>\n",
       "      <td>22</td>\n",
       "      <td>21</td>\n",
       "      <td>23</td>\n",
       "      <td>20</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fifth  first  fourth  second  third\n",
       "b      2      1       3       0      4\n",
       "a      7      6       8       5      9\n",
       "d     12     11      13      10     14\n",
       "f     17     16      18      15     19\n",
       "e     22     21      23      20     24"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_rd.sort_index(axis=1, ascending = True)\n",
    "# axis = 1 is X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "11    -234\n",
       "0        1\n",
       "1        2\n",
       "2        3\n",
       "5        3\n",
       "3        5\n",
       "4        6\n",
       "6        7\n",
       "7        9\n",
       "12      32\n",
       "9       56\n",
       "10     234\n",
       "8     2123\n",
       "dtype: int64"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser_11 = Series([1,2,3,5,6,3,7,9,2123,56,234,-234,32])\n",
    "ser_11 = ser_11.sort_values()\n",
    "ser_11"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "11     1.0\n",
       "0      2.0\n",
       "1      3.0\n",
       "2      4.5\n",
       "5      4.5\n",
       "3      6.0\n",
       "4      7.0\n",
       "6      8.0\n",
       "7      9.0\n",
       "12    10.0\n",
       "9     11.0\n",
       "10    12.0\n",
       "8     13.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser_11.rank()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>bar</th>\n",
       "      <th>baz</th>\n",
       "      <th>foo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-5</td>\n",
       "      <td>-1</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>-5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>7</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>9</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   bar  baz  foo\n",
       "0   -5   -1    7\n",
       "1    4    2   -5\n",
       "2    2    3    7\n",
       "3    0    0    4\n",
       "4    4    5    2\n",
       "5    7    9    0\n",
       "6    7    9    4\n",
       "7    8    5    7"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_13 = DataFrame({'foo' : [7, -5, 7, 4, 2, 0, 4, 7],\n",
    "                   'bar' : [-5, 4, 2, 0, 4, 7, 7, 8],\n",
    "                   'baz' : [-1, 2, 3, 0, 5, 9, 9, 5]})\n",
    "df_13"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>bar</th>\n",
       "      <th>baz</th>\n",
       "      <th>foo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.5</td>\n",
       "      <td>5.5</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.5</td>\n",
       "      <td>7.5</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.5</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>5.5</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   bar  baz  foo\n",
       "0  1.0  1.0  7.0\n",
       "1  4.5  3.0  1.0\n",
       "2  3.0  4.0  7.0\n",
       "3  2.0  2.0  4.5\n",
       "4  4.5  5.5  3.0\n",
       "5  6.5  7.5  2.0\n",
       "6  6.5  7.5  4.5\n",
       "7  8.0  5.5  7.0"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_13.rank()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bar    27\n",
       "baz    32\n",
       "foo    26\n",
       "dtype: int64"
      ]
     },
     "execution_count": 132,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_13.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     1\n",
       "1     1\n",
       "2    12\n",
       "3     4\n",
       "4    11\n",
       "5    16\n",
       "6    20\n",
       "7    20\n",
       "dtype: int64"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_13.sum(axis=1)\n",
    "\n",
    "# This sums the rows, no the columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.0</td>\n",
       "      <td>VA</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.1</td>\n",
       "      <td>VA</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.2</td>\n",
       "      <td>VA</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>MD</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.1</td>\n",
       "      <td>MD</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   population state  year\n",
       "0         5.0    VA  2012\n",
       "1         5.1    VA  2013\n",
       "2         5.2    VA  2014\n",
       "3         4.0    MD  2014\n",
       "4         4.1    MD  2015"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
    "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
    "          'population' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
    "df_1 = DataFrame(data_1)\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.0</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.1</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.2</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>MD</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.1</td>\n",
       "      <td>MD</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   population     state  year\n",
       "0         5.0  Virginia  2012\n",
       "1         5.1  Virginia  2013\n",
       "2         5.2  Virginia  2014\n",
       "3         4.0        MD  2014\n",
       "4         4.1        MD  2015"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_1.replace('VA', 'Virginia', inplace=True)\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.0</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.1</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.2</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>Maryland</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.1</td>\n",
       "      <td>Maryland</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   population     state  year\n",
       "0         5.0  Virginia  2012\n",
       "1         5.1  Virginia  2013\n",
       "2         5.2  Virginia  2014\n",
       "3         4.0  Maryland  2014\n",
       "4         4.1  Maryland  2015"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# What if you want to just edit one column\n",
    "df_1.replace({'state' : { 'MD' : 'Maryland' }}, inplace=True)\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Virginia</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Virginia</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Virginia</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Maryland</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Maryland</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      state  year\n",
       "0  Virginia  2012\n",
       "1  Virginia  2013\n",
       "2  Virginia  2014\n",
       "3  Maryland  2014\n",
       "4  Maryland  2015"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_2 = df_1.drop('population', axis = 1)\n",
    "df_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.0</td>\n",
       "      <td>NY</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.1</td>\n",
       "      <td>NY</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6.2</td>\n",
       "      <td>NY</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.0</td>\n",
       "      <td>FL</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.1</td>\n",
       "      <td>FL</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   population state  year\n",
       "0         6.0    NY  2012\n",
       "1         6.1    NY  2013\n",
       "2         6.2    NY  2014\n",
       "3         3.0    FL  2014\n",
       "4         3.1    FL  2015"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Concat with pandas adds more rows to the bottom of one of the df\n",
    "\n",
    "data_2 = {'state' : ['NY', 'NY', 'NY', 'FL', 'FL'],\n",
    "          'year' : [2012, 2013, 2014, 2014, 2015],\n",
    "          'population' : [6.0, 6.1, 6.2, 3.0, 3.1]}\n",
    "df_3 = DataFrame(data_2)\n",
    "df_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>state</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.0</td>\n",
       "      <td>NY</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.1</td>\n",
       "      <td>NY</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6.2</td>\n",
       "      <td>NY</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.0</td>\n",
       "      <td>FL</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.1</td>\n",
       "      <td>FL</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Virginia</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Maryland</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Maryland</td>\n",
       "      <td>2015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   population     state  year\n",
       "0         6.0        NY  2012\n",
       "1         6.1        NY  2013\n",
       "2         6.2        NY  2014\n",
       "3         3.0        FL  2014\n",
       "4         3.1        FL  2015\n",
       "0         NaN  Virginia  2012\n",
       "1         NaN  Virginia  2013\n",
       "2         NaN  Virginia  2014\n",
       "3         NaN  Maryland  2014\n",
       "4         NaN  Maryland  2015"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_concat = pd.concat([df_3, df_2])\n",
    "df_concat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}