diff --git a/PlayingWithPySpark.ipynb b/PlayingWithPySpark.ipynb
new file mode 100644
index 0000000..f8e2650
--- /dev/null
+++ b/PlayingWithPySpark.ipynb
@@ -0,0 +1,1603 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "PlayingWithPySpark.ipynb",
+      "provenance": [],
+      "authorship_tag": "ABX9TyOF7+/AN17kQLuEoGi/PlvX",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/RahulParajuli/DataVisualizationandML/blob/devraul/PlayingWithPySpark.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#Basic File handling in pyspark"
+      ],
+      "metadata": {
+        "id": "WvhoMDm3qYXY"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "YTmURVunjz-b",
+        "outputId": "d97d3537-12ba-4b7d-c7d4-792f836328cc"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+            "Collecting pyspark\n",
+            "  Downloading pyspark-3.3.0.tar.gz (281.3 MB)\n",
+            "\u001b[K     |████████████████████████████████| 281.3 MB 44 kB/s \n",
+            "\u001b[?25hCollecting py4j==0.10.9.5\n",
+            "  Downloading py4j-0.10.9.5-py2.py3-none-any.whl (199 kB)\n",
+            "\u001b[K     |████████████████████████████████| 199 kB 23.2 MB/s \n",
+            "\u001b[?25hBuilding wheels for collected packages: pyspark\n",
+            "  Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for pyspark: filename=pyspark-3.3.0-py2.py3-none-any.whl size=281764026 sha256=989eb92b401d94eed999e05a79755e4016b986bcba113aedc51dd7a64fe1f890\n",
+            "  Stored in directory: /root/.cache/pip/wheels/7a/8e/1b/f73a52650d2e5f337708d9f6a1750d451a7349a867f928b885\n",
+            "Successfully built pyspark\n",
+            "Installing collected packages: py4j, pyspark\n",
+            "Successfully installed py4j-0.10.9.5 pyspark-3.3.0\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install pyspark"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pyspark"
+      ],
+      "metadata": {
+        "id": "wu2_80ZOj2EN"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from pyspark.sql import SparkSession"
+      ],
+      "metadata": {
+        "id": "8r0aUQpWj4vu"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spark = SparkSession.builder.appName(\"Practice\").getOrCreate()"
+      ],
+      "metadata": {
+        "id": "6Jr8Y72vkpel"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spark"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 219
+        },
+        "id": "PgeetEYmkwc_",
+        "outputId": "2b6e6a53-4638-46ae-da39-8e0e4c88aa9a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<pyspark.sql.session.SparkSession at 0x7f18d7a90850>"
+            ],
+            "text/html": [
+              "\n",
+              "            <div>\n",
+              "                <p><b>SparkSession - in-memory</b></p>\n",
+              "                \n",
+              "        <div>\n",
+              "            <p><b>SparkContext</b></p>\n",
+              "\n",
+              "            <p><a href=\"http://09f26e936462:4040\">Spark UI</a></p>\n",
+              "\n",
+              "            <dl>\n",
+              "              <dt>Version</dt>\n",
+              "                <dd><code>v3.3.0</code></dd>\n",
+              "              <dt>Master</dt>\n",
+              "                <dd><code>local[*]</code></dd>\n",
+              "              <dt>AppName</dt>\n",
+              "                <dd><code>Practice</code></dd>\n",
+              "            </dl>\n",
+              "        </div>\n",
+              "        \n",
+              "            </div>\n",
+              "        "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 5
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark = spark.read.csv(\"/content/5000_sales_records.csv\")"
+      ],
+      "metadata": {
+        "id": "IGc2mnbDkxWy"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "42CsxNRUk9xU",
+        "outputId": "f91eae4a-b3aa-4798-ab54-6b26df21ffc9"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "DataFrame[_c0: string, _c1: string, _c2: string, _c3: string, _c4: string, _c5: string, _c6: string, _c7: string, _c8: string, _c9: string, _c10: string, _c11: string, _c12: string, _c13: string]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 38
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "bL3O-W4NlA99",
+        "outputId": "5269efb9-0dbf-42b2-b391-9ad7394d146e"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|                 _c0|                 _c1|            _c2|          _c3|           _c4|       _c5|      _c6|       _c7|       _c8|       _c9|     _c10|         _c11|      _c12|        _c13|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|    226716.10| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|    205.70|   117.11|   1854591.20|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|   467630.00|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|    437.20|   263.33|   3227410.40|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|    205.70|   117.11|   2008043.40|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|    437.20|   263.33|   2966839.20|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|   211239.60|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|    205.70|   117.11|   1155211.20| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|   791082.50|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|     82657.90|  55378.18|    27279.72|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark = spark.read.option(\"header\", \"true\").csv(\"/content/5000_sales_records.csv\")"
+      ],
+      "metadata": {
+        "id": "qOjlOq1hlwnD"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "KiTTLvy9mRJ_",
+        "outputId": "64096b44-98fb-4074-a458-4223312a75ae"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|    226716.10| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|    205.70|   117.11|   1854591.20|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|   467630.00|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|    437.20|   263.33|   3227410.40|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|    205.70|   117.11|   2008043.40|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|    437.20|   263.33|   2966839.20|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|   211239.60|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|    205.70|   117.11|   1155211.20| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|   791082.50|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|     82657.90|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "type(df_pyspark)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "6t1J1sUvmD1j",
+        "outputId": "044d8f28-4183-40f6-f6d6-0d9edb15c5a4"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "pyspark.sql.dataframe.DataFrame"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 19
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.printSchema()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "h1T9Fy0nmL6O",
+        "outputId": "d764fafc-4c73-4058-daf5-2fd6081940c6"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "root\n",
+            " |-- Region: string (nullable = true)\n",
+            " |-- Country: string (nullable = true)\n",
+            " |-- Item Type: string (nullable = true)\n",
+            " |-- Sales Channel: string (nullable = true)\n",
+            " |-- Order Priority: string (nullable = true)\n",
+            " |-- Order Date: string (nullable = true)\n",
+            " |-- Order ID: string (nullable = true)\n",
+            " |-- Ship Date: string (nullable = true)\n",
+            " |-- Units Sold: string (nullable = true)\n",
+            " |-- Unit Price: string (nullable = true)\n",
+            " |-- Unit Cost: string (nullable = true)\n",
+            " |-- Total Revenue: string (nullable = true)\n",
+            " |-- Total Cost: string (nullable = true)\n",
+            " |-- Total Profit: string (nullable = true)\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Picking up data"
+      ],
+      "metadata": {
+        "id": "LeIvG6cpoUjA"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.select([\"Region\",\"Country\"]).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "1QhCW-WYmhpz",
+        "outputId": "d1956f24-83a5-46d3-ef5b-ae6315f00b72"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+\n",
+            "|              Region|             Country|\n",
+            "+--------------------+--------------------+\n",
+            "|Central America a...|Antigua and Barbuda |\n",
+            "|Central America a...|              Panama|\n",
+            "|              Europe|      Czech Republic|\n",
+            "|                Asia|         North Korea|\n",
+            "|                Asia|           Sri Lanka|\n",
+            "|Middle East and N...|             Morocco|\n",
+            "|Australia and Oce...|Federated States ...|\n",
+            "|              Europe|Bosnia and Herzeg...|\n",
+            "|Middle East and N...|         Afghanistan|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|\n",
+            "|Middle East and N...|              Turkey|\n",
+            "|Middle East and N...|                Oman|\n",
+            "|                Asia|            Malaysia|\n",
+            "|Central America a...|         Saint Lucia|\n",
+            "|Central America a...|Saint Vincent and...|\n",
+            "|Middle East and N...|             Lebanon|\n",
+            "|              Europe|             Austria|\n",
+            "|              Europe|            Bulgaria|\n",
+            "|       North America|              Mexico|\n",
+            "|Central America a...| Trinidad and Tobago|\n",
+            "+--------------------+--------------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.dtypes"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "lXt_9Pt9niic",
+        "outputId": "6f8bd081-a67c-43bf-8396-11beac0b91f6"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[('Region', 'string'),\n",
+              " ('Country', 'string'),\n",
+              " ('Item Type', 'string'),\n",
+              " ('Sales Channel', 'string'),\n",
+              " ('Order Priority', 'string'),\n",
+              " ('Order Date', 'string'),\n",
+              " ('Order ID', 'string'),\n",
+              " ('Ship Date', 'string'),\n",
+              " ('Units Sold', 'string'),\n",
+              " ('Unit Price', 'string'),\n",
+              " ('Unit Cost', 'string'),\n",
+              " ('Total Revenue', 'string'),\n",
+              " ('Total Cost', 'string'),\n",
+              " ('Total Profit', 'string')]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 30
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.describe().show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wKk4pwxFoN91",
+        "outputId": "c6bcb8f9-d8bf-4c2c-c1e5-206d79f6f381"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+-------+------------------+-----------+----------+-------------+--------------+----------+------------------+---------+------------------+-----------------+------------------+------------------+------------------+------------------+\n",
+            "|summary|            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",
+            "+-------+------------------+-----------+----------+-------------+--------------+----------+------------------+---------+------------------+-----------------+------------------+------------------+------------------+------------------+\n",
+            "|  count|              5000|       5000|      5000|         5000|          5000|      5000|              5000|     5000|              5000|             5000|              5000|              5000|              5000|              5000|\n",
+            "|   mean|              null|       null|      null|         null|          null|      null|  5.486447372216E8|     null|         5030.6982|265.7455639999977|187.49414399999978|1325737.8417080024| 933093.1958900003|392644.64581800025|\n",
+            "| stddev|              null|       null|      null|         null|          null|      null|2.59467108849919E8|     null|2914.5154267478674|218.7166954289816| 176.4162798197045| 1475374.673360283|1150873.2176060663| 382935.1484319066|\n",
+            "|    min|              Asia|Afghanistan| Baby Food|      Offline|             C|  1/1/2010|         100090873| 1/1/2011|                10|           109.28|            117.11|         100024.60|        1000002.29|        1000278.75|\n",
+            "|    max|Sub-Saharan Africa|   Zimbabwe|Vegetables|       Online|             M|  9/9/2015|         999879729| 9/9/2016|              9999|             9.33|             97.44|         998462.86|          99979.55|          99990.00|\n",
+            "+-------+------------------+-----------+----------+-------------+--------------+----------+------------------+---------+------------------+-----------------+------------------+------------------+------------------+------------------+\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Adding Columns"
+      ],
+      "metadata": {
+        "id": "uJKqyQs6osQJ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark = df_pyspark.withColumn(\"adding 200 rupee in total cost\", df_pyspark['Total Cost']+200)"
+      ],
+      "metadata": {
+        "id": "tSLhXvHbofg6"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "L7bSCWmPpIeo",
+        "outputId": "b97e91da-14f4-4dc4-f7ad-3e5db70d90fa"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|              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|adding 200 rupee in total cost|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|                      88199.84|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|                     211352.48|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|    226716.10| 151892.62|    74823.48|                     152092.62|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|    205.70|   117.11|   1854591.20|1055863.76|   798727.44|                    1056063.76|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|                     735092.48|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|                       2920.16|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|                     296166.72|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|                      33423.68|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|                     317061.44|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|                    1565226.14|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|   467630.00|                    1944651.84|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|    437.20|   263.33|   3227410.40|1943902.06|  1283508.34|                    1944102.06|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|    205.70|   117.11|   2008043.40|1143227.82|   864815.58|                    1143427.82|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|    437.20|   263.33|   2966839.20|1786957.38|  1179881.82|                    1787157.38|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|                    1024951.76|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|   211239.60|                    1347000.17|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|    205.70|   117.11|   1155211.20| 657689.76|   497521.44|                     657889.76|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|   791082.50|                    3289599.36|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|     82657.90|  55378.18|    27279.72|                      55578.18|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|                     824720.24|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "dropping column"
+      ],
+      "metadata": {
+        "id": "TXYiKuvnp3FM"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark = df_pyspark.drop(\"Region\")"
+      ],
+      "metadata": {
+        "id": "Q6awTLOwpruu"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "VM9VRUW3pz_T",
+        "outputId": "0e0382c8-a288-426a-b433-efc224993b91"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|             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|adding 200 rupee in total cost|\n",
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|                      88199.84|\n",
+            "|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|                     211352.48|\n",
+            "|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|    226716.10| 151892.62|    74823.48|                     152092.62|\n",
+            "|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|    205.70|   117.11|   1854591.20|1055863.76|   798727.44|                    1056063.76|\n",
+            "|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|                     735092.48|\n",
+            "|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|                       2920.16|\n",
+            "|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|                     296166.72|\n",
+            "|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|                      33423.68|\n",
+            "|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|                     317061.44|\n",
+            "|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|                    1565226.14|\n",
+            "|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|   467630.00|                    1944651.84|\n",
+            "|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|    437.20|   263.33|   3227410.40|1943902.06|  1283508.34|                    1944102.06|\n",
+            "|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|    205.70|   117.11|   2008043.40|1143227.82|   864815.58|                    1143427.82|\n",
+            "|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|    437.20|   263.33|   2966839.20|1786957.38|  1179881.82|                    1787157.38|\n",
+            "|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|                    1024951.76|\n",
+            "|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|   211239.60|                    1347000.17|\n",
+            "|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|    205.70|   117.11|   1155211.20| 657689.76|   497521.44|                     657889.76|\n",
+            "|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|   791082.50|                    3289599.36|\n",
+            "|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|     82657.90|  55378.18|    27279.72|                      55578.18|\n",
+            "| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|                     824720.24|\n",
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Rename columns"
+      ],
+      "metadata": {
+        "id": "52oD6KkXp5Ve"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.withColumnRenamed(\"Country\", \"Region\").show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "VoMKuwm9p1cB",
+        "outputId": "d7b5b708-399d-4b3d-a7ef-48019fd544ab"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|              Region|      Item Type|Sales Channel|Order Priority|Order Date| Order ID| Ship Date|Units Sold|Unit Price|Unit Cost|Total Revenue|Total Cost|Total Profit|adding 200 rupee in total cost|\n",
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|                      88199.84|\n",
+            "|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|                     211352.48|\n",
+            "|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|    226716.10| 151892.62|    74823.48|                     152092.62|\n",
+            "|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|    205.70|   117.11|   1854591.20|1055863.76|   798727.44|                    1056063.76|\n",
+            "|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|                     735092.48|\n",
+            "|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|                       2920.16|\n",
+            "|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|                     296166.72|\n",
+            "|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|                      33423.68|\n",
+            "|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|                     317061.44|\n",
+            "|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|                    1565226.14|\n",
+            "|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|   467630.00|                    1944651.84|\n",
+            "|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|    437.20|   263.33|   3227410.40|1943902.06|  1283508.34|                    1944102.06|\n",
+            "|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|    205.70|   117.11|   2008043.40|1143227.82|   864815.58|                    1143427.82|\n",
+            "|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|    437.20|   263.33|   2966839.20|1786957.38|  1179881.82|                    1787157.38|\n",
+            "|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|                    1024951.76|\n",
+            "|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|   211239.60|                    1347000.17|\n",
+            "|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|    205.70|   117.11|   1155211.20| 657689.76|   497521.44|                     657889.76|\n",
+            "|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|   791082.50|                    3289599.36|\n",
+            "|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|     82657.90|  55378.18|    27279.72|                      55578.18|\n",
+            "| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|                     824720.24|\n",
+            "+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**Handling Missing Value in pyspark**"
+      ],
+      "metadata": {
+        "id": "D7LEZTm5qNJO"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#create session which is already made in top\n",
+        "spark"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 219
+        },
+        "id": "cpQXhhruqB6T",
+        "outputId": "889f4a6a-a22e-4099-d2d2-0bb7292eb595"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<pyspark.sql.session.SparkSession at 0x7f18d7a90850>"
+            ],
+            "text/html": [
+              "\n",
+              "            <div>\n",
+              "                <p><b>SparkSession - in-memory</b></p>\n",
+              "                \n",
+              "        <div>\n",
+              "            <p><b>SparkContext</b></p>\n",
+              "\n",
+              "            <p><a href=\"http://09f26e936462:4040\">Spark UI</a></p>\n",
+              "\n",
+              "            <dl>\n",
+              "              <dt>Version</dt>\n",
+              "                <dd><code>v3.3.0</code></dd>\n",
+              "              <dt>Master</dt>\n",
+              "                <dd><code>local[*]</code></dd>\n",
+              "              <dt>AppName</dt>\n",
+              "                <dd><code>Practice</code></dd>\n",
+              "            </dl>\n",
+              "        </div>\n",
+              "        \n",
+              "            </div>\n",
+              "        "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 48
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark = spark.read.csv(\"/content/5000_sales_records.csv\", header = True, inferSchema = True)"
+      ],
+      "metadata": {
+        "id": "HBwAaOjWqppc"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "dlxEWEefq-oR",
+        "outputId": "92b9775c-6ab0-43d6-b023-79b430074d89"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "##drop columns\n",
+        "df_pyspark.drop(\"Order Priority\").show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "FzVgDq9MrJRI",
+        "outputId": "93d65472-32c4-4f03-b5ca-44c4ab2080a5"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              Region|             Country|      Item Type|Sales Channel|Order Date| Order ID| Ship Date|Units Sold|Unit Price|Unit Cost|Total Revenue|Total Cost|Total Profit|\n",
+            "+--------------------+--------------------+---------------+-------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#deletes rows containing null value\n",
+        "df_pyspark.na.drop().show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "lyEdvPTqrR_B",
+        "outputId": "749d09e4-94e8-4999-e85a-0dbe78995f58"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "### any = how (any row containing null value)\n",
+        "### all = how(any row containing all null value)\n",
+        "df_pyspark.na.drop(how=\"any\").show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "T61WAtwrrcQD",
+        "outputId": "4e4a2fba-dbb8-4e00-dfb0-5963f791d176"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#thresh = threshold (if its 2 then we must have atleast 2 non null value)\n",
+        "df_pyspark.na.drop(how=\"any\", thresh= 2).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ra7IH1CSr3Dn",
+        "outputId": "75c79a09-1cb9-43d2-e156-f0bdf5d3c630"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#subset= only from specific column\n",
+        "df_pyspark.na.drop(how=\"any\", subset=[\"Item Type\"]).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ljaYa0WwsWdk",
+        "outputId": "ce3c7911-6f74-4e70-9dfc-bfe2bcbd643c"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "## filling the missing value\n",
+        "df_pyspark.na.fill(\"Missing Values\", \"Region\").show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "nK_H8g46sw-I",
+        "outputId": "201897b5-98af-4218-dd81-2ddbc280196e"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "kjKsOHhptDFA",
+        "outputId": "c57a35c5-3b9c-495f-c2d7-98256fcf88b0"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#imputer function for filling null values\n",
+        "\n",
+        "from pyspark.ml.feature import Imputer\n",
+        "imputer = Imputer(\n",
+        "    inputCols = ['Unit Price','Total Revenue','Total Cost'],\n",
+        "    outputCols = ['{}_imputed'.format(c) for c in ['Unit Price','Total Revenue','Total Cost']]\n",
+        ").setStrategy(\"mean\")"
+      ],
+      "metadata": {
+        "id": "zaxEflzdtNY0"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "imputer.fit(df_pyspark).transform(df_pyspark).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "vB_lvoxOt4uZ",
+        "outputId": "994f88c5-8fd8-4665-b045-da37f6d9647e"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------+---------------------+------------------+\n",
+            "|              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|Unit Price_imputed|Total Revenue_imputed|Total Cost_imputed|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------+---------------------+------------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|            255.28|            140914.56|          87999.84|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|            152.58|            330640.86|         211152.48|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|             47.45|             226716.1|         151892.62|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|             205.7|            1854591.2|        1055863.76|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|            152.58|           1150758.36|         734892.48|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|             81.73|              3923.04|           2720.16|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|            109.28|            902434.24|         295966.72|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|            109.28|            101302.56|          33223.68|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|            109.28|            966144.48|         316861.44|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|            255.28|           2506083.76|        1565026.14|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|            651.21|           2412081.84|        1944451.84|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|             437.2|            3227410.4|        1943902.06|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|             205.7|            2008043.4|        1143227.82|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|             437.2|            2966839.2|        1786957.38|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|            255.28|           1640939.84|        1024751.76|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|            421.89|           1558039.77|        1346800.17|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|             205.7|            1155211.2|         657689.76|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|            651.21|           4080481.86|        3289399.36|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|             47.45|              82657.9|          55378.18|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|            255.28|           1320308.16|         824520.24|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+------------------+---------------------+------------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#Filter operation"
+      ],
+      "metadata": {
+        "id": "oYxVvo2Kuf77"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "rdeT55X4t98W",
+        "outputId": "17690dfa-57ae-4bcd-d725-a2f75f6fed6d"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Middle East and N...|             Morocco|  Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|              Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|       North America|              Mexico|      Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "### Units sold less than or equal to 300\n",
+        "df_pyspark.filter(df_pyspark['Total Cost']<=80000).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qKrv8-fsvBRy",
+        "outputId": "c65cd792-c130-4b66-f468-cf20df6c0dd1"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+-------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+-------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Middle East and N...|             Morocco|Personal Care|      Offline|             L| 11/8/2010|412882792|11/22/2010|        48|     81.73|    56.67|      3923.04|   2720.16|     1202.88|\n",
+            "|              Europe|Bosnia and Herzeg...|      Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|       North America|              Mexico|    Beverages|       Online|             C| 3/13/2017|127374303| 3/20/2017|      1742|     47.45|    31.79|      82657.9|  55378.18|    27279.72|\n",
+            "|Middle East and N...|               Libya|    Beverages|      Offline|             L| 1/18/2010|993345010|  3/3/2010|      1718|     47.45|    31.79|      81519.1|  54615.22|    26903.88|\n",
+            "|              Europe|             Estonia|       Fruits|       Online|             L| 9/28/2016|579463422| 11/1/2016|      4958|      9.33|     6.92|     46258.14|  34309.36|    11948.78|\n",
+            "|              Europe|          Montenegro|       Fruits|      Offline|             L| 5/29/2016|313705861| 7/10/2016|      1390|      9.33|     6.92|      12968.7|    9618.8|      3349.9|\n",
+            "|Middle East and N...|             Lebanon|       Fruits|       Online|             H|  4/5/2013|441150701| 5/12/2013|      5150|      9.33|     6.92|      48049.5|   35638.0|     12411.5|\n",
+            "|                Asia|          Kyrgyzstan|       Snacks|       Online|             C|  8/6/2013|727492606| 9/22/2013|        84|    152.58|    97.44|     12816.72|   8184.96|     4631.76|\n",
+            "|                Asia|              Taiwan|    Baby Food|       Online|             M| 5/27/2014|369560611| 6/13/2014|        52|    255.28|   159.42|     13274.56|   8289.84|     4984.72|\n",
+            "|Australia and Oce...|             Vanuatu|       Fruits|       Online|             M| 7/13/2017|135336816| 8/17/2017|      8026|      9.33|     6.92|     74882.58|  55539.92|    19342.66|\n",
+            "|              Europe|              Russia|    Household|       Online|             M| 7/10/2017|194176757| 8/20/2017|        72|    668.27|   502.54|     48115.44|  36182.88|    11932.56|\n",
+            "|              Europe|              Serbia|    Beverages|       Online|             L|  9/3/2012|599624192| 9/21/2012|       978|     47.45|    31.79|      46406.1|  31090.62|    15315.48|\n",
+            "|                Asia|           Sri Lanka|       Cereal|       Online|             C| 2/24/2015|743410336| 3/20/2015|       494|     205.7|   117.11|     101615.8|  57852.34|    43763.46|\n",
+            "|  Sub-Saharan Africa|             Senegal|    Beverages|      Offline|             L| 6/30/2014|530853211|  8/2/2014|       117|     47.45|    31.79|      5551.65|   3719.43|     1832.22|\n",
+            "|Australia and Oce...|            Kiribati|       Fruits|       Online|             L| 12/7/2011|905054843| 1/12/2012|      4695|      9.33|     6.92|     43804.35|   32489.4|    11314.95|\n",
+            "|              Europe|       Liechtenstein|    Cosmetics|       Online|             L| 7/15/2012|229693067| 7/15/2012|       138|     437.2|   263.33|      60333.6|  36339.54|    23994.06|\n",
+            "|Australia and Oce...|             Vanuatu|       Fruits|      Offline|             L| 11/6/2015|202262866|12/14/2015|      2932|      9.33|     6.92|     27355.56|  20289.44|     7066.12|\n",
+            "|Central America a...|               Haiti|      Clothes|      Offline|             L| 8/12/2010|422752892| 8/12/2010|       830|    109.28|    35.84|      90702.4|   29747.2|     60955.2|\n",
+            "|              Europe|            Slovenia|       Fruits|       Online|             H|10/22/2012|169799983|11/20/2012|      6443|      9.33|     6.92|     60113.19|  44585.56|    15527.63|\n",
+            "|              Europe|              Cyprus|       Fruits|      Offline|             M| 7/12/2015|600515115| 8/30/2015|      4622|      9.33|     6.92|     43123.26|  31984.24|    11139.02|\n",
+            "+--------------------+--------------------+-------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#multiple condition\n",
+        "\n",
+        "df_pyspark.filter((df_pyspark['Total Cost']<=80000) & (df_pyspark['Region']==\"Europe\")).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "FBQLb1Mmwd9N",
+        "outputId": "330e69b8-d4fa-42e7-e2ac-a4a1441b9d9a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|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",
+            "+------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Europe|Bosnia and Herzeg...|        Clothes|       Online|             M|10/14/2013|919133651| 11/4/2013|       927|    109.28|    35.84|    101302.56|  33223.68|    68078.88|\n",
+            "|Europe|             Estonia|         Fruits|       Online|             L| 9/28/2016|579463422| 11/1/2016|      4958|      9.33|     6.92|     46258.14|  34309.36|    11948.78|\n",
+            "|Europe|          Montenegro|         Fruits|      Offline|             L| 5/29/2016|313705861| 7/10/2016|      1390|      9.33|     6.92|      12968.7|    9618.8|      3349.9|\n",
+            "|Europe|              Russia|      Household|       Online|             M| 7/10/2017|194176757| 8/20/2017|        72|    668.27|   502.54|     48115.44|  36182.88|    11932.56|\n",
+            "|Europe|              Serbia|      Beverages|       Online|             L|  9/3/2012|599624192| 9/21/2012|       978|     47.45|    31.79|      46406.1|  31090.62|    15315.48|\n",
+            "|Europe|       Liechtenstein|      Cosmetics|       Online|             L| 7/15/2012|229693067| 7/15/2012|       138|     437.2|   263.33|      60333.6|  36339.54|    23994.06|\n",
+            "|Europe|            Slovenia|         Fruits|       Online|             H|10/22/2012|169799983|11/20/2012|      6443|      9.33|     6.92|     60113.19|  44585.56|    15527.63|\n",
+            "|Europe|              Cyprus|         Fruits|      Offline|             M| 7/12/2015|600515115| 8/30/2015|      4622|      9.33|     6.92|     43123.26|  31984.24|    11139.02|\n",
+            "|Europe|              Norway|         Cereal|       Online|             M| 10/8/2014|100640618|10/18/2014|       650|     205.7|   117.11|     133705.0|   76121.5|     57583.5|\n",
+            "|Europe|             Armenia|         Fruits|       Online|             M| 3/23/2011|120977771|  5/2/2011|      8866|      9.33|     6.92|     82719.78|  61352.72|    21367.06|\n",
+            "|Europe|             Denmark|      Beverages|       Online|             H|  6/5/2016|973268353| 6/26/2016|       589|     47.45|    31.79|     27948.05|  18724.31|     9223.74|\n",
+            "|Europe|              Kosovo|         Fruits|       Online|             L|  5/2/2010|291995418|  6/6/2010|      6788|      9.33|     6.92|     63332.04|  46972.96|    16359.08|\n",
+            "|Europe|Bosnia and Herzeg...|      Baby Food|       Online|             C| 4/30/2014|871923768| 5/30/2014|       474|    255.28|   159.42|    121002.72|  75565.08|    45437.64|\n",
+            "|Europe|           Lithuania|Office Supplies|      Offline|             C|12/15/2016|112330758| 1/11/2017|        22|    651.21|   524.96|     14326.62|  11549.12|      2777.5|\n",
+            "|Europe|               Spain|         Fruits|       Online|             H|10/22/2011|817006289|11/14/2011|      9172|      9.33|     6.92|     85574.76|  63470.24|    22104.52|\n",
+            "|Europe|               Malta|  Personal Care|      Offline|             M| 8/16/2011|466988742| 8/16/2011|      1201|     81.73|    56.67|     98157.73|  68060.67|    30097.06|\n",
+            "|Europe|               Italy|  Personal Care|       Online|             C| 2/25/2011|309342658| 3/28/2011|       222|     81.73|    56.67|     18144.06|  12580.74|     5563.32|\n",
+            "|Europe|              Kosovo|         Fruits|       Online|             C|  3/2/2012|899868094| 3/26/2012|      9821|      9.33|     6.92|     91629.93|  67961.32|    23668.61|\n",
+            "|Europe|Bosnia and Herzeg...|         Fruits|       Online|             H|  1/5/2013|291305768|  1/6/2013|      2705|      9.33|     6.92|     25237.65|   18718.6|     6519.05|\n",
+            "|Europe|            Slovenia|         Fruits|      Offline|             M|12/15/2013|812637078|  1/5/2014|      6225|      9.33|     6.92|     58079.25|   43077.0|    15002.25|\n",
+            "+------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#inverse operation\n",
+        "df_pyspark.filter(~(df_pyspark['Total Cost']<=80000)).show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "VgXHvC318iTF",
+        "outputId": "21c9e5b4-d0ca-4095-fd25-da06edb4f7e2"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|              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",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "|Central America a...|Antigua and Barbuda |      Baby Food|       Online|             M|12/20/2013|957081544| 1/11/2014|       552|    255.28|   159.42|    140914.56|  87999.84|    52914.72|\n",
+            "|Central America a...|              Panama|         Snacks|      Offline|             C|  7/5/2010|301644504| 7/26/2010|      2167|    152.58|    97.44|    330640.86| 211152.48|   119488.38|\n",
+            "|              Europe|      Czech Republic|      Beverages|      Offline|             C| 9/12/2011|478051030| 9/29/2011|      4778|     47.45|    31.79|     226716.1| 151892.62|    74823.48|\n",
+            "|                Asia|         North Korea|         Cereal|      Offline|             L| 5/13/2010|892599952| 6/15/2010|      9016|     205.7|   117.11|    1854591.2|1055863.76|   798727.44|\n",
+            "|                Asia|           Sri Lanka|         Snacks|      Offline|             C| 7/20/2015|571902596| 7/27/2015|      7542|    152.58|    97.44|   1150758.36| 734892.48|   415865.88|\n",
+            "|Australia and Oce...|Federated States ...|        Clothes|      Offline|             H| 3/28/2011|932776868| 5/10/2011|      8258|    109.28|    35.84|    902434.24| 295966.72|   606467.52|\n",
+            "|Middle East and N...|         Afghanistan|        Clothes|      Offline|             M| 8/27/2016|579814469| 10/5/2016|      8841|    109.28|    35.84|    966144.48| 316861.44|   649283.04|\n",
+            "|  Sub-Saharan Africa|            Ethiopia|      Baby Food|       Online|             M| 4/13/2015|192993152|  5/7/2015|      9817|    255.28|   159.42|   2506083.76|1565026.14|   941057.62|\n",
+            "|Middle East and N...|              Turkey|Office Supplies|      Offline|             C| 9/25/2013|557156026|10/15/2013|      3704|    651.21|   524.96|   2412081.84|1944451.84|    467630.0|\n",
+            "|Middle East and N...|                Oman|      Cosmetics|       Online|             M| 5/12/2013|741101920| 5/17/2013|      7382|     437.2|   263.33|    3227410.4|1943902.06|  1283508.34|\n",
+            "|                Asia|            Malaysia|         Cereal|      Offline|             L| 7/31/2016|333942162| 8/25/2016|      9762|     205.7|   117.11|    2008043.4|1143227.82|   864815.58|\n",
+            "|Central America a...|         Saint Lucia|      Cosmetics|      Offline|             H|  7/6/2015|795100581| 7/16/2015|      6786|     437.2|   263.33|    2966839.2|1786957.38|  1179881.82|\n",
+            "|Central America a...|Saint Vincent and...|      Baby Food|       Online|             L|11/28/2010|504313504| 12/3/2010|      6428|    255.28|   159.42|   1640939.84|1024751.76|   616188.08|\n",
+            "|Middle East and N...|             Lebanon|           Meat|      Offline|             H|12/17/2015|611629760| 1/31/2016|      3693|    421.89|   364.69|   1558039.77|1346800.17|    211239.6|\n",
+            "|              Europe|             Austria|         Cereal|      Offline|             C| 8/13/2014|987410676|  9/6/2014|      5616|     205.7|   117.11|    1155211.2| 657689.76|   497521.44|\n",
+            "|              Europe|            Bulgaria|Office Supplies|       Online|             L|10/31/2010|672330081|11/29/2010|      6266|    651.21|   524.96|   4080481.86|3289399.36|    791082.5|\n",
+            "|Central America a...| Trinidad and Tobago|      Baby Food|      Offline|             C| 4/16/2013|783842170|  6/1/2013|      5172|    255.28|   159.42|   1320308.16| 824520.24|   495787.92|\n",
+            "|Middle East and N...|             Algeria|      Baby Food|      Offline|             M|  9/5/2015|977806651|10/14/2015|      3572|    255.28|   159.42|    911860.16| 569448.24|   342411.92|\n",
+            "|Australia and Oce...|              Tuvalu|      Beverages|      Offline|             L| 3/22/2012|610864150|  4/7/2012|      7132|     47.45|    31.79|     338413.4| 226726.28|   111687.12|\n",
+            "|Middle East and N...|        Saudi Arabia|         Snacks|      Offline|             L| 4/25/2017|604870164|  6/5/2017|      3378|    152.58|    97.44|    515415.24| 329152.32|   186262.92|\n",
+            "+--------------------+--------------------+---------------+-------------+--------------+----------+---------+----------+----------+----------+---------+-------------+----------+------------+\n",
+            "only showing top 20 rows\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#Groupby and aggregation"
+      ],
+      "metadata": {
+        "id": "llhOyJua9Jqg"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from pyspark.sql import SparkSession\n",
+        "spark = SparkSession.builder.appName(\"Aggregate\").getOrCreate()"
+      ],
+      "metadata": {
+        "id": "8tbfOvxv9E-H"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "IGFm7O2z9c5s",
+        "outputId": "5d4d9486-420c-467d-f0f0-d6d1b2f87437"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Row(Region='Central America and the Caribbean', Country='Antigua and Barbuda ', Item Type='Baby Food', Sales Channel='Online', Order Priority='M', Order Date='12/20/2013', Order ID=957081544, Ship Date='1/11/2014', Units Sold=552, Unit Price=255.28, Unit Cost=159.42, Total Revenue=140914.56, Total Cost=87999.84, Total Profit=52914.72)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 90
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pyspark.printSchema()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Okb_Wwmw9d7m",
+        "outputId": "f565628f-83c6-4d58-d197-97cfda3e5c62"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "root\n",
+            " |-- Region: string (nullable = true)\n",
+            " |-- Country: string (nullable = true)\n",
+            " |-- Item Type: string (nullable = true)\n",
+            " |-- Sales Channel: string (nullable = true)\n",
+            " |-- Order Priority: string (nullable = true)\n",
+            " |-- Order Date: string (nullable = true)\n",
+            " |-- Order ID: integer (nullable = true)\n",
+            " |-- Ship Date: string (nullable = true)\n",
+            " |-- Units Sold: integer (nullable = true)\n",
+            " |-- Unit Price: double (nullable = true)\n",
+            " |-- Unit Cost: double (nullable = true)\n",
+            " |-- Total Revenue: double (nullable = true)\n",
+            " |-- Total Cost: double (nullable = true)\n",
+            " |-- Total Profit: double (nullable = true)\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Groupby\n",
+        "#group to find maximum selling region\n",
+        "df_pyspark.groupby(\"Region\").sum().show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "R5v7YHME9vTz",
+        "outputId": "c3188a30-dcdc-46cb-d181-28020bd65d5b"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+--------------------+-------------+---------------+------------------+------------------+--------------------+--------------------+--------------------+\n",
+            "|              Region|sum(Order ID)|sum(Units Sold)|   sum(Unit Price)|    sum(Unit Cost)|  sum(Total Revenue)|     sum(Total Cost)|   sum(Total Profit)|\n",
+            "+--------------------+-------------+---------------+------------------+------------------+--------------------+--------------------+--------------------+\n",
+            "|Middle East and N...| 329477662194|        3013431|157454.56999999983|110155.62999999966| 7.668677777200001E8| 5.354874771899998E8| 2.313803005300001E8|\n",
+            "|Australia and Oce...| 233075865831|        2111786|116833.26999999983| 82580.71999999994| 5.873640885299999E8|4.1242951558999985E8|1.7493457293999985E8|\n",
+            "|              Europe| 719802331123|        6582322|  352308.410000005|249038.25999999998|1.7036223981099987E9|1.2019463497899995E9|5.0167604832000005E8|\n",
+            "|  Sub-Saharan Africa| 714129889652|        6642380| 349025.5400000039|246882.89000000057|1.8145672823999999E9|     1.28342501448E9|5.3114226791999996E8|\n",
+            "|Central America a...| 295473045677|        2698776|138441.96999999983| 97945.32999999967| 6.849763237699999E8|4.8036434404999995E8| 2.046119797200002E8|\n",
+            "|       North America|  53808179824|         484760|31107.340000000026|22288.680000000004|      1.5101425209E8|1.0977385412000002E8|4.1240397970000006E7|\n",
+            "|                Asia| 397456711807|        3620036|183556.71999999988|128579.20999999954| 9.202770859200008E8| 6.420394242299997E8| 2.782376616899999E8|\n",
+            "+--------------------+-------------+---------------+------------------+------------------+--------------------+--------------------+--------------------+\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# from pyspark.mllib.classification import LogisticRegressionWithSGD\n",
+        "# from pyspark.mllib.regression import LabeledPoint\n",
+        "# from numpy import array\n",
+        "\n",
+        "# # Load and parse the data\n",
+        "# def parsePoint(line):\n",
+        "#     values = [float(x) for x in line.split(' ')]\n",
+        "#     return LabeledPoint(values[0], values[1:])\n",
+        "\n",
+        "# data = sc.textFile(\"/content/5000_sales_records.csv\")\n",
+        "# parsedData = data.map(parsePoint)\n",
+        "\n",
+        "# # Build the model\n",
+        "# model = LogisticRegressionWithSGD.train(parsedData)\n",
+        "\n",
+        "# # Evaluating the model on training data\n",
+        "# labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))\n",
+        "# trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count())\n",
+        "# print(\"Training Error = \" + str(trainErr))"
+      ],
+      "metadata": {
+        "id": "UpS_aHY194m7"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "8gjAVr7DBvr7",
+        "outputId": "a0f9a97f-1ad4-408b-885e-29fe32019db7"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "DataFrame[Region: string, Country: string, Item Type: string, Sales Channel: string, Order Priority: string, Order Date: string, Order ID: int, Ship Date: string, Units Sold: int, Unit Price: double, Unit Cost: double, Total Revenue: double, Total Cost: double, Total Profit: double]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 95
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "CvVdj8QrBxNA"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}
\ No newline at end of file