data_analysis_with_pandas_dataFrame_1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pandas DataFrame overview\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**A DataFrame represents a rectangular table of data and contains an ordered collection of columns, each of which can be a different value type (numeric, string,\n",
    "boolean, etc.). The DataFrame has both a row and column index**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# DataFrame\n",
    "![dataframe](photos/finalpandas.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   apples  oranges\n",
      "0       3        3\n",
      "1       2        4\n",
      "2       0        7\n",
      "3       1        8\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "apples = pd.Series([3,2,0,1])\n",
    "oranges = pd.Series([3,4,7,8])\n",
    "\n",
    "#print(apples, oranges)\n",
    "data = {\"apples\": apples, \"oranges\": oranges}\n",
    "fruits_df = pd.DataFrame(data)\n",
    "print(fruits_df)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# keep in mind, Indexes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     apples  oranges\n",
      "a       3.0      NaN\n",
      "b       2.0      NaN\n",
      "c       0.0      NaN\n",
      "d       1.0      NaN\n",
      "mon     NaN      3.0\n",
      "thr     NaN      1.0\n",
      "tue     NaN      2.0\n",
      "wed     NaN      0.0\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "apples = pd.Series([3,2,0,1], [\"a\", \"b\", \"c\", \"d\"] )\n",
    "oranges = pd.Series([3,2,0,1], index = [\"mon\", \"tue\", \"wed\", \"thr\"])\n",
    "\n",
    "#print(apples, oranges)\n",
    "data = {\"apples\": apples, \"oranges\": oranges}\n",
    "fruits_df = pd.DataFrame(data)\n",
    "print(fruits_df)\n",
    "# index not matched"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     apples  oranges\n",
      "mon       3        3\n",
      "tue       2        2\n",
      "wed       0        0\n",
      "thr       1        1\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "apples = pd.Series([3,2,0,1] , index = [\"mon\", \"tue\", \"wed\", \"thr\"] )\n",
    "oranges = pd.Series([3,2,0,1], index = [\"mon\", \"tue\", \"wed\", \"thr\"])\n",
    "\n",
    "#print(apples,\"\\n\", oranges)\n",
    "data = {\"apples\": apples, \"oranges\": oranges}\n",
    "fruits_df = pd.DataFrame(data)\n",
    "print(fruits_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      state  year  pop\n",
      "1st    Ohio  2000  1.5\n",
      "2nd    Ohio  2001  1.7\n",
      "3rd    Ohio  2002  3.6\n",
      "4th  Nevada  2001  2.4\n",
      "5th  Nevada  2002  2.9\n",
      "6th  Nevada  2003  3.2\n"
     ]
    }
   ],
   "source": [
    "state = ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada']\n",
    "data = {'state': state ,\n",
    "        'year' : [2000, 2001, 2002, 2001, 2002, 2003],\n",
    "        'pop'  : [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}\n",
    "state_pop_df = pd.DataFrame(data \n",
    "                     , index = ['1st', '2nd', '3rd', \n",
    "                                '4th', '5th','6th'] )\n",
    "print(state_pop_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>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": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#state_pop_df.head()\n",
    "state_pop_df =pd.DataFrame(data, columns=['year', 'state', 'pop'])\n",
    "state_pop_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>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": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'],\n",
    "index=['one', 'two', 'three', 'four','five', 'six'])\n",
    "frame2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['year', 'state', 'pop', 'debt'], dtype='object')\n",
      "Index(['one', 'two', 'three', 'four', 'five', 'six'], dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(frame2.columns)\n",
    "print( frame2.index )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# A column in a DataFrame can be retrieved as a Series either by dict-like notation or by attribute:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "one        Ohio\n",
       "two        Ohio\n",
       "three      Ohio\n",
       "four     Nevada\n",
       "five     Nevada\n",
       "six      Nevada\n",
       "Name: state, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#print(data)\n",
    "#data['state']\n",
    "# this is dictinary like notation to access or extract\n",
    "# dataframe column data\n",
    "frame2[\"state\"]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "one        Ohio\n",
       "two        Ohio\n",
       "three      Ohio\n",
       "four     Nevada\n",
       "five     Nevada\n",
       "six      Nevada\n",
       "Name: state, dtype: object"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# there frame2 is another method , attribute style of accessing\n",
    "# dataframe data.\n",
    "frame2.state"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "year     2001\n",
      "state    Ohio\n",
      "pop       1.7\n",
      "debt      NaN\n",
      "Name: two, dtype: object\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>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": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(frame2.loc['two'] )\n",
    "state_pop_df.head()\n",
    "frame2.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Columns can be modified by assignment. For example, the empty 'debt' column\n",
    "could be assigned a scalar value or an array of values:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>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>16.5</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",
       "    </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",
       "    </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",
       "    </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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt\n",
       "one    2000    Ohio  1.5  16.5\n",
       "two    2001    Ohio  1.7  16.5\n",
       "three  2002    Ohio  3.6  16.5\n",
       "four   2001  Nevada  2.4  16.5\n",
       "five   2002  Nevada  2.9  16.5"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frame2['debt'] = 16.5\n",
    "frame2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6\n",
      "[0. 1. 2. 3. 4. 5.]\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>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>0.0</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",
       "    </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",
       "    </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",
       "    </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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>six</th>\n",
       "      <td>2003</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>3.2</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt\n",
       "one    2000    Ohio  1.5   0.0\n",
       "two    2001    Ohio  1.7   1.0\n",
       "three  2002    Ohio  3.6   2.0\n",
       "four   2001  Nevada  2.4   3.0\n",
       "five   2002  Nevada  2.9   4.0\n",
       "six    2003  Nevada  3.2   5.0"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# important cell for codes review\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "frame2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'],\n",
    "index=['one', 'two', 'three', 'four','five', 'six'])\n",
    "\n",
    "print(len(frame2))\n",
    "rng = np.arange(6.0)\n",
    "print(rng)\n",
    "frame2['debt'] = rng\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# point to remember , inserting new values, needs to be match in length (number of elements)"
   ]
  },
  {
   "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>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>-1.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>2001</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>1.7</td>\n",
       "      <td>-1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three</th>\n",
       "      <td>2002</td>\n",
       "      <td>Ohio</td>\n",
       "      <td>3.6</td>\n",
       "      <td>-1.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>four</th>\n",
       "      <td>2001</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.4</td>\n",
       "      <td>-1.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>five</th>\n",
       "      <td>2002</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>2.9</td>\n",
       "      <td>-1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>six</th>\n",
       "      <td>2003</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>3.2</td>\n",
       "      <td>-1.7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       year   state  pop  debt\n",
       "one    2000    Ohio  1.5  -1.2\n",
       "two    2001    Ohio  1.7  -1.5\n",
       "three  2002    Ohio  3.6  -1.7\n",
       "four   2001  Nevada  2.4  -1.2\n",
       "five   2002  Nevada  2.9  -1.5\n",
       "six    2003  Nevada  3.2  -1.7"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val = pd.Series([-1.2, -1.5, -1.7, -1.2, -1.5, -1.7, 2.2],\n",
    "            index=['one', 'two', 'three', 'four', 'five', 'six', 'seven'])\n",
    "frame2['debt'] = val\n",
    "frame2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>-1.2</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>-1.5</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>six</th>\n",
       "      <td>2003</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>3.2</td>\n",
       "      <td>2.6</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  -1.2\n",
       "three  2002    Ohio  3.6   NaN\n",
       "four   2001  Nevada  2.4  -1.5\n",
       "five   2002  Nevada  2.9  -1.7\n",
       "six    2003  Nevada  3.2   2.6"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val = pd.Series([-1.2, -1.5, -1.7, 2.6], index=['two', 'four', 'five', 'six'])\n",
    "frame2['debt'] = val\n",
    "frame2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# remmeber! index length must be equal to values ( or , do not provide index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Mind Teaser !!\n",
    "#Assigning a column that already exist will ________ and \n",
    "# assigning a column that does not exist will ________\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0      blue\n",
      "3    purple\n",
      "6    yellow\n",
      "dtype: object\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0      blue\n",
       "1      blue\n",
       "2      blue\n",
       "3    purple\n",
       "4    purple\n",
       "5    purple\n",
       "6    yellow\n",
       "7    yellow\n",
       "8    yellow\n",
       "dtype: object"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "obj3 = pd.Series(['blue', 'purple', 'yellow'], index=[0, 3, 6])\n",
    "print( obj3 )\n",
    "obj3 =obj3.reindex(range(9), method='ffill')\n",
    "obj3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Ohio  Texas  California\n",
      "a     0      1           2\n",
      "c     3      4           5\n",
      "d     6      7           8\n",
      "   Ohio  Texas  California\n",
      "a     0      1           2\n",
      "b     0      1           2\n",
      "c     3      4           5\n",
      "d     6      7           8\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "states = pd.DataFrame(np.arange(9).reshape((3, 3) ),\n",
    "index=['a', 'c', 'd'], columns=['Ohio', 'Texas', 'California'])\n",
    "\n",
    "print(states)\n",
    "# without ffile \n",
    "states = states.reindex(['a', 'b', 'c', 'd'],method = 'ffill')\n",
    "print(states)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Ohio  Texas  California\n",
      "a     0      1           2\n",
      "c     3      4           5\n",
      "d     6      7           8\n",
      "   Texas  Utah  California  Ohio\n",
      "a      1   NaN           2     0\n",
      "c      4   NaN           5     3\n",
      "d      7   NaN           8     6\n"
     ]
    }
   ],
   "source": [
    "states = pd.DataFrame(np.arange(9).reshape((3, 3) ),\n",
    "index=['a', 'c', 'd'], columns=['Ohio', 'Texas', 'California'])\n",
    "print(states)\n",
    "states_name = ['Texas', 'Utah', 'California','Ohio']\n",
    "\n",
    "states =states.reindex(columns=states_name)\n",
    "print(states)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Deleting data (row or column from dataframe) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          one  two  three  four\n",
      "Ohio        0    1      2     3\n",
      "Colorado    4    5      6     7\n",
      "Utah        8    9     10    11\n",
      "New York   12   13     14    15\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "data_df = pd.DataFrame(np.arange(16).reshape((4, 4)), \n",
    "             index=['Ohio', 'Colorado', 'Utah', 'New York'],\n",
    "             columns=['one', 'two', 'three', 'four'])\n",
    "print(data_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          one  two  three  four\n",
      "Ohio        0    1      2     3\n",
      "Colorado    4    5      6     7\n",
      "Utah        8    9     10    11\n",
      "New York   12   13     14    15 \n",
      "\n",
      "          one  three  four\n",
      "Ohio        0      2     3\n",
      "Colorado    4      6     7\n",
      "Utah        8     10    11\n",
      "New York   12     14    15\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "data_df = pd.DataFrame(np.arange(16).reshape((4, 4)), \n",
    "             index=['Ohio', 'Colorado', 'Utah', 'New York'],\n",
    "             columns=['one', 'two', 'three', 'four'])\n",
    "\n",
    "print(data_df, \"\\n\")\n",
    "\n",
    "# dataframe.drop method would return a new dataframe without \n",
    "# having deleted rows. so store its into to dataframe variable\n",
    "# or use inplace=True while droping rows or column\n",
    "\n",
    "#data_df.drop(['Colorado', 'Ohio'], inplace =True)\n",
    "#print(data_df)\n",
    "\n",
    "#You can drop values from the columns by passing axis=1 \n",
    "#or axis='columns' :\n",
    "data_df = data_df.drop('two', axis=1)\n",
    "print(data_df)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Indexing, Selection, and Filtering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          one  two  three  four\n",
      "Ohio        0    1      2     3\n",
      "Colorado    4    5      6     7\n",
      "Utah        8    9     10    11\n",
      "New York   12   13     14    15 \n",
      "\n",
      "Ohio        False\n",
      "Colorado     True\n",
      "Utah         True\n",
      "New York     True\n",
      "Name: three, dtype: bool\n",
      "          one  two  three  four\n",
      "Colorado    4    5      6     7\n",
      "Utah        8    9     10    11\n",
      "New York   12   13     14    15\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "data_df = pd.DataFrame(np.arange(16).reshape((4, 4)), \n",
    "             index=['Ohio', 'Colorado', 'Utah', 'New York'],\n",
    "             columns=['one', 'two', 'three', 'four'])\n",
    "\n",
    "#print(data_df, \"\\n\")\n",
    "#data_df[ [\"one\", \"three\"] ]\n",
    "#print( data_df[2:] )\n",
    "#print(data_df.Ohio[:2])\n",
    "\n",
    "# Conditonal Selection\n",
    "#print ( data_df[data_df['three'] > 5] )\n",
    "print(data_df, \"\\n\")\n",
    "\n",
    "df2 = data_df[\"three\"] > 5 \n",
    "print(df2)\n",
    "print( data_df[ data_df[\"three\"] > 5  ] )\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Selection with loc and iloc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          one  two  three  four\n",
      "Ohio        0    1      2     3\n",
      "Colorado    4    5      6     7\n",
      "Utah        8    9     10    11\n",
      "New York   12   13     14    15\n",
      "          one  two  three\n",
      "Ohio        0    1      2\n",
      "Colorado    4    5      6\n",
      "Utah        8    9     10\n",
      "New York   12   13     14\n",
      "          one  two  three  four\n",
      "Ohio        0    1      2     3\n",
      "Colorado    4    5      6     7\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "data_df = pd.DataFrame(np.arange(16).reshape((4, 4)), \n",
    "             index=['Ohio', 'Colorado', 'Utah', 'New York'],\n",
    "             columns=['one', 'two', 'three', 'four'])\n",
    "\n",
    "#print(data_df, \"\\n\")\n",
    "# in the loc method specify row label\n",
    "# then , \n",
    "# then specify column names\n",
    "# remember! mutiple column names require array notation\n",
    "#print( data_df.loc['Colorado', ['two',  'three'] ] )\n",
    "#print(\"\\n\")\n",
    "#print( data_df.iloc[2, [3, 0, 1] ] ) \n",
    "print( data_df.iloc[:])\n",
    "print ( data_df.iloc[ : , :3 ] )\n",
    "print( data_df.iloc[:2])\n",
    "       #[data_df.three > 5] )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Arithmetic and Data Alignment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "            b    c    d\n",
      "Ohio      0.0  1.0  2.0\n",
      "Texas     3.0  4.0  5.0\n",
      "Colorado  6.0  7.0  8.0\n",
      "          b     d     e\n",
      "Utah    0.0   1.0   2.0\n",
      "Ohio    3.0   4.0   5.0\n",
      "Texas   6.0   7.0   8.0\n",
      "Oregon  9.0  10.0  11.0\n",
      "\n",
      "            b   c     d   e\n",
      "Colorado  NaN NaN   NaN NaN\n",
      "Ohio      3.0 NaN   6.0 NaN\n",
      "Oregon    NaN NaN   NaN NaN\n",
      "Texas     9.0 NaN  12.0 NaN\n",
      "Utah      NaN NaN   NaN NaN\n"
     ]
    }
   ],
   "source": [
    "#print(list('bcd'))\n",
    "df1 = pd.DataFrame(np.arange(9.).reshape((3, 3)), \n",
    "                   columns=list('bcd'), \n",
    "                   index=['Ohio', 'Texas', 'Colorado'])\n",
    "\n",
    "df2 = pd.DataFrame(np.arange(12.).reshape((4, 3)), \n",
    "                   columns=list('bde'),\n",
    "                    index=['Utah', 'Ohio', 'Texas', 'Oregon'])\n",
    "\n",
    "print(df1)\n",
    "print(df2)\n",
    "print()\n",
    "# applying plus operation between two data frames\n",
    "df3 = df1 + df2\n",
    "\n",
    "print(df3)\n",
    "# your work is to fill all Nan values of  this df3 with a number, \n",
    "# choice of number is yours"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Arithmetic methods with fill values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     a    b     c     d\n",
      "0  0.0  1.0   2.0   3.0\n",
      "1  4.0  5.0   6.0   7.0\n",
      "2  8.0  9.0  10.0  11.0\n",
      "      a     b     c     d     e\n",
      "0   0.0   1.0   2.0   3.0   4.0\n",
      "1   5.0   NaN   7.0   8.0   9.0\n",
      "2  10.0  11.0  12.0  13.0  14.0\n",
      "3  15.0  16.0  17.0  18.0  19.0\n",
      "\n",
      "direct + operation without fill_value\n",
      "      a     b     c     d   e\n",
      "0   0.0   2.0   4.0   6.0 NaN\n",
      "1   9.0   NaN  13.0  15.0 NaN\n",
      "2  18.0  20.0  22.0  24.0 NaN\n",
      "3   NaN   NaN   NaN   NaN NaN\n",
      "--------\n",
      "\n",
      "addition using a method with replacing Nan with 0\n",
      "      a     b     c     d     e\n",
      "0   0.0   2.0   4.0   6.0   4.0\n",
      "1   9.0   5.0  13.0  15.0   9.0\n",
      "2  18.0  20.0  22.0  24.0  14.0\n",
      "3  15.0  16.0  17.0  18.0  19.0\n"
     ]
    }
   ],
   "source": [
    "df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)),\n",
    "                   columns=list('abcd'))\n",
    "df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)),\n",
    "                    columns=list('abcde'))\n",
    "print(df1)\n",
    "#print(df2)\n",
    "\n",
    "df2.loc[1, 'b'] = np.nan\n",
    "print(df2)\n",
    "df3 = df1 + df2\n",
    "print()\n",
    "print(\"direct + operation without fill_value\")\n",
    "print(df3)\n",
    "print(\"--------\")\n",
    "print()\n",
    "# We can use add method for filling NaN cells with a value\n",
    "# Nan will be replaced by 0 and then addition operation will apply\n",
    "print(\"addition using a method with replacing Nan with 0\")\n",
    "df3 = df1.add(df2, fill_value=0)\n",
    "print(df3)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Operations between DataFrame and Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          b     d     e\n",
      "Utah    0.0   1.0   2.0\n",
      "Ohio    3.0   4.0   5.0\n",
      "Texas   6.0   7.0   8.0\n",
      "Oregon  9.0  10.0  11.0\n",
      "---- using new series\n",
      "Index(['b', 'd', 'e'], dtype='object') [1 2 3]\n",
      "          b    d    e\n",
      "Utah   -1.0 -1.0 -1.0\n",
      "Ohio    2.0  2.0  2.0\n",
      "Texas   5.0  5.0  5.0\n",
      "Oregon  8.0  8.0  8.0\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "frame = pd.DataFrame(np.arange(12.).reshape((4, 3)),\n",
    "            columns=list('bde'), \n",
    "                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])\n",
    "# iloc syntax\n",
    "# iloc[start_row_pos:end_row_pos, start_column_pos: end_col_positin ]\n",
    "series = frame.iloc[0]\n",
    "print(frame)\n",
    "#print(series)\n",
    "#print(series.values)\n",
    "#print(series.index)\n",
    "#print(frame - series)\n",
    "# step 1: run above commands after uncomment\n",
    "# step 2: comment above prints except the line contains print(frame)\n",
    "# write following lines\n",
    "# and run the cell again\n",
    "print(\"---- using new series\")\n",
    "series = pd.Series([1,2,3], index =list('bde') )\n",
    "print(series.index, series.values)\n",
    "print(frame - series)\n",
    "# dateframe column names will be match with series index\n",
    "# because its rows wise broadcasting operation\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Function Application and Mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               b         d         e\n",
      "Utah   -0.312886  1.911314  0.350087\n",
      "Ohio   -0.188534  1.437493  1.946389\n",
      "Texas   0.258189  0.070244 -0.051748\n",
      "Oregon  2.068551 -0.207543  1.917078\n",
      "b    2.381437\n",
      "d    2.118857\n",
      "e    1.998137\n",
      "dtype: float64 <class 'pandas.core.series.Series'>\n",
      "Utah      2.224200\n",
      "Ohio      2.134923\n",
      "Texas     0.309937\n",
      "Oregon    2.276094\n",
      "dtype: float64\n",
      "            b         d         e\n",
      "min -0.312886 -0.207543 -0.051748\n",
      "max  2.068551  1.911314  1.946389 <class 'pandas.core.frame.DataFrame'>\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "frame = frame = pd.DataFrame(np.random.randn(4, 3), \n",
    "                             columns=list('bde'), \n",
    "                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])\n",
    "print(frame)\n",
    "#print(np.abs(frame))\n",
    "\n",
    "#print(frame[\"d\"]. min())\n",
    "#print(frame[\"d\"].max())\n",
    "#print(frame[\"d\"].max() - frame[\"d\"]. min())\n",
    "\n",
    "f = lambda x: x.max() - x.min() \n",
    "df = frame.apply(f)\n",
    "print(df, type(df))\n",
    "df = frame.apply(f, axis=1)\n",
    "print(df)\n",
    "\n",
    "def min_max(x):\n",
    "    minimum = x.min()\n",
    "    maximum = x.max()\n",
    "    return pd.Series( [ x.min(),x.max() ], index=['min', 'max'])    \n",
    "\n",
    "df = frame.apply(min_max)\n",
    "print(df, type(df))\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}