lesson 2 - Machine learning .ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "list1= (1,2,2,2,2,3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list1.index(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list1[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list1.count(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "s =set(list1)\n",
    "mul = lambda s : s+1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n = lambda num : num**3 \n",
    "n(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "unsupported operand type(s) for +: 'set' and 'int'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-26-43dcba5391b6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmul\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-25-186b96b9aa65>\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(s)\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0ms\u001b[0m \u001b[0;34m=\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlist1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mmul\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mlambda\u001b[0m \u001b[0ms\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0ms\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m: unsupported operand type(s) for +: 'set' and 'int'"
     ]
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from random import randint as ri\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(1, 1),\n",
       " (1, 2),\n",
       " (1, 3),\n",
       " (1, 4),\n",
       " (1, 5),\n",
       " (1, 6),\n",
       " (1, 7),\n",
       " (1, 8),\n",
       " (1, 9),\n",
       " (2, 1),\n",
       " (2, 2),\n",
       " (2, 3),\n",
       " (2, 4),\n",
       " (2, 5),\n",
       " (2, 6),\n",
       " (2, 7),\n",
       " (2, 8),\n",
       " (2, 9),\n",
       " (3, 1),\n",
       " (3, 2),\n",
       " (3, 3),\n",
       " (3, 4),\n",
       " (3, 5),\n",
       " (3, 6),\n",
       " (3, 7),\n",
       " (3, 8),\n",
       " (3, 9),\n",
       " (4, 1),\n",
       " (4, 2),\n",
       " (4, 3),\n",
       " (4, 4),\n",
       " (4, 5),\n",
       " (4, 6),\n",
       " (4, 7),\n",
       " (4, 8),\n",
       " (4, 9),\n",
       " (5, 1),\n",
       " (5, 2),\n",
       " (5, 3),\n",
       " (5, 4),\n",
       " (5, 5),\n",
       " (5, 6),\n",
       " (5, 7),\n",
       " (5, 8),\n",
       " (5, 9),\n",
       " (6, 1),\n",
       " (6, 2),\n",
       " (6, 3),\n",
       " (6, 4),\n",
       " (6, 5),\n",
       " (6, 6),\n",
       " (6, 7),\n",
       " (6, 8),\n",
       " (6, 9),\n",
       " (7, 1),\n",
       " (7, 2),\n",
       " (7, 3),\n",
       " (7, 4),\n",
       " (7, 5),\n",
       " (7, 6),\n",
       " (7, 7),\n",
       " (7, 8),\n",
       " (7, 9),\n",
       " (8, 1),\n",
       " (8, 2),\n",
       " (8, 3),\n",
       " (8, 4),\n",
       " (8, 5),\n",
       " (8, 6),\n",
       " (8, 7),\n",
       " (8, 8),\n",
       " (8, 9),\n",
       " (9, 1),\n",
       " (9, 2),\n",
       " (9, 3),\n",
       " (9, 4),\n",
       " (9, 5),\n",
       " (9, 6),\n",
       " (9, 7),\n",
       " (9, 8),\n",
       " (9, 9)]"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list2 = []\n",
    "for (a) in range (1,10):\n",
    "    for (b) in range (1,10):\n",
    "        a==ri(0,10)\n",
    "        b==ri(0,10)\n",
    "        list2.append((a,b))\n",
    "list2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[4, 4, 6, 10, 10, 0, 0, 2, 10, 8]"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(filter(lambda num: num%2==0, list2)) ## list out items that meet the lambda expression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['hio', 'jou', 'jjj']"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = \"hio jou jjj \"\n",
    "list(s.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "the diamter of the planet earth is 12742\n"
     ]
    }
   ],
   "source": [
    "planet = \"earth\"\n",
    "diameter = 12742\n",
    "print (\"the diamter of the planet {} is {}\".format (planet, diameter))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'domain.com'"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\"user@domain.com\").split(\"@\")[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n"
     ]
    }
   ],
   "source": [
    "s = \"i love my DOG DOGDOGGOGODDOGDOG\"\n",
    "def dog(s):\n",
    "    count= 0\n",
    "    for word in s.split():\n",
    "        if \"dog\" in s.lower():\n",
    "            count+=1\n",
    "    print(count)\n",
    "dog(s)           "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 185,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['pepper']"
      ]
     },
     "execution_count": 185,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list3= [\"Soup\", \"salad\", \"salt\", \"pepper\", \"Srange\"]\n",
    "list(filter(lambda word : word[0].lower()!=\"s\", list3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "metadata": {},
   "outputs": [],
   "source": [
    "def ticket(speed, birtday): \n",
    "    if birtday: \n",
    "        speeding = speed -5\n",
    "    else:\n",
    "        speeding = speed\n",
    "        \n",
    "    if speeding<=60:\n",
    "        return \"no ticket\"\n",
    "    elif 60<speeding<=80:\n",
    "        return \"small ticket\"\n",
    "    else:\n",
    "        return \"big ticket\"\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 202,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'small ticket'"
      ]
     },
     "execution_count": 202,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ticket(67, True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Numpy \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "my_list = [1,2,3,4,5,6]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 2, 3, 4, 5, 6])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr = np.array(my_list)\n",
    "arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 2],\n",
       "       [3, 4],\n",
       "       [5, 6]])"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.reshape(3,2) ## tranform an array from one dimentional vector to a matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0,  1],\n",
       "       [ 2,  3],\n",
       "       [ 4,  5],\n",
       "       [ 6,  7],\n",
       "       [ 8,  9],\n",
       "       [10, 11],\n",
       "       [12, 13],\n",
       "       [14, 15],\n",
       "       [16, 17],\n",
       "       [18, 19],\n",
       "       [20, 21]])"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(np.arange(0,22)).reshape(11,2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[0., 0., 0., 0.],\n",
       "        [0., 0., 0., 0.]]), array([0., 0., 0., 0., 0.]))"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.zeros((2,4)), np.zeros(5)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[1., 1.],\n",
       "        [1., 1.]]), array([1., 1., 1., 1., 1.]))"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "np.ones((2,2)), np.ones(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0.        ,  1.66666667,  3.33333333,  5.        ,  6.66666667,\n",
       "        8.33333333, 10.        ])"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.linspace(0,10,7) ## 7 equaly spaces floats within the range"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 0., 0., 0., 0., 0.],\n",
       "       [0., 1., 0., 0., 0., 0.],\n",
       "       [0., 0., 1., 0., 0., 0.],\n",
       "       [0., 0., 0., 1., 0., 0.],\n",
       "       [0., 0., 0., 0., 1., 0.],\n",
       "       [0., 0., 0., 0., 0., 1.]])"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " np.eye(6) #identity matrix, square matrix of 0 and 1 6X6\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3, 2])"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.randint(0,10,2) ## 2 random nubmers from 0 to 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.21629045, 0.94098275, 0.48360987, 0.5343739 , 0.67732959])"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.rand(5)  # 5 random equaly distributed from 0 to 1, similar to linspace, but from 0 to 1 only \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.02483838, 0.19002964, 0.01629712, 0.1209968 , 0.09328501],\n",
       "       [0.46951317, 0.98907665, 0.30508063, 0.43868742, 0.69052696],\n",
       "       [0.2778694 , 0.78314267, 0.00983983, 0.66355287, 0.28961134],\n",
       "       [0.48138857, 0.24869418, 0.68536598, 0.86804309, 0.8769666 ],\n",
       "       [0.16898152, 0.41726398, 0.9423215 , 0.59826855, 0.38138818]])"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.rand(5,5) # same like above, but a 5X5 matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.52226783, -0.70483112, -0.81087247,  0.7894285 ,  1.37943036])"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.randn(5) ## ramdon normal distribution centered around 0  5-by-5 matrix of normally distributed random numbers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.09014517,  0.09299117, -1.08762616,  0.02214307, -0.87952078],\n",
       "       [ 0.54006791,  0.03670679, -0.81753255, -0.91496387,  0.92452712]])"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.randn(2,5) # ramdon normal distribution "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[24, 24,  9, 16, 12],\n",
       "       [13, 11, 20,  6,  9]])"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(np.random.randint(0,25,10)).reshape(2,5)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "21"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(np.random.randint(1,25,10)).max()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(np.random.randint(1,25,10)).min()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 7, 17, 18, 11,  2, 15, 24, 15, 16, 12])"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr = np.random.randint(0,25,10)\n",
    "arr "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "24"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.argmax() ##index of max number in the array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.min()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.argmin()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10"
      ]
     },
     "execution_count": 144,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 7, 17, 18, 11,  2],\n",
       "       [15, 24, 15, 16, 12]])"
      ]
     },
     "execution_count": 149,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr = arr.reshape(2,5)\n",
    "arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 5)"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('int64')"
      ]
     },
     "execution_count": 153,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "24"
      ]
     },
     "execution_count": 156,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr[1][1] ## just like a list "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,\n",
       "       17, 18, 19, 20, 21, 22, 23, 24])"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r = np.arange(0,25)\n",
    "r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3, 4])"
      ]
     },
     "execution_count": 177,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r[:5] ## up to and including index 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,\n",
       "       22, 23, 24])"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r[5:] ## from and excluding index 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,\n",
       "       17, 18, 19, 20, 21, 22, 23, 24])"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r = np.arange(0,25)\n",
    "r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([100, 100, 100, 100, 100,   5,   6,   7,   8,   9,  10,  11,  12,\n",
       "        13,  14,  15,  16,  17,  18,  19,  20,  21,  22,  23,  24])"
      ]
     },
     "execution_count": 183,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r[0:5]= 100 ## broadcasting, change the value of the first 5 indexed to 100, note it changed the values in the array r\n",
    "r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([100, 100, 100, 100, 100,   5,   6,   7,   8,   9,  10,  11,  12,\n",
       "        13,  14,  15,  16,  17,  18,  19,  20,  21,  22,  23,  24])"
      ]
     },
     "execution_count": 187,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_copy = r.copy() ## made a copy of the array r, now we can broadcase values in the copy without affecting the original array r \n",
    "r_copy "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 199,
   "metadata": {},
   "outputs": [],
   "source": [
    "r_copy[0:5] = np.arange(0,5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 200,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,\n",
       "       17, 18, 19, 20, 21, 22, 23, 24])"
      ]
     },
     "execution_count": 200,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_copy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([100, 100, 100, 100, 100,   5,   6,   7,   8,   9,  10,  11,  12,\n",
       "        13,  14,  15,  16,  17,  18,  19,  20,  21,  22,  23,  24])"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r ## r still shows the changed values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0,  1,  2,  3,  4,  5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12, 13, 14, 15, 16, 17],\n",
       "       [18, 19, 20, 21, 22, 23, 24, 25, 26],\n",
       "       [27, 28, 29, 30, 31, 32, 33, 34, 35],\n",
       "       [36, 37, 38, 39, 40, 41, 42, 43, 44]])"
      ]
     },
     "execution_count": 221,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2 = (np.arange(0,45,1)).reshape(5,9)\n",
    "r_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "11"
      ]
     },
     "execution_count": 224,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2[1][2] ## grabe data from a matrix array using double braket"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "11"
      ]
     },
     "execution_count": 225,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2[1,2] ## grabe data from a matrix array using a single braket (comma), this does no work for lists my_list[1][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0,  1,  2,  3,  4,  5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12, 13, 14, 15, 16, 17],\n",
       "       [18, 19, 20, 21, 22, 23, 24, 25, 26],\n",
       "       [27, 28, 29, 30, 31, 32, 33, 34, 35],\n",
       "       [36, 37, 38, 39, 40, 41, 42, 43, 44]])"
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 4,  5,  6,  7,  8],\n",
       "       [13, 14, 15, 16, 17],\n",
       "       [22, 23, 24, 25, 26]])"
      ]
     },
     "execution_count": 230,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2[:3,4:] ## cool stuff no? "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 238,
   "metadata": {},
   "outputs": [],
   "source": [
    "bool_arr = r_2>30  ## name the bool array that meet the condition "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 239,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44])"
      ]
     },
     "execution_count": 239,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2[bool_arr] ## slice the array using the bool array that meets the condition "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44])"
      ]
     },
     "execution_count": 252,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2[r_2>30]  ## same result in one line of code, as if you wrote select from r_2 when r_2>30"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 266,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 266,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_2.any() ## if any of the values is  of them are true"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10],\n",
       "       [11, 12, 13, 14, 15, 16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25, 26, 27, 28, 29, 30],\n",
       "       [31, 32, 33, 34, 35, 36, 37, 38, 39, 40],\n",
       "       [41, 42, 43, 44, 45, 46, 47, 48, 49, 50]])"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_3 = np.arange(1,51).reshape(5,10)\n",
    "r_3 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[14, 15],\n",
       "       [24, 25]])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_3[1:3,3:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "r_3_list = r_3.tolist() ## convert an array into a list "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10],\n",
       "       [11, 12, 13, 14, 15, 16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25, 26, 27, 28, 29, 30],\n",
       "       [31, 32, 33, 34, 35, 36, 37, 38, 39, 40],\n",
       "       [41, 42, 43, 44, 45, 46, 47, 48, 49, 50]])"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_3\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  2,   4,   6,   8,  10,  12,  14,  16,  18,  20],\n",
       "       [ 22,  24,  26,  28,  30,  32,  34,  36,  38,  40],\n",
       "       [ 42,  44,  46,  48,  50,  52,  54,  56,  58,  60],\n",
       "       [ 62,  64,  66,  68,  70,  72,  74,  76,  78,  80],\n",
       "       [ 82,  84,  86,  88,  90,  92,  94,  96,  98, 100]])"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_3+r_3 # adding arrays, you can +, -, / (as long as not zero) , * "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  3,   6,   9,  12,  15,  18,  21,  24,  27,  30],\n",
       "       [ 33,  36,  39,  42,  45,  48,  51,  54,  57,  60],\n",
       "       [ 63,  66,  69,  72,  75,  78,  81,  84,  87,  90],\n",
       "       [ 93,  96,  99, 102, 105, 108, 111, 114, 117, 120],\n",
       "       [123, 126, 129, 132, 135, 138, 141, 144, 147, 150]])"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_3*3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/msellamia/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:2: RuntimeWarning: invalid value encountered in true_divide\n",
      "  \n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([nan,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,\n",
       "        1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,\n",
       "        1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,\n",
       "        1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.,  1.])"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r_4 = np.arange(0,50)\n",
    "r_4/r_4 ## nan for fist value "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/msellamia/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:1: RuntimeWarning: divide by zero encountered in true_divide\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([       inf, 1.        , 0.5       , 0.33333333, 0.25      ,\n",
       "       0.2       , 0.16666667, 0.14285714, 0.125     , 0.11111111,\n",
       "       0.1       , 0.09090909, 0.08333333, 0.07692308, 0.07142857,\n",
       "       0.06666667, 0.0625    , 0.05882353, 0.05555556, 0.05263158,\n",
       "       0.05      , 0.04761905, 0.04545455, 0.04347826, 0.04166667,\n",
       "       0.04      , 0.03846154, 0.03703704, 0.03571429, 0.03448276,\n",
       "       0.03333333, 0.03225806, 0.03125   , 0.03030303, 0.02941176,\n",
       "       0.02857143, 0.02777778, 0.02702703, 0.02631579, 0.02564103,\n",
       "       0.025     , 0.02439024, 0.02380952, 0.02325581, 0.02272727,\n",
       "       0.02222222, 0.02173913, 0.0212766 , 0.02083333, 0.02040816])"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "1/r_4 ## or infinity inf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,\n",
       "       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,\n",
       "       34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 70])"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.append(r_4, 70) ## add an element to an array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.        , 1.        , 1.41421356, 1.73205081, 2.        ,\n",
       "       2.23606798, 2.44948974, 2.64575131, 2.82842712, 3.        ,\n",
       "       3.16227766, 3.31662479, 3.46410162, 3.60555128, 3.74165739,\n",
       "       3.87298335, 4.        , 4.12310563, 4.24264069, 4.35889894,\n",
       "       4.47213595, 4.58257569, 4.69041576, 4.79583152, 4.89897949,\n",
       "       5.        , 5.09901951, 5.19615242, 5.29150262, 5.38516481,\n",
       "       5.47722558, 5.56776436, 5.65685425, 5.74456265, 5.83095189,\n",
       "       5.91607978, 6.        , 6.08276253, 6.164414  , 6.244998  ,\n",
       "       6.32455532, 6.40312424, 6.4807407 , 6.55743852, 6.63324958,\n",
       "       6.70820393, 6.78232998, 6.8556546 , 6.92820323, 7.        ])"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sqrt(r_4) ## square root"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31, 33,\n",
       "       35, 37, 39, 41, 43, 45, 47, 49, 51, 53, 55, 57, 59, 61, 63, 65, 67,\n",
       "       69])"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "r_5= np.arange(1,70,2)\n",
    "r_5\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "def array_index(array_to_search, value): ## pull out the index on an element in an array \n",
    "    for i in range (0, array_to_search.size):\n",
    "        if array_to_search[i]==value:\n",
    "            return (i)\n",
    "\n",
    "    return (\"no index\")\n",
    "\n",
    "\n",
    "      \n",
    "   \n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "array_index(r_5,25)  ## formula to find the index of a value in an array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [],
   "source": [
    "def array_index(array_to_search, value):\n",
    "    for i in range (0, array_to_search.size):\n",
    "        if array_to_search[i]==value:\n",
    "            print (i)\n",
    "        else:\n",
    "            return \"no index\"\n",
    "        \n",
    "        \n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "metadata": {},
   "outputs": [],
   "source": [
    "#exercies "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])"
      ]
     },
     "execution_count": 145,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.zeros(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1.])"
      ]
     },
     "execution_count": 146,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.ones(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5., 5., 5., 5., 5., 5., 5., 5., 5., 5.])"
      ]
     },
     "execution_count": 149,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.ones(10)*5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38, 40, 42,\n",
       "       44, 46, 48, 50])"
      ]
     },
     "execution_count": 157,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.arange(10,51,2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 1, 2],\n",
       "       [3, 4, 5],\n",
       "       [6, 7, 8]])"
      ]
     },
     "execution_count": 158,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.arange(9).reshape(3,3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 0., 0.],\n",
       "       [0., 1., 0.],\n",
       "       [0., 0., 1.]])"
      ]
     },
     "execution_count": 159,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.eye(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.81272398])"
      ]
     },
     "execution_count": 170,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.rand(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 2.14349829,  0.49350881, -0.30813131,  0.14172124,  0.37825925,\n",
       "       -0.50208449,  1.61207027, -1.21577431,  0.06621232, -0.96604783,\n",
       "        0.47386003,  0.19516475, -2.09549055, -1.7863974 , -1.52576686,\n",
       "       -0.87724112,  0.05358041,  0.03099159,  1.6193956 ,  0.42591518,\n",
       "       -0.90360751, -1.44578694,  0.80141748,  0.15424738,  1.05504723])"
      ]
     },
     "execution_count": 173,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.randn(25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.01, 0.02, 0.03, 0.04, 0.05, 0.06, 0.07, 0.08, 0.09, 0.1 ],\n",
       "       [0.11, 0.12, 0.13, 0.14, 0.15, 0.16, 0.17, 0.18, 0.19, 0.2 ],\n",
       "       [0.21, 0.22, 0.23, 0.24, 0.25, 0.26, 0.27, 0.28, 0.29, 0.3 ],\n",
       "       [0.31, 0.32, 0.33, 0.34, 0.35, 0.36, 0.37, 0.38, 0.39, 0.4 ],\n",
       "       [0.41, 0.42, 0.43, 0.44, 0.45, 0.46, 0.47, 0.48, 0.49, 0.5 ],\n",
       "       [0.51, 0.52, 0.53, 0.54, 0.55, 0.56, 0.57, 0.58, 0.59, 0.6 ],\n",
       "       [0.61, 0.62, 0.63, 0.64, 0.65, 0.66, 0.67, 0.68, 0.69, 0.7 ],\n",
       "       [0.71, 0.72, 0.73, 0.74, 0.75, 0.76, 0.77, 0.78, 0.79, 0.8 ],\n",
       "       [0.81, 0.82, 0.83, 0.84, 0.85, 0.86, 0.87, 0.88, 0.89, 0.9 ],\n",
       "       [0.91, 0.92, 0.93, 0.94, 0.95, 0.96, 0.97, 0.98, 0.99, 1.  ]])"
      ]
     },
     "execution_count": 179,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.arange(0.01,1.01,0.01).reshape(10,10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.        , 0.05263158, 0.10526316, 0.15789474, 0.21052632,\n",
       "       0.26315789, 0.31578947, 0.36842105, 0.42105263, 0.47368421,\n",
       "       0.52631579, 0.57894737, 0.63157895, 0.68421053, 0.73684211,\n",
       "       0.78947368, 0.84210526, 0.89473684, 0.94736842, 1.        ])"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.linspace(0,1,20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5],\n",
       "       [ 6,  7,  8,  9, 10],\n",
       "       [11, 12, 13, 14, 15],\n",
       "       [16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25]])"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat = np.arange(1,26).reshape(5,5)\n",
    "mat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 266,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[12, 13, 14, 15],\n",
       "       [17, 18, 19, 20],\n",
       "       [22, 23, 24, 25]])"
      ]
     },
     "execution_count": 266,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat[2:,1:] ## fuck, use a come, it's not a list!!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 289,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 2],\n",
       "       [ 7],\n",
       "       [12]])"
      ]
     },
     "execution_count": 289,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat[:3,1:2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 290,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5],\n",
       "       [ 6,  7,  8,  9, 10],\n",
       "       [11, 12, 13, 14, 15],\n",
       "       [16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25]])"
      ]
     },
     "execution_count": 290,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 294,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25]])"
      ]
     },
     "execution_count": 294,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat[3:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 296,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "325"
      ]
     },
     "execution_count": 296,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 303,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4,  5],\n",
       "       [ 6,  7,  8,  9, 10],\n",
       "       [11, 12, 13, 14, 15],\n",
       "       [16, 17, 18, 19, 20],\n",
       "       [21, 22, 23, 24, 25]])"
      ]
     },
     "execution_count": 303,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 363,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([55, 60, 65, 70, 75])"
      ]
     },
     "execution_count": 363,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat.sum(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "## array of objects: \n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "arr = np.arange (0,50, dtype=object)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,\n",
       "       19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35,\n",
       "       36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "### NLTK Tokenization \n",
    "import nltk\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "showing info https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/index.xml\n"
     ]
    }
   ],
   "source": [
    "nltk.download()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"WASHINGTON — Petro O. Poroshenko was still the president of Ukraine earlier this year when his team sought a lifeline. With the polls showing him in clear danger of losing his re-election campaign, some of his associates, eager to hold on to their own jobs and influence, took steps that could have yielded a signal of public support from a vital ally: President Trump. Over several weeks in March, the office of Ukraine’s top prosecutor moved ahead on two investigations of intense interest to Mr. Trump. One was focused on an oligarch — previously cleared of wrongdoing by the same prosecutor — whose company employed former Vice President Joseph R. Biden Jr.’s son. The other dealt with the release by a separate Ukrainian law enforcement agency to the media of information that hurt Mr. Trump’s 2016 campaign\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['WASHINGTON',\n",
       " '—',\n",
       " 'Petro',\n",
       " 'O.',\n",
       " 'Poroshenko',\n",
       " 'was',\n",
       " 'still',\n",
       " 'the',\n",
       " 'president',\n",
       " 'of',\n",
       " 'Ukraine',\n",
       " 'earlier',\n",
       " 'this',\n",
       " 'year',\n",
       " 'when',\n",
       " 'his',\n",
       " 'team',\n",
       " 'sought',\n",
       " 'a',\n",
       " 'lifeline.',\n",
       " 'With',\n",
       " 'the',\n",
       " 'polls',\n",
       " 'showing',\n",
       " 'him',\n",
       " 'in',\n",
       " 'clear',\n",
       " 'danger',\n",
       " 'of',\n",
       " 'losing',\n",
       " 'his',\n",
       " 're-election',\n",
       " 'campaign,',\n",
       " 'some',\n",
       " 'of',\n",
       " 'his',\n",
       " 'associates,',\n",
       " 'eager',\n",
       " 'to',\n",
       " 'hold',\n",
       " 'on',\n",
       " 'to',\n",
       " 'their',\n",
       " 'own',\n",
       " 'jobs',\n",
       " 'and',\n",
       " 'influence,',\n",
       " 'took',\n",
       " 'steps',\n",
       " 'that',\n",
       " 'could',\n",
       " 'have',\n",
       " 'yielded',\n",
       " 'a',\n",
       " 'signal',\n",
       " 'of',\n",
       " 'public',\n",
       " 'support',\n",
       " 'from',\n",
       " 'a',\n",
       " 'vital',\n",
       " 'ally:',\n",
       " 'President',\n",
       " 'Trump.',\n",
       " 'Over',\n",
       " 'several',\n",
       " 'weeks',\n",
       " 'in',\n",
       " 'March,',\n",
       " 'the',\n",
       " 'office',\n",
       " 'of',\n",
       " 'Ukraine’s',\n",
       " 'top',\n",
       " 'prosecutor',\n",
       " 'moved',\n",
       " 'ahead',\n",
       " 'on',\n",
       " 'two',\n",
       " 'investigations',\n",
       " 'of',\n",
       " 'intense',\n",
       " 'interest',\n",
       " 'to',\n",
       " 'Mr.',\n",
       " 'Trump.',\n",
       " 'One',\n",
       " 'was',\n",
       " 'focused',\n",
       " 'on',\n",
       " 'an',\n",
       " 'oligarch',\n",
       " '—',\n",
       " 'previously',\n",
       " 'cleared',\n",
       " 'of',\n",
       " 'wrongdoing',\n",
       " 'by',\n",
       " 'the',\n",
       " 'same',\n",
       " 'prosecutor',\n",
       " '—',\n",
       " 'whose',\n",
       " 'company',\n",
       " 'employed',\n",
       " 'former',\n",
       " 'Vice',\n",
       " 'President',\n",
       " 'Joseph',\n",
       " 'R.',\n",
       " 'Biden',\n",
       " 'Jr.’s',\n",
       " 'son.',\n",
       " 'The',\n",
       " 'other',\n",
       " 'dealt',\n",
       " 'with',\n",
       " 'the',\n",
       " 'release',\n",
       " 'by',\n",
       " 'a',\n",
       " 'separate',\n",
       " 'Ukrainian',\n",
       " 'law',\n",
       " 'enforcement',\n",
       " 'agency',\n",
       " 'to',\n",
       " 'the',\n",
       " 'media',\n",
       " 'of',\n",
       " 'information',\n",
       " 'that',\n",
       " 'hurt',\n",
       " 'Mr.',\n",
       " 'Trump’s',\n",
       " '2016',\n",
       " 'campaign']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer = nltk.tokenize.WhitespaceTokenizer()\n",
    "tokenizer.tokenize(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['WASHINGTON',\n",
       " '—',\n",
       " 'Petro',\n",
       " 'O.',\n",
       " 'Poroshenko',\n",
       " 'was',\n",
       " 'still',\n",
       " 'the',\n",
       " 'president',\n",
       " 'of',\n",
       " 'Ukraine',\n",
       " 'earlier',\n",
       " 'this',\n",
       " 'year',\n",
       " 'when',\n",
       " 'his',\n",
       " 'team',\n",
       " 'sought',\n",
       " 'a',\n",
       " 'lifeline.',\n",
       " 'With',\n",
       " 'the',\n",
       " 'polls',\n",
       " 'showing',\n",
       " 'him',\n",
       " 'in',\n",
       " 'clear',\n",
       " 'danger',\n",
       " 'of',\n",
       " 'losing',\n",
       " 'his',\n",
       " 're-election',\n",
       " 'campaign',\n",
       " ',',\n",
       " 'some',\n",
       " 'of',\n",
       " 'his',\n",
       " 'associates',\n",
       " ',',\n",
       " 'eager',\n",
       " 'to',\n",
       " 'hold',\n",
       " 'on',\n",
       " 'to',\n",
       " 'their',\n",
       " 'own',\n",
       " 'jobs',\n",
       " 'and',\n",
       " 'influence',\n",
       " ',',\n",
       " 'took',\n",
       " 'steps',\n",
       " 'that',\n",
       " 'could',\n",
       " 'have',\n",
       " 'yielded',\n",
       " 'a',\n",
       " 'signal',\n",
       " 'of',\n",
       " 'public',\n",
       " 'support',\n",
       " 'from',\n",
       " 'a',\n",
       " 'vital',\n",
       " 'ally',\n",
       " ':',\n",
       " 'President',\n",
       " 'Trump.',\n",
       " 'Over',\n",
       " 'several',\n",
       " 'weeks',\n",
       " 'in',\n",
       " 'March',\n",
       " ',',\n",
       " 'the',\n",
       " 'office',\n",
       " 'of',\n",
       " 'Ukraine',\n",
       " '’',\n",
       " 's',\n",
       " 'top',\n",
       " 'prosecutor',\n",
       " 'moved',\n",
       " 'ahead',\n",
       " 'on',\n",
       " 'two',\n",
       " 'investigations',\n",
       " 'of',\n",
       " 'intense',\n",
       " 'interest',\n",
       " 'to',\n",
       " 'Mr.',\n",
       " 'Trump.',\n",
       " 'One',\n",
       " 'was',\n",
       " 'focused',\n",
       " 'on',\n",
       " 'an',\n",
       " 'oligarch',\n",
       " '—',\n",
       " 'previously',\n",
       " 'cleared',\n",
       " 'of',\n",
       " 'wrongdoing',\n",
       " 'by',\n",
       " 'the',\n",
       " 'same',\n",
       " 'prosecutor',\n",
       " '—',\n",
       " 'whose',\n",
       " 'company',\n",
       " 'employed',\n",
       " 'former',\n",
       " 'Vice',\n",
       " 'President',\n",
       " 'Joseph',\n",
       " 'R.',\n",
       " 'Biden',\n",
       " 'Jr.',\n",
       " '’',\n",
       " 's',\n",
       " 'son.',\n",
       " 'The',\n",
       " 'other',\n",
       " 'dealt',\n",
       " 'with',\n",
       " 'the',\n",
       " 'release',\n",
       " 'by',\n",
       " 'a',\n",
       " 'separate',\n",
       " 'Ukrainian',\n",
       " 'law',\n",
       " 'enforcement',\n",
       " 'agency',\n",
       " 'to',\n",
       " 'the',\n",
       " 'media',\n",
       " 'of',\n",
       " 'information',\n",
       " 'that',\n",
       " 'hurt',\n",
       " 'Mr.',\n",
       " 'Trump',\n",
       " '’',\n",
       " 's',\n",
       " '2016',\n",
       " 'campaign']"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer = nltk.tokenize.TreebankWordTokenizer()\n",
    "tokenizer.tokenize(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['WASHINGTON',\n",
       " '—',\n",
       " 'Petro',\n",
       " 'O',\n",
       " '.',\n",
       " 'Poroshenko',\n",
       " 'was',\n",
       " 'still',\n",
       " 'the',\n",
       " 'president',\n",
       " 'of',\n",
       " 'Ukraine',\n",
       " 'earlier',\n",
       " 'this',\n",
       " 'year',\n",
       " 'when',\n",
       " 'his',\n",
       " 'team',\n",
       " 'sought',\n",
       " 'a',\n",
       " 'lifeline',\n",
       " '.',\n",
       " 'With',\n",
       " 'the',\n",
       " 'polls',\n",
       " 'showing',\n",
       " 'him',\n",
       " 'in',\n",
       " 'clear',\n",
       " 'danger',\n",
       " 'of',\n",
       " 'losing',\n",
       " 'his',\n",
       " 're',\n",
       " '-',\n",
       " 'election',\n",
       " 'campaign',\n",
       " ',',\n",
       " 'some',\n",
       " 'of',\n",
       " 'his',\n",
       " 'associates',\n",
       " ',',\n",
       " 'eager',\n",
       " 'to',\n",
       " 'hold',\n",
       " 'on',\n",
       " 'to',\n",
       " 'their',\n",
       " 'own',\n",
       " 'jobs',\n",
       " 'and',\n",
       " 'influence',\n",
       " ',',\n",
       " 'took',\n",
       " 'steps',\n",
       " 'that',\n",
       " 'could',\n",
       " 'have',\n",
       " 'yielded',\n",
       " 'a',\n",
       " 'signal',\n",
       " 'of',\n",
       " 'public',\n",
       " 'support',\n",
       " 'from',\n",
       " 'a',\n",
       " 'vital',\n",
       " 'ally',\n",
       " ':',\n",
       " 'President',\n",
       " 'Trump',\n",
       " '.',\n",
       " 'Over',\n",
       " 'several',\n",
       " 'weeks',\n",
       " 'in',\n",
       " 'March',\n",
       " ',',\n",
       " 'the',\n",
       " 'office',\n",
       " 'of',\n",
       " 'Ukraine',\n",
       " '’',\n",
       " 's',\n",
       " 'top',\n",
       " 'prosecutor',\n",
       " 'moved',\n",
       " 'ahead',\n",
       " 'on',\n",
       " 'two',\n",
       " 'investigations',\n",
       " 'of',\n",
       " 'intense',\n",
       " 'interest',\n",
       " 'to',\n",
       " 'Mr',\n",
       " '.',\n",
       " 'Trump',\n",
       " '.',\n",
       " 'One',\n",
       " 'was',\n",
       " 'focused',\n",
       " 'on',\n",
       " 'an',\n",
       " 'oligarch',\n",
       " '—',\n",
       " 'previously',\n",
       " 'cleared',\n",
       " 'of',\n",
       " 'wrongdoing',\n",
       " 'by',\n",
       " 'the',\n",
       " 'same',\n",
       " 'prosecutor',\n",
       " '—',\n",
       " 'whose',\n",
       " 'company',\n",
       " 'employed',\n",
       " 'former',\n",
       " 'Vice',\n",
       " 'President',\n",
       " 'Joseph',\n",
       " 'R',\n",
       " '.',\n",
       " 'Biden',\n",
       " 'Jr',\n",
       " '.’',\n",
       " 's',\n",
       " 'son',\n",
       " '.',\n",
       " 'The',\n",
       " 'other',\n",
       " 'dealt',\n",
       " 'with',\n",
       " 'the',\n",
       " 'release',\n",
       " 'by',\n",
       " 'a',\n",
       " 'separate',\n",
       " 'Ukrainian',\n",
       " 'law',\n",
       " 'enforcement',\n",
       " 'agency',\n",
       " 'to',\n",
       " 'the',\n",
       " 'media',\n",
       " 'of',\n",
       " 'information',\n",
       " 'that',\n",
       " 'hurt',\n",
       " 'Mr',\n",
       " '.',\n",
       " 'Trump',\n",
       " '’',\n",
       " 's',\n",
       " '2016',\n",
       " 'campaign']"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer = nltk.tokenize.WordPunctTokenizer()\n",
    "tokenizer.tokenize(text)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "## stemming\n",
    "\n",
    "stemmer = nltk.stem.PorterStemmer()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'washington — petro O . poroshenko wa still the presid of ukrain earlier thi year when hi team sought a lifelin . with the poll show him in clear danger of lose hi re - elect campaign , some of hi associ , eager to hold on to their own job and influenc , took step that could have yield a signal of public support from a vital alli : presid trump . over sever week in march , the offic of ukrain ’ s top prosecutor move ahead on two investig of intens interest to Mr . trump . one wa focus on an oligarch — previous clear of wrongdo by the same prosecutor — whose compani employ former vice presid joseph R . biden Jr .’ s son . the other dealt with the releas by a separ ukrainian law enforc agenc to the media of inform that hurt Mr . trump ’ s 2016 campaign'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\" \".join(stemmer.stem(token) for token in tokenizer.tokenize(text))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Lemmatizing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "stemmer = nltk.stem.WordNetLemmatizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'WASHINGTON — Petro O . Poroshenko wa still the president of Ukraine earlier this year when his team sought a lifeline . With the poll showing him in clear danger of losing his re - election campaign , some of his associate , eager to hold on to their own job and influence , took step that could have yielded a signal of public support from a vital ally : President Trump . Over several week in March , the office of Ukraine ’ s top prosecutor moved ahead on two investigation of intense interest to Mr . Trump . One wa focused on an oligarch — previously cleared of wrongdoing by the same prosecutor — whose company employed former Vice President Joseph R . Biden Jr .’ s son . The other dealt with the release by a separate Ukrainian law enforcement agency to the medium of information that hurt Mr . Trump ’ s 2016 campaign'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\" \".join(stemmer.lemmatize(token) for token in tokenizer.tokenize(text))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Series "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a': 10, 'b': 20, 'c': 30}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = [\"a\",\"b\",\"c\"]\n",
    "data = [10,20,30]\n",
    "d = {}\n",
    "for i in range (len(letters)): ## build a dictioary from a list \n",
    "        d[letters[i]]=data[i]\n",
    "d"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    10\n",
       "b    20\n",
       "c    30\n",
       "dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser1= pd.Series(d)\n",
    "ser1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    10\n",
       "4    20\n",
       "5    30\n",
       "dtype: int64"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser2=pd.Series(data, [2,4,5])\n",
    "ser2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   NaN\n",
       "b   NaN\n",
       "c   NaN\n",
       "2   NaN\n",
       "4   NaN\n",
       "5   NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser1+ser2 ## adding series, nan when the values in the series do not match "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "from numpy.random import randn\n",
    "import pandas as pd\n",
    "              "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(101) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [],
   "source": [
    "## DataFrame(a bunch of series that share the same index, like excel sheets. used to read data from csv files\n",
    "\n",
    "df = pd.DataFrame(randn(5,4),[\"A\",\"B\",\"C\",\"E\",\"F\"],[\"W\",\"X\",\"Y\",\"Z\"]) ## 5 rows, 4 columns and corresponding values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A  0.642004 -0.958897 -0.229701  0.882410\n",
       "B  0.806865 -1.184201  1.604061  0.372874\n",
       "C  1.390378  0.156855  0.555215  0.391733\n",
       "E -1.065717 -0.963127 -1.193229  1.954080\n",
       "F -0.472403  0.586068 -0.301780  0.832385"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A   -0.228742\n",
       "B   -1.204769\n",
       "C    0.319940\n",
       "E    0.858659\n",
       "F   -0.007258\n",
       "Name: W, dtype: float64"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"W\"] ## grabs colums values in a form of series \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.31994042669524864"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"W\"][\"C\"] ## grapbs coordinates values, status with columsn first "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df[\"W\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.31994042669524864"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.W.C ## another way of doing it, just like SQL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "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>W</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.228742</td>\n",
       "      <td>0.862113</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-1.204769</td>\n",
       "      <td>-1.289125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>0.319940</td>\n",
       "      <td>-0.802368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.858659</td>\n",
       "      <td>2.087678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.007258</td>\n",
       "      <td>-1.123236</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         Z\n",
       "A -0.228742  0.862113\n",
       "B -1.204769 -1.289125\n",
       "C  0.319940 -0.802368\n",
       "E  0.858659  2.087678\n",
       "F -0.007258 -1.123236"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"W\",\"Z\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1.524414\n",
       "B    1.179739\n",
       "C    1.782110\n",
       "E    0.888362\n",
       "F    0.359982\n",
       "Name: New, dtype: float64"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"New\"] = df[\"W\"] + df[\"Z\"] ## added a new coloum to df, by simply added it to df\n",
    "df[\"New\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "      <th>New</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "      <td>1.524414</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "      <td>1.179739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "      <td>1.782110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "      <td>0.888362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "      <td>0.359982</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z       New\n",
       "A  0.642004 -0.958897 -0.229701  0.882410  1.524414\n",
       "B  0.806865 -1.184201  1.604061  0.372874  1.179739\n",
       "C  1.390378  0.156855  0.555215  0.391733  1.782110\n",
       "E -1.065717 -0.963127 -1.193229  1.954080  0.888362\n",
       "F -0.472403  0.586068 -0.301780  0.832385  0.359982"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A  0.642004 -0.958897 -0.229701  0.882410\n",
       "B  0.806865 -1.184201  1.604061  0.372874\n",
       "C  1.390378  0.156855  0.555215  0.391733\n",
       "E -1.065717 -0.963127 -1.193229  1.954080\n",
       "F -0.472403  0.586068 -0.301780  0.832385"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df.drop(\"New\",axis=1) ## axis=1 to specify the column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "      <th>New</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "      <td>1.524414</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "      <td>1.179739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "      <td>1.782110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "      <td>0.888362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "      <td>0.359982</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z       New\n",
       "A  0.642004 -0.958897 -0.229701  0.882410  1.524414\n",
       "B  0.806865 -1.184201  1.604061  0.372874  1.179739\n",
       "C  1.390378  0.156855  0.555215  0.391733  1.782110\n",
       "E -1.065717 -0.963127 -1.193229  1.954080  0.888362\n",
       "F -0.472403  0.586068 -0.301780  0.832385  0.359982"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df ## new not removed permantly unless you specify inplace=True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(\"New\",axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A  0.642004 -0.958897 -0.229701  0.882410\n",
       "B  0.806865 -1.184201  1.604061  0.372874\n",
       "C  1.390378  0.156855  0.555215  0.391733\n",
       "E -1.065717 -0.963127 -1.193229  1.954080\n",
       "F -0.472403  0.586068 -0.301780  0.832385"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "B  0.806865 -1.184201  1.604061  0.372874\n",
       "C  1.390378  0.156855  0.555215  0.391733\n",
       "E -1.065717 -0.963127 -1.193229  1.954080\n",
       "F -0.472403  0.586068 -0.301780  0.832385"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df.drop(\"A\") ## dopped a line, no need to specify the axis, unless there was coloum with the same name, then axis=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.642004</td>\n",
       "      <td>-0.958897</td>\n",
       "      <td>-0.229701</td>\n",
       "      <td>0.882410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.806865</td>\n",
       "      <td>-1.184201</td>\n",
       "      <td>1.604061</td>\n",
       "      <td>0.372874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>1.390378</td>\n",
       "      <td>0.156855</td>\n",
       "      <td>0.555215</td>\n",
       "      <td>0.391733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>-1.065717</td>\n",
       "      <td>-0.963127</td>\n",
       "      <td>-1.193229</td>\n",
       "      <td>1.954080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.472403</td>\n",
       "      <td>0.586068</td>\n",
       "      <td>-0.301780</td>\n",
       "      <td>0.832385</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A  0.642004 -0.958897 -0.229701  0.882410\n",
       "B  0.806865 -1.184201  1.604061  0.372874\n",
       "C  1.390378  0.156855  0.555215  0.391733\n",
       "E -1.065717 -0.963127 -1.193229  1.954080\n",
       "F -0.472403  0.586068 -0.301780  0.832385"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "W    0.642004\n",
       "X   -0.958897\n",
       "Y   -0.229701\n",
       "Z    0.882410\n",
       "Name: A, dtype: float64"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[\"A\"] ## to return the values of the index, or row, same as df[\"w\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "W    0.642004\n",
       "X   -0.958897\n",
       "Y   -0.229701\n",
       "Z    0.882410\n",
       "Name: A, dtype: float64"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.iloc[0] ## use iloc to return the values of index, or row, iloc for the hidden number of the index "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>1.359712</td>\n",
       "      <td>0.771970</td>\n",
       "      <td>0.294217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>0.147486</td>\n",
       "      <td>-0.729466</td>\n",
       "      <td>-0.720110</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          X         Y         Z\n",
       "E  1.359712  0.771970  0.294217\n",
       "F  0.147486 -0.729466 -0.720110"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[\"E\":,\"X\":] ## grab values from the DataFrame "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       W      X      Y      Z\n",
       "A  False   True   True   True\n",
       "B  False  False  False   True\n",
       "C   True  False   True   True\n",
       "E   True   True  False  False\n",
       "F  False  False  False  False"
      ]
     },
     "execution_count": 201,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df > 0 ## where the bool is true"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 203,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.292795</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>0.834355</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.119145</td>\n",
       "      <td>0.665715</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A       NaN  2.090539  1.004056  1.031916\n",
       "B       NaN       NaN       NaN  0.292795\n",
       "C  0.834355       NaN  0.119145  0.665715\n",
       "E  0.407586  0.807843       NaN       NaN\n",
       "F       NaN       NaN       NaN       NaN"
      ]
     },
     "execution_count": 203,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df>0] ## grab the values when the bool is true "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>-2.736464</td>\n",
       "      <td>-0.985153</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A -0.285257  2.090539  1.004056  1.031916\n",
       "E  0.407586  0.807843 -2.736464 -0.985153"
      ]
     },
     "execution_count": 221,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"X\"]>0] ## filter value in colomn X that are > 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1.031916\n",
       "E   -0.985153\n",
       "Name: Z, dtype: float64"
      ]
     },
     "execution_count": 223,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"X\"]>0][\"Z\"] ## filter value in colomn X that are > 0 and by colom that meet the condition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A -0.285257  2.090539  1.004056  1.031916"
      ]
     },
     "execution_count": 233,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df[\"X\"]>0) & (df[\"Z\"]>1)] ## filter value in colomn X that are > 0 and in colom Z that are > 1, we use & instead of + or , "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 234,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>-2.736464</td>\n",
       "      <td>-0.985153</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z\n",
       "A -0.285257  2.090539  1.004056  1.031916\n",
       "E  0.407586  0.807843 -2.736464 -0.985153"
      ]
     },
     "execution_count": 234,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df[\"X\"]>0) | (df[\"Z\"]>1)] ## for or, use the pipe operator \"|\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 237,
   "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>index</th>\n",
       "      <th>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>B</td>\n",
       "      <td>-1.081118</td>\n",
       "      <td>-0.000355</td>\n",
       "      <td>-0.219882</td>\n",
       "      <td>0.292795</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>0.834355</td>\n",
       "      <td>-0.140432</td>\n",
       "      <td>0.119145</td>\n",
       "      <td>0.665715</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>E</td>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>-2.736464</td>\n",
       "      <td>-0.985153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>F</td>\n",
       "      <td>-0.155276</td>\n",
       "      <td>-1.013228</td>\n",
       "      <td>-1.087436</td>\n",
       "      <td>-2.567767</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  index         W         X         Y         Z\n",
       "0     A -0.285257  2.090539  1.004056  1.031916\n",
       "1     B -1.081118 -0.000355 -0.219882  0.292795\n",
       "2     C  0.834355 -0.140432  0.119145  0.665715\n",
       "3     E  0.407586  0.807843 -2.736464 -0.985153\n",
       "4     F -0.155276 -1.013228 -1.087436 -2.567767"
      ]
     },
     "execution_count": 237,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.reset_index()## to reset the index to a numerical values, add inplace=True to permanantly change df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "new = \"AL BH NJ BN GH\".split() ## easily create a list without adding the parantheses"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['AL', 'BH', 'NJ', 'BN', 'GH']"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 245,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Sates\"] = new ## addeda new coloum to the df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 244,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "      <th>Sates</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-1.081118</td>\n",
       "      <td>-0.000355</td>\n",
       "      <td>-0.219882</td>\n",
       "      <td>0.292795</td>\n",
       "      <td>BH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>0.834355</td>\n",
       "      <td>-0.140432</td>\n",
       "      <td>0.119145</td>\n",
       "      <td>0.665715</td>\n",
       "      <td>NJ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>-2.736464</td>\n",
       "      <td>-0.985153</td>\n",
       "      <td>BN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.155276</td>\n",
       "      <td>-1.013228</td>\n",
       "      <td>-1.087436</td>\n",
       "      <td>-2.567767</td>\n",
       "      <td>GH</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z Sates\n",
       "A -0.285257  2.090539  1.004056  1.031916    AL\n",
       "B -1.081118 -0.000355 -0.219882  0.292795    BH\n",
       "C  0.834355 -0.140432  0.119145  0.665715    NJ\n",
       "E  0.407586  0.807843 -2.736464 -0.985153    BN\n",
       "F -0.155276 -1.013228 -1.087436 -2.567767    GH"
      ]
     },
     "execution_count": 244,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyError",
     "evalue": "'Sates'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3077\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3078\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3079\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'Sates'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-95-e54d41a6ee88>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Sates\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m## set states to be the index, not permanant unless I specify inplace=True\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36mset_index\u001b[0;34m(self, keys, drop, append, inplace, verify_integrity)\u001b[0m\n\u001b[1;32m   3907\u001b[0m                 \u001b[0mnames\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3908\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3909\u001b[0;31m                 \u001b[0mlevel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mframe\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcol\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3910\u001b[0m                 \u001b[0mnames\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3911\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mdrop\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2686\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2687\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2688\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2689\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2690\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_getitem_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_getitem_column\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2693\u001b[0m         \u001b[0;31m# get column\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2694\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_unique\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2695\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_item_cache\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2696\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2697\u001b[0m         \u001b[0;31m# duplicate columns & possible reduce dimensionality\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m_get_item_cache\u001b[0;34m(self, item)\u001b[0m\n\u001b[1;32m   2487\u001b[0m         \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2488\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mres\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2489\u001b[0;31m             \u001b[0mvalues\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2490\u001b[0m             \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_box_item_values\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalues\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2491\u001b[0m             \u001b[0mcache\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/internals.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(self, item, fastpath)\u001b[0m\n\u001b[1;32m   4113\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4114\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4115\u001b[0;31m                 \u001b[0mloc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4116\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4117\u001b[0m                 \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0misna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3078\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3079\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3080\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3081\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3082\u001b[0m         \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'Sates'"
     ]
    }
   ],
   "source": [
    "df.set_index(\"Sates\") ## set states to be the index, not permanant unless I specify inplace=True z"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 248,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "      <th>Sates</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>-0.285257</td>\n",
       "      <td>2.090539</td>\n",
       "      <td>1.004056</td>\n",
       "      <td>1.031916</td>\n",
       "      <td>AL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-1.081118</td>\n",
       "      <td>-0.000355</td>\n",
       "      <td>-0.219882</td>\n",
       "      <td>0.292795</td>\n",
       "      <td>BH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>0.834355</td>\n",
       "      <td>-0.140432</td>\n",
       "      <td>0.119145</td>\n",
       "      <td>0.665715</td>\n",
       "      <td>NJ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.407586</td>\n",
       "      <td>0.807843</td>\n",
       "      <td>-2.736464</td>\n",
       "      <td>-0.985153</td>\n",
       "      <td>BN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>-0.155276</td>\n",
       "      <td>-1.013228</td>\n",
       "      <td>-1.087436</td>\n",
       "      <td>-2.567767</td>\n",
       "      <td>GH</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          W         X         Y         Z Sates\n",
       "A -0.285257  2.090539  1.004056  1.031916    AL\n",
       "B -1.081118 -0.000355 -0.219882  0.292795    BH\n",
       "C  0.834355 -0.140432  0.119145  0.665715    NJ\n",
       "E  0.407586  0.807843 -2.736464 -0.985153    BN\n",
       "F -0.155276 -1.013228 -1.087436 -2.567767    GH"
      ]
     },
     "execution_count": 248,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = {\"age\":[25, 20], \"name\":[\"Mohamed\",\"Lauren\"]} ## another way to create a DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "lauren = pd.DataFrame(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "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>age</th>\n",
       "      <th>name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>Mohamed</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20</td>\n",
       "      <td>Lauren</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     name\n",
       "0   25  Mohamed\n",
       "1   20   Lauren"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lauren"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "25    1\n",
       "20    1\n",
       "Name: age, dtype: int64"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lauren.age.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [],
   "source": [
    "# MultiIndex DataFrame "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from numpy.random import randn\n",
    "outside = \"G1 G1 G1 G2 G2 G2\".split() \n",
    "inside =[1,2,3,1,2,3]\n",
    "hier_index = list(zip(outside, inside)) ## used zip to create tuple pairs, list as a type \n",
    "hier_index = pd.MultiIndex.from_tuples(hier_index)  # MultiIndex DataFrame "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultiIndex(levels=[['G1', 'G2'], [1, 2, 3]],\n",
       "           labels=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]])"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hier_index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(randn(6,2),hier_index,[\"A\",\"B\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">G1</th>\n",
       "      <th>1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.797202</td>\n",
       "      <td>-0.168735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.002557</td>\n",
       "      <td>-1.724318</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">G2</th>\n",
       "      <th>1</th>\n",
       "      <td>0.521441</td>\n",
       "      <td>1.398482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.673742</td>\n",
       "      <td>-0.155775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-2.276052</td>\n",
       "      <td>-0.031072</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             A         B\n",
       "G1 1  0.865421  1.566943\n",
       "   2 -1.797202 -0.168735\n",
       "   3  1.002557 -1.724318\n",
       "G2 1  0.521441  1.398482\n",
       "   2 -0.673742 -0.155775\n",
       "   3 -2.276052 -0.031072"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.797202</td>\n",
       "      <td>-0.168735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.002557</td>\n",
       "      <td>-1.724318</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          A         B\n",
       "1  0.865421  1.566943\n",
       "2 -1.797202 -0.168735\n",
       "3  1.002557 -1.724318"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[\"G1\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    0.865421\n",
       "B    1.566943\n",
       "Name: 1, dtype: float64"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[\"G1\"].loc[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "FrozenList([None, None])"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.index.names ## check the name of the indexes "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.index.names = [\"Groups\", \"Num\"] # rename the indexes "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Groups</th>\n",
       "      <th>Num</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">G1</th>\n",
       "      <th>1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.797202</td>\n",
       "      <td>-0.168735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.002557</td>\n",
       "      <td>-1.724318</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">G2</th>\n",
       "      <th>1</th>\n",
       "      <td>0.521441</td>\n",
       "      <td>1.398482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.673742</td>\n",
       "      <td>-0.155775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-2.276052</td>\n",
       "      <td>-0.031072</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   A         B\n",
       "Groups Num                    \n",
       "G1     1    0.865421  1.566943\n",
       "       2   -1.797202 -0.168735\n",
       "       3    1.002557 -1.724318\n",
       "G2     1    0.521441  1.398482\n",
       "       2   -0.673742 -0.155775\n",
       "       3   -2.276052 -0.031072"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.15577453480039566"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[\"G2\"].loc[2][\"B\"] ## looking for value using rows(loc[\"rowname\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.15577453480039566"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"B\"][\"G2\"][2] ## looking for value using colums ([\"columnname\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Num</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.797202</td>\n",
       "      <td>-0.168735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.002557</td>\n",
       "      <td>-1.724318</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            A         B\n",
       "Num                    \n",
       "1    0.865421  1.566943\n",
       "2   -1.797202 -0.168735\n",
       "3    1.002557 -1.724318"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.xs(\"G1\") ## to filter out cross section "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Num</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.797202</td>\n",
       "      <td>-0.168735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.002557</td>\n",
       "      <td>-1.724318</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            A         B\n",
       "Num                    \n",
       "1    0.865421  1.566943\n",
       "2   -1.797202 -0.168735\n",
       "3    1.002557 -1.724318"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.xs(\"G1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(A    0.865421\n",
       " B    1.566943\n",
       " Name: 1, dtype: float64, A    0.521441\n",
       " B    1.398482\n",
       " Name: 1, dtype: float64)"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['G1'].loc[1], df.loc['G2'].loc[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Groups</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>G1</th>\n",
       "      <td>0.865421</td>\n",
       "      <td>1.566943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>G2</th>\n",
       "      <td>0.521441</td>\n",
       "      <td>1.398482</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               A         B\n",
       "Groups                    \n",
       "G1      0.865421  1.566943\n",
       "G2      0.521441  1.398482"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.xs(1, level=\"Num\") ## easier way to do it, Grab Num 1 for both G1 and G2, this the only way to use Multiindex df "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    0\n",
       "B    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum() ## To grabe all  blank/ nill values in df, in this example, there is none"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "MultiIndex: 6 entries, (G1, 1) to (G2, 3)\n",
      "Data columns (total 2 columns):\n",
      "A    6 non-null float64\n",
      "B    6 non-null float64\n",
      "dtypes: float64(2)\n",
      "memory usage: 415.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Missing Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "d = {\"A\":[1,2, np.nan], \"B\":[5,np.nan, np.nan], \"C\":[1,2,3]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(d)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B  C\n",
       "0  1.0  5.0  1\n",
       "1  2.0  NaN  2\n",
       "2  NaN  NaN  3"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1\n",
       "B    2\n",
       "C    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum() ## number of blank values per column  A, B, C, sum(axis=1) for rows "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B  C\n",
       "0  1.0  5.0  1"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna() ## to drop rows with any null values per axis=0 (columns), "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "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>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   C\n",
       "0  1\n",
       "1  2\n",
       "2  3"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(axis=1) ## drop columns with null values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B  C\n",
       "0  1.0  5.0  1\n",
       "1  2.0  NaN  2"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(thresh=2) ## drop all rwos with 2 or more non-null values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>momo</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>momo</td>\n",
       "      <td>momo</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      A     B  C\n",
       "0     1     5  1\n",
       "1     2  momo  2\n",
       "2  momo  momo  3"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.fillna (value=\"momo\") ## fill missing values  with number 1 or text momo, you can skip value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1.0\n",
       "1    2.0\n",
       "2    1.5\n",
       "Name: A, dtype: float64"
      ]
     },
     "execution_count": 146,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"A\"].fillna(value=df[\"A\"].mean()) ## filled missing values in A with mean of column A, or median(), or std(), or mode() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = np.arange(20).reshape(5,4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(data, (\"A B C D F\").split(), (\"W X Y Z\").split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>W</th>\n",
       "      <th>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>8</td>\n",
       "      <td>9</td>\n",
       "      <td>10</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D</th>\n",
       "      <td>12</td>\n",
       "      <td>13</td>\n",
       "      <td>14</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\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": [
       "    W   X   Y   Z\n",
       "A   0   1   2   3\n",
       "B   4   5   6   7\n",
       "C   8   9  10  11\n",
       "D  12  13  14  15\n",
       "F  16  17  18  19"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Group by "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "data  = {\"Company\":[\"Goole\", \"FB\", \"MST\",\"Goole\", \"FB\", \"MST\"], \"Person\":[\"Lauren\", \"Moahamed\", \"Ben\", \"Lauren\", \"Moahamed\", \"Ben\"], \"Sales\":[100, 200, 300, 400, 500, 600]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(data) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>Company</th>\n",
       "      <th>Person</th>\n",
       "      <th>Sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Goole</td>\n",
       "      <td>Lauren</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>FB</td>\n",
       "      <td>Moahamed</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MST</td>\n",
       "      <td>Ben</td>\n",
       "      <td>300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Goole</td>\n",
       "      <td>Lauren</td>\n",
       "      <td>400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>FB</td>\n",
       "      <td>Moahamed</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>MST</td>\n",
       "      <td>Ben</td>\n",
       "      <td>600</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Company    Person  Sales\n",
       "0   Goole    Lauren    100\n",
       "1      FB  Moahamed    200\n",
       "2     MST       Ben    300\n",
       "3   Goole    Lauren    400\n",
       "4      FB  Moahamed    500\n",
       "5     MST       Ben    600"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "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>Sales</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Person</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ben</th>\n",
       "      <td>900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Lauren</th>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Moahamed</th>\n",
       "      <td>700</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Sales\n",
       "Person         \n",
       "Ben         900\n",
       "Lauren      500\n",
       "Moahamed    700"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"Person\").sum() ## group by column name, and choose the output: .mean(), std(), sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Sales    900\n",
       "Name: Ben, dtype: int64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"Person\").sum().loc[\"Ben\"] ## to grab the output "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Company    6\n",
       "Person     6\n",
       "Sales      6\n",
       "dtype: int64"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"Person\").count() ## count the number of instances by column "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Company    6\n",
       "Person     6\n",
       "Sales      6\n",
       "dtype: int64"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.count() ## count for each column "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Company         MST\n",
       "Person     Moahamed\n",
       "Sales           600\n",
       "dtype: object"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.max() ## for max() and min() could be done at colum level "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "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>Sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>350.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>187.082869</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>225.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>350.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>475.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>600.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Sales\n",
       "count    6.000000\n",
       "mean   350.000000\n",
       "std    187.082869\n",
       "min    100.000000\n",
       "25%    225.000000\n",
       "50%    350.000000\n",
       "75%    475.000000\n",
       "max    600.000000"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe() ## could be done at colum level "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Sales</th>\n",
       "      <td>6.0</td>\n",
       "      <td>350.0</td>\n",
       "      <td>187.082869</td>\n",
       "      <td>100.0</td>\n",
       "      <td>225.0</td>\n",
       "      <td>350.0</td>\n",
       "      <td>475.0</td>\n",
       "      <td>600.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       count   mean         std    min    25%    50%    75%    max\n",
       "Sales    6.0  350.0  187.082869  100.0  225.0  350.0  475.0  600.0"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe().transpose()  ## use transpose to mnake it easier to read"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Merging / Joining \n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "df1 = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'], ## you can specify the index numbers \n",
    "                        'B': ['B0', 'B1', 'B2', 'B3'],\n",
    "                        'C': ['C0', 'C1', 'C2', 'C3'],\n",
    "                        'D': ['D0', 'D1', 'D2', 'D3']},\n",
    "                        index=[0, 1, 2, 3])\n",
    "df2 = pd.DataFrame({'A': ['A4', 'A5', 'A6', 'A7'],\n",
    "                        'B': ['B4', 'B5', 'B6', 'B7'],\n",
    "                        'C': ['C4', 'C5', 'C6', 'C7'],\n",
    "                        'D': ['D4', 'D5', 'D6', 'D7']},\n",
    "                         index=[4, 5, 6, 7])\n",
    "df3 = pd.DataFrame({'A': ['A8', 'A9', 'A10', 'A11'],\n",
    "                        'B': ['B8', 'B9', 'B10', 'B11'],\n",
    "                        'C': ['C8', 'C9', 'C10', 'C11'],\n",
    "                        'D': ['D8', 'D9', 'D10', 'D11']},\n",
    "                        index=[8, 9, 10, 11])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  A0  B0  C0  D0\n",
       "1  A1  B1  C1  D1\n",
       "2  A2  B2  C2  D2\n",
       "3  A3  B3  C3  D3"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A4</td>\n",
       "      <td>B4</td>\n",
       "      <td>C4</td>\n",
       "      <td>D4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>A5</td>\n",
       "      <td>B5</td>\n",
       "      <td>C5</td>\n",
       "      <td>D5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>A6</td>\n",
       "      <td>B6</td>\n",
       "      <td>C6</td>\n",
       "      <td>D6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>A7</td>\n",
       "      <td>B7</td>\n",
       "      <td>C7</td>\n",
       "      <td>D7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "4  A4  B4  C4  D4\n",
       "5  A5  B5  C5  D5\n",
       "6  A6  B6  C6  D6\n",
       "7  A7  B7  C7  D7"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>A8</td>\n",
       "      <td>B8</td>\n",
       "      <td>C8</td>\n",
       "      <td>D8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>A9</td>\n",
       "      <td>B9</td>\n",
       "      <td>C9</td>\n",
       "      <td>D9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>A10</td>\n",
       "      <td>B10</td>\n",
       "      <td>C10</td>\n",
       "      <td>D10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>A11</td>\n",
       "      <td>B11</td>\n",
       "      <td>C11</td>\n",
       "      <td>D11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      A    B    C    D\n",
       "8    A8   B8   C8   D8\n",
       "9    A9   B9   C9   D9\n",
       "10  A10  B10  C10  D10\n",
       "11  A11  B11  C11  D11"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "#concatenation "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A4</td>\n",
       "      <td>B4</td>\n",
       "      <td>C4</td>\n",
       "      <td>D4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>A5</td>\n",
       "      <td>B5</td>\n",
       "      <td>C5</td>\n",
       "      <td>D5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>A6</td>\n",
       "      <td>B6</td>\n",
       "      <td>C6</td>\n",
       "      <td>D6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>A7</td>\n",
       "      <td>B7</td>\n",
       "      <td>C7</td>\n",
       "      <td>D7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>A8</td>\n",
       "      <td>B8</td>\n",
       "      <td>C8</td>\n",
       "      <td>D8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>A9</td>\n",
       "      <td>B9</td>\n",
       "      <td>C9</td>\n",
       "      <td>D9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>A10</td>\n",
       "      <td>B10</td>\n",
       "      <td>C10</td>\n",
       "      <td>D10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>A11</td>\n",
       "      <td>B11</td>\n",
       "      <td>C11</td>\n",
       "      <td>D11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      A    B    C    D\n",
       "0    A0   B0   C0   D0\n",
       "1    A1   B1   C1   D1\n",
       "2    A2   B2   C2   D2\n",
       "3    A3   B3   C3   D3\n",
       "4    A4   B4   C4   D4\n",
       "5    A5   B5   C5   D5\n",
       "6    A6   B6   C6   D6\n",
       "7    A7   B7   C7   D7\n",
       "8    A8   B8   C8   D8\n",
       "9    A9   B9   C9   D9\n",
       "10  A10  B10  C10  D10\n",
       "11  A11  B11  C11  D11"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([df1,df2,df3]) ## glue dataframes together based on the index numbers, axis=1 to concatenate columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "# merge \n",
    "left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],\n",
    "                     'A': ['A0', 'A1', 'A2', 'A3'],\n",
    "                     'B': ['B0', 'B1', 'B2', 'B3']})\n",
    "   \n",
    "right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],\n",
    "                          'C': ['C0', 'C1', 'C2', 'C3'],\n",
    "                          'D': ['D0', 'D1', 'D2', 'D3']})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>key</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   A   B\n",
       "0  K0  A0  B0\n",
       "1  K1  A1  B1\n",
       "2  K2  A2  B2\n",
       "3  K3  A3  B3"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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>key</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   C   D\n",
       "0  K0  C0  D0\n",
       "1  K1  C1  D1\n",
       "2  K2  C2  D2\n",
       "3  K3  C3  D3"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "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>key</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>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   A   B   C   D\n",
       "0  K0  A0  B0  C0  D0\n",
       "1  K1  A1  B1  C1  D1\n",
       "2  K2  A2  B2  C2  D2\n",
       "3  K3  A3  B3  C3  D3"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, on=\"key\") ## merge 2 dataframe based on common column, defaut is how='inner', on to spacify the key column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],\n",
    "                     'key2': ['K0', 'K1', 'K0', 'K1'],\n",
    "                        'A': ['A0', 'A1', 'A2', 'A3'],\n",
    "                        'B': ['B0', 'B1', 'B2', 'B3']})\n",
    "    \n",
    "right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],\n",
    "                               'key2': ['K0', 'K0', 'K0', 'K0'],\n",
    "                                  'C': ['C0', 'C1', 'C2', 'C3'],\n",
    "                                  'D': ['D0', 'D1', 'D2', 'D3']})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "## merge on multiple keys "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "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>key1</th>\n",
       "      <th>key2</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>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B   C   D\n",
       "0   K0   K0  A0  B0  C0  D0\n",
       "1   K1   K0  A2  B2  C1  D1\n",
       "2   K1   K0  A2  B2  C2  D2"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "# joining : merge based on the index instead of column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],\n",
    "                     'B': ['B0', 'B1', 'B2']},\n",
    "                      index=['K0', 'K1', 'K2']) \n",
    "\n",
    "right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],\n",
    "                    'D': ['D0', 'D2', 'D3']},\n",
    "                      index=['K0', 'K2', 'K3'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A   B\n",
       "K0  A0  B0\n",
       "K1  A1  B1\n",
       "K2  A2  B2"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "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>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K3</th>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     C   D\n",
       "K0  C0  D0\n",
       "K2  C2  D2\n",
       "K3  C3  D3"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A   B    C    D\n",
       "K0  A0  B0   C0   D0\n",
       "K1  A1  B1  NaN  NaN\n",
       "K2  A2  B2   C2   D2"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left.join(right) ## join is used when 2 dataframes have no column in common "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.23.4\n"
     ]
    }
   ],
   "source": [
    "print (pd.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "mylist = list('abcedfghijklmnopqrstuvwxyz')\n",
    "myarr = np.arange(26)\n",
    "mydict = dict(zip(mylist, myarr))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a     0\n",
       "b     1\n",
       "c     2\n",
       "e     3\n",
       "d     4\n",
       "f     5\n",
       "g     6\n",
       "h     7\n",
       "i     8\n",
       "j     9\n",
       "k    10\n",
       "l    11\n",
       "m    12\n",
       "n    13\n",
       "o    14\n",
       "p    15\n",
       "q    16\n",
       "r    17\n",
       "s    18\n",
       "t    19\n",
       "u    20\n",
       "v    21\n",
       "w    22\n",
       "x    23\n",
       "y    24\n",
       "z    25\n",
       "dtype: int64"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.Series(mydict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a': 0,\n",
       " 'b': 1,\n",
       " 'c': 2,\n",
       " 'e': 3,\n",
       " 'd': 4,\n",
       " 'f': 5,\n",
       " 'g': 6,\n",
       " 'h': 7,\n",
       " 'i': 8,\n",
       " 'j': 9,\n",
       " 'k': 10,\n",
       " 'l': 11,\n",
       " 'm': 12,\n",
       " 'n': 13,\n",
       " 'o': 14,\n",
       " 'p': 15,\n",
       " 'q': 16,\n",
       " 'r': 17,\n",
       " 's': 18,\n",
       " 't': 19,\n",
       " 'u': 20,\n",
       " 'v': 21,\n",
       " 'w': 22,\n",
       " 'x': 23,\n",
       " 'y': 24,\n",
       " 'z': 25}"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mydict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "mylist = list('abcedfghijklmnopqrstuvwxyz')\n",
    "myarr = np.arange(26)\n",
    "mydict = dict(zip(mylist, myarr))\n",
    "ser = pd.Series(mydict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "table = pd.DataFrame(ser)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "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>index</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>b</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>c</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>e</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>d</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>f</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>g</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>h</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>i</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>j</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>k</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>l</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>m</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>n</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>o</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>p</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>q</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>r</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>s</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>t</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>u</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>v</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>w</td>\n",
       "      <td>22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>x</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>y</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>z</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   index   0\n",
       "0      a   0\n",
       "1      b   1\n",
       "2      c   2\n",
       "3      e   3\n",
       "4      d   4\n",
       "5      f   5\n",
       "6      g   6\n",
       "7      h   7\n",
       "8      i   8\n",
       "9      j   9\n",
       "10     k  10\n",
       "11     l  11\n",
       "12     m  12\n",
       "13     n  13\n",
       "14     o  14\n",
       "15     p  15\n",
       "16     q  16\n",
       "17     r  17\n",
       "18     s  18\n",
       "19     t  19\n",
       "20     u  20\n",
       "21     v  21\n",
       "22     w  22\n",
       "23     x  23\n",
       "24     y  24\n",
       "25     z  25"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table = table.reset_index()\n",
    "table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {},
   "outputs": [],
   "source": [
    "ser1 = pd.Series([1, 2, 3, 4, 5])\n",
    "ser2 = pd.Series([4, 5, 6, 7, 8])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    2\n",
       "2    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 163,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser1[~ser1.not'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [],
   "source": [
    "ser1 = pd.Series([1, 2, 3, 4, 5])\n",
    "ser2 = pd.Series([4, 5, 6, 7, 8])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [],
   "source": [
    "ser = pd.Series(np.random.normal(10, 5, 25))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.07841486,  7.69619142,  9.86694583, 13.92213534, 20.72522811])"
      ]
     },
     "execution_count": 186,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.percentile(ser, q=[0,25, 50, 75, 100])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {},
   "outputs": [],
   "source": [
    "ser = pd.Series(np.take(list('abcdefgh'), np.random.randint(8, size=30)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (<ipython-input-1-8be6d5c96463>, line 1)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-1-8be6d5c96463>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m    ser.unique()value_counts()\u001b[0m\n\u001b[0m                           ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "ser.unique()value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "from numpy.random import rand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(randn(2,2), columns = [\"A\", \"B\" ], index=[\"Mo\", \"lo\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Mo</th>\n",
       "      <td>0.412557</td>\n",
       "      <td>0.900999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>lo</th>\n",
       "      <td>-1.284911</td>\n",
       "      <td>1.994032</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           A         B\n",
       "Mo  0.412557  0.900999\n",
       "lo -1.284911  1.994032"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "#operations "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>444</td>\n",
       "      <td>abc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>555</td>\n",
       "      <td>def</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>666</td>\n",
       "      <td>ghi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>444</td>\n",
       "      <td>xyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2 col3\n",
       "0     1   444  abc\n",
       "1     2   555  def\n",
       "2     3   666  ghi\n",
       "3     4   444  xyz"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "import pandas as pd\n",
    "df = pd.DataFrame({'col1':[1,2,3,4],'col2':[444,555,666,444],'col3':['abc','def','ghi','xyz']})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([444, 555, 666])"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"col2\"].unique() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"col2\"].nunique() ## nunique() returns the number of unique values, similar to len()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "444    2\n",
       "555    1\n",
       "666    1\n",
       "Name: col2, dtype: int64"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"col2\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>444</td>\n",
       "      <td>xyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2 col3\n",
       "3     4   444  xyz"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df[\"col1\"]>2) & (df[\"col2\"]==444)] ## user parentheses to combine 2 conditions "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [],
   "source": [
    "## apply a function on a df "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>444</td>\n",
       "      <td>abc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>555</td>\n",
       "      <td>def</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>666</td>\n",
       "      <td>ghi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>444</td>\n",
       "      <td>xyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2 col3\n",
       "0     1   444  abc\n",
       "1     2   555  def\n",
       "2     3   666  ghi\n",
       "3     4   444  xyz"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [],
   "source": [
    "def double(x):\n",
    "    return x*2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>888</td>\n",
       "      <td>abcabc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>1110</td>\n",
       "      <td>defdef</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>1332</td>\n",
       "      <td>ghighi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>888</td>\n",
       "      <td>xyzxyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2    col3\n",
       "0     2   888  abcabc\n",
       "1     4  1110  defdef\n",
       "2     6  1332  ghighi\n",
       "3     8   888  xyzxyz"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.apply(double) ## use apply to apply a function on the values in df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "col1         4\n",
       "col2      1110\n",
       "col3    defdef\n",
       "Name: 1, dtype: object"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[1].apply(double) ## on a row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>1110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>1332</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>888</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2\n",
       "0     2   888\n",
       "1     4  1110\n",
       "2     6  1332\n",
       "3     8   888"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"col1\",\"col2\"]].apply(double) ## on a column or 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "col1    4\n",
       "col2    4\n",
       "col3    4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.apply(len) ## apply len, type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>888</td>\n",
       "      <td>abcabc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>1110</td>\n",
       "      <td>defdef</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>1332</td>\n",
       "      <td>ghighi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>888</td>\n",
       "      <td>xyzxyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2    col3\n",
       "0     2   888  abcabc\n",
       "1     4  1110  defdef\n",
       "2     6  1332  ghighi\n",
       "3     8   888  xyzxyz"
      ]
     },
     "execution_count": 144,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.apply(lambda x : x*2) ## same thing using lambda expression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "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>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>444</td>\n",
       "      <td>abc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>555</td>\n",
       "      <td>def</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>666</td>\n",
       "      <td>ghi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>444</td>\n",
       "      <td>xyz</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col2 col3\n",
       "0   444  abc\n",
       "1   555  def\n",
       "2   666  ghi\n",
       "3   444  xyz"
      ]
     },
     "execution_count": 149,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop(columns = \"col1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['col1', 'col2', 'col3'], dtype='object')"
      ]
     },
     "execution_count": 158,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns ## return the columns "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RangeIndex(start=0, stop=4, step=1)"
      ]
     },
     "execution_count": 159,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.index ## range index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>444</td>\n",
       "      <td>abc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>444</td>\n",
       "      <td>xyz</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>555</td>\n",
       "      <td>def</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>666</td>\n",
       "      <td>ghi</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col2 col3\n",
       "0     1   444  abc\n",
       "3     4   444  xyz\n",
       "1     2   555  def\n",
       "2     3   666  ghi"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sort_values(\"col2\") ## sort values by the number of the column, index does not change "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "isnull() takes 1 positional argument but 2 were given",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-178-96075c4851fb>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misnull\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m: isnull() takes 1 positional argument but 2 were given"
     ]
    }
   ],
   "source": [
    "df.isnull(False).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "\n",
    "data = list(map(lambda x : x **2, np.arange(50).reshape(5,10)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(data)"
   ]
  },
  {
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>16</td>\n",
       "      <td>25</td>\n",
       "      <td>36</td>\n",
       "      <td>49</td>\n",
       "      <td>64</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100</td>\n",
       "      <td>121</td>\n",
       "      <td>144</td>\n",
       "      <td>169</td>\n",
       "      <td>196</td>\n",
       "      <td>225</td>\n",
       "      <td>256</td>\n",
       "      <td>289</td>\n",
       "      <td>324</td>\n",
       "      <td>361</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>400</td>\n",
       "      <td>441</td>\n",
       "      <td>484</td>\n",
       "      <td>529</td>\n",
       "      <td>576</td>\n",
       "      <td>625</td>\n",
       "      <td>676</td>\n",
       "      <td>729</td>\n",
       "      <td>784</td>\n",
       "      <td>841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900</td>\n",
       "      <td>961</td>\n",
       "      <td>1024</td>\n",
       "      <td>1089</td>\n",
       "      <td>1156</td>\n",
       "      <td>1225</td>\n",
       "      <td>1296</td>\n",
       "      <td>1369</td>\n",
       "      <td>1444</td>\n",
       "      <td>1521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1600</td>\n",
       "      <td>1681</td>\n",
       "      <td>1764</td>\n",
       "      <td>1849</td>\n",
       "      <td>1936</td>\n",
       "      <td>2025</td>\n",
       "      <td>2116</td>\n",
       "      <td>2209</td>\n",
       "      <td>2304</td>\n",
       "      <td>2401</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      0     1     2     3     4     5     6     7     8     9\n",
       "0     0     1     4     9    16    25    36    49    64    81\n",
       "1   100   121   144   169   196   225   256   289   324   361\n",
       "2   400   441   484   529   576   625   676   729   784   841\n",
       "3   900   961  1024  1089  1156  1225  1296  1369  1444  1521\n",
       "4  1600  1681  1764  1849  1936  2025  2116  2209  2304  2401"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import bs4\n",
    "import string\n",
    "import pandas as pd\n",
    "def datarabia():\n",
    "    output = []\n",
    "    pager=1\n",
    "    while pager<=10:\n",
    "        page = requests.get(\"https://www.datarabia.com/biz/searchOrgs.do?id=0&sectorid=0&more=1&submit=Search&orgname=&listid=&type=0&d-49489-p=\"+str(pager))\n",
    "        soup = bs4.BeautifulSoup(page.text, \"lxml\")\n",
    "        match = soup.find(class_=\"table\").findAll(\"a\")\n",
    "        size = len(match)\n",
    "        i=0\n",
    "        while i <size:\n",
    "            output.append(match[i].getText())\n",
    "            i+=1\n",
    "        pager+=1\n",
    "    return output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Al Aziziah Panda United Inc. (Branch)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Council of Political and Security Affairs</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Council of Political and Security Affairs</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Ministry of Culture and Information</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Ministry of Petroleum and Mineral Resources</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>National Company for Cooperative Insurance</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>100 Hour Tailor for Gents Tailoring</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1000 RT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1000 Sateen Tailors</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>101 Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>101 Laundry</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>117 Barber Shop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>120 Cars Workshop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>12011404 Sportation Company Ltd.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>123 Farooj</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>13 Center For Car Services</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>13th Center for Cars Services</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>1st Barber</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>1st Computer Center</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>2 X 1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>200 Tailor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>2000 Automatic Laundry</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>2000 Barber</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>2000 Barber Shop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>2000 Barbershop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>120</th>\n",
       "      <td>A Mdad Alkhlij Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>121</th>\n",
       "      <td>A Mdad Brother Intl Co.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>A Mdad Najid Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123</th>\n",
       "      <td>A Mdad Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>A Mdadat Altaga Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>A Mdha Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>A Mdullah S. al-Amro Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>127</th>\n",
       "      <td>A-Adwa al-Mareia Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>128</th>\n",
       "      <td>A-Amoodi Stores</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>129</th>\n",
       "      <td>A-Basri Ladies Tailor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>A. A. al-Issa Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>A. A. al-Quaymi Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>A. A. Muqbil Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>A. A. Turki Corporation</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>A. Abdallah al-Muhaymil Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>135</th>\n",
       "      <td>A. Abu Nayyan Trading Corp.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>136</th>\n",
       "      <td>A. Abu Nayyan Trading Corp.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>A. Al Assailan Est. For Contracting</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>A. al-Askar Trans</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139</th>\n",
       "      <td>A. al-Faris Industrial Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>A. al-Jalil S. Ba-Hakim Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141</th>\n",
       "      <td>A. al-La Mabruk al-Safari Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>A. al-Mohawwis Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>143</th>\n",
       "      <td>A. al-Najida Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>A. al-Rishood Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>A. al-Ruways Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>A. al-Sultaihi Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>A. al-Ubayd Office for Authorized Translation</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>A. al-Zuhayr Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>A. Alaunizaan Making House For Ladies Dresses</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  0\n",
       "0                                                  \n",
       "1                                                  \n",
       "2                                                  \n",
       "3                                                  \n",
       "4                                                  \n",
       "5             Al Aziziah Panda United Inc. (Branch)\n",
       "6         Council of Political and Security Affairs\n",
       "7         Council of Political and Security Affairs\n",
       "8               Ministry of Culture and Information\n",
       "9       Ministry of Petroleum and Mineral Resources\n",
       "10       National Company for Cooperative Insurance\n",
       "11              100 Hour Tailor for Gents Tailoring\n",
       "12                                          1000 RT\n",
       "13                              1000 Sateen Tailors\n",
       "14                             101 Contracting Est.\n",
       "15                                      101 Laundry\n",
       "16                                  117 Barber Shop\n",
       "17                                120 Cars Workshop\n",
       "18                 12011404 Sportation Company Ltd.\n",
       "19                                       123 Farooj\n",
       "20                       13 Center For Car Services\n",
       "21                    13th Center for Cars Services\n",
       "22                                       1st Barber\n",
       "23                              1st Computer Center\n",
       "24                                            2 X 1\n",
       "25                                       200 Tailor\n",
       "26                           2000 Automatic Laundry\n",
       "27                                      2000 Barber\n",
       "28                                 2000 Barber Shop\n",
       "29                                  2000 Barbershop\n",
       "..                                              ...\n",
       "120                 A Mdad Alkhlij Contracting Est.\n",
       "121                         A Mdad Brother Intl Co.\n",
       "122                       A Mdad Najid Trading Est.\n",
       "123                             A Mdad Trading Est.\n",
       "124                A Mdadat Altaga Contracting Est.\n",
       "125                         A Mdha Contracting Est.\n",
       "126           A Mdullah S. al-Amro Contracting Est.\n",
       "127                           A-Adwa al-Mareia Est.\n",
       "128                                 A-Amoodi Stores\n",
       "129                           A-Basri Ladies Tailor\n",
       "130                      A. A. al-Issa Trading Est.\n",
       "131                    A. A. al-Quaymi Trading Est.\n",
       "132                               A. A. Muqbil Est.\n",
       "133                         A. A. Turki Corporation\n",
       "134                    A. Abdallah al-Muhaymil Est.\n",
       "135                     A. Abu Nayyan Trading Corp.\n",
       "136                     A. Abu Nayyan Trading Corp.\n",
       "137             A. Al Assailan Est. For Contracting\n",
       "138                               A. al-Askar Trans\n",
       "139                     A. al-Faris Industrial Est.\n",
       "140            A. al-Jalil S. Ba-Hakim Trading Est.\n",
       "141                  A. al-La Mabruk al-Safari Est.\n",
       "142                     A. al-Mohawwis Trading Est.\n",
       "143                       A. al-Najida Trading Est.\n",
       "144                  A. al-Rishood Contracting Est.\n",
       "145                   A. al-Ruways Contracting Est.\n",
       "146                     A. al-Sultaihi Trading Est.\n",
       "147   A. al-Ubayd Office for Authorized Translation\n",
       "148                       A. al-Zuhayr Trading Est.\n",
       "149   A. Alaunizaan Making House For Ladies Dresses\n",
       "\n",
       "[150 rows x 1 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame (datarabia())\n"
   ]
  },
  {
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Al Aziziah Panda United Inc. (Branch)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Council of Political and Security Affairs</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Council of Political and Security Affairs</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Ministry of Culture and Information</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Ministry of Petroleum and Mineral Resources</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>National Company for Cooperative Insurance</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>100 Hour Tailor for Gents Tailoring</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1000 RT</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1000 Sateen Tailors</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>101 Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>101 Laundry</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>117 Barber Shop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>120 Cars Workshop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>12011404 Sportation Company Ltd.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>123 Farooj</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>13 Center For Car Services</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>13th Center for Cars Services</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>1st Barber</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>1st Computer Center</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>2 X 1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>200 Tailor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>2000 Automatic Laundry</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>2000 Barber</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>2000 Barber Shop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>2000 Barbershop</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>120</th>\n",
       "      <td>A Mdad Alkhlij Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>121</th>\n",
       "      <td>A Mdad Brother Intl Co.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>A Mdad Najid Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123</th>\n",
       "      <td>A Mdad Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>A Mdadat Altaga Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>A Mdha Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>A Mdullah S. al-Amro Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>127</th>\n",
       "      <td>A-Adwa al-Mareia Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>128</th>\n",
       "      <td>A-Amoodi Stores</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>129</th>\n",
       "      <td>A-Basri Ladies Tailor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>A. A. al-Issa Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>A. A. al-Quaymi Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>A. A. Muqbil Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>A. A. Turki Corporation</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>A. Abdallah al-Muhaymil Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>135</th>\n",
       "      <td>A. Abu Nayyan Trading Corp.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>136</th>\n",
       "      <td>A. Abu Nayyan Trading Corp.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>A. Al Assailan Est. For Contracting</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>A. al-Askar Trans</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139</th>\n",
       "      <td>A. al-Faris Industrial Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>A. al-Jalil S. Ba-Hakim Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141</th>\n",
       "      <td>A. al-La Mabruk al-Safari Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>A. al-Mohawwis Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>143</th>\n",
       "      <td>A. al-Najida Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>A. al-Rishood Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>A. al-Ruways Contracting Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>A. al-Sultaihi Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>A. al-Ubayd Office for Authorized Translation</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>A. al-Zuhayr Trading Est.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>A. Alaunizaan Making House For Ladies Dresses</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  0\n",
       "0                                                  \n",
       "1                                                  \n",
       "2                                                  \n",
       "3                                                  \n",
       "4                                                  \n",
       "5             Al Aziziah Panda United Inc. (Branch)\n",
       "6         Council of Political and Security Affairs\n",
       "7         Council of Political and Security Affairs\n",
       "8               Ministry of Culture and Information\n",
       "9       Ministry of Petroleum and Mineral Resources\n",
       "10       National Company for Cooperative Insurance\n",
       "11              100 Hour Tailor for Gents Tailoring\n",
       "12                                          1000 RT\n",
       "13                              1000 Sateen Tailors\n",
       "14                             101 Contracting Est.\n",
       "15                                      101 Laundry\n",
       "16                                  117 Barber Shop\n",
       "17                                120 Cars Workshop\n",
       "18                 12011404 Sportation Company Ltd.\n",
       "19                                       123 Farooj\n",
       "20                       13 Center For Car Services\n",
       "21                    13th Center for Cars Services\n",
       "22                                       1st Barber\n",
       "23                              1st Computer Center\n",
       "24                                            2 X 1\n",
       "25                                       200 Tailor\n",
       "26                           2000 Automatic Laundry\n",
       "27                                      2000 Barber\n",
       "28                                 2000 Barber Shop\n",
       "29                                  2000 Barbershop\n",
       "..                                              ...\n",
       "120                 A Mdad Alkhlij Contracting Est.\n",
       "121                         A Mdad Brother Intl Co.\n",
       "122                       A Mdad Najid Trading Est.\n",
       "123                             A Mdad Trading Est.\n",
       "124                A Mdadat Altaga Contracting Est.\n",
       "125                         A Mdha Contracting Est.\n",
       "126           A Mdullah S. al-Amro Contracting Est.\n",
       "127                           A-Adwa al-Mareia Est.\n",
       "128                                 A-Amoodi Stores\n",
       "129                           A-Basri Ladies Tailor\n",
       "130                      A. A. al-Issa Trading Est.\n",
       "131                    A. A. al-Quaymi Trading Est.\n",
       "132                               A. A. Muqbil Est.\n",
       "133                         A. A. Turki Corporation\n",
       "134                    A. Abdallah al-Muhaymil Est.\n",
       "135                     A. Abu Nayyan Trading Corp.\n",
       "136                     A. Abu Nayyan Trading Corp.\n",
       "137             A. Al Assailan Est. For Contracting\n",
       "138                               A. al-Askar Trans\n",
       "139                     A. al-Faris Industrial Est.\n",
       "140            A. al-Jalil S. Ba-Hakim Trading Est.\n",
       "141                  A. al-La Mabruk al-Safari Est.\n",
       "142                     A. al-Mohawwis Trading Est.\n",
       "143                       A. al-Najida Trading Est.\n",
       "144                  A. al-Rishood Contracting Est.\n",
       "145                   A. al-Ruways Contracting Est.\n",
       "146                     A. al-Sultaihi Trading Est.\n",
       "147   A. al-Ubayd Office for Authorized Translation\n",
       "148                       A. al-Zuhayr Trading Est.\n",
       "149   A. Alaunizaan Making House For Ladies Dresses\n",
       "\n",
       "[150 rows x 1 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}