{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "d4f5a90b",
   "metadata": {},
   "source": [
    "# Revenue Forecasting, Scenario Planning, and Business Intelligence Dashboard\n",
    "\n",
    "**Client portfolio project prepared for DataScienceConsultingPro.com**\n",
    "\n",
    "This notebook presents the Python section of a revenue forecasting portfolio project. It demonstrates how raw revenue data can be cleaned, explored, summarized with pivot tables, visualized with graphs, and converted into practical revenue forecasts for business planning.\n",
    "\n",
    "## Brief Introduction\n",
    "\n",
    "Many businesses know what they earned in the past but still struggle to plan future revenue with confidence. Revenue forecasting helps leadership estimate expected monthly, quarterly, or annual revenue using historical patterns, seasonality, product performance, customer segments, and business assumptions.\n",
    "\n",
    "## Aim of the Project\n",
    "\n",
    "The aim of this project is to build a practical Python revenue forecasting workflow that supports budgeting, investor updates, hiring planning, marketing spend decisions, and executive reporting.\n",
    "\n",
    "## Project Objectives\n",
    "\n",
    "The objectives of this project are to:\n",
    "\n",
    "1. Load and inspect raw revenue data.\n",
    "2. Clean the dataset and prepare it for analysis.\n",
    "3. Create useful time-based features such as month, quarter, and year.\n",
    "4. Analyze historical revenue trends, seasonality, and revenue drivers.\n",
    "5. Build pivot tables inside the Jupyter Notebook.\n",
    "6. Create graphs for monthly revenue trends, revenue by product, and forecast scenarios.\n",
    "7. Build a simple forecasting model using trend and month-based seasonality features.\n",
    "8. Prepare conservative, base, and growth forecast scenarios.\n",
    "9. Export dashboard-ready outputs for reporting and business intelligence use.\n",
    "10. Explain the findings in clear business language.\n",
    "\n",
    "## Compatibility Note\n",
    "\n",
    "This notebook uses standard Python libraries and avoids `ipywidgets`, `VBox`, and `@jupyter-widgets/controls`. This keeps the notebook easier to open in different JupyterLab environments."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c314a27-0b4e-4236-80c3-4f9f29c70f3b",
   "metadata": {},
   "source": [
    "## 1. Import Python libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3db7efcf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Libraries imported successfully.\n"
     ]
    }
   ],
   "source": [
    "# These libraries support data cleaning, pivot tables, charts, and forecasting.\n",
    "\n",
    "import warnings\n",
    "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
    "\n",
    "from pathlib import Path\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from IPython.display import display, HTML\n",
    "\n",
    "# Display settings make tables easier to review inside the notebook.\n",
    "pd.set_option('display.max_columns', 100)\n",
    "pd.set_option('display.float_format', lambda x: f'{x:,.2f}')\n",
    "\n",
    "print('Libraries imported successfully.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3fb1f1e3-6988-4cdf-bd9a-a5598a7e63bd",
   "metadata": {},
   "source": [
    "## 2. Load raw revenue data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "36fb0aa6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Raw data loaded successfully.\n",
      "Rows: 30,180\n",
      "Columns: 15\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Order_ID</th>\n",
       "      <th>Order_Date</th>\n",
       "      <th>Customer_ID</th>\n",
       "      <th>Customer_Segment</th>\n",
       "      <th>Region</th>\n",
       "      <th>Sales_Channel</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Product_Name</th>\n",
       "      <th>Units_Sold</th>\n",
       "      <th>Unit_Price</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Gross_Revenue</th>\n",
       "      <th>Net_Revenue</th>\n",
       "      <th>Marketing_Campaign</th>\n",
       "      <th>Refund_Flag</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ORD-100000</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-1189</td>\n",
       "      <td>Consumer</td>\n",
       "      <td>North America</td>\n",
       "      <td>Marketplace</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Enterprise Plan</td>\n",
       "      <td>1</td>\n",
       "      <td>479.73</td>\n",
       "      <td>0.18</td>\n",
       "      <td>479.73</td>\n",
       "      <td>394.46</td>\n",
       "      <td>Year-End Push</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ORD-100001</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8513</td>\n",
       "      <td>Small Business</td>\n",
       "      <td>North America</td>\n",
       "      <td>Marketplace</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Growth Plan</td>\n",
       "      <td>1</td>\n",
       "      <td>143.90</td>\n",
       "      <td>0.06</td>\n",
       "      <td>143.90</td>\n",
       "      <td>135.89</td>\n",
       "      <td>Black Friday</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ORD-100002</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-1995</td>\n",
       "      <td>Enterprise</td>\n",
       "      <td>Middle East</td>\n",
       "      <td>Direct Sales</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Enterprise Plan</td>\n",
       "      <td>2</td>\n",
       "      <td>481.17</td>\n",
       "      <td>0.35</td>\n",
       "      <td>962.33</td>\n",
       "      <td>625.52</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ORD-100003</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8208</td>\n",
       "      <td>Consumer</td>\n",
       "      <td>North America</td>\n",
       "      <td>Website</td>\n",
       "      <td>Analytics Packages</td>\n",
       "      <td>Revenue Forecasting</td>\n",
       "      <td>1</td>\n",
       "      <td>1,809.60</td>\n",
       "      <td>0.06</td>\n",
       "      <td>1,809.60</td>\n",
       "      <td>1,709.35</td>\n",
       "      <td>Q1 Planning</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ORD-100004</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8215</td>\n",
       "      <td>Enterprise</td>\n",
       "      <td>North America</td>\n",
       "      <td>Retail Store</td>\n",
       "      <td>Cloud Services</td>\n",
       "      <td>Storage Add-on</td>\n",
       "      <td>1</td>\n",
       "      <td>82.68</td>\n",
       "      <td>0.33</td>\n",
       "      <td>82.68</td>\n",
       "      <td>55.79</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Order_ID  Order_Date Customer_ID Customer_Segment         Region  \\\n",
       "0  ORD-100000  2021-01-01   CUST-1189         Consumer  North America   \n",
       "1  ORD-100001  2021-01-01   CUST-8513   Small Business  North America   \n",
       "2  ORD-100002  2021-01-01   CUST-1995       Enterprise    Middle East   \n",
       "3  ORD-100003  2021-01-01   CUST-8208         Consumer  North America   \n",
       "4  ORD-100004  2021-01-01   CUST-8215       Enterprise  North America   \n",
       "\n",
       "  Sales_Channel        Product_Category         Product_Name  Units_Sold  \\\n",
       "0   Marketplace  Software Subscriptions      Enterprise Plan           1   \n",
       "1   Marketplace  Software Subscriptions          Growth Plan           1   \n",
       "2  Direct Sales  Software Subscriptions      Enterprise Plan           2   \n",
       "3       Website      Analytics Packages  Revenue Forecasting           1   \n",
       "4  Retail Store          Cloud Services       Storage Add-on           1   \n",
       "\n",
       "   Unit_Price  Discount_Rate  Gross_Revenue  Net_Revenue Marketing_Campaign  \\\n",
       "0      479.73           0.18         479.73       394.46      Year-End Push   \n",
       "1      143.90           0.06         143.90       135.89       Black Friday   \n",
       "2      481.17           0.35         962.33       625.52                NaN   \n",
       "3    1,809.60           0.06       1,809.60     1,709.35        Q1 Planning   \n",
       "4       82.68           0.33          82.68        55.79                NaN   \n",
       "\n",
       "  Refund_Flag  \n",
       "0          No  \n",
       "1          No  \n",
       "2          No  \n",
       "3          No  \n",
       "4          No  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# The raw data file should be saved in the same folder as this notebook.\n",
    "\n",
    "DATA_PATH = Path('01_raw_revenue_forecasting_data.csv')\n",
    "\n",
    "if not DATA_PATH.exists():\n",
    "    raise FileNotFoundError('The raw data file was not found. Place 01_raw_revenue_forecasting_data.csv in the same folder as this notebook.')\n",
    "\n",
    "raw_df = pd.read_csv(DATA_PATH)\n",
    "\n",
    "print('Raw data loaded successfully.')\n",
    "print(f'Rows: {raw_df.shape[0]:,}')\n",
    "print(f'Columns: {raw_df.shape[1]:,}')\n",
    "display(raw_df.head())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a0f8de3-f9de-40b7-bef0-905f5e34892c",
   "metadata": {},
   "source": [
    "## 3. Data audit before cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3d85f9d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Duplicate Order_ID count: 25\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Column</th>\n",
       "      <th>Data_Type</th>\n",
       "      <th>Missing_Values</th>\n",
       "      <th>Missing_%</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Order_ID</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Order_Date</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Customer_ID</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Customer_Segment</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Region</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Sales_Channel</td>\n",
       "      <td>object</td>\n",
       "      <td>91</td>\n",
       "      <td>0.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Product_Category</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Product_Name</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Units_Sold</td>\n",
       "      <td>int64</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Unit_Price</td>\n",
       "      <td>float64</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Discount_Rate</td>\n",
       "      <td>float64</td>\n",
       "      <td>90</td>\n",
       "      <td>0.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Gross_Revenue</td>\n",
       "      <td>float64</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Net_Revenue</td>\n",
       "      <td>float64</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Marketing_Campaign</td>\n",
       "      <td>object</td>\n",
       "      <td>15112</td>\n",
       "      <td>50.07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Refund_Flag</td>\n",
       "      <td>object</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Column Data_Type  Missing_Values  Missing_%\n",
       "0             Order_ID    object               0       0.00\n",
       "1           Order_Date    object               0       0.00\n",
       "2          Customer_ID    object               0       0.00\n",
       "3     Customer_Segment    object               0       0.00\n",
       "4               Region    object               0       0.00\n",
       "5        Sales_Channel    object              91       0.30\n",
       "6     Product_Category    object               0       0.00\n",
       "7         Product_Name    object               0       0.00\n",
       "8           Units_Sold     int64               0       0.00\n",
       "9           Unit_Price   float64               0       0.00\n",
       "10       Discount_Rate   float64              90       0.30\n",
       "11       Gross_Revenue   float64               0       0.00\n",
       "12         Net_Revenue   float64               0       0.00\n",
       "13  Marketing_Campaign    object           15112      50.07\n",
       "14         Refund_Flag    object               0       0.00"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# This step checks data types, missing values, and duplicate order IDs.\n",
    "# A clear audit helps clients understand the quality of the starting data.\n",
    "\n",
    "audit_table = pd.DataFrame({\n",
    "    'Column': raw_df.columns,\n",
    "    'Data_Type': raw_df.dtypes.astype(str).values,\n",
    "    'Missing_Values': raw_df.isna().sum().values,\n",
    "    'Missing_%': (raw_df.isna().mean().values * 100).round(2)\n",
    "})\n",
    "\n",
    "print('Duplicate Order_ID count:', raw_df.duplicated(subset=['Order_ID']).sum())\n",
    "display(audit_table)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f3c7ec06-1362-4e3e-9b91-a4cf8a673990",
   "metadata": {},
   "source": [
    "## 4. Clean and prepare the revenue data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3affa984",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Clean data prepared successfully.\n",
      "Clean rows: 30,155\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Order_ID</th>\n",
       "      <th>Order_Date</th>\n",
       "      <th>Customer_ID</th>\n",
       "      <th>Customer_Segment</th>\n",
       "      <th>Region</th>\n",
       "      <th>Sales_Channel</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Product_Name</th>\n",
       "      <th>Units_Sold</th>\n",
       "      <th>Unit_Price</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Gross_Revenue</th>\n",
       "      <th>Net_Revenue</th>\n",
       "      <th>Marketing_Campaign</th>\n",
       "      <th>Refund_Flag</th>\n",
       "      <th>Month</th>\n",
       "      <th>Month_Label</th>\n",
       "      <th>Quarter</th>\n",
       "      <th>Year</th>\n",
       "      <th>Month_Number</th>\n",
       "      <th>Month_Name</th>\n",
       "      <th>Revenue_Type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ORD-100000</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-1189</td>\n",
       "      <td>Consumer</td>\n",
       "      <td>North America</td>\n",
       "      <td>Marketplace</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Enterprise Plan</td>\n",
       "      <td>1</td>\n",
       "      <td>479.73</td>\n",
       "      <td>0.18</td>\n",
       "      <td>479.73</td>\n",
       "      <td>394.46</td>\n",
       "      <td>Year-End Push</td>\n",
       "      <td>No</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>2021-01</td>\n",
       "      <td>2021Q1</td>\n",
       "      <td>2021</td>\n",
       "      <td>1</td>\n",
       "      <td>Jan</td>\n",
       "      <td>Positive Revenue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ORD-100001</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8513</td>\n",
       "      <td>Small Business</td>\n",
       "      <td>North America</td>\n",
       "      <td>Marketplace</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Growth Plan</td>\n",
       "      <td>1</td>\n",
       "      <td>143.90</td>\n",
       "      <td>0.06</td>\n",
       "      <td>143.90</td>\n",
       "      <td>135.89</td>\n",
       "      <td>Black Friday</td>\n",
       "      <td>No</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>2021-01</td>\n",
       "      <td>2021Q1</td>\n",
       "      <td>2021</td>\n",
       "      <td>1</td>\n",
       "      <td>Jan</td>\n",
       "      <td>Positive Revenue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ORD-100002</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-1995</td>\n",
       "      <td>Enterprise</td>\n",
       "      <td>Middle East</td>\n",
       "      <td>Direct Sales</td>\n",
       "      <td>Software Subscriptions</td>\n",
       "      <td>Enterprise Plan</td>\n",
       "      <td>2</td>\n",
       "      <td>481.17</td>\n",
       "      <td>0.35</td>\n",
       "      <td>962.33</td>\n",
       "      <td>625.52</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>2021-01</td>\n",
       "      <td>2021Q1</td>\n",
       "      <td>2021</td>\n",
       "      <td>1</td>\n",
       "      <td>Jan</td>\n",
       "      <td>Positive Revenue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ORD-100003</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8208</td>\n",
       "      <td>Consumer</td>\n",
       "      <td>North America</td>\n",
       "      <td>Website</td>\n",
       "      <td>Analytics Packages</td>\n",
       "      <td>Revenue Forecasting</td>\n",
       "      <td>1</td>\n",
       "      <td>1,809.60</td>\n",
       "      <td>0.06</td>\n",
       "      <td>1,809.60</td>\n",
       "      <td>1,709.35</td>\n",
       "      <td>Q1 Planning</td>\n",
       "      <td>No</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>2021-01</td>\n",
       "      <td>2021Q1</td>\n",
       "      <td>2021</td>\n",
       "      <td>1</td>\n",
       "      <td>Jan</td>\n",
       "      <td>Positive Revenue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ORD-100004</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>CUST-8215</td>\n",
       "      <td>Enterprise</td>\n",
       "      <td>North America</td>\n",
       "      <td>Retail Store</td>\n",
       "      <td>Cloud Services</td>\n",
       "      <td>Storage Add-on</td>\n",
       "      <td>1</td>\n",
       "      <td>82.68</td>\n",
       "      <td>0.33</td>\n",
       "      <td>82.68</td>\n",
       "      <td>55.79</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No</td>\n",
       "      <td>2021-01-01</td>\n",
       "      <td>2021-01</td>\n",
       "      <td>2021Q1</td>\n",
       "      <td>2021</td>\n",
       "      <td>1</td>\n",
       "      <td>Jan</td>\n",
       "      <td>Positive Revenue</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Order_ID Order_Date Customer_ID Customer_Segment         Region  \\\n",
       "0  ORD-100000 2021-01-01   CUST-1189         Consumer  North America   \n",
       "1  ORD-100001 2021-01-01   CUST-8513   Small Business  North America   \n",
       "2  ORD-100002 2021-01-01   CUST-1995       Enterprise    Middle East   \n",
       "3  ORD-100003 2021-01-01   CUST-8208         Consumer  North America   \n",
       "4  ORD-100004 2021-01-01   CUST-8215       Enterprise  North America   \n",
       "\n",
       "  Sales_Channel        Product_Category         Product_Name  Units_Sold  \\\n",
       "0   Marketplace  Software Subscriptions      Enterprise Plan           1   \n",
       "1   Marketplace  Software Subscriptions          Growth Plan           1   \n",
       "2  Direct Sales  Software Subscriptions      Enterprise Plan           2   \n",
       "3       Website      Analytics Packages  Revenue Forecasting           1   \n",
       "4  Retail Store          Cloud Services       Storage Add-on           1   \n",
       "\n",
       "   Unit_Price  Discount_Rate  Gross_Revenue  Net_Revenue Marketing_Campaign  \\\n",
       "0      479.73           0.18         479.73       394.46      Year-End Push   \n",
       "1      143.90           0.06         143.90       135.89       Black Friday   \n",
       "2      481.17           0.35         962.33       625.52                NaN   \n",
       "3    1,809.60           0.06       1,809.60     1,709.35        Q1 Planning   \n",
       "4       82.68           0.33          82.68        55.79                NaN   \n",
       "\n",
       "  Refund_Flag      Month Month_Label Quarter  Year  Month_Number Month_Name  \\\n",
       "0          No 2021-01-01     2021-01  2021Q1  2021             1        Jan   \n",
       "1          No 2021-01-01     2021-01  2021Q1  2021             1        Jan   \n",
       "2          No 2021-01-01     2021-01  2021Q1  2021             1        Jan   \n",
       "3          No 2021-01-01     2021-01  2021Q1  2021             1        Jan   \n",
       "4          No 2021-01-01     2021-01  2021Q1  2021             1        Jan   \n",
       "\n",
       "       Revenue_Type  \n",
       "0  Positive Revenue  \n",
       "1  Positive Revenue  \n",
       "2  Positive Revenue  \n",
       "3  Positive Revenue  \n",
       "4  Positive Revenue  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# The cleaning process handles date conversion, blank channels, missing discounts,\n",
    "# duplicate order IDs, and time-based features used for pivot tables and forecasting.\n",
    "\n",
    "df = raw_df.copy()\n",
    "\n",
    "df['Order_Date'] = pd.to_datetime(df['Order_Date'], errors='coerce')\n",
    "df['Sales_Channel'] = df['Sales_Channel'].replace('', np.nan).fillna('Unknown')\n",
    "df['Discount_Rate'] = pd.to_numeric(df['Discount_Rate'], errors='coerce')\n",
    "df['Discount_Rate'] = df['Discount_Rate'].fillna(df['Discount_Rate'].median())\n",
    "df['Gross_Revenue'] = pd.to_numeric(df['Gross_Revenue'], errors='coerce')\n",
    "df['Net_Revenue'] = pd.to_numeric(df['Net_Revenue'], errors='coerce')\n",
    "\n",
    "# Remove duplicate orders so revenue is not overstated.\n",
    "df = df.drop_duplicates(subset=['Order_ID']).copy()\n",
    "\n",
    "# Create time features for trend analysis, seasonality, and pivot tables.\n",
    "df['Month'] = df['Order_Date'].dt.to_period('M').dt.to_timestamp()\n",
    "df['Month_Label'] = df['Order_Date'].dt.strftime('%Y-%m')\n",
    "df['Quarter'] = df['Order_Date'].dt.to_period('Q').astype(str)\n",
    "df['Year'] = df['Order_Date'].dt.year\n",
    "df['Month_Number'] = df['Order_Date'].dt.month\n",
    "df['Month_Name'] = df['Order_Date'].dt.strftime('%b')\n",
    "df['Revenue_Type'] = np.where(df['Net_Revenue'] >= 0, 'Positive Revenue', 'Refund / Credit')\n",
    "\n",
    "print('Clean data prepared successfully.')\n",
    "print(f'Clean rows: {df.shape[0]:,}')\n",
    "display(df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "94ec884f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Metric</th>\n",
       "      <th>Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Total Net Revenue</td>\n",
       "      <td>$44,964,128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Total Gross Revenue</td>\n",
       "      <td>$56,901,438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Number of Orders</td>\n",
       "      <td>30,155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Average Net Revenue per Order</td>\n",
       "      <td>$1,491.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Refund / Credit Records</td>\n",
       "      <td>806</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Date Range</td>\n",
       "      <td>2021-01-01 to 2024-12-31</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Metric                     Value\n",
       "0              Total Net Revenue               $44,964,128\n",
       "1            Total Gross Revenue               $56,901,438\n",
       "2               Number of Orders                    30,155\n",
       "3  Average Net Revenue per Order                 $1,491.10\n",
       "4        Refund / Credit Records                       806\n",
       "5                     Date Range  2021-01-01 to 2024-12-31"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# These KPIs summarize the overall business picture before forecasting.\n",
    "\n",
    "kpis = pd.DataFrame({\n",
    "    'Metric': [\n",
    "        'Total Net Revenue', 'Total Gross Revenue', 'Number of Orders',\n",
    "        'Average Net Revenue per Order', 'Refund / Credit Records', 'Date Range'\n",
    "    ],\n",
    "    'Value': [\n",
    "        f\"${df['Net_Revenue'].sum():,.0f}\",\n",
    "        f\"${df['Gross_Revenue'].sum():,.0f}\",\n",
    "        f\"{df['Order_ID'].nunique():,}\",\n",
    "        f\"${df['Net_Revenue'].mean():,.2f}\",\n",
    "        f\"{(df['Revenue_Type'] == 'Refund / Credit').sum():,}\",\n",
    "        f\"{df['Order_Date'].min().date()} to {df['Order_Date'].max().date()}\"\n",
    "    ]\n",
    "})\n",
    "\n",
    "display(kpis)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c93966e-c776-4508-809b-9672842eee85",
   "metadata": {},
   "source": [
    "## 6. Real pivot tables inside Jupyter Notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "25b5bfd2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pivot Table 1: Monthly Revenue by Year\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Year</th>\n",
       "      <th>2021</th>\n",
       "      <th>2022</th>\n",
       "      <th>2023</th>\n",
       "      <th>2024</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Month_Name</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Jan</th>\n",
       "      <td>657,531.03</td>\n",
       "      <td>807,152.21</td>\n",
       "      <td>879,815.96</td>\n",
       "      <td>888,322.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Feb</th>\n",
       "      <td>708,150.41</td>\n",
       "      <td>794,641.55</td>\n",
       "      <td>1,014,389.96</td>\n",
       "      <td>1,068,992.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mar</th>\n",
       "      <td>858,657.95</td>\n",
       "      <td>1,113,106.20</td>\n",
       "      <td>1,098,128.86</td>\n",
       "      <td>1,062,679.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Apr</th>\n",
       "      <td>756,772.14</td>\n",
       "      <td>930,229.42</td>\n",
       "      <td>1,147,080.87</td>\n",
       "      <td>1,355,247.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>May</th>\n",
       "      <td>835,090.07</td>\n",
       "      <td>1,145,921.91</td>\n",
       "      <td>1,138,260.28</td>\n",
       "      <td>1,273,488.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jun</th>\n",
       "      <td>660,591.27</td>\n",
       "      <td>1,035,309.76</td>\n",
       "      <td>1,125,987.99</td>\n",
       "      <td>1,122,133.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jul</th>\n",
       "      <td>774,549.87</td>\n",
       "      <td>740,752.82</td>\n",
       "      <td>941,078.37</td>\n",
       "      <td>1,110,436.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aug</th>\n",
       "      <td>695,348.01</td>\n",
       "      <td>759,451.08</td>\n",
       "      <td>766,689.93</td>\n",
       "      <td>1,031,256.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sep</th>\n",
       "      <td>544,375.13</td>\n",
       "      <td>622,389.82</td>\n",
       "      <td>845,789.19</td>\n",
       "      <td>802,301.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Oct</th>\n",
       "      <td>624,843.65</td>\n",
       "      <td>664,121.00</td>\n",
       "      <td>821,563.88</td>\n",
       "      <td>856,643.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nov</th>\n",
       "      <td>883,569.97</td>\n",
       "      <td>937,484.96</td>\n",
       "      <td>1,165,126.85</td>\n",
       "      <td>1,318,944.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dec</th>\n",
       "      <td>888,175.22</td>\n",
       "      <td>1,044,442.37</td>\n",
       "      <td>1,168,533.08</td>\n",
       "      <td>1,478,579.06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Year             2021         2022         2023         2024\n",
       "Month_Name                                                  \n",
       "Jan        657,531.03   807,152.21   879,815.96   888,322.26\n",
       "Feb        708,150.41   794,641.55 1,014,389.96 1,068,992.96\n",
       "Mar        858,657.95 1,113,106.20 1,098,128.86 1,062,679.16\n",
       "Apr        756,772.14   930,229.42 1,147,080.87 1,355,247.60\n",
       "May        835,090.07 1,145,921.91 1,138,260.28 1,273,488.14\n",
       "Jun        660,591.27 1,035,309.76 1,125,987.99 1,122,133.77\n",
       "Jul        774,549.87   740,752.82   941,078.37 1,110,436.35\n",
       "Aug        695,348.01   759,451.08   766,689.93 1,031,256.68\n",
       "Sep        544,375.13   622,389.82   845,789.19   802,301.06\n",
       "Oct        624,843.65   664,121.00   821,563.88   856,643.21\n",
       "Nov        883,569.97   937,484.96 1,165,126.85 1,318,944.62\n",
       "Dec        888,175.22 1,044,442.37 1,168,533.08 1,478,579.06"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pivot Table 2: Revenue by Product Category and Customer Segment\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Customer_Segment</th>\n",
       "      <th>Consumer</th>\n",
       "      <th>Enterprise</th>\n",
       "      <th>Public Sector</th>\n",
       "      <th>Small Business</th>\n",
       "      <th>All</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Product_Category</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>All</th>\n",
       "      <td>11,307,935.18</td>\n",
       "      <td>15,972,045.29</td>\n",
       "      <td>5,164,680.88</td>\n",
       "      <td>12,519,466.56</td>\n",
       "      <td>44,964,127.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Consulting Services</th>\n",
       "      <td>5,899,140.87</td>\n",
       "      <td>8,406,664.29</td>\n",
       "      <td>2,550,593.81</td>\n",
       "      <td>6,347,273.30</td>\n",
       "      <td>23,203,672.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Analytics Packages</th>\n",
       "      <td>3,211,827.34</td>\n",
       "      <td>4,511,362.83</td>\n",
       "      <td>1,653,917.68</td>\n",
       "      <td>3,776,898.40</td>\n",
       "      <td>13,154,006.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Training Products</th>\n",
       "      <td>1,034,933.30</td>\n",
       "      <td>1,471,015.34</td>\n",
       "      <td>455,698.07</td>\n",
       "      <td>1,138,585.02</td>\n",
       "      <td>4,100,231.73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Software Subscriptions</th>\n",
       "      <td>809,056.81</td>\n",
       "      <td>1,090,461.70</td>\n",
       "      <td>348,176.22</td>\n",
       "      <td>877,270.03</td>\n",
       "      <td>3,124,964.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cloud Services</th>\n",
       "      <td>352,976.86</td>\n",
       "      <td>492,541.13</td>\n",
       "      <td>156,295.10</td>\n",
       "      <td>379,439.81</td>\n",
       "      <td>1,381,252.90</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Customer_Segment            Consumer    Enterprise  Public Sector  \\\n",
       "Product_Category                                                    \n",
       "All                    11,307,935.18 15,972,045.29   5,164,680.88   \n",
       "Consulting Services     5,899,140.87  8,406,664.29   2,550,593.81   \n",
       "Analytics Packages      3,211,827.34  4,511,362.83   1,653,917.68   \n",
       "Training Products       1,034,933.30  1,471,015.34     455,698.07   \n",
       "Software Subscriptions    809,056.81  1,090,461.70     348,176.22   \n",
       "Cloud Services            352,976.86    492,541.13     156,295.10   \n",
       "\n",
       "Customer_Segment        Small Business           All  \n",
       "Product_Category                                      \n",
       "All                      12,519,466.56 44,964,127.91  \n",
       "Consulting Services       6,347,273.30 23,203,672.27  \n",
       "Analytics Packages        3,776,898.40 13,154,006.25  \n",
       "Training Products         1,138,585.02  4,100,231.73  \n",
       "Software Subscriptions      877,270.03  3,124,964.76  \n",
       "Cloud Services              379,439.81  1,381,252.90  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pivot Table 3: Revenue by Region and Sales Channel\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Sales_Channel</th>\n",
       "      <th>Direct Sales</th>\n",
       "      <th>Marketplace</th>\n",
       "      <th>Partner</th>\n",
       "      <th>Retail Store</th>\n",
       "      <th>Unknown</th>\n",
       "      <th>Website</th>\n",
       "      <th>All</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Region</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>All</th>\n",
       "      <td>8,754,673.54</td>\n",
       "      <td>9,981,665.33</td>\n",
       "      <td>5,253,033.28</td>\n",
       "      <td>5,173,102.14</td>\n",
       "      <td>144,249.43</td>\n",
       "      <td>15,657,404.19</td>\n",
       "      <td>44,964,127.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>North America</th>\n",
       "      <td>2,863,464.79</td>\n",
       "      <td>3,255,114.71</td>\n",
       "      <td>1,808,512.56</td>\n",
       "      <td>1,821,252.96</td>\n",
       "      <td>42,016.54</td>\n",
       "      <td>5,343,520.75</td>\n",
       "      <td>15,133,882.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Europe</th>\n",
       "      <td>2,314,733.57</td>\n",
       "      <td>2,474,272.88</td>\n",
       "      <td>1,388,119.45</td>\n",
       "      <td>1,344,241.03</td>\n",
       "      <td>27,859.69</td>\n",
       "      <td>3,994,564.68</td>\n",
       "      <td>11,543,791.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Asia Pacific</th>\n",
       "      <td>1,269,577.93</td>\n",
       "      <td>1,570,828.62</td>\n",
       "      <td>738,547.19</td>\n",
       "      <td>733,397.98</td>\n",
       "      <td>23,728.31</td>\n",
       "      <td>2,200,269.56</td>\n",
       "      <td>6,536,349.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Middle East</th>\n",
       "      <td>1,252,610.54</td>\n",
       "      <td>1,405,860.87</td>\n",
       "      <td>654,168.59</td>\n",
       "      <td>665,735.11</td>\n",
       "      <td>13,266.90</td>\n",
       "      <td>2,166,643.24</td>\n",
       "      <td>6,158,285.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Africa</th>\n",
       "      <td>1,054,286.71</td>\n",
       "      <td>1,275,588.25</td>\n",
       "      <td>663,685.49</td>\n",
       "      <td>608,475.06</td>\n",
       "      <td>37,377.99</td>\n",
       "      <td>1,952,405.96</td>\n",
       "      <td>5,591,819.46</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Sales_Channel  Direct Sales  Marketplace      Partner  Retail Store  \\\n",
       "Region                                                                \n",
       "All            8,754,673.54 9,981,665.33 5,253,033.28  5,173,102.14   \n",
       "North America  2,863,464.79 3,255,114.71 1,808,512.56  1,821,252.96   \n",
       "Europe         2,314,733.57 2,474,272.88 1,388,119.45  1,344,241.03   \n",
       "Asia Pacific   1,269,577.93 1,570,828.62   738,547.19    733,397.98   \n",
       "Middle East    1,252,610.54 1,405,860.87   654,168.59    665,735.11   \n",
       "Africa         1,054,286.71 1,275,588.25   663,685.49    608,475.06   \n",
       "\n",
       "Sales_Channel    Unknown       Website           All  \n",
       "Region                                                \n",
       "All           144,249.43 15,657,404.19 44,964,127.91  \n",
       "North America  42,016.54  5,343,520.75 15,133,882.31  \n",
       "Europe         27,859.69  3,994,564.68 11,543,791.30  \n",
       "Asia Pacific   23,728.31  2,200,269.56  6,536,349.59  \n",
       "Middle East    13,266.90  2,166,643.24  6,158,285.25  \n",
       "Africa         37,377.99  1,952,405.96  5,591,819.46  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Pivot tables help managers summarize revenue by month, product, customer segment,\n",
    "# region, channel, and quarter without reading every transaction row.\n",
    "\n",
    "# Pivot Table 1: Monthly revenue by year\n",
    "pivot_month_year = pd.pivot_table(\n",
    "    df, values='Net_Revenue', index='Month_Name', columns='Year',\n",
    "    aggfunc='sum', fill_value=0\n",
    ").reindex(['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec'])\n",
    "\n",
    "# Pivot Table 2: Revenue by product category and customer segment\n",
    "pivot_category_segment = pd.pivot_table(\n",
    "    df, values='Net_Revenue', index='Product_Category', columns='Customer_Segment',\n",
    "    aggfunc='sum', fill_value=0, margins=True\n",
    ").sort_values('All', ascending=False)\n",
    "\n",
    "# Pivot Table 3: Revenue by region and sales channel\n",
    "pivot_region_channel = pd.pivot_table(\n",
    "    df, values='Net_Revenue', index='Region', columns='Sales_Channel',\n",
    "    aggfunc='sum', fill_value=0, margins=True\n",
    ").sort_values('All', ascending=False)\n",
    "\n",
    "print('Pivot Table 1: Monthly Revenue by Year')\n",
    "display(pivot_month_year)\n",
    "\n",
    "print('Pivot Table 2: Revenue by Product Category and Customer Segment')\n",
    "display(pivot_category_segment)\n",
    "\n",
    "print('Pivot Table 3: Revenue by Region and Sales Channel')\n",
    "display(pivot_region_channel)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b2cb6eed-416f-43a7-96da-128545d4fc87",
   "metadata": {},
   "source": [
    "## 7. Graphs for revenue analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "da343035",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# The graphs make the revenue pattern easier to understand for non-technical users.\n",
    "\n",
    "monthly = df.groupby('Month', as_index=False)['Net_Revenue'].sum().sort_values('Month')\n",
    "category_revenue = df.groupby('Product_Category', as_index=False)['Net_Revenue'].sum().sort_values('Net_Revenue', ascending=False)\n",
    "segment_revenue = df.groupby('Customer_Segment', as_index=False)['Net_Revenue'].sum().sort_values('Net_Revenue', ascending=False)\n",
    "\n",
    "plt.figure(figsize=(12, 5))\n",
    "plt.plot(monthly['Month'], monthly['Net_Revenue'], marker='o', linewidth=1)\n",
    "plt.title('Monthly Net Revenue Trend')\n",
    "plt.xlabel('Month')\n",
    "plt.ylabel('Net Revenue')\n",
    "plt.xticks(rotation=45)\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "plt.figure(figsize=(10, 5))\n",
    "plt.bar(category_revenue['Product_Category'], category_revenue['Net_Revenue'])\n",
    "plt.title('Revenue by Product Category')\n",
    "plt.xlabel('Product Category')\n",
    "plt.ylabel('Net Revenue')\n",
    "plt.xticks(rotation=30, ha='right')\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "plt.figure(figsize=(8, 5))\n",
    "plt.bar(segment_revenue['Customer_Segment'], segment_revenue['Net_Revenue'])\n",
    "plt.title('Revenue by Customer Segment')\n",
    "plt.xlabel('Customer Segment')\n",
    "plt.ylabel('Net Revenue')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "11ac2140-9e30-49ce-be05-83697250e31c",
   "metadata": {},
   "source": [
    "## 8. Revenue forecasting model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7bc8e22b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Month_Label</th>\n",
       "      <th>Conservative_Forecast</th>\n",
       "      <th>Base_Forecast</th>\n",
       "      <th>Growth_Forecast</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2025-01</td>\n",
       "      <td>1,007,913.94</td>\n",
       "      <td>1,119,904.38</td>\n",
       "      <td>1,254,292.90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2025-02</td>\n",
       "      <td>1,087,418.46</td>\n",
       "      <td>1,208,242.73</td>\n",
       "      <td>1,353,231.86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2025-03</td>\n",
       "      <td>1,210,357.85</td>\n",
       "      <td>1,344,842.05</td>\n",
       "      <td>1,506,223.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2025-04</td>\n",
       "      <td>1,223,128.37</td>\n",
       "      <td>1,359,031.52</td>\n",
       "      <td>1,522,115.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2025-05</td>\n",
       "      <td>1,268,900.20</td>\n",
       "      <td>1,409,889.11</td>\n",
       "      <td>1,579,075.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2025-06</td>\n",
       "      <td>1,167,934.24</td>\n",
       "      <td>1,297,704.71</td>\n",
       "      <td>1,453,429.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2025-07</td>\n",
       "      <td>1,083,063.03</td>\n",
       "      <td>1,203,403.36</td>\n",
       "      <td>1,347,811.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2025-08</td>\n",
       "      <td>1,012,396.89</td>\n",
       "      <td>1,124,885.44</td>\n",
       "      <td>1,259,871.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2025-09</td>\n",
       "      <td>913,871.53</td>\n",
       "      <td>1,015,412.81</td>\n",
       "      <td>1,137,262.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2025-10</td>\n",
       "      <td>948,142.75</td>\n",
       "      <td>1,053,491.95</td>\n",
       "      <td>1,179,910.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2025-11</td>\n",
       "      <td>1,249,182.55</td>\n",
       "      <td>1,387,980.61</td>\n",
       "      <td>1,554,538.29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2025-12</td>\n",
       "      <td>1,310,968.30</td>\n",
       "      <td>1,456,631.44</td>\n",
       "      <td>1,631,427.22</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Month_Label  Conservative_Forecast  Base_Forecast  Growth_Forecast\n",
       "0      2025-01           1,007,913.94   1,119,904.38     1,254,292.90\n",
       "1      2025-02           1,087,418.46   1,208,242.73     1,353,231.86\n",
       "2      2025-03           1,210,357.85   1,344,842.05     1,506,223.10\n",
       "3      2025-04           1,223,128.37   1,359,031.52     1,522,115.30\n",
       "4      2025-05           1,268,900.20   1,409,889.11     1,579,075.81\n",
       "5      2025-06           1,167,934.24   1,297,704.71     1,453,429.27\n",
       "6      2025-07           1,083,063.03   1,203,403.36     1,347,811.77\n",
       "7      2025-08           1,012,396.89   1,124,885.44     1,259,871.69\n",
       "8      2025-09             913,871.53   1,015,412.81     1,137,262.35\n",
       "9      2025-10             948,142.75   1,053,491.95     1,179,910.98\n",
       "10     2025-11           1,249,182.55   1,387,980.61     1,554,538.29\n",
       "11     2025-12           1,310,968.30   1,456,631.44     1,631,427.22"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# This simple forecasting model uses a trend feature and month-based seasonality.\n",
    "# It is suitable for a clear portfolio demonstration and can be expanded for more advanced projects.\n",
    "\n",
    "monthly = df.groupby('Month', as_index=False)['Net_Revenue'].sum().sort_values('Month')\n",
    "monthly['t'] = np.arange(len(monthly))\n",
    "\n",
    "# Create month dummy variables so the model can learn recurring seasonal patterns.\n",
    "X = pd.concat([\n",
    "    monthly[['t']],\n",
    "    pd.get_dummies(monthly['Month'].dt.month, prefix='month', drop_first=False)\n",
    "], axis=1)\n",
    "y = monthly['Net_Revenue']\n",
    "\n",
    "forecast_model = LinearRegression()\n",
    "forecast_model.fit(X, y)\n",
    "\n",
    "future_months = pd.date_range(monthly['Month'].max() + pd.offsets.MonthBegin(1), periods=12, freq='MS')\n",
    "future = pd.DataFrame({'Month': future_months})\n",
    "future['t'] = np.arange(len(monthly), len(monthly) + len(future))\n",
    "\n",
    "X_future = pd.concat([\n",
    "    future[['t']],\n",
    "    pd.get_dummies(future['Month'].dt.month, prefix='month', drop_first=False)\n",
    "], axis=1)\n",
    "X_future = X_future.reindex(columns=X.columns, fill_value=0)\n",
    "\n",
    "future['Base_Forecast'] = forecast_model.predict(X_future)\n",
    "future['Conservative_Forecast'] = future['Base_Forecast'] * 0.90\n",
    "future['Growth_Forecast'] = future['Base_Forecast'] * 1.12\n",
    "future['Month_Label'] = future['Month'].dt.strftime('%Y-%m')\n",
    "\n",
    "forecast_table = future[['Month_Label', 'Conservative_Forecast', 'Base_Forecast', 'Growth_Forecast']]\n",
    "display(forecast_table)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d113624a-03bb-4c19-a0a1-750781494d29",
   "metadata": {},
   "source": [
    "## 9. Forecast scenario graph"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "1e356a2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12, 5))\n",
    "plt.plot(monthly['Month'], monthly['Net_Revenue'], marker='o', linewidth=1, label='Actual')\n",
    "plt.plot(future['Month'], future['Conservative_Forecast'], marker='o', linewidth=1, label='Conservative')\n",
    "plt.plot(future['Month'], future['Base_Forecast'], marker='o', linewidth=1, label='Base')\n",
    "plt.plot(future['Month'], future['Growth_Forecast'], marker='o', linewidth=1, label='Growth')\n",
    "plt.title('Revenue Forecast Scenarios')\n",
    "plt.xlabel('Month')\n",
    "plt.ylabel('Net Revenue')\n",
    "plt.xticks(rotation=45)\n",
    "plt.legend()\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a78a34c3-85f0-4f5f-a375-760708c572d8",
   "metadata": {},
   "source": [
    "## 10. Export dashboard-ready outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "e3a984b9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Client-ready outputs exported to: C:\\Users\\user\\python_outputs\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# These exports can later be used in Power BI, Tableau, Excel, or a client reporting workflow.\n",
    "\n",
    "output_dir = Path('python_outputs')\n",
    "output_dir.mkdir(exist_ok=True)\n",
    "\n",
    "df.to_csv(output_dir / 'clean_revenue_data.csv', index=False)\n",
    "monthly.to_csv(output_dir / 'monthly_revenue_actuals.csv', index=False)\n",
    "forecast_table.to_csv(output_dir / 'revenue_forecast_scenarios.csv', index=False)\n",
    "pivot_category_segment.to_csv(output_dir / 'pivot_revenue_by_category_and_segment.csv')\n",
    "pivot_region_channel.to_csv(output_dir / 'pivot_revenue_by_region_and_channel.csv')\n",
    "\n",
    "print('Client-ready outputs exported to:', output_dir.resolve())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f19281c-606b-448c-831c-15985d90299f",
   "metadata": {},
   "source": [
    "## 11. Plain-language interpretation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a6d552e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Business Interpretation:\n",
      "\n",
      "The historical data shows clear monthly revenue movement and a visible contribution from product categories, customer segments, and sales channels. The strongest product category is Consulting Services, while the strongest customer segment is Enterprise.\n",
      "\n",
      "For the next 12 months, the base forecast estimates approximately $14,981,420 in revenue. The conservative scenario estimates approximately $13,483,278, while the growth scenario estimates approximately $16,779,191.\n",
      "\n",
      "Management can use these scenario outputs for budgeting, hiring planning, marketing spend discussions, investor updates, and revenue target setting. These forecasts should be treated as planning estimates, not guaranteed outcomes.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# This section turns the analysis into business language for a client or manager.\n",
    "\n",
    "top_category = category_revenue.iloc[0]['Product_Category']\n",
    "top_segment = segment_revenue.iloc[0]['Customer_Segment']\n",
    "base_total = future['Base_Forecast'].sum()\n",
    "conservative_total = future['Conservative_Forecast'].sum()\n",
    "growth_total = future['Growth_Forecast'].sum()\n",
    "\n",
    "interpretation = f'''\n",
    "Business Interpretation:\n",
    "\n",
    "The historical data shows clear monthly revenue movement and a visible contribution from product categories, customer segments, and sales channels. The strongest product category is {top_category}, while the strongest customer segment is {top_segment}.\n",
    "\n",
    "For the next 12 months, the base forecast estimates approximately ${base_total:,.0f} in revenue. The conservative scenario estimates approximately ${conservative_total:,.0f}, while the growth scenario estimates approximately ${growth_total:,.0f}.\n",
    "\n",
    "Management can use these scenario outputs for budgeting, hiring planning, marketing spend discussions, investor updates, and revenue target setting. These forecasts should be treated as planning estimates, not guaranteed outcomes.\n",
    "'''\n",
    "\n",
    "print(interpretation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2290f3a3-abde-4ae5-a752-25d9987855cf",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}