Python_BasicOperations.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Topic 1: Basic Dataframe Reading/Operations \n",
    "\n",
    "#Code Block 1.1: Reading the dataframe\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Two most common encodings- UTF-8 and Latin-1\n",
    "\n",
    "df=pd.read_csv(\"1000_Sales_Records.csv\", encoding=\"Latin-1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1000, 14)\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.2: Getting to know the shape of the dataset (Rows and Columns)\n",
    "\n",
    "data_size= df.shape\n",
    "\n",
    "print(data_size)\n",
    "\n",
    "#Dataset contains 1000 rows and 14 columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.3: Length of dataframe. Using len function also prints the no of rows. However, len only prints no of rows, but not columns. Here the result is : 1000\n",
    "\n",
    "print(len(df))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.4: Getting to know the data type of the dataset. The data created here is of type :DataFrame\n",
    "\n",
    "data_type=type(df)\n",
    "print(data_type)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.5: Extracting one column from the dataframe and getting to know the data type and the size (of Series)\n",
    "\n",
    "country=df[\"Country\"]\n",
    "series_type= type(country)\n",
    "\n",
    "print(series_type)\n",
    "\n",
    "#Extracting one columns is of Series type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.6: Printing the size of the series\n",
    "#size is used to print the size of series and len (rows)/shape (rows,columns) is used to get the size of dataframe\n",
    "\n",
    "series_size= country.size\n",
    "print(series_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Region             object\n",
      "Country            object\n",
      "Item Type          object\n",
      "Sales Channel      object\n",
      "Order Priority     object\n",
      "Order Date         object\n",
      "Order ID            int64\n",
      "Ship Date          object\n",
      "Units Sold          int64\n",
      "Unit Price        float64\n",
      "Unit Cost         float64\n",
      "Total Revenue     float64\n",
      "Total Cost        float64\n",
      "Total Profit      float64\n",
      "dtype: object\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.7: Data types for whole dataframe (variables)\n",
    "\n",
    "print(df.dtypes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                             Country   Item Type Sales Channel Order Priority  \\\n",
      "Data                                                                            \n",
      "Middle East and North Africa   Libya   Cosmetics       Offline              M   \n",
      "North America                 Canada  Vegetables        Online              M   \n",
      "Middle East and North Africa   Libya   Baby Food       Offline              C   \n",
      "Asia                           Japan      Cereal       Offline              C   \n",
      "Sub-Saharan Africa              Chad      Fruits       Offline              H   \n",
      "\n",
      "                              Order Date   Order ID   Ship Date  Units Sold  \\\n",
      "Data                                                                          \n",
      "Middle East and North Africa  10/18/2014  686800706  10/31/2014        8446   \n",
      "North America                  11/7/2011  185941302   12/8/2011        3018   \n",
      "Middle East and North Africa  10/31/2016  246222341   12/9/2016        1517   \n",
      "Asia                           4/10/2010  161442649   5/12/2010        3322   \n",
      "Sub-Saharan Africa             8/16/2011  645713555   8/31/2011        9845   \n",
      "\n",
      "                              Unit Price  Unit Cost  Total Revenue  \\\n",
      "Data                                                                 \n",
      "Middle East and North Africa      437.20     263.33     3692591.20   \n",
      "North America                     154.06      90.93      464953.08   \n",
      "Middle East and North Africa      255.28     159.42      387259.76   \n",
      "Asia                              205.70     117.11      683335.40   \n",
      "Sub-Saharan Africa                  9.33       6.92       91853.85   \n",
      "\n",
      "                              Total Cost  Total Profit  \n",
      "Data                                                    \n",
      "Middle East and North Africa  2224085.18    1468506.02  \n",
      "North America                  274426.74     190526.34  \n",
      "Middle East and North Africa   241840.14     145419.62  \n",
      "Asia                           389039.42     294295.98  \n",
      "Sub-Saharan Africa              68127.40      23726.45  \n"
     ]
    }
   ],
   "source": [
    "##Code Block 1.8: Working on creating specific indexes\n",
    "\n",
    "## By default the index is not created for first column. So index of 0,1,2 etc were created. So, lets change that and create first column as index \n",
    "## As we have 14 columns, only 13 columns will be printed and first column is created with index name- Data\n",
    "\n",
    "df1=pd.read_csv(\"1000_Sales_Records.csv\", encoding=\"Latin-1\", index_col=0)\n",
    "\n",
    "df1.index.name='Data'\n",
    "\n",
    "print(df1.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item Type</th>\n",
       "      <th>Sales Channel</th>\n",
       "      <th>Order Priority</th>\n",
       "      <th>Order Date</th>\n",
       "      <th>Order ID</th>\n",
       "      <th>Ship Date</th>\n",
       "      <th>Units Sold</th>\n",
       "      <th>Unit Price</th>\n",
       "      <th>Unit Cost</th>\n",
       "      <th>Total Revenue</th>\n",
       "      <th>Total Cost</th>\n",
       "      <th>Total Profit</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Cosmetics</td>\n",
       "      <td>Offline</td>\n",
       "      <td>M</td>\n",
       "      <td>10/18/2014</td>\n",
       "      <td>686800706</td>\n",
       "      <td>10/31/2014</td>\n",
       "      <td>8446</td>\n",
       "      <td>437.20</td>\n",
       "      <td>263.33</td>\n",
       "      <td>3692591.20</td>\n",
       "      <td>2224085.18</td>\n",
       "      <td>1468506.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North America</td>\n",
       "      <td>Canada</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>M</td>\n",
       "      <td>11/7/2011</td>\n",
       "      <td>185941302</td>\n",
       "      <td>12/8/2011</td>\n",
       "      <td>3018</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>464953.08</td>\n",
       "      <td>274426.74</td>\n",
       "      <td>190526.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>10/31/2016</td>\n",
       "      <td>246222341</td>\n",
       "      <td>12/9/2016</td>\n",
       "      <td>1517</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>387259.76</td>\n",
       "      <td>241840.14</td>\n",
       "      <td>145419.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Asia</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2010</td>\n",
       "      <td>161442649</td>\n",
       "      <td>5/12/2010</td>\n",
       "      <td>3322</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>683335.40</td>\n",
       "      <td>389039.42</td>\n",
       "      <td>294295.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Sub-Saharan Africa</td>\n",
       "      <td>Chad</td>\n",
       "      <td>Fruits</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/16/2011</td>\n",
       "      <td>645713555</td>\n",
       "      <td>8/31/2011</td>\n",
       "      <td>9845</td>\n",
       "      <td>9.33</td>\n",
       "      <td>6.92</td>\n",
       "      <td>91853.85</td>\n",
       "      <td>68127.40</td>\n",
       "      <td>23726.45</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Region Country   Item Type Sales Channel  \\\n",
       "0  Middle East and North Africa   Libya   Cosmetics       Offline   \n",
       "1                 North America  Canada  Vegetables        Online   \n",
       "2  Middle East and North Africa   Libya   Baby Food       Offline   \n",
       "3                          Asia   Japan      Cereal       Offline   \n",
       "4            Sub-Saharan Africa    Chad      Fruits       Offline   \n",
       "\n",
       "  Order Priority  Order Date   Order ID   Ship Date  Units Sold  Unit Price  \\\n",
       "0              M  10/18/2014  686800706  10/31/2014        8446      437.20   \n",
       "1              M   11/7/2011  185941302   12/8/2011        3018      154.06   \n",
       "2              C  10/31/2016  246222341   12/9/2016        1517      255.28   \n",
       "3              C   4/10/2010  161442649   5/12/2010        3322      205.70   \n",
       "4              H   8/16/2011  645713555   8/31/2011        9845        9.33   \n",
       "\n",
       "   Unit Cost  Total Revenue  Total Cost  Total Profit  \n",
       "0     263.33     3692591.20  2224085.18    1468506.02  \n",
       "1      90.93      464953.08   274426.74     190526.34  \n",
       "2     159.42      387259.76   241840.14     145419.62  \n",
       "3     117.11      683335.40   389039.42     294295.98  \n",
       "4       6.92       91853.85    68127.40      23726.45  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Code Block 1.9: Printing the first 5 rows and last 5 rows of the dataframe\n",
    "\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item Type</th>\n",
       "      <th>Sales Channel</th>\n",
       "      <th>Order Priority</th>\n",
       "      <th>Order Date</th>\n",
       "      <th>Order ID</th>\n",
       "      <th>Ship Date</th>\n",
       "      <th>Units Sold</th>\n",
       "      <th>Unit Price</th>\n",
       "      <th>Unit Cost</th>\n",
       "      <th>Total Revenue</th>\n",
       "      <th>Total Cost</th>\n",
       "      <th>Total Profit</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Azerbaijan</td>\n",
       "      <td>Snacks</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/18/2010</td>\n",
       "      <td>534085166</td>\n",
       "      <td>4/25/2010</td>\n",
       "      <td>6524</td>\n",
       "      <td>152.58</td>\n",
       "      <td>97.44</td>\n",
       "      <td>995431.92</td>\n",
       "      <td>635698.56</td>\n",
       "      <td>359733.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Georgia</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/1/2011</td>\n",
       "      <td>590768182</td>\n",
       "      <td>9/7/2011</td>\n",
       "      <td>288</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>73520.64</td>\n",
       "      <td>45912.96</td>\n",
       "      <td>27607.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>C</td>\n",
       "      <td>5/12/2011</td>\n",
       "      <td>524363124</td>\n",
       "      <td>6/28/2011</td>\n",
       "      <td>9556</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>1472197.36</td>\n",
       "      <td>868927.08</td>\n",
       "      <td>603270.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Finland</td>\n",
       "      <td>Household</td>\n",
       "      <td>Offline</td>\n",
       "      <td>L</td>\n",
       "      <td>1/25/2016</td>\n",
       "      <td>289606320</td>\n",
       "      <td>2/14/2016</td>\n",
       "      <td>9801</td>\n",
       "      <td>668.27</td>\n",
       "      <td>502.54</td>\n",
       "      <td>6549714.27</td>\n",
       "      <td>4925394.54</td>\n",
       "      <td>1624319.73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Portugal</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2014</td>\n",
       "      <td>811546599</td>\n",
       "      <td>5/8/2014</td>\n",
       "      <td>3528</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>725709.60</td>\n",
       "      <td>413164.08</td>\n",
       "      <td>312545.52</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           Region               Country   Item Type  \\\n",
       "995  Middle East and North Africa            Azerbaijan      Snacks   \n",
       "996                        Europe               Georgia   Baby Food   \n",
       "997  Middle East and North Africa  United Arab Emirates  Vegetables   \n",
       "998                        Europe               Finland   Household   \n",
       "999                        Europe              Portugal      Cereal   \n",
       "\n",
       "    Sales Channel Order Priority Order Date   Order ID  Ship Date  Units Sold  \\\n",
       "995       Offline              C  4/18/2010  534085166  4/25/2010        6524   \n",
       "996       Offline              H   8/1/2011  590768182   9/7/2011         288   \n",
       "997        Online              C  5/12/2011  524363124  6/28/2011        9556   \n",
       "998       Offline              L  1/25/2016  289606320  2/14/2016        9801   \n",
       "999       Offline              C  4/10/2014  811546599   5/8/2014        3528   \n",
       "\n",
       "     Unit Price  Unit Cost  Total Revenue  Total Cost  Total Profit  \n",
       "995      152.58      97.44      995431.92   635698.56     359733.36  \n",
       "996      255.28     159.42       73520.64    45912.96      27607.68  \n",
       "997      154.06      90.93     1472197.36   868927.08     603270.28  \n",
       "998      668.27     502.54     6549714.27  4925394.54    1624319.73  \n",
       "999      205.70     117.11      725709.60   413164.08     312545.52  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Code Block 1.10: Printing the last 5 rows of the dataframe\n",
    "\n",
    "df.tail(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1000 entries, 0 to 999\n",
      "Data columns (total 14 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   Region          1000 non-null   object \n",
      " 1   Country         1000 non-null   object \n",
      " 2   Item Type       1000 non-null   object \n",
      " 3   Sales Channel   1000 non-null   object \n",
      " 4   Order Priority  1000 non-null   object \n",
      " 5   Order Date      1000 non-null   object \n",
      " 6   Order ID        1000 non-null   int64  \n",
      " 7   Ship Date       1000 non-null   object \n",
      " 8   Units Sold      1000 non-null   int64  \n",
      " 9   Unit Price      1000 non-null   float64\n",
      " 10  Unit Cost       1000 non-null   float64\n",
      " 11  Total Revenue   1000 non-null   float64\n",
      " 12  Total Cost      1000 non-null   float64\n",
      " 13  Total Profit    1000 non-null   float64\n",
      "dtypes: float64(5), int64(2), object(7)\n",
      "memory usage: 109.5+ KB\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "# Code Block 1.11: Displaying the information of the dataframe\n",
    "\n",
    "print(df.info())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0      Middle East and North Africa\n",
      "1                     North America\n",
      "2      Middle East and North Africa\n",
      "3                              Asia\n",
      "4                Sub-Saharan Africa\n",
      "                   ...             \n",
      "995    Middle East and North Africa\n",
      "996                          Europe\n",
      "997    Middle East and North Africa\n",
      "998                          Europe\n",
      "999                          Europe\n",
      "Name: Region, Length: 1000, dtype: object\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.12: Extracting all rows from the dataframe, and include only \"Region\" column\n",
    "\n",
    "print(df.loc[:,\"Region\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n",
      "                           Region               Country\n",
      "0    Middle East and North Africa                 Libya\n",
      "1                   North America                Canada\n",
      "2    Middle East and North Africa                 Libya\n",
      "3                            Asia                 Japan\n",
      "4              Sub-Saharan Africa                  Chad\n",
      "..                            ...                   ...\n",
      "995  Middle East and North Africa            Azerbaijan\n",
      "996                        Europe               Georgia\n",
      "997  Middle East and North Africa  United Arab Emirates\n",
      "998                        Europe               Finland\n",
      "999                        Europe              Portugal\n",
      "\n",
      "[1000 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.13: Understanding difference between Series and Dataframe\n",
    "\n",
    "##Series- Pandas type for one dimensional objects\n",
    "##Dataframe- Pandas type for >1 dimensional objects\n",
    "\n",
    "##Getting to know the data type when only one column is extracted\n",
    "\n",
    "print(type(df.loc[:, \"Region\"])) ## Its series\n",
    "\n",
    "##Extracting multiple columns from dataframe rather than one\n",
    "\n",
    "print(df.loc[:,[\"Region\",\"Country\"]]) #Datatype of this is dataframe beacuase it contains more than 1 column\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                  Country   Item Type Sales Channel Order Priority  \\\n",
      "0                   Libya   Cosmetics       Offline              M   \n",
      "1                  Canada  Vegetables        Online              M   \n",
      "2                   Libya   Baby Food       Offline              C   \n",
      "3                   Japan      Cereal       Offline              C   \n",
      "4                    Chad      Fruits       Offline              H   \n",
      "..                    ...         ...           ...            ...   \n",
      "995            Azerbaijan      Snacks       Offline              C   \n",
      "996               Georgia   Baby Food       Offline              H   \n",
      "997  United Arab Emirates  Vegetables        Online              C   \n",
      "998               Finland   Household       Offline              L   \n",
      "999              Portugal      Cereal       Offline              C   \n",
      "\n",
      "     Order Date   Order ID  \n",
      "0    10/18/2014  686800706  \n",
      "1     11/7/2011  185941302  \n",
      "2    10/31/2016  246222341  \n",
      "3     4/10/2010  161442649  \n",
      "4     8/16/2011  645713555  \n",
      "..          ...        ...  \n",
      "995   4/18/2010  534085166  \n",
      "996    8/1/2011  590768182  \n",
      "997   5/12/2011  524363124  \n",
      "998   1/25/2016  289606320  \n",
      "999   4/10/2014  811546599  \n",
      "\n",
      "[1000 rows x 6 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.14: Extracting range of columns. For example all columns from country to right end\n",
    "\n",
    "print(df.loc[:,\"Country\":\"Order ID\"]) ##Note for range of columns we should not include them in []\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##Common syntaxes for selecting rows based on values for Indexed Column (Region)\n",
    "\n",
    "#a) Selecting one column- df.loc[:, \"col1\"]  (OR) df[\"col\"]\n",
    "#b) Selecting two columns- df.loc[:,[\"col1,\"col7\"]] (OR) df[[\"col1\",col7\"]]\n",
    "#c) Selecting range of columns- df.loc[:,\"col1\":\"col7\"] and there is not shortcut command for slice of columns. We need to use loc\n",
    "\n",
    "\n",
    "## Please note that columns can be accesses via loc and shortcut. However, rows are accessed only using loc\n",
    "## Rows are used to locate only in case when we have row that is created as index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                             Country   Item Type Sales Channel Order Priority  \\\n",
      "Data                                                                            \n",
      "Middle East and North Africa   Libya   Cosmetics       Offline              M   \n",
      "North America                 Canada  Vegetables        Online              M   \n",
      "Middle East and North Africa   Libya   Baby Food       Offline              C   \n",
      "Asia                           Japan      Cereal       Offline              C   \n",
      "Sub-Saharan Africa              Chad      Fruits       Offline              H   \n",
      "\n",
      "                              Order Date   Order ID   Ship Date  Units Sold  \\\n",
      "Data                                                                          \n",
      "Middle East and North Africa  10/18/2014  686800706  10/31/2014        8446   \n",
      "North America                  11/7/2011  185941302   12/8/2011        3018   \n",
      "Middle East and North Africa  10/31/2016  246222341   12/9/2016        1517   \n",
      "Asia                           4/10/2010  161442649   5/12/2010        3322   \n",
      "Sub-Saharan Africa             8/16/2011  645713555   8/31/2011        9845   \n",
      "\n",
      "                              Unit Price  Unit Cost  Total Revenue  \\\n",
      "Data                                                                 \n",
      "Middle East and North Africa      437.20     263.33     3692591.20   \n",
      "North America                     154.06      90.93      464953.08   \n",
      "Middle East and North Africa      255.28     159.42      387259.76   \n",
      "Asia                              205.70     117.11      683335.40   \n",
      "Sub-Saharan Africa                  9.33       6.92       91853.85   \n",
      "\n",
      "                              Total Cost  Total Profit  \n",
      "Data                                                    \n",
      "Middle East and North Africa  2224085.18    1468506.02  \n",
      "North America                  274426.74     190526.34  \n",
      "Middle East and North Africa   241840.14     145419.62  \n",
      "Asia                           389039.42     294295.98  \n",
      "Sub-Saharan Africa              68127.40      23726.45  \n",
      "       Country  Item Type Sales Channel Order Priority  Order Date   Order ID  \\\n",
      "Data                                                                            \n",
      "Asia     Japan     Cereal       Offline              C   4/10/2010  161442649   \n",
      "Asia  Maldives     Fruits       Offline              L    1/8/2011  714135205   \n",
      "Asia  Mongolia    Clothes        Online              L  12/12/2015  770478332   \n",
      "Asia  Mongolia  Beverages        Online              M    8/3/2013  329110324   \n",
      "Asia      Laos  Beverages        Online              M   3/22/2013  693473613   \n",
      "...        ...        ...           ...            ...         ...        ...   \n",
      "Asia  Mongolia  Beverages       Offline              M   4/23/2014  270611131   \n",
      "Asia      Laos     Snacks       Offline              M    1/3/2012  232389438   \n",
      "Asia    Brunei    Clothes       Offline              H    8/6/2011  612573039   \n",
      "Asia  Mongolia    Clothes       Offline              H   9/23/2016  308168065   \n",
      "Asia     Nepal       Meat       Offline              C    4/9/2017  919890248   \n",
      "\n",
      "       Ship Date  Units Sold  Unit Price  Unit Cost  Total Revenue  \\\n",
      "Data                                                                 \n",
      "Asia   5/12/2010        3322      205.70     117.11      683335.40   \n",
      "Asia    2/6/2011        7332        9.33       6.92       68407.56   \n",
      "Asia   1/24/2016         515      109.28      35.84       56279.20   \n",
      "Asia    9/2/2013        9913       47.45      31.79      470371.85   \n",
      "Asia   4/21/2013        3107       47.45      31.79      147427.15   \n",
      "...          ...         ...         ...        ...            ...   \n",
      "Asia   5/24/2014        8702       47.45      31.79      412909.90   \n",
      "Asia    1/8/2012        8054      152.58      97.44     1228879.32   \n",
      "Asia    8/9/2011        2830      109.28      35.84      309262.40   \n",
      "Asia  10/18/2016        2633      109.28      35.84      287734.24   \n",
      "Asia   5/18/2017        4821      421.89     364.69     2033931.69   \n",
      "\n",
      "      Total Cost  Total Profit  \n",
      "Data                            \n",
      "Asia   389039.42     294295.98  \n",
      "Asia    50737.44      17670.12  \n",
      "Asia    18457.60      37821.60  \n",
      "Asia   315134.27     155237.58  \n",
      "Asia    98771.53      48655.62  \n",
      "...          ...           ...  \n",
      "Asia   276636.58     136273.32  \n",
      "Asia   784781.76     444097.56  \n",
      "Asia   101427.20     207835.20  \n",
      "Asia    94366.72     193367.52  \n",
      "Asia  1758170.49     275761.20  \n",
      "\n",
      "[136 rows x 13 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.15: Selection Based on single index column\n",
    "\n",
    "print(df1.head())\n",
    "\n",
    "print(df1.loc[\"Asia\"]) #It prints all rows where index column Region has \"Asia\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                Country      Item Type Sales Channel  \\\n",
      "Data                                                                   \n",
      "Asia                              Japan         Cereal       Offline   \n",
      "Asia                           Maldives         Fruits       Offline   \n",
      "Asia                           Mongolia        Clothes        Online   \n",
      "Asia                           Mongolia      Beverages        Online   \n",
      "Asia                               Laos      Beverages        Online   \n",
      "...                                 ...            ...           ...   \n",
      "North America  United States of America  Personal Care       Offline   \n",
      "North America  United States of America           Meat        Online   \n",
      "North America                 Greenland        Clothes        Online   \n",
      "North America                 Greenland         Snacks       Offline   \n",
      "North America                    Mexico      Baby Food        Online   \n",
      "\n",
      "              Order Priority  Order Date   Order ID  Ship Date  Units Sold  \\\n",
      "Data                                                                         \n",
      "Asia                       C   4/10/2010  161442649  5/12/2010        3322   \n",
      "Asia                       L    1/8/2011  714135205   2/6/2011        7332   \n",
      "Asia                       L  12/12/2015  770478332  1/24/2016         515   \n",
      "Asia                       M    8/3/2013  329110324   9/2/2013        9913   \n",
      "Asia                       M   3/22/2013  693473613  4/21/2013        3107   \n",
      "...                      ...         ...        ...        ...         ...   \n",
      "North America              C   7/16/2010  551057326  8/22/2010        8963   \n",
      "North America              M    3/6/2011  908136594  3/10/2011        6654   \n",
      "North America              L   1/28/2011  851299941   2/1/2011        7425   \n",
      "North America              L   6/24/2010  977499377  8/12/2010        2643   \n",
      "North America              H   8/17/2013  434355056  9/28/2013        4168   \n",
      "\n",
      "               Unit Price  Unit Cost  Total Revenue  Total Cost  Total Profit  \n",
      "Data                                                                           \n",
      "Asia               205.70     117.11      683335.40   389039.42     294295.98  \n",
      "Asia                 9.33       6.92       68407.56    50737.44      17670.12  \n",
      "Asia               109.28      35.84       56279.20    18457.60      37821.60  \n",
      "Asia                47.45      31.79      470371.85   315134.27     155237.58  \n",
      "Asia                47.45      31.79      147427.15    98771.53      48655.62  \n",
      "...                   ...        ...            ...         ...           ...  \n",
      "North America       81.73      56.67      732545.99   507933.21     224612.78  \n",
      "North America      421.89     364.69     2807256.06  2426647.26     380608.80  \n",
      "North America      109.28      35.84      811404.00   266112.00     545292.00  \n",
      "North America      152.58      97.44      403268.94   257533.92     145735.02  \n",
      "North America      255.28     159.42     1064007.04   664462.56     399544.48  \n",
      "\n",
      "[155 rows x 13 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 1.16: Selection Based on multiple index columns values\n",
    "\n",
    "print(df1.loc[[\"Asia\",\"North America\"]]) # #It prints all rows where index column Region has \"Asia\" and \"North America\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Code Block 1.17: Selection Based on multiple index columns values\n",
    "\n",
    "#print(df1.loc[\"Asia\":\"North America\"])  # #It prints all rows where index column Region has \"Asia\" to \"North America\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##Concept of Series vs Dataframe (for selecting rows and columns)\n",
    "\n",
    "#Series\n",
    "#Rows- df.loc[\"v\"]\n",
    "#columns- df[\"v\"]\n",
    "\n",
    "#Dataframe\n",
    "\n",
    "#Rows- df.loc[[\"A\",\"B\",\"C\"]]\n",
    "#Columns- df[[\"A\",\"B\",\"C\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Region   Country  Item Type Sales Channel Order Priority  Order Date  \\\n",
      "3     Asia     Japan     Cereal       Offline              C   4/10/2010   \n",
      "14    Asia  Maldives     Fruits       Offline              L    1/8/2011   \n",
      "23    Asia  Mongolia    Clothes        Online              L  12/12/2015   \n",
      "41    Asia  Mongolia  Beverages        Online              M    8/3/2013   \n",
      "45    Asia      Laos  Beverages        Online              M   3/22/2013   \n",
      "..     ...       ...        ...           ...            ...         ...   \n",
      "960   Asia  Mongolia  Beverages       Offline              M   4/23/2014   \n",
      "969   Asia      Laos     Snacks       Offline              M    1/3/2012   \n",
      "973   Asia    Brunei    Clothes       Offline              H    8/6/2011   \n",
      "986   Asia  Mongolia    Clothes       Offline              H   9/23/2016   \n",
      "994   Asia     Nepal       Meat       Offline              C    4/9/2017   \n",
      "\n",
      "      Order ID   Ship Date  Units Sold  Unit Price  Unit Cost  Total Revenue  \\\n",
      "3    161442649   5/12/2010        3322      205.70     117.11      683335.40   \n",
      "14   714135205    2/6/2011        7332        9.33       6.92       68407.56   \n",
      "23   770478332   1/24/2016         515      109.28      35.84       56279.20   \n",
      "41   329110324    9/2/2013        9913       47.45      31.79      470371.85   \n",
      "45   693473613   4/21/2013        3107       47.45      31.79      147427.15   \n",
      "..         ...         ...         ...         ...        ...            ...   \n",
      "960  270611131   5/24/2014        8702       47.45      31.79      412909.90   \n",
      "969  232389438    1/8/2012        8054      152.58      97.44     1228879.32   \n",
      "973  612573039    8/9/2011        2830      109.28      35.84      309262.40   \n",
      "986  308168065  10/18/2016        2633      109.28      35.84      287734.24   \n",
      "994  919890248   5/18/2017        4821      421.89     364.69     2033931.69   \n",
      "\n",
      "     Total Cost  Total Profit  \n",
      "3     389039.42     294295.98  \n",
      "14     50737.44      17670.12  \n",
      "23     18457.60      37821.60  \n",
      "41    315134.27     155237.58  \n",
      "45     98771.53      48655.62  \n",
      "..          ...           ...  \n",
      "960   276636.58     136273.32  \n",
      "969   784781.76     444097.56  \n",
      "973   101427.20     207835.20  \n",
      "986    94366.72     193367.52  \n",
      "994  1758170.49     275761.20  \n",
      "\n",
      "[136 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "#Topic 2: Conversion of operations/code from SQL to Python\n",
    "\n",
    "#Code Block 2.1: SQL (where clause with single condition)-->Python Code\n",
    "\n",
    "#Select all rows where Region='Asia'\n",
    "## In pandas you can extract the specific column using the column name, in case of numpy- we need to know the exact column location\n",
    "\n",
    "reg_fl= df['Region']=='Asia'\n",
    "\n",
    "df_asia_reg=df[reg_fl]\n",
    "\n",
    "print(df_asia_reg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "136\n",
      "(136, 14)\n"
     ]
    }
   ],
   "source": [
    "print(len(df_asia_reg)) # 136 is the output\n",
    "\n",
    "print(df_asia_reg.shape) # (136,14) is the output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Region    Country      Item Type Sales Channel Order Priority  Order Date  \\\n",
      "23    Asia   Mongolia        Clothes        Online              L  12/12/2015   \n",
      "41    Asia   Mongolia      Beverages        Online              M    8/3/2013   \n",
      "45    Asia       Laos      Beverages        Online              M   3/22/2013   \n",
      "49    Asia     Bhutan           Meat        Online              H   12/9/2016   \n",
      "70    Asia      India         Fruits        Online              H   7/29/2010   \n",
      "..     ...        ...            ...           ...            ...         ...   \n",
      "901   Asia      Japan      Cosmetics        Online              L    1/6/2016   \n",
      "923   Asia  Indonesia  Personal Care        Online              H   9/10/2011   \n",
      "931   Asia      Nepal         Fruits        Online              C   7/22/2014   \n",
      "935   Asia   Maldives  Personal Care        Online              M   10/9/2013   \n",
      "940   Asia      India         Cereal        Online              C   3/27/2010   \n",
      "\n",
      "      Order ID   Ship Date  Units Sold  Unit Price  Unit Cost  Total Revenue  \\\n",
      "23   770478332   1/24/2016         515      109.28      35.84       56279.20   \n",
      "41   329110324    9/2/2013        9913       47.45      31.79      470371.85   \n",
      "45   693473613   4/21/2013        3107       47.45      31.79      147427.15   \n",
      "49   726708972   1/26/2017        8189      421.89     364.69     3454857.21   \n",
      "70   658348691   8/22/2010        8862        9.33       6.92       82682.46   \n",
      "..         ...         ...         ...         ...        ...            ...   \n",
      "901  453569972   2/19/2016         289      437.20     263.33      126350.80   \n",
      "923  777840888  10/23/2011        9259       81.73      56.67      756738.07   \n",
      "931  673803794   7/29/2014        2371        9.33       6.92       22121.43   \n",
      "935  849312102  11/23/2013        9180       81.73      56.67      750281.40   \n",
      "940  160299813    4/6/2010        5132      205.70     117.11     1055652.40   \n",
      "\n",
      "     Total Cost  Total Profit  \n",
      "23     18457.60      37821.60  \n",
      "41    315134.27     155237.58  \n",
      "45     98771.53      48655.62  \n",
      "49   2986446.41     468410.80  \n",
      "70     61325.04      21357.42  \n",
      "..          ...           ...  \n",
      "901    76102.37      50248.43  \n",
      "923   524707.53     232030.54  \n",
      "931    16407.32       5714.11  \n",
      "935   520230.60     230050.80  \n",
      "940   601008.52     454643.88  \n",
      "\n",
      "[67 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 2.2: SQL (where clause with multiple conditions)-->Python Code\n",
    "\n",
    "# Select all rows where Region='Asia' and Sales Channel is Online'\n",
    "# Using AND (&) operator\n",
    "# OR Operator can be used like |\n",
    "\n",
    "reg_fl=df['Region']=='Asia'\n",
    "\n",
    "sales_ch_fl=df['Sales Channel']== 'Online'\n",
    "\n",
    "combined= reg_fl & sales_ch_fl\n",
    "\n",
    "df_Asia_Online=df[combined]\n",
    "\n",
    "print(df_Asia_Online)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Region     Country        Item Type Sales Channel Order Priority  \\\n",
      "3     Asia       Japan           Cereal       Offline              C   \n",
      "14    Asia    Maldives           Fruits       Offline              L   \n",
      "55    Asia    Malaysia           Snacks       Offline              M   \n",
      "56    Asia  Uzbekistan  Office Supplies       Offline              L   \n",
      "58    Asia       Nepal       Vegetables       Offline              C   \n",
      "..     ...         ...              ...           ...            ...   \n",
      "960   Asia    Mongolia        Beverages       Offline              M   \n",
      "969   Asia        Laos           Snacks       Offline              M   \n",
      "973   Asia      Brunei          Clothes       Offline              H   \n",
      "986   Asia    Mongolia          Clothes       Offline              H   \n",
      "994   Asia       Nepal             Meat       Offline              C   \n",
      "\n",
      "    Order Date   Order ID   Ship Date  Units Sold  Unit Price  Unit Cost  \\\n",
      "3    4/10/2010  161442649   5/12/2010        3322      205.70     117.11   \n",
      "14    1/8/2011  714135205    2/6/2011        7332        9.33       6.92   \n",
      "55   10/6/2012  175033080   11/5/2012        5033      152.58      97.44   \n",
      "56   3/10/2012  276595246   3/15/2012        9535      651.21     524.96   \n",
      "58    6/2/2014  443121373   6/19/2014        8316      154.06      90.93   \n",
      "..         ...        ...         ...         ...         ...        ...   \n",
      "960  4/23/2014  270611131   5/24/2014        8702       47.45      31.79   \n",
      "969   1/3/2012  232389438    1/8/2012        8054      152.58      97.44   \n",
      "973   8/6/2011  612573039    8/9/2011        2830      109.28      35.84   \n",
      "986  9/23/2016  308168065  10/18/2016        2633      109.28      35.84   \n",
      "994   4/9/2017  919890248   5/18/2017        4821      421.89     364.69   \n",
      "\n",
      "     Total Revenue  Total Cost  Total Profit  \n",
      "3        683335.40   389039.42     294295.98  \n",
      "14        68407.56    50737.44      17670.12  \n",
      "55       767935.14   490415.52     277519.62  \n",
      "56      6209287.35  5005493.60    1203793.75  \n",
      "58      1281162.96   756173.88     524989.08  \n",
      "..             ...         ...           ...  \n",
      "960      412909.90   276636.58     136273.32  \n",
      "969     1228879.32   784781.76     444097.56  \n",
      "973      309262.40   101427.20     207835.20  \n",
      "986      287734.24    94366.72     193367.52  \n",
      "994     2033931.69  1758170.49     275761.20  \n",
      "\n",
      "[69 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 2.3: SQL (where clause with multiple conditions using NOT IN)-->Python Code\n",
    "\n",
    "##Select all rows where Region='Asia' and Sales Channel is not Online'\n",
    "# Using NOT (!=) operator\n",
    "\n",
    "reg_fl=df['Region']=='Asia'\n",
    "\n",
    "sales_ch_fl=df['Sales Channel'] != 'Online'\n",
    "\n",
    "combined= reg_fl & sales_ch_fl\n",
    "\n",
    "df_Asia_not_Online=df[combined]\n",
    "\n",
    "print(df_Asia_not_Online)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Region       Country        Item Type Sales Channel Order Priority  \\\n",
      "855   Asia   Philippines           Fruits       Offline              L   \n",
      "14    Asia      Maldives           Fruits       Offline              L   \n",
      "437   Asia    Kyrgyzstan           Fruits        Online              C   \n",
      "70    Asia         India           Fruits        Online              H   \n",
      "82    Asia   South Korea           Fruits       Offline              L   \n",
      "..     ...           ...              ...           ...            ...   \n",
      "801   Asia  Turkmenistan  Office Supplies       Offline              M   \n",
      "567   Asia    Bangladesh  Office Supplies       Offline              C   \n",
      "454   Asia          Laos  Office Supplies       Offline              M   \n",
      "236   Asia   South Korea  Office Supplies       Offline              M   \n",
      "787   Asia      Maldives  Office Supplies        Online              H   \n",
      "\n",
      "     Order Date   Order ID   Ship Date  Units Sold  Unit Price  Unit Cost  \\\n",
      "855    5/4/2013  827964293    6/1/2013        1888        9.33       6.92   \n",
      "14     1/8/2011  714135205    2/6/2011        7332        9.33       6.92   \n",
      "437   1/14/2012  402614009    3/2/2012        1287        9.33       6.92   \n",
      "70    7/29/2010  658348691   8/22/2010        8862        9.33       6.92   \n",
      "82     3/7/2010  769205892   3/17/2010        3972        9.33       6.92   \n",
      "..          ...        ...         ...         ...         ...        ...   \n",
      "801  11/24/2016  143657672    1/8/2017         352      651.21     524.96   \n",
      "567  10/28/2015  210409057   12/4/2015        3570      651.21     524.96   \n",
      "454   8/31/2015  588200986  10/15/2015         598      651.21     524.96   \n",
      "236   7/26/2015  312927377    9/7/2015        1020      651.21     524.96   \n",
      "787    4/4/2010  989928519   4/11/2010         702      651.21     524.96   \n",
      "\n",
      "     Total Revenue  Total Cost  Total Profit  \n",
      "855       17615.04    13064.96       4550.08  \n",
      "14        68407.56    50737.44      17670.12  \n",
      "437       12007.71     8906.04       3101.67  \n",
      "70        82682.46    61325.04      21357.42  \n",
      "82        37058.76    27486.24       9572.52  \n",
      "..             ...         ...           ...  \n",
      "801      229225.92   184785.92      44440.00  \n",
      "567     2324819.70  1874107.20     450712.50  \n",
      "454      389423.58   313926.08      75497.50  \n",
      "236      664234.20   535459.20     128775.00  \n",
      "787      457149.42   368521.92      88627.50  \n",
      "\n",
      "[136 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 2.4: SQL (where clause with order by on single variable)-->Python Code\n",
    "\n",
    "##Select all rows where Region='Asia' order by Unit Cost\n",
    "\n",
    "reg_fl=df['Region']=='Asia'\n",
    "\n",
    "df_asia_unit_cost=df[reg_fl].sort_values(by='Unit Cost')\n",
    "\n",
    "print(df_asia_unit_cost)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Region      Country        Item Type Sales Channel Order Priority  \\\n",
      "563   Asia     Mongolia           Fruits        Online              M   \n",
      "437   Asia   Kyrgyzstan           Fruits        Online              C   \n",
      "855   Asia  Philippines           Fruits       Offline              L   \n",
      "931   Asia        Nepal           Fruits        Online              C   \n",
      "82    Asia  South Korea           Fruits       Offline              L   \n",
      "..     ...          ...              ...           ...            ...   \n",
      "158   Asia      Vietnam  Office Supplies        Online              H   \n",
      "719   Asia     Malaysia  Office Supplies        Online              C   \n",
      "504   Asia        China  Office Supplies        Online              C   \n",
      "56    Asia   Uzbekistan  Office Supplies       Offline              L   \n",
      "943   Asia       Bhutan  Office Supplies       Offline              M   \n",
      "\n",
      "     Order Date   Order ID   Ship Date  Units Sold  Unit Price  Unit Cost  \\\n",
      "563   9/12/2013  171131217   10/8/2013         385        9.33       6.92   \n",
      "437   1/14/2012  402614009    3/2/2012        1287        9.33       6.92   \n",
      "855    5/4/2013  827964293    6/1/2013        1888        9.33       6.92   \n",
      "931   7/22/2014  673803794   7/29/2014        2371        9.33       6.92   \n",
      "82     3/7/2010  769205892   3/17/2010        3972        9.33       6.92   \n",
      "..          ...        ...         ...         ...         ...        ...   \n",
      "158   8/16/2016  606970441   9/16/2016        4897      651.21     524.96   \n",
      "719    7/7/2014  560608565   8/24/2014        5387      651.21     524.96   \n",
      "504   9/30/2015  893779695   11/7/2015        8128      651.21     524.96   \n",
      "56    3/10/2012  276595246   3/15/2012        9535      651.21     524.96   \n",
      "943  10/19/2011  221007430  11/10/2011        9865      651.21     524.96   \n",
      "\n",
      "     Total Revenue  Total Cost  Total Profit  \n",
      "563        3592.05     2664.20        927.85  \n",
      "437       12007.71     8906.04       3101.67  \n",
      "855       17615.04    13064.96       4550.08  \n",
      "931       22121.43    16407.32       5714.11  \n",
      "82        37058.76    27486.24       9572.52  \n",
      "..             ...         ...           ...  \n",
      "158     3188975.37  2570729.12     618246.25  \n",
      "719     3508068.27  2827959.52     680108.75  \n",
      "504     5293034.88  4266874.88    1026160.00  \n",
      "56      6209287.35  5005493.60    1203793.75  \n",
      "943     6424186.65  5178730.40    1245456.25  \n",
      "\n",
      "[136 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 2.5: SQL (where clause with order by on multiple variables)-->Python Code\n",
    "\n",
    "##Select all rows where Region='Asia' order by Unit Cost and Units Sold\n",
    "\n",
    "reg_fl=df['Region']=='Asia'\n",
    "\n",
    "df_asia_unit_cost_usold=df[reg_fl].sort_values(by=['Unit Cost', 'Units Sold'])\n",
    "\n",
    "print(df_asia_unit_cost_usold)\n",
    "## Please note: If you want to have the columns sorted in descending order use like below\n",
    "\n",
    "## df_asia_unit_cost_usold=df[reg_fl].sort_values(by=['Unit Cost', 'Units Sold'], ascending='False')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count       1000\n",
      "unique         7\n",
      "top       Europe\n",
      "freq         267\n",
      "Name: Region, dtype: object\n",
      "Europe                               267\n",
      "Sub-Saharan Africa                   262\n",
      "Middle East and North Africa         138\n",
      "Asia                                 136\n",
      "Central America and the Caribbean     99\n",
      "Australia and Oceania                 79\n",
      "North America                         19\n",
      "Name: Region, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "#Topic 3: Data Exploration\n",
    "\n",
    "#Code Block 3.1:Checking on various statistics for categorical variables with 1 variable (Series)\n",
    "## The output of this basically returns count, unique regions, top and freq\n",
    "# Top is basically the region name whichever has more rows\n",
    "# Freq is basically the highest number pertaining to the top region\n",
    "\n",
    "print(df[\"Region\"].describe())\n",
    "\n",
    "print(df[\"Region\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count    1000.000000\n",
      "mean      184.965110\n",
      "std       175.289311\n",
      "min         6.920000\n",
      "25%        56.670000\n",
      "50%        97.440000\n",
      "75%       263.330000\n",
      "max       524.960000\n",
      "Name: Unit Cost, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "## Code Block 3.2:Checking on various statistics for integer variables with 1 variable (Series)\n",
    "## The output of this will give us count, mean, std, min, 25%, 50%, 75%, max\n",
    "print(df[\"Unit Cost\"].describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "           Order ID   Units Sold  Unit Price    Unit Cost  Total Revenue  \\\n",
      "count  1.000000e+03  1000.000000  1000.00000  1000.000000   1.000000e+03   \n",
      "mean   5.496813e+08  5053.988000   262.10684   184.965110   1.327322e+06   \n",
      "std    2.571334e+08  2901.375317   216.02106   175.289311   1.486515e+06   \n",
      "min    1.029280e+08    13.000000     9.33000     6.920000   2.043250e+03   \n",
      "25%    3.280740e+08  2420.250000    81.73000    56.670000   2.811919e+05   \n",
      "50%    5.566097e+08  5184.000000   154.06000    97.440000   7.549392e+05   \n",
      "75%    7.696945e+08  7536.750000   421.89000   263.330000   1.733503e+06   \n",
      "max    9.955298e+08  9998.000000   668.27000   524.960000   6.617210e+06   \n",
      "\n",
      "         Total Cost  Total Profit  \n",
      "count  1.000000e+03  1.000000e+03  \n",
      "mean   9.361192e+05  3.912026e+05  \n",
      "std    1.162571e+06  3.836402e+05  \n",
      "min    1.416750e+03  5.326100e+02  \n",
      "25%    1.649319e+05  9.837612e+04  \n",
      "50%    4.647261e+05  2.772260e+05  \n",
      "75%    1.141750e+06  5.484568e+05  \n",
      "max    5.204978e+06  1.726181e+06  \n"
     ]
    }
   ],
   "source": [
    "#Code Block 3.3:Working on describe method for the whole dataframe which basically consists a mix of numbers and categorical variables\n",
    "## Please note that by default describe method on dataframe will give statistics only for numeric columns\n",
    "print(df.describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        Region Country  Item Type Sales Channel Order Priority Order Date  \\\n",
      "count     1000    1000       1000          1000           1000       1000   \n",
      "unique       7     185         12             2              4        841   \n",
      "top     Europe    Cuba  Beverages       Offline              L   2/5/2013   \n",
      "freq       267      11        101           520            268          3   \n",
      "mean       NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "std        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "min        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "25%        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "50%        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "75%        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "max        NaN     NaN        NaN           NaN            NaN        NaN   \n",
      "\n",
      "            Order ID  Ship Date   Units Sold  Unit Price    Unit Cost  \\\n",
      "count   1.000000e+03       1000  1000.000000  1000.00000  1000.000000   \n",
      "unique           NaN        835          NaN         NaN          NaN   \n",
      "top              NaN  2/22/2015          NaN         NaN          NaN   \n",
      "freq             NaN          3          NaN         NaN          NaN   \n",
      "mean    5.496813e+08        NaN  5053.988000   262.10684   184.965110   \n",
      "std     2.571334e+08        NaN  2901.375317   216.02106   175.289311   \n",
      "min     1.029280e+08        NaN    13.000000     9.33000     6.920000   \n",
      "25%     3.280740e+08        NaN  2420.250000    81.73000    56.670000   \n",
      "50%     5.566097e+08        NaN  5184.000000   154.06000    97.440000   \n",
      "75%     7.696945e+08        NaN  7536.750000   421.89000   263.330000   \n",
      "max     9.955298e+08        NaN  9998.000000   668.27000   524.960000   \n",
      "\n",
      "        Total Revenue    Total Cost  Total Profit  \n",
      "count    1.000000e+03  1.000000e+03  1.000000e+03  \n",
      "unique            NaN           NaN           NaN  \n",
      "top               NaN           NaN           NaN  \n",
      "freq              NaN           NaN           NaN  \n",
      "mean     1.327322e+06  9.361192e+05  3.912026e+05  \n",
      "std      1.486515e+06  1.162571e+06  3.836402e+05  \n",
      "min      2.043250e+03  1.416750e+03  5.326100e+02  \n",
      "25%      2.811919e+05  1.649319e+05  9.837612e+04  \n",
      "50%      7.549392e+05  4.647261e+05  2.772260e+05  \n",
      "75%      1.733503e+06  1.141750e+06  5.484568e+05  \n",
      "max      6.617210e+06  5.204978e+06  1.726181e+06  \n"
     ]
    }
   ],
   "source": [
    "## If you want to use the describe against both integer and categorical values. Use below option\n",
    "# Here you will get statistics for categorical and numerical variables. Whereever, they don't apply- NaN will be populated\n",
    "\n",
    "print(df.describe(include='all'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Profit    277225.980\n",
      "Total Cost      464726.065\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "##Code Block 3.4: Data exploration methods for Series vs Dataframe\n",
    "## Series and Dataframe exploration methods\n",
    "\n",
    "## Series.max() and Dataframe.max()\n",
    "## Series.median() and Dataframe.median()\n",
    "\n",
    "## But for dataframe- we also need to give axis parameter. (axis=1 for row and axis=0 for column)\n",
    "\n",
    "print(df[[\"Total Profit\",\"Total Cost\"]].median(axis=0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Order ID         5.566097e+08\n",
      "Units Sold       5.184000e+03\n",
      "Unit Price       1.540600e+02\n",
      "Unit Cost        9.744000e+01\n",
      "Total Revenue    7.549392e+05\n",
      "Total Cost       4.647261e+05\n",
      "Total Profit     2.772260e+05\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Code Block 3.5:Checking median of all integer columns in the dataframe\n",
    "# There are other several functions like mean(), sum(), max(), min(), mode().\n",
    "# You can use all the above methods with both Series and with dataframe\n",
    "# This prints median for all integer variables in the dataframe\n",
    "print(df.median())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    2224085.18\n",
      "1     274426.74\n",
      "2     241840.14\n",
      "3     389039.42\n",
      "4      68127.40\n",
      "Name: Total Cost, dtype: float64\n",
      "464726.065\n"
     ]
    }
   ],
   "source": [
    "# Code Block 3.5(contd..)When printing out the statistics like mean, median etc in above steps, i do see thet are printed in exponential form\n",
    "# Using the below print function with head and median prints numbers as it is.\n",
    "## This is used to see the exact values\n",
    "print(df[\"Total Cost\"].head(5))\n",
    "print(df[\"Total Cost\"].median())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Middle East and North Africa' 'North America' 'Asia'\n",
      " 'Sub-Saharan Africa' 'Europe' 'Central America and the Caribbean'\n",
      " 'Australia and Oceania']\n"
     ]
    }
   ],
   "source": [
    "#Code Block 3.6: Select distinct values of any column\n",
    "# The output of this is a list which looks like below\n",
    "#['Middle East and North Africa' 'North America' 'Asia' 'Sub-Saharan Africa'\n",
    "# 'Europe' 'Central America and the Caribbean' 'Australia and Oceania']\n",
    "\n",
    "print(df['Region'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3         Japan\n",
      "14     Maldives\n",
      "23     Mongolia\n",
      "41     Mongolia\n",
      "45         Laos\n",
      "         ...   \n",
      "960    Mongolia\n",
      "969        Laos\n",
      "973      Brunei\n",
      "986    Mongolia\n",
      "994       Nepal\n",
      "Name: Country, Length: 136, dtype: object\n"
     ]
    }
   ],
   "source": [
    "##Code Block 3.7: Creating boolean value and returning only rows where boolean values is true but with only one column you need\n",
    "## This can be done by passng bool flag as row and column you desire as column to loc function\n",
    "#loc is must when you select the row and column from the dataframe\n",
    "\n",
    "bool_flag=df[\"Region\"]=='Asia'\n",
    "\n",
    "print(df.loc[bool_flag,\"Country\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cuba              11\n",
      "Malaysia          10\n",
      "Bahrain           10\n",
      "Czech Republic    10\n",
      "Zimbabwe          10\n",
      "                  ..\n",
      "Zambia             2\n",
      "The Gambia         2\n",
      "Cameroon           1\n",
      "Kosovo             1\n",
      "Malta              1\n",
      "Name: Country, Length: 185, dtype: int64\n",
      "Cuba        11\n",
      "Malaysia    10\n",
      "Bahrain     10\n",
      "Name: Country, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "##Code Block 3.8:Top 3 countries whichever existed more in our dataset\n",
    "\n",
    "print(df[\"Country\"].value_counts())\n",
    "print(df[\"Country\"].value_counts().head(3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "       Country  Total Profit\n",
      "Data                        \n",
      "Asia     Japan     294295.98\n",
      "Asia  Maldives      17670.12\n",
      "Asia  Mongolia      37821.60\n",
      "Asia  Mongolia     155237.58\n",
      "Asia      Laos      48655.62\n",
      "...        ...           ...\n",
      "Asia  Mongolia     136273.32\n",
      "Asia      Laos     444097.56\n",
      "Asia    Brunei     207835.20\n",
      "Asia  Mongolia     193367.52\n",
      "Asia     Nepal     275761.20\n",
      "\n",
      "[136 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "#Code Block 3.9 : For example, if you want to select rows and columns of dataframe in case when indexes on row exists\n",
    "# loc is must when you want to select row and column from the dataframe\n",
    "# df1 is used as this dataframe is created with first column as index\n",
    "print(df1.loc[[\"Asia\"],[\"Country\",\"Total Profit\"]])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Sub-Saharan Africa'"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Code Block 3.10: Using iloc vs loc\n",
    "##iloc is integer based selection when no index is created on the dataset\n",
    "## for example, if you want to select 500th row from df\n",
    "\n",
    "df.iloc[500] # This prints the row 500 completely with all variables\n",
    "\n",
    "\n",
    "#df.iloc[500, \"Region\"] # This will give you an error as iloc doesn't accept variable names for columns\n",
    "\n",
    "df.iloc[500,0] ## This will print the 500th row Region column. Region column is located at 0. Hence, 0 is used for col position\n",
    "\n",
    "##When iloc is useful?\n",
    "## For example- if you extract all the rows and want to check 1st row, 25th row- this is only possible with iloc\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0      False\n",
      "1      False\n",
      "2      False\n",
      "3      False\n",
      "4      False\n",
      "       ...  \n",
      "995    False\n",
      "996    False\n",
      "997    False\n",
      "998    False\n",
      "999    False\n",
      "Name: Region, Length: 1000, dtype: bool\n",
      "Empty DataFrame\n",
      "Columns: [Region, Country, Item Type, Sales Channel, Order Priority, Order Date, Order ID, Ship Date, Units Sold, Unit Price, Unit Cost, Total Revenue, Total Cost, Total Profit]\n",
      "Index: []\n"
     ]
    }
   ],
   "source": [
    "#Code Block 3.11: isnull() and notnull()\n",
    "\n",
    "isnull_flag=df[\"Region\"].isnull()\n",
    "\n",
    "print(isnull_flag) ## True/False values are printed depending whether the Region is null or not for the row\n",
    "\n",
    "print(df[isnull_flag]) #Empty dataframe is created because there are no rows with null value in Region\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0      True\n",
      "1      True\n",
      "2      True\n",
      "3      True\n",
      "4      True\n",
      "       ... \n",
      "995    True\n",
      "996    True\n",
      "997    True\n",
      "998    True\n",
      "999    True\n",
      "Name: Region, Length: 1000, dtype: bool\n",
      "                           Region               Country   Item Type  \\\n",
      "0    Middle East and North Africa                 Libya   Cosmetics   \n",
      "1                   North America                Canada  Vegetables   \n",
      "2    Middle East and North Africa                 Libya   Baby Food   \n",
      "3                            Asia                 Japan      Cereal   \n",
      "4              Sub-Saharan Africa                  Chad      Fruits   \n",
      "..                            ...                   ...         ...   \n",
      "995  Middle East and North Africa            Azerbaijan      Snacks   \n",
      "996                        Europe               Georgia   Baby Food   \n",
      "997  Middle East and North Africa  United Arab Emirates  Vegetables   \n",
      "998                        Europe               Finland   Household   \n",
      "999                        Europe              Portugal      Cereal   \n",
      "\n",
      "    Sales Channel Order Priority  Order Date   Order ID   Ship Date  \\\n",
      "0         Offline              M  10/18/2014  686800706  10/31/2014   \n",
      "1          Online              M   11/7/2011  185941302   12/8/2011   \n",
      "2         Offline              C  10/31/2016  246222341   12/9/2016   \n",
      "3         Offline              C   4/10/2010  161442649   5/12/2010   \n",
      "4         Offline              H   8/16/2011  645713555   8/31/2011   \n",
      "..            ...            ...         ...        ...         ...   \n",
      "995       Offline              C   4/18/2010  534085166   4/25/2010   \n",
      "996       Offline              H    8/1/2011  590768182    9/7/2011   \n",
      "997        Online              C   5/12/2011  524363124   6/28/2011   \n",
      "998       Offline              L   1/25/2016  289606320   2/14/2016   \n",
      "999       Offline              C   4/10/2014  811546599    5/8/2014   \n",
      "\n",
      "     Units Sold  Unit Price  Unit Cost  Total Revenue  Total Cost  \\\n",
      "0          8446      437.20     263.33     3692591.20  2224085.18   \n",
      "1          3018      154.06      90.93      464953.08   274426.74   \n",
      "2          1517      255.28     159.42      387259.76   241840.14   \n",
      "3          3322      205.70     117.11      683335.40   389039.42   \n",
      "4          9845        9.33       6.92       91853.85    68127.40   \n",
      "..          ...         ...        ...            ...         ...   \n",
      "995        6524      152.58      97.44      995431.92   635698.56   \n",
      "996         288      255.28     159.42       73520.64    45912.96   \n",
      "997        9556      154.06      90.93     1472197.36   868927.08   \n",
      "998        9801      668.27     502.54     6549714.27  4925394.54   \n",
      "999        3528      205.70     117.11      725709.60   413164.08   \n",
      "\n",
      "     Total Profit  \n",
      "0      1468506.02  \n",
      "1       190526.34  \n",
      "2       145419.62  \n",
      "3       294295.98  \n",
      "4        23726.45  \n",
      "..            ...  \n",
      "995     359733.36  \n",
      "996      27607.68  \n",
      "997     603270.28  \n",
      "998    1624319.73  \n",
      "999     312545.52  \n",
      "\n",
      "[1000 rows x 14 columns]\n"
     ]
    }
   ],
   "source": [
    "##Code Block 3.11 (contd..) let's try with notnull- Using notnull()\n",
    "\n",
    "isnotnull_flag=df[\"Region\"].notnull()\n",
    "\n",
    "print(isnotnull_flag) ## True/False values are printed depending whether the Region is not null or not for the row\n",
    "\n",
    "print(df[isnotnull_flag]) #Empty dataframe is created because there are no rows with null value in Region"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "200                  Asia\n",
      "188                  Asia\n",
      "787                  Asia\n",
      "791                  Asia\n",
      "943                  Asia\n",
      "              ...        \n",
      "414    Sub-Saharan Africa\n",
      "415    Sub-Saharan Africa\n",
      "416    Sub-Saharan Africa\n",
      "769    Sub-Saharan Africa\n",
      "820    Sub-Saharan Africa\n",
      "Name: Region, Length: 1000, dtype: object\n",
      "['Asia' 'Australia and Oceania' 'Central America and the Caribbean'\n",
      " 'Europe' 'Middle East and North Africa' 'North America'\n",
      " 'Sub-Saharan Africa']\n"
     ]
    }
   ],
   "source": [
    "##Code Block 3.12 : Printing the unique values of the column\n",
    "\n",
    "print(df['Region'].sort_values()) ## All rows are printed, but not unique Regions\n",
    "\n",
    "print(df['Region'].sort_values().unique()) #Now unique Region list sorted in alphabetical order will be produced\n",
    "\n",
    "## Please note that unique operation should be used after sort_values() and it shouldn't be used before sort_values()"
   ]
  },
  {
   "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>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item Type</th>\n",
       "      <th>Sales Channel</th>\n",
       "      <th>Order Priority</th>\n",
       "      <th>Order Date</th>\n",
       "      <th>Order ID</th>\n",
       "      <th>Ship Date</th>\n",
       "      <th>Units Sold</th>\n",
       "      <th>Unit Price</th>\n",
       "      <th>Unit Cost</th>\n",
       "      <th>Total Revenue</th>\n",
       "      <th>Total Cost</th>\n",
       "      <th>Total Profit</th>\n",
       "      <th>New Column</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Cosmetics</td>\n",
       "      <td>Offline</td>\n",
       "      <td>M</td>\n",
       "      <td>10/18/2014</td>\n",
       "      <td>686800706</td>\n",
       "      <td>10/31/2014</td>\n",
       "      <td>8446</td>\n",
       "      <td>437.20</td>\n",
       "      <td>263.33</td>\n",
       "      <td>3692591.20</td>\n",
       "      <td>2224085.18</td>\n",
       "      <td>1468506.02</td>\n",
       "      <td>8546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North America</td>\n",
       "      <td>Canada</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>M</td>\n",
       "      <td>11/7/2011</td>\n",
       "      <td>185941302</td>\n",
       "      <td>12/8/2011</td>\n",
       "      <td>3018</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>464953.08</td>\n",
       "      <td>274426.74</td>\n",
       "      <td>190526.34</td>\n",
       "      <td>3118</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>10/31/2016</td>\n",
       "      <td>246222341</td>\n",
       "      <td>12/9/2016</td>\n",
       "      <td>1517</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>387259.76</td>\n",
       "      <td>241840.14</td>\n",
       "      <td>145419.62</td>\n",
       "      <td>1617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Asia</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2010</td>\n",
       "      <td>161442649</td>\n",
       "      <td>5/12/2010</td>\n",
       "      <td>3322</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>683335.40</td>\n",
       "      <td>389039.42</td>\n",
       "      <td>294295.98</td>\n",
       "      <td>3422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Sub-Saharan Africa</td>\n",
       "      <td>Chad</td>\n",
       "      <td>Fruits</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/16/2011</td>\n",
       "      <td>645713555</td>\n",
       "      <td>8/31/2011</td>\n",
       "      <td>9845</td>\n",
       "      <td>9.33</td>\n",
       "      <td>6.92</td>\n",
       "      <td>91853.85</td>\n",
       "      <td>68127.40</td>\n",
       "      <td>23726.45</td>\n",
       "      <td>9945</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Region Country   Item Type Sales Channel  \\\n",
       "0  Middle East and North Africa   Libya   Cosmetics       Offline   \n",
       "1                 North America  Canada  Vegetables        Online   \n",
       "2  Middle East and North Africa   Libya   Baby Food       Offline   \n",
       "3                          Asia   Japan      Cereal       Offline   \n",
       "4            Sub-Saharan Africa    Chad      Fruits       Offline   \n",
       "\n",
       "  Order Priority  Order Date   Order ID   Ship Date  Units Sold  Unit Price  \\\n",
       "0              M  10/18/2014  686800706  10/31/2014        8446      437.20   \n",
       "1              M   11/7/2011  185941302   12/8/2011        3018      154.06   \n",
       "2              C  10/31/2016  246222341   12/9/2016        1517      255.28   \n",
       "3              C   4/10/2010  161442649   5/12/2010        3322      205.70   \n",
       "4              H   8/16/2011  645713555   8/31/2011        9845        9.33   \n",
       "\n",
       "   Unit Cost  Total Revenue  Total Cost  Total Profit  New Column  \n",
       "0     263.33     3692591.20  2224085.18    1468506.02        8546  \n",
       "1      90.93      464953.08   274426.74     190526.34        3118  \n",
       "2     159.42      387259.76   241840.14     145419.62        1617  \n",
       "3     117.11      683335.40   389039.42     294295.98        3422  \n",
       "4       6.92       91853.85    68127.40      23726.45        9945  "
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " # Topic 4: Creating a new column, calculated columns, cleaning the column names, dropping rows/columns\n",
    "    \n",
    "##4.1 Creating a new column with addition of value=100 to the Units Sold\n",
    "\n",
    "df2=pd.read_csv(\"1000_Sales_Records.csv\", encoding=\"Latin-1\")\n",
    "\n",
    "df2['New Column']= df2['Units Sold']+100\n",
    "\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Region', 'Country', 'Item Type', 'Sales Channel', 'Order Priority',\n",
      "       'Order Date', 'Order ID', 'Ship Date', 'Units Sold', 'Unit Price',\n",
      "       'Unit Cost', 'Total Revenue', 'Total Cost', 'Total Profit'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "##4.2 Printing all the columns from the dataset/Getting to know the column names\n",
    "\n",
    "print(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Region', 'Country', 'Item Type', 'Sales Channel', 'Order Priority',\n",
      "       'Order Date', 'Order ID', 'Ship Date', 'Units Sold', 'Unit Price',\n",
      "       'Unit Cost', 'Total Revenue', 'Total Cost', 'Total Profit',\n",
      "       'New Column'],\n",
      "      dtype='object')\n",
      "Index(['Region', 'Country', 'Item_Type', 'Sales_Channel', 'Order_Priority',\n",
      "       'Order_Date', 'Order_ID', 'Ship_Date', 'Units_Sold', 'Unit_Price',\n",
      "       'Unit_Cost', 'Total_Revenue', 'Total_Cost', 'Total_Profit',\n",
      "       'New_Column'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "##4.3 Cleaning the columns\n",
    "#Remvoing the blank space between the columns whichever has blanks with underscore\n",
    "#str.title() can be used if you want to have column names that begin with Caps and small letters for rest\n",
    "#Inserting variables into strings: \n",
    "    #output=\"{}'s favorite number is {}\".format(\"Kyle\",8)\n",
    "    #print(output)\n",
    "    #Output is as follows: Kyle's favorite number is 8\n",
    "\n",
    "print(df2.columns)\n",
    "\n",
    "df2.columns = df2.columns.str.replace(' ', '_')\n",
    "\n",
    "print(df2.columns)\n",
    "\n",
    "## For example: if you want only few columns to be cleaned use the below technique\n",
    "\n",
    "#colu=['Order Date','Unit Cost']\n",
    "# for n in colu:\n",
    "    #n.replace()\n",
    "\n",
    "#You can see that all columns that has space between two words were replaced with _"
   ]
  },
  {
   "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>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item_Type</th>\n",
       "      <th>Sales_Channel</th>\n",
       "      <th>Order_Priority</th>\n",
       "      <th>Order_Date</th>\n",
       "      <th>Order_ID</th>\n",
       "      <th>Ship_Date</th>\n",
       "      <th>Units_Sold</th>\n",
       "      <th>Unit_Price</th>\n",
       "      <th>Unit_Cost</th>\n",
       "      <th>Total_Revenue</th>\n",
       "      <th>Total_Cost</th>\n",
       "      <th>Total_Profit</th>\n",
       "      <th>New_Column</th>\n",
       "      <th>Order_Date_Calc1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Cosmetics</td>\n",
       "      <td>Offline</td>\n",
       "      <td>M</td>\n",
       "      <td>10/18/2014</td>\n",
       "      <td>686800706</td>\n",
       "      <td>10/31/2014</td>\n",
       "      <td>8446</td>\n",
       "      <td>437.20</td>\n",
       "      <td>263.33</td>\n",
       "      <td>3692591.20</td>\n",
       "      <td>2224085.18</td>\n",
       "      <td>1468506.02</td>\n",
       "      <td>8546</td>\n",
       "      <td>2014-10-18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North America</td>\n",
       "      <td>Canada</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>M</td>\n",
       "      <td>11/7/2011</td>\n",
       "      <td>185941302</td>\n",
       "      <td>12/8/2011</td>\n",
       "      <td>3018</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>464953.08</td>\n",
       "      <td>274426.74</td>\n",
       "      <td>190526.34</td>\n",
       "      <td>3118</td>\n",
       "      <td>2011-11-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>10/31/2016</td>\n",
       "      <td>246222341</td>\n",
       "      <td>12/9/2016</td>\n",
       "      <td>1517</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>387259.76</td>\n",
       "      <td>241840.14</td>\n",
       "      <td>145419.62</td>\n",
       "      <td>1617</td>\n",
       "      <td>2016-10-31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Asia</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2010</td>\n",
       "      <td>161442649</td>\n",
       "      <td>5/12/2010</td>\n",
       "      <td>3322</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>683335.40</td>\n",
       "      <td>389039.42</td>\n",
       "      <td>294295.98</td>\n",
       "      <td>3422</td>\n",
       "      <td>2010-04-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Sub-Saharan Africa</td>\n",
       "      <td>Chad</td>\n",
       "      <td>Fruits</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/16/2011</td>\n",
       "      <td>645713555</td>\n",
       "      <td>8/31/2011</td>\n",
       "      <td>9845</td>\n",
       "      <td>9.33</td>\n",
       "      <td>6.92</td>\n",
       "      <td>91853.85</td>\n",
       "      <td>68127.40</td>\n",
       "      <td>23726.45</td>\n",
       "      <td>9945</td>\n",
       "      <td>2011-08-16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Region Country   Item_Type Sales_Channel  \\\n",
       "0  Middle East and North Africa   Libya   Cosmetics       Offline   \n",
       "1                 North America  Canada  Vegetables        Online   \n",
       "2  Middle East and North Africa   Libya   Baby Food       Offline   \n",
       "3                          Asia   Japan      Cereal       Offline   \n",
       "4            Sub-Saharan Africa    Chad      Fruits       Offline   \n",
       "\n",
       "  Order_Priority  Order_Date   Order_ID   Ship_Date  Units_Sold  Unit_Price  \\\n",
       "0              M  10/18/2014  686800706  10/31/2014        8446      437.20   \n",
       "1              M   11/7/2011  185941302   12/8/2011        3018      154.06   \n",
       "2              C  10/31/2016  246222341   12/9/2016        1517      255.28   \n",
       "3              C   4/10/2010  161442649   5/12/2010        3322      205.70   \n",
       "4              H   8/16/2011  645713555   8/31/2011        9845        9.33   \n",
       "\n",
       "   Unit_Cost  Total_Revenue  Total_Cost  Total_Profit  New_Column  \\\n",
       "0     263.33     3692591.20  2224085.18    1468506.02        8546   \n",
       "1      90.93      464953.08   274426.74     190526.34        3118   \n",
       "2     159.42      387259.76   241840.14     145419.62        1617   \n",
       "3     117.11      683335.40   389039.42     294295.98        3422   \n",
       "4       6.92       91853.85    68127.40      23726.45        9945   \n",
       "\n",
       "  Order_Date_Calc1  \n",
       "0       2014-10-18  \n",
       "1       2011-11-07  \n",
       "2       2016-10-31  \n",
       "3       2010-04-10  \n",
       "4       2011-08-16  "
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "##4.4 Converting the data type of the column \n",
    "## Order date is in String format. Lets convert it to date\n",
    "\n",
    "\n",
    "df2[\"Order_Date_Calc1\"]= pd.to_datetime(df2['Order_Date'])\n",
    "\n",
    "df2.head()\n",
    "\n",
    "#You can see the converted order date in the last column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1000 entries, 0 to 999\n",
      "Data columns (total 16 columns):\n",
      " #   Column            Non-Null Count  Dtype         \n",
      "---  ------            --------------  -----         \n",
      " 0   Region            1000 non-null   object        \n",
      " 1   Country           1000 non-null   object        \n",
      " 2   Item_Type         1000 non-null   object        \n",
      " 3   Sales_Channel     1000 non-null   object        \n",
      " 4   Order_Priority    1000 non-null   object        \n",
      " 5   Order_Date        1000 non-null   object        \n",
      " 6   Order_ID          1000 non-null   int64         \n",
      " 7   Ship_Date         1000 non-null   object        \n",
      " 8   Units_Sold        1000 non-null   int64         \n",
      " 9   Unit_Price        1000 non-null   float64       \n",
      " 10  Unit_Cost         1000 non-null   float64       \n",
      " 11  Total_Revenue     1000 non-null   float64       \n",
      " 12  Total_Cost        1000 non-null   float64       \n",
      " 13  Total_Profit      1000 non-null   float64       \n",
      " 14  New_Column        1000 non-null   int64         \n",
      " 15  Order_Date_Calc1  1000 non-null   datetime64[ns]\n",
      "dtypes: datetime64[ns](1), float64(5), int64(3), object(7)\n",
      "memory usage: 125.1+ KB\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "print(df2.info()) # The new column is created and the type was changed form object to datetime64[ns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Region', 'Country', 'Item_Type', 'Sales_Channel', 'Order_Priority',\n",
      "       'Order_Date', 'Order_ID', 'Ship_Date', 'Units_Sold', 'Unit_Price',\n",
      "       'Unit_Cost', 'Total_Revenue', 'Total_Cost', 'Total_Profit',\n",
      "       'New_Column', 'Order_Date_Calc1'],\n",
      "      dtype='object')\n",
      "Index(['Region', 'Country', 'Item_Type', 'Sales_Channel', 'Order_Priority',\n",
      "       'Order_Date', 'Order_ID', 'Ship_Date', 'Units_Sold', 'Unit_Price',\n",
      "       'Unit_Cost', 'Total_Revenue', 'Total_Cost', 'Total_Profit',\n",
      "       'New_Column', 'Order_Date_Calc1'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "##4.5 Renaming the column names\n",
    "# Lets rename the newly converted date column \"Order_Date_Calc1\" to \"Order_Date_Calc'\n",
    "# inplace=True when we are ready to implement the permanent changes to the dataset\n",
    "\n",
    "df2.rename({\"Order_Date\":\"Order_Date_Orig\"}, inplace=True)\n",
    "print(df2.columns)\n",
    "\n",
    "df2.rename({\"Order_Date_Calc1\":\"Order_Date_Calc\"}, inplace=True)\n",
    "print(df2.columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Region', 'Country', 'Item_Type', 'Sales_Channel', 'Order_Priority',\n",
      "       'Order_Date_Orig', 'Order_ID', 'Ship_Date', 'Units_Sold', 'Unit_Price',\n",
      "       'Unit_Cost', 'Total_Revenue', 'Total_Cost', 'Total_Profit',\n",
      "       'New_Column', 'Order_Date_Calc1'],\n",
      "      dtype='object')\n",
      "Index(['Region', 'Country', 'Item_Type', 'Sales_Channel', 'Order_Priority',\n",
      "       'Order_Date_Orig', 'Order_ID', 'Ship_Date', 'Units_Sold', 'Unit_Price',\n",
      "       'Unit_Cost', 'Total_Revenue', 'Total_Cost', 'Total_Profit',\n",
      "       'New_Column', 'Order_Date_Calc'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "## Both the above statements works, but doesn't produce desired output\n",
    "#Below statements work after including axis=1\n",
    "# axis=1- we need to speecify this so that pandas knows that we want to rename labels in the column axis\n",
    "df2.rename({\"Order_Date\":\"Order_Date_Orig\"},axis=1, inplace=True)\n",
    "print(df2.columns)\n",
    "\n",
    "df2.rename({\"Order_Date_Calc1\":\"Order_Date_Calc\"}, axis=1, inplace=True)\n",
    "print(df2.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Region            0\n",
      "Country           0\n",
      "Item Type         0\n",
      "Sales Channel     0\n",
      "Order Priority    0\n",
      "Order Date        0\n",
      "Order ID          0\n",
      "Ship Date         0\n",
      "Units Sold        0\n",
      "Unit Price        0\n",
      "Unit Cost         0\n",
      "Total Revenue     0\n",
      "Total Cost        0\n",
      "Total Profit      0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "##4.6 Counting the missing values for each column in the dataset\n",
    "##None of the columns in this dataset has missing values\n",
    "print(df.isnull().sum())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "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>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item Type</th>\n",
       "      <th>Sales Channel</th>\n",
       "      <th>Order Priority</th>\n",
       "      <th>Order Date</th>\n",
       "      <th>Order ID</th>\n",
       "      <th>Ship Date</th>\n",
       "      <th>Units Sold</th>\n",
       "      <th>Unit Price</th>\n",
       "      <th>Unit Cost</th>\n",
       "      <th>Total Revenue</th>\n",
       "      <th>Total Cost</th>\n",
       "      <th>Total Profit</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Cosmetics</td>\n",
       "      <td>Offline</td>\n",
       "      <td>M</td>\n",
       "      <td>10/18/2014</td>\n",
       "      <td>686800706</td>\n",
       "      <td>10/31/2014</td>\n",
       "      <td>8446</td>\n",
       "      <td>437.20</td>\n",
       "      <td>263.33</td>\n",
       "      <td>3692591.20</td>\n",
       "      <td>2224085.18</td>\n",
       "      <td>1468506.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North America</td>\n",
       "      <td>Canada</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>M</td>\n",
       "      <td>11/7/2011</td>\n",
       "      <td>185941302</td>\n",
       "      <td>12/8/2011</td>\n",
       "      <td>3018</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>464953.08</td>\n",
       "      <td>274426.74</td>\n",
       "      <td>190526.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>10/31/2016</td>\n",
       "      <td>246222341</td>\n",
       "      <td>12/9/2016</td>\n",
       "      <td>1517</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>387259.76</td>\n",
       "      <td>241840.14</td>\n",
       "      <td>145419.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Asia</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2010</td>\n",
       "      <td>161442649</td>\n",
       "      <td>5/12/2010</td>\n",
       "      <td>3322</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>683335.40</td>\n",
       "      <td>389039.42</td>\n",
       "      <td>294295.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Sub-Saharan Africa</td>\n",
       "      <td>Chad</td>\n",
       "      <td>Fruits</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/16/2011</td>\n",
       "      <td>645713555</td>\n",
       "      <td>8/31/2011</td>\n",
       "      <td>9845</td>\n",
       "      <td>9.33</td>\n",
       "      <td>6.92</td>\n",
       "      <td>91853.85</td>\n",
       "      <td>68127.40</td>\n",
       "      <td>23726.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Azerbaijan</td>\n",
       "      <td>Snacks</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/18/2010</td>\n",
       "      <td>534085166</td>\n",
       "      <td>4/25/2010</td>\n",
       "      <td>6524</td>\n",
       "      <td>152.58</td>\n",
       "      <td>97.44</td>\n",
       "      <td>995431.92</td>\n",
       "      <td>635698.56</td>\n",
       "      <td>359733.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Georgia</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/1/2011</td>\n",
       "      <td>590768182</td>\n",
       "      <td>9/7/2011</td>\n",
       "      <td>288</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>73520.64</td>\n",
       "      <td>45912.96</td>\n",
       "      <td>27607.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>C</td>\n",
       "      <td>5/12/2011</td>\n",
       "      <td>524363124</td>\n",
       "      <td>6/28/2011</td>\n",
       "      <td>9556</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>1472197.36</td>\n",
       "      <td>868927.08</td>\n",
       "      <td>603270.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Finland</td>\n",
       "      <td>Household</td>\n",
       "      <td>Offline</td>\n",
       "      <td>L</td>\n",
       "      <td>1/25/2016</td>\n",
       "      <td>289606320</td>\n",
       "      <td>2/14/2016</td>\n",
       "      <td>9801</td>\n",
       "      <td>668.27</td>\n",
       "      <td>502.54</td>\n",
       "      <td>6549714.27</td>\n",
       "      <td>4925394.54</td>\n",
       "      <td>1624319.73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>Europe</td>\n",
       "      <td>Portugal</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2014</td>\n",
       "      <td>811546599</td>\n",
       "      <td>5/8/2014</td>\n",
       "      <td>3528</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>725709.60</td>\n",
       "      <td>413164.08</td>\n",
       "      <td>312545.52</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           Region               Country   Item Type  \\\n",
       "0    Middle East and North Africa                 Libya   Cosmetics   \n",
       "1                   North America                Canada  Vegetables   \n",
       "2    Middle East and North Africa                 Libya   Baby Food   \n",
       "3                            Asia                 Japan      Cereal   \n",
       "4              Sub-Saharan Africa                  Chad      Fruits   \n",
       "..                            ...                   ...         ...   \n",
       "995  Middle East and North Africa            Azerbaijan      Snacks   \n",
       "996                        Europe               Georgia   Baby Food   \n",
       "997  Middle East and North Africa  United Arab Emirates  Vegetables   \n",
       "998                        Europe               Finland   Household   \n",
       "999                        Europe              Portugal      Cereal   \n",
       "\n",
       "    Sales Channel Order Priority  Order Date   Order ID   Ship Date  \\\n",
       "0         Offline              M  10/18/2014  686800706  10/31/2014   \n",
       "1          Online              M   11/7/2011  185941302   12/8/2011   \n",
       "2         Offline              C  10/31/2016  246222341   12/9/2016   \n",
       "3         Offline              C   4/10/2010  161442649   5/12/2010   \n",
       "4         Offline              H   8/16/2011  645713555   8/31/2011   \n",
       "..            ...            ...         ...        ...         ...   \n",
       "995       Offline              C   4/18/2010  534085166   4/25/2010   \n",
       "996       Offline              H    8/1/2011  590768182    9/7/2011   \n",
       "997        Online              C   5/12/2011  524363124   6/28/2011   \n",
       "998       Offline              L   1/25/2016  289606320   2/14/2016   \n",
       "999       Offline              C   4/10/2014  811546599    5/8/2014   \n",
       "\n",
       "     Units Sold  Unit Price  Unit Cost  Total Revenue  Total Cost  \\\n",
       "0          8446      437.20     263.33     3692591.20  2224085.18   \n",
       "1          3018      154.06      90.93      464953.08   274426.74   \n",
       "2          1517      255.28     159.42      387259.76   241840.14   \n",
       "3          3322      205.70     117.11      683335.40   389039.42   \n",
       "4          9845        9.33       6.92       91853.85    68127.40   \n",
       "..          ...         ...        ...            ...         ...   \n",
       "995        6524      152.58      97.44      995431.92   635698.56   \n",
       "996         288      255.28     159.42       73520.64    45912.96   \n",
       "997        9556      154.06      90.93     1472197.36   868927.08   \n",
       "998        9801      668.27     502.54     6549714.27  4925394.54   \n",
       "999        3528      205.70     117.11      725709.60   413164.08   \n",
       "\n",
       "     Total Profit  \n",
       "0      1468506.02  \n",
       "1       190526.34  \n",
       "2       145419.62  \n",
       "3       294295.98  \n",
       "4        23726.45  \n",
       "..            ...  \n",
       "995     359733.36  \n",
       "996      27607.68  \n",
       "997     603270.28  \n",
       "998    1624319.73  \n",
       "999     312545.52  \n",
       "\n",
       "[1000 rows x 14 columns]"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#4.7 Dropping rows and columns that has missing values\n",
    "\n",
    "df.dropna(axis=0) # Dropping rows that have missing values. Only for this one row is 0\n",
    "df.dropna(axis=1) # Dropping columns that have missing values\n",
    "\n",
    "# Pleaase note that in the above scenario, we don't have missing rows or columns. Hence, noting is being dropped"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "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>Region</th>\n",
       "      <th>Country</th>\n",
       "      <th>Item_Type</th>\n",
       "      <th>Sales_Channel</th>\n",
       "      <th>Order_Priority</th>\n",
       "      <th>Order_Date_Orig</th>\n",
       "      <th>Order_ID</th>\n",
       "      <th>Ship_Date</th>\n",
       "      <th>Units_Sold</th>\n",
       "      <th>Unit_Price</th>\n",
       "      <th>Unit_Cost</th>\n",
       "      <th>Total_Revenue</th>\n",
       "      <th>Total_Cost</th>\n",
       "      <th>Total_Profit</th>\n",
       "      <th>New_Column</th>\n",
       "      <th>Order_Date_Calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Cosmetics</td>\n",
       "      <td>Offline</td>\n",
       "      <td>M</td>\n",
       "      <td>10/18/2014</td>\n",
       "      <td>686800706</td>\n",
       "      <td>10/31/2014</td>\n",
       "      <td>8446</td>\n",
       "      <td>437.20</td>\n",
       "      <td>263.33</td>\n",
       "      <td>3692591.20</td>\n",
       "      <td>2224085.18</td>\n",
       "      <td>1468506.02</td>\n",
       "      <td>0</td>\n",
       "      <td>2014-10-18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North America</td>\n",
       "      <td>Canada</td>\n",
       "      <td>Vegetables</td>\n",
       "      <td>Online</td>\n",
       "      <td>M</td>\n",
       "      <td>11/7/2011</td>\n",
       "      <td>185941302</td>\n",
       "      <td>12/8/2011</td>\n",
       "      <td>3018</td>\n",
       "      <td>154.06</td>\n",
       "      <td>90.93</td>\n",
       "      <td>464953.08</td>\n",
       "      <td>274426.74</td>\n",
       "      <td>190526.34</td>\n",
       "      <td>3118</td>\n",
       "      <td>2011-11-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Middle East and North Africa</td>\n",
       "      <td>Libya</td>\n",
       "      <td>Baby Food</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>10/31/2016</td>\n",
       "      <td>246222341</td>\n",
       "      <td>12/9/2016</td>\n",
       "      <td>1517</td>\n",
       "      <td>255.28</td>\n",
       "      <td>159.42</td>\n",
       "      <td>387259.76</td>\n",
       "      <td>241840.14</td>\n",
       "      <td>145419.62</td>\n",
       "      <td>1617</td>\n",
       "      <td>2016-10-31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Asia</td>\n",
       "      <td>Japan</td>\n",
       "      <td>Cereal</td>\n",
       "      <td>Offline</td>\n",
       "      <td>C</td>\n",
       "      <td>4/10/2010</td>\n",
       "      <td>161442649</td>\n",
       "      <td>5/12/2010</td>\n",
       "      <td>3322</td>\n",
       "      <td>205.70</td>\n",
       "      <td>117.11</td>\n",
       "      <td>683335.40</td>\n",
       "      <td>389039.42</td>\n",
       "      <td>294295.98</td>\n",
       "      <td>3422</td>\n",
       "      <td>2010-04-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Sub-Saharan Africa</td>\n",
       "      <td>Chad</td>\n",
       "      <td>Fruits</td>\n",
       "      <td>Offline</td>\n",
       "      <td>H</td>\n",
       "      <td>8/16/2011</td>\n",
       "      <td>645713555</td>\n",
       "      <td>8/31/2011</td>\n",
       "      <td>9845</td>\n",
       "      <td>9.33</td>\n",
       "      <td>6.92</td>\n",
       "      <td>91853.85</td>\n",
       "      <td>68127.40</td>\n",
       "      <td>23726.45</td>\n",
       "      <td>0</td>\n",
       "      <td>2011-08-16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Region Country   Item_Type Sales_Channel  \\\n",
       "0  Middle East and North Africa   Libya   Cosmetics       Offline   \n",
       "1                 North America  Canada  Vegetables        Online   \n",
       "2  Middle East and North Africa   Libya   Baby Food       Offline   \n",
       "3                          Asia   Japan      Cereal       Offline   \n",
       "4            Sub-Saharan Africa    Chad      Fruits       Offline   \n",
       "\n",
       "  Order_Priority Order_Date_Orig   Order_ID   Ship_Date  Units_Sold  \\\n",
       "0              M      10/18/2014  686800706  10/31/2014        8446   \n",
       "1              M       11/7/2011  185941302   12/8/2011        3018   \n",
       "2              C      10/31/2016  246222341   12/9/2016        1517   \n",
       "3              C       4/10/2010  161442649   5/12/2010        3322   \n",
       "4              H       8/16/2011  645713555   8/31/2011        9845   \n",
       "\n",
       "   Unit_Price  Unit_Cost  Total_Revenue  Total_Cost  Total_Profit  New_Column  \\\n",
       "0      437.20     263.33     3692591.20  2224085.18    1468506.02           0   \n",
       "1      154.06      90.93      464953.08   274426.74     190526.34        3118   \n",
       "2      255.28     159.42      387259.76   241840.14     145419.62        1617   \n",
       "3      205.70     117.11      683335.40   389039.42     294295.98        3422   \n",
       "4        9.33       6.92       91853.85    68127.40      23726.45           0   \n",
       "\n",
       "  Order_Date_Calc  \n",
       "0      2014-10-18  \n",
       "1      2011-11-07  \n",
       "2      2016-10-31  \n",
       "3      2010-04-10  \n",
       "4      2011-08-16  "
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#4.8 Replacing the missing values with some value (provided with some conditional logic)\n",
    "#Replacing the New_Column only if the new column is >4000\n",
    "\n",
    "df2.loc[df2[\"New_Column\"]>4000, \"New_Column\"]=0\n",
    "\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<map object at 0x000001F61E12FB08>\n",
      "{16, 1, 4, 9}\n"
     ]
    }
   ],
   "source": [
    "#4.9 Map funciton\n",
    "# Map()- this applies the given function to each item of iterable and returns list of results\n",
    "\n",
    "def calculateSquare(n):\n",
    "    return n*n\n",
    "\n",
    "numbers= (1,2,3,4)\n",
    "\n",
    "result= map(calculateSquare, numbers)\n",
    "\n",
    "print(result) #Directly using print result won't work. We need to convert the map result to set result and then print\n",
    "\n",
    "numbersSquare=set(result)\n",
    "\n",
    "print(numbersSquare)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##Another example where you can use map() to apply string value columns to function as dictionary looking\n",
    "\n",
    "corrections={\n",
    "        \"pair\":\"pear\",\n",
    "        \"orang\":\"orange\"}\n",
    "\n",
    "s=s.map(corrections) #sting s- here is nothing but series\n",
    "\n",
    "print(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##4.10 Writing the final dataset (cleaned) one into csv\n",
    "##Given that we created df2 with some new columns and renamed some columns- let's convert that df2 into csv and write into file\n",
    "\n",
    "df2.to_csv(\"df2.csv\", index=False) #With this I am able to create df2.csv which is visible in Jupiter Notebook local files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                    Units Sold\n",
      "Region                                        \n",
      "Asia                               4981.794118\n",
      "Australia and Oceania              5282.253165\n",
      "Central America and the Caribbean  5084.464646\n",
      "Europe                             4815.760300\n",
      "Middle East and North Africa       4944.659420\n",
      "North America                      5302.052632\n",
      "Sub-Saharan Africa                 5293.488550\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1f61e4d1808>"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Topic 5: Plotting\n",
    "\n",
    "#5.1 Plotting a horizontal bar/histogram\n",
    "# To do this, lets first plot the pivot table- summarize the data and plot the graph\n",
    "# The below code is continuation of pivot tables created above in Topic 2\n",
    "# The xlim has 10000 here(which is maximum in x axis. We need to actually observe the values and change xlim accordingly. \n",
    "# if xlim value is 100 as all the mean values of Region is above 100. so bar will be the same for all regions which will make us confused\n",
    "# In below code, we didn't include any aggregation function with in pivot_table, but the plot was done.\n",
    "# By default, the aggregation function with in pivot_table is mean. If you want the min plot or max plot- you need to include option with in\n",
    "# pivot table.\n",
    "\n",
    "pivot_to_plot=df.pivot_table('Units Sold', 'Region')\n",
    "print(df.pivot_table('Units Sold', 'Region'))\n",
    "\n",
    "pivot_to_plot.plot(kind='barh', title='Mean Units Sold Graph by Region', xlim=(1,10000), legend=False)"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}