Upload 2 files

datacreation.ipynb

@@ -0,0 +1,1076 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4ba6aba8"
+      },
+      "source": [
+        "# 🤖 **Data Collection, Creation, Storage, and Processing**\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jpASMyIQMaAq"
+      },
+      "source": [
+        "## **1.** 📦 Install required packages"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "f48c8f8c",
+        "outputId": "7e50dd72-2e2a-47b1-e59b-ed7c5511d9cd"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.12/dist-packages (4.13.5)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
+            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
+            "Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
+            "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (2.0.2)\n",
+            "Requirement already satisfied: textblob in /usr/local/lib/python3.12/dist-packages (0.19.0)\n",
+            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (2.8.3)\n",
+            "Requirement already satisfied: typing-extensions>=4.0.0 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (4.15.0)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
+            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.3)\n",
+            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
+            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
+            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.62.1)\n",
+            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.5.0)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (26.0)\n",
+            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
+            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (3.3.2)\n",
+            "Requirement already satisfied: nltk>=3.9 in /usr/local/lib/python3.12/dist-packages (from textblob) (3.9.1)\n",
+            "Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (8.3.1)\n",
+            "Requirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (1.5.3)\n",
+            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (2025.11.3)\n",
+            "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (4.67.3)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install beautifulsoup4 pandas matplotlib seaborn numpy textblob"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "lquNYCbfL9IM"
+      },
+      "source": [
+        "## **2.** ⛏ Load the Superstore dataset from Kaggle\n",
+        "\n",
+        "Dataset source: [Superstore Dataset – Kaggle](https://www.kaggle.com/datasets/vivek468/superstore-dataset-final?resource=download)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0IWuNpxxYDJF"
+      },
+      "source": [
+        "### *a. Initial setup*\n",
+        "Define the base url of the dataset source as well as how and what you will load"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "91d52125"
+      },
+      "outputs": [],
+      "source": [
+        "import requests\n",
+        "from bs4 import BeautifulSoup\n",
+        "import pandas as pd\n",
+        "import time\n",
+        "\n",
+        "# Dataset source\n",
+        "base_url = \"https://www.kaggle.com/datasets/vivek468/superstore-dataset-final?resource=download\"\n",
+        "headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
+        "\n",
+        "df_raw = pd.read_csv(\"Sample - Superstore.csv\", encoding=\"latin-1\")\n",
+        "df_raw[\"Order Date\"] = pd.to_datetime(df_raw[\"Order Date\"], format=\"%m/%d/%Y\")\n",
+        "df_raw[\"Ship Date\"]  = pd.to_datetime(df_raw[\"Ship Date\"],  format=\"%m/%d/%Y\")\n",
+        "\n",
+        "sub_categories, avg_prices, avg_profits = [], [], []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "oCdTsin2Yfp3"
+      },
+      "source": [
+        "### *b. Fill sub_categories, avg_prices, and avg_profits from the dataset*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xqO5Y3dnYhxt"
+      },
+      "outputs": [],
+      "source": [
+        "# Aggregate over all Sub-Categories\n",
+        "for sub_cat, group in df_raw.groupby(\"Sub-Category\"):\n",
+        "    sub_categories.append(sub_cat)\n",
+        "    avg_prices.append(round(group[\"Sales\"].sum() / group[\"Quantity\"].sum(), 2))\n",
+        "    avg_profits.append(round(group[\"Profit\"].mean(), 2))\n",
+        "\n",
+        "    time.sleep(0)  # kept for structural parity"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T0TOeRC4Yrnn"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Create a dataframe df_products that contains the now complete \"sub_category\", \"avg_price\", and \"avg_profit\" objects*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "l5FkkNhUYTHh"
+      },
+      "outputs": [],
+      "source": [
+        "# 🗂️ Create DataFrame\n",
+        "df_products = pd.DataFrame({\n",
+        "    \"sub_category\": sub_categories,\n",
+        "    \"avg_price\": avg_prices,\n",
+        "    \"avg_profit\": avg_profits\n",
+        "})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "duI5dv3CZYvF"
+      },
+      "source": [
+        "### *d. Save dataframe either as a CSV or Excel file*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "lC1U_YHtZifh"
+      },
+      "outputs": [],
+      "source": [
+        "# 💾 Save to CSV\n",
+        "df_products.to_csv(\"superstore_data.csv\", index=False)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "qMjRKMBQZlJi"
+      },
+      "source": [
+        "### *e. ✋🏻🛑⛔️ View first few lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "O_wIvTxYZqCK",
+        "outputId": "5c622472-47de-4352-daa9-c7da226d0c30"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "  sub_category  avg_price  avg_profit\n",
+              "0  Accessories      57.42       55.81\n",
+              "1   Appliances      62.69       38.47\n",
+              "2          Art       9.09        8.15\n",
+              "3      Binders      33.07       20.72\n",
+              "4    Bookcases     124.61      -19.17"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-511757e8-63e2-4e0d-9c9c-fd889e0a92a4\" class=\"colab-df-container\">\n",
+              "    <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>sub_category</th>\n",
+              "      <th>avg_price</th>\n",
+              "      <th>avg_profit</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>Accessories</td>\n",
+              "      <td>57.42</td>\n",
+              "      <td>55.81</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>Appliances</td>\n",
+              "      <td>62.69</td>\n",
+              "      <td>38.47</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>Art</td>\n",
+              "      <td>9.09</td>\n",
+              "      <td>8.15</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>Binders</td>\n",
+              "      <td>33.07</td>\n",
+              "      <td>20.72</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>Bookcases</td>\n",
+              "      <td>124.61</td>\n",
+              "      <td>-19.17</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-511757e8-63e2-4e0d-9c9c-fd889e0a92a4')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-511757e8-63e2-4e0d-9c9c-fd889e0a92a4 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-511757e8-63e2-4e0d-9c9c-fd889e0a92a4');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df_products",
+              "summary": "{\n  \"name\": \"df_products\",\n  \"rows\": 17,\n  \"fields\": [\n    {\n      \"column\": \"sub_category\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 17,\n        \"samples\": [\n          \"Accessories\",\n          \"Appliances\",\n          \"Chairs\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 171.03515695739625,\n        \"min\": 3.37,\n        \"max\": 651.79,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          57.42,\n          62.69,\n          138.76\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_profit\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 200.76924667278809,\n        \"min\": -55.48,\n        \"max\": 837.47,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          55.81,\n          38.47,\n          43.23\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 8
+        }
+      ],
+      "source": [
+        "df_products.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "p-1Pr2szaqLk"
+      },
+      "source": [
+        "## **3.** 🧩 Create a meaningful connection between real & synthetic datasets"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "SIaJUGIpaH4V"
+      },
+      "source": [
+        "### *a. Initial setup*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-gPXGcRPuV_9"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import random\n",
+        "from datetime import datetime\n",
+        "import warnings\n",
+        "\n",
+        "warnings.filterwarnings(\"ignore\")\n",
+        "random.seed(2025)\n",
+        "np.random.seed(2025)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pY4yCoIuaQqp"
+      },
+      "source": [
+        "### *b. Generate popularity scores based on avg_profit (with some randomness) with a generate_popularity_score function*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "mnd5hdAbaNjz"
+      },
+      "outputs": [],
+      "source": [
+        "def generate_popularity_score(avg_profit):\n",
+        "    if avg_profit >= 50:\n",
+        "        base = 4\n",
+        "    elif avg_profit >= 10:\n",
+        "        base = 3\n",
+        "    elif avg_profit >= 0:\n",
+        "        base = 2\n",
+        "    else:\n",
+        "        base = 1\n",
+        "    trend_factor = random.choices([-1, 0, 1], weights=[1, 3, 2])[0]\n",
+        "    return int(np.clip(base + trend_factor, 1, 5))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "n4-TaNTFgPak"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Run the function to create a \"popularity_score\" column from \"avg_profit\"*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "V-G3OCUCgR07"
+      },
+      "outputs": [],
+      "source": [
+        "df_products[\"popularity_score\"] = df_products[\"avg_profit\"].apply(generate_popularity_score)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HnngRNTgacYt"
+      },
+      "source": [
+        "### *d. Decide on the sentiment_label based on the popularity score with a get_sentiment function*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "kUtWmr8maZLZ"
+      },
+      "outputs": [],
+      "source": [
+        "def get_sentiment(popularity_score):\n",
+        "    if popularity_score <= 2:\n",
+        "        return \"negative\"\n",
+        "    elif popularity_score == 3:\n",
+        "        return \"neutral\"\n",
+        "    else:\n",
+        "        return \"positive\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HF9F9HIzgT7Z"
+      },
+      "source": [
+        "### *e. ✋🏻🛑⛔️ Run the function to create a \"sentiment_label\" column from \"popularity_score\"*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tafQj8_7gYCG"
+      },
+      "outputs": [],
+      "source": [
+        "df_products[\"sentiment_label\"] = df_products[\"popularity_score\"].apply(get_sentiment)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T8AdKkmASq9a"
+      },
+      "source": [
+        "## **4.** 📈 Generate synthetic sub-category sales data of 18 months"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OhXbdGD5fH0c"
+      },
+      "source": [
+        "### *a. Create a generate_sales_profit function that would generate sales patterns based on sentiment_label (with some randomness)*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qkVhYPXGbgEn"
+      },
+      "outputs": [],
+      "source": [
+        "def generate_sales_profile(sentiment):\n",
+        "    months = pd.date_range(end=datetime.today(), periods=18, freq=\"M\")\n",
+        "\n",
+        "    if sentiment == \"positive\":\n",
+        "        base = random.randint(200, 300)\n",
+        "        trend = np.linspace(base, base + random.randint(20, 60), len(months))\n",
+        "    elif sentiment == \"negative\":\n",
+        "        base = random.randint(20, 80)\n",
+        "        trend = np.linspace(base, base - random.randint(10, 30), len(months))\n",
+        "    else:  # neutral\n",
+        "        base = random.randint(80, 160)\n",
+        "        trend = np.full(len(months), base + random.randint(-10, 10))\n",
+        "\n",
+        "    seasonality = 10 * np.sin(np.linspace(0, 3 * np.pi, len(months)))\n",
+        "    noise = np.random.normal(0, 5, len(months))\n",
+        "    monthly_sales = np.clip(trend + seasonality + noise, a_min=0, a_max=None).astype(int)\n",
+        "\n",
+        "    return list(zip(months.strftime(\"%Y-%m\"), monthly_sales))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "L2ak1HlcgoTe"
+      },
+      "source": [
+        "### *b. Run the function as part of building sales_data*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SlJ24AUafoDB"
+      },
+      "outputs": [],
+      "source": [
+        "sales_data = []\n",
+        "for _, row in df_products.iterrows():\n",
+        "    records = generate_sales_profile(row[\"sentiment_label\"])\n",
+        "    for month, units in records:\n",
+        "        sales_data.append({\n",
+        "            \"sub_category\": row[\"sub_category\"],\n",
+        "            \"month\": month,\n",
+        "            \"units_sold\": units,\n",
+        "            \"sentiment_label\": row[\"sentiment_label\"]\n",
+        "        })"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4IXZKcCSgxnq"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Create a df_sales DataFrame from sales_data*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "wcN6gtiZg-ws"
+      },
+      "outputs": [],
+      "source": [
+        "df_sales = pd.DataFrame(sales_data)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EhIjz9WohAmZ"
+      },
+      "source": [
+        "### *d. Save df_sales as synthetic_sales_data.csv & view first few lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "MzbZvLcAhGaH",
+        "outputId": "683d930c-27a4-4925-b01f-af8490fa8b9b"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "  sub_category    month  units_sold sentiment_label\n",
+            "0  Accessories  2024-10         223        positive\n",
+            "1  Accessories  2024-11         234        positive\n",
+            "2  Accessories  2024-12         229        positive\n",
+            "3  Accessories  2025-01         236        positive\n",
+            "4  Accessories  2025-02         239        positive\n"
+          ]
+        }
+      ],
+      "source": [
+        "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
+        "\n",
+        "print(df_sales.head())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7g9gqBgQMtJn"
+      },
+      "source": [
+        "## **5.** 🎯 Generate synthetic customer reviews"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Gi4y9M9KuDWx"
+      },
+      "source": [
+        "### *a. ✋🏻🛑⛔️ Ask ChatGPT to create a list of 50 distinct generic retail product review texts for the sentiment labels \"positive\", \"neutral\", and \"negative\" called synthetic_reviews_by_sentiment*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b3cd2a50"
+      },
+      "outputs": [],
+      "source": [
+        "synthetic_reviews_by_sentiment = {\n",
+        "    \"positive\": [\n",
+        "        \"This product line is exactly what we needed — quality and value combined.\",\n",
+        "        \"Consistently impressed with the performance across every item in this range.\",\n",
+        "        \"Our team relies on these products daily — they never let us down.\",\n",
+        "        \"Top-tier quality that justifies every cent spent.\",\n",
+        "        \"Outstanding selection that meets every requirement our office has.\",\n",
+        "        \"Remarkable durability and design. Will definitely reorder.\",\n",
+        "        \"These products set the bar — nothing else comes close.\",\n",
+        "        \"Every purchase from this category has exceeded expectations.\",\n",
+        "        \"Huge uplift in team productivity since we started stocking these.\",\n",
+        "        \"Perfect balance of price and quality. Highly recommended.\",\n",
+        "        \"A consistent bestseller in our store — customers keep coming back.\",\n",
+        "        \"Rarely see products deliver at this level — truly impressive.\",\n",
+        "        \"Our highest-rated category by a wide margin.\",\n",
+        "        \"Revenue from this range keeps growing quarter over quarter.\",\n",
+        "        \"Customers praise reliability and style in equal measure.\",\n",
+        "        \"Flawless functionality and great aesthetics — perfect combo.\",\n",
+        "        \"Demand for this sub-category is always strong.\",\n",
+        "        \"These items turn first-time buyers into loyal repeat customers.\",\n",
+        "        \"Low return rates and high satisfaction scores tell the whole story.\",\n",
+        "        \"The profit margins from this category are the envy of the floor.\",\n",
+        "        \"Never overstocked, never understocked — a category manager's dream.\",\n",
+        "        \"Positive word of mouth keeps driving new customers our way.\",\n",
+        "        \"An anchor category that props up overall store performance.\",\n",
+        "        \"Premium feel at a competitive price — customers notice.\",\n",
+        "        \"Strong sell-through rate with minimal markdowns needed.\",\n",
+        "        \"Year-on-year growth in this sub-category continues to impress.\",\n",
+        "        \"Staff love recommending these — they practically sell themselves.\",\n",
+        "        \"Margin-accretive with broad appeal across all customer segments.\",\n",
+        "        \"Dependable supply chain and consistent quality from this range.\",\n",
+        "        \"A strategic priority that keeps delivering returns.\",\n",
+        "        \"These products make every planogram look good.\",\n",
+        "        \"Our highest NPS scores come from buyers of this category.\",\n",
+        "        \"Inventory turnover in this range is best in class.\",\n",
+        "        \"High basket attachment — customers rarely buy just one.\",\n",
+        "        \"Category leadership is clearly visible in the sales data.\",\n",
+        "        \"Priced right, built right, and always in demand.\",\n",
+        "        \"Zero complaints this quarter — quality control is excellent.\",\n",
+        "        \"Seasonal lifts are strong and predictable for this sub-category.\",\n",
+        "        \"The data backs what the floor team feels: this range is thriving.\",\n",
+        "        \"Promotional uplift is consistently strong when we feature this.\",\n",
+        "        \"Low shrinkage and high margins make this our star performer.\",\n",
+        "        \"Vendor relationship is excellent — orders arrive on time.\",\n",
+        "        \"Shelf velocity is outstanding — we rarely see excess stock.\",\n",
+        "        \"A go-to category for cross-sell opportunities.\",\n",
+        "        \"Customers actively seek this sub-category out.\",\n",
+        "        \"Strong online and in-store performance in tandem.\",\n",
+        "        \"This range punches above its weight in every metric.\",\n",
+        "        \"Customer lifetime value is highest in this category.\",\n",
+        "        \"Our data team flagged this as a priority to protect and grow.\",\n",
+        "        \"Consistently the top contributor to monthly profit targets.\",\n",
+        "    ],\n",
+        "    \"neutral\": [\n",
+        "        \"Decent products but nothing that really stands out.\",\n",
+        "        \"Sells steadily but rarely generates excitement on the floor.\",\n",
+        "        \"A serviceable category — not driving growth, not dragging it down.\",\n",
+        "        \"Average performance across the board; room for improvement.\",\n",
+        "        \"Customers buy when they need to, but won't seek it out.\",\n",
+        "        \"Margins are acceptable but could be healthier.\",\n",
+        "        \"We hold stock at standard levels — no need to over-invest.\",\n",
+        "        \"Reliable but uninspiring category for us.\",\n",
+        "        \"Turnover is consistent; just not a headline performer.\",\n",
+        "        \"Some lines do well, others just sit there.\",\n",
+        "        \"Not a category that drives footfall but serves a purpose.\",\n",
+        "        \"Could benefit from a range refresh to boost interest.\",\n",
+        "        \"Sales are predictable but plateau-ed for two quarters.\",\n",
+        "        \"Customers rate it fine — three stars is the norm.\",\n",
+        "        \"We reorder on schedule but rarely see spikes in demand.\",\n",
+        "        \"A middle-of-the-range performer in our assortment.\",\n",
+        "        \"Acceptable quality with a price point that matches.\",\n",
+        "        \"Would benefit from promotional support to lift velocity.\",\n",
+        "        \"Returns are low but so is enthusiasm.\",\n",
+        "        \"Not losing money here, but not winning either.\",\n",
+        "        \"Lacks the wow factor that drives impulse purchases.\",\n",
+        "        \"A category we maintain rather than invest in.\",\n",
+        "        \"Steady demand with flat growth trajectory.\",\n",
+        "        \"Fine as a filler category but not a focus area.\",\n",
+        "        \"Moderate satisfaction scores — room to grow.\",\n",
+        "        \"No complaints, but no praise either.\",\n",
+        "        \"Neither the best nor worst in our assortment.\",\n",
+        "        \"Metrics are in range — just not remarkable.\",\n",
+        "        \"Could be optimised further to push margins up.\",\n",
+        "        \"It does its job without causing problems.\",\n",
+        "        \"We've seen better quarters and worse quarters from this range.\",\n",
+        "        \"Shelf space allocation seems appropriate for the returns.\",\n",
+        "        \"No urgent action needed but worth monitoring.\",\n",
+        "        \"Customer feedback is uneventful — nothing to act on urgently.\",\n",
+        "        \"Average sell-through rate with seasonal fluctuation.\",\n",
+        "        \"An important category but not a strategic priority right now.\",\n",
+        "        \"Returns are in line with expectations — nothing alarming.\",\n",
+        "        \"Standard performance for a mature product category.\",\n",
+        "        \"Moderate margin contribution across the range.\",\n",
+        "        \"Sales are ticking along — no cause for alarm or celebration.\",\n",
+        "        \"Inventory sits around target levels most weeks.\",\n",
+        "        \"We manage this category on autopilot.\",\n",
+        "        \"Neither growing the basket nor shrinking it.\",\n",
+        "        \"Prices are competitive but not differentiated.\",\n",
+        "        \"A solid but unremarkable part of our assortment.\",\n",
+        "        \"Customer interest is stable, not building.\",\n",
+        "        \"We'll keep it in range until the data tells us otherwise.\",\n",
+        "        \"Balanced between fast movers and slow movers.\",\n",
+        "        \"A 'wait and see' category for next quarter.\",\n",
+        "        \"Performs as expected given market conditions.\",\n",
+        "    ],\n",
+        "    \"negative\": [\n",
+        "        \"Consistently underperforming — needs urgent review.\",\n",
+        "        \"Margins are being squeezed and sales volume isn't compensating.\",\n",
+        "        \"We're carrying too much stock in a category customers avoid.\",\n",
+        "        \"High return rate is eating into what little margin we have.\",\n",
+        "        \"Customer feedback is predominantly negative for this range.\",\n",
+        "        \"This sub-category drags down our overall category scorecard.\",\n",
+        "        \"Markdown frequency is too high — a sign of poor demand.\",\n",
+        "        \"Demand has been declining for three consecutive months.\",\n",
+        "        \"Slow sell-through is causing costly clearance cycles.\",\n",
+        "        \"The vendor quality issues are now showing up in reviews.\",\n",
+        "        \"We're losing customers to competitors in this category.\",\n",
+        "        \"Profitability is negative on several key lines.\",\n",
+        "        \"Poor basket attachment — rarely part of a multi-item purchase.\",\n",
+        "        \"Staff are reluctant to recommend this range to customers.\",\n",
+        "        \"Shrinkage and damages are above average in this sub-category.\",\n",
+        "        \"Supply chain delays have damaged customer trust in this range.\",\n",
+        "        \"We're overstocked with no clear path to clear inventory.\",\n",
+        "        \"Worst NPS scores in the store come from this category.\",\n",
+        "        \"Customers complain about value for money consistently.\",\n",
+        "        \"A legacy category that no longer meets modern customer needs.\",\n",
+        "        \"The data makes it clear: this sub-category needs rationalising.\",\n",
+        "        \"Low traffic and poor conversion make this a liability.\",\n",
+        "        \"Promotional support hasn't moved the needle at all.\",\n",
+        "        \"Price reductions have failed to stimulate demand.\",\n",
+        "        \"A drain on resources — time to consider ranging out.\",\n",
+        "        \"Multiple customers have cited quality issues in recent weeks.\",\n",
+        "        \"Inventory obsolescence risk is high in this sub-category.\",\n",
+        "        \"We need a full range review to fix this underperformance.\",\n",
+        "        \"Contribution margin is insufficient to justify space allocation.\",\n",
+        "        \"Consistent poor performance across all three KPIs: sales, margin, units.\",\n",
+        "        \"The category has no clear differentiation in our assortment.\",\n",
+        "        \"Weak competitive positioning with no obvious fix.\",\n",
+        "        \"Customer returns have doubled in the past quarter.\",\n",
+        "        \"Our worst performing lines sit in this sub-category.\",\n",
+        "        \"Brand perception damage is spilling over from this range.\",\n",
+        "        \"Order quantities have been cut as confidence has dropped.\",\n",
+        "        \"We've tried relaunching this — it hasn't worked.\",\n",
+        "        \"No seasonal uplift to speak of — flat and declining.\",\n",
+        "        \"Even discounting hasn't driven meaningful volume.\",\n",
+        "        \"The opportunity cost of this shelf space is significant.\",\n",
+        "        \"Vendor reliability has been poor — impacting availability.\",\n",
+        "        \"Category performance is a red flag in every monthly report.\",\n",
+        "        \"Stock provision risk is increasing as demand erodes.\",\n",
+        "        \"A persistent weak spot that needs a decisive decision.\",\n",
+        "        \"Write-downs in this category are becoming a regular occurrence.\",\n",
+        "        \"Customer satisfaction surveys single this out for criticism.\",\n",
+        "        \"No investment case can be made for this sub-category currently.\",\n",
+        "        \"Foot traffic drops off near this section of the store.\",\n",
+        "        \"Management escalations about this category are increasing.\",\n",
+        "        \"The exit scenario is being actively evaluated.\",\n",
+        "    ],\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fQhfVaDmuULT"
+      },
+      "source": [
+        "### *b. Generate 10 reviews per sub-category using random sampling from the corresponding 50*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "l2SRc3PjuTGM"
+      },
+      "outputs": [],
+      "source": [
+        "review_rows = []\n",
+        "for _, row in df_products.iterrows():\n",
+        "    sub_category = row['sub_category']\n",
+        "    sentiment_label = row['sentiment_label']\n",
+        "    review_pool = synthetic_reviews_by_sentiment[sentiment_label]\n",
+        "    sampled_reviews = random.sample(review_pool, 10)\n",
+        "    for review_text in sampled_reviews:\n",
+        "        review_rows.append({\n",
+        "            \"sub_category\": sub_category,\n",
+        "            \"sentiment_label\": sentiment_label,\n",
+        "            \"review_text\": review_text,\n",
+        "            \"avg_profit\": row['avg_profit'],\n",
+        "            \"popularity_score\": row['popularity_score']\n",
+        "        })"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bmJMXF-Bukdm"
+      },
+      "source": [
+        "### *c. Create the final dataframe df_reviews & save it as synthetic_superstore_reviews.csv*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZUKUqZsuumsp"
+      },
+      "outputs": [],
+      "source": [
+        "df_reviews = pd.DataFrame(review_rows)\n",
+        "df_reviews.to_csv(\"synthetic_superstore_reviews.csv\", index=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "3946e521",
+        "outputId": "bdb1ca17-6b82-46b9-e790-cd5b20312507"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Wrote synthetic_title_level_features.csv\n",
+            "✅ Wrote synthetic_monthly_revenue_series.csv\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "# ============================================================\n",
+        "# ✅ Create \"R-ready\" derived inputs (root-level files)\n",
+        "# ============================================================\n",
+        "# These two files make the R notebook robust and fast:\n",
+        "# 1) synthetic_title_level_features.csv  -> regression-ready, one row per sub-category\n",
+        "# 2) synthetic_monthly_revenue_series.csv -> forecasting-ready, one row per month\n",
+        "\n",
+        "import numpy as np\n",
+        "\n",
+        "def _safe_num(s):\n",
+        "    return pd.to_numeric(\n",
+        "        pd.Series(s).astype(str).str.replace(r\"[^0-9.]\", \"\", regex=True),\n",
+        "        errors=\"coerce\"\n",
+        "    )\n",
+        "\n",
+        "# --- Clean product metadata (avg_price/avg_profit) ---\n",
+        "df_books_r = df_products.copy()\n",
+        "if \"avg_price\" in df_books_r.columns:\n",
+        "    df_books_r[\"avg_price\"] = _safe_num(df_books_r[\"avg_price\"])\n",
+        "if \"avg_profit\" in df_books_r.columns:\n",
+        "    df_books_r[\"avg_profit\"] = _safe_num(df_books_r[\"avg_profit\"])\n",
+        "\n",
+        "df_books_r[\"sub_category\"] = df_books_r[\"sub_category\"].astype(str).str.strip()\n",
+        "\n",
+        "# --- Clean sales ---\n",
+        "df_sales_r = df_sales.copy()\n",
+        "df_sales_r[\"sub_category\"] = df_sales_r[\"sub_category\"].astype(str).str.strip()\n",
+        "df_sales_r[\"month\"] = pd.to_datetime(df_sales_r[\"month\"], errors=\"coerce\")\n",
+        "df_sales_r[\"units_sold\"] = _safe_num(df_sales_r[\"units_sold\"])\n",
+        "\n",
+        "# --- Clean reviews ---\n",
+        "df_reviews_r = df_reviews.copy()\n",
+        "df_reviews_r[\"sub_category\"] = df_reviews_r[\"sub_category\"].astype(str).str.strip()\n",
+        "df_reviews_r[\"sentiment_label\"] = df_reviews_r[\"sentiment_label\"].astype(str).str.lower().str.strip()\n",
+        "if \"avg_profit\" in df_reviews_r.columns:\n",
+        "    df_reviews_r[\"avg_profit\"] = _safe_num(df_reviews_r[\"avg_profit\"])\n",
+        "if \"popularity_score\" in df_reviews_r.columns:\n",
+        "    df_reviews_r[\"popularity_score\"] = _safe_num(df_reviews_r[\"popularity_score\"])\n",
+        "\n",
+        "# --- Sentiment shares per sub-category (from reviews) ---\n",
+        "sent_counts = (\n",
+        "    df_reviews_r.groupby([\"sub_category\", \"sentiment_label\"])\n",
+        "    .size()\n",
+        "    .unstack(fill_value=0)\n",
+        ")\n",
+        "for lab in [\"positive\", \"neutral\", \"negative\"]:\n",
+        "    if lab not in sent_counts.columns:\n",
+        "        sent_counts[lab] = 0\n",
+        "\n",
+        "sent_counts[\"total_reviews\"] = sent_counts[[\"positive\", \"neutral\", \"negative\"]].sum(axis=1)\n",
+        "den = sent_counts[\"total_reviews\"].replace(0, np.nan)\n",
+        "sent_counts[\"share_positive\"] = sent_counts[\"positive\"] / den\n",
+        "sent_counts[\"share_neutral\"]  = sent_counts[\"neutral\"]  / den\n",
+        "sent_counts[\"share_negative\"] = sent_counts[\"negative\"] / den\n",
+        "sent_counts = sent_counts.reset_index()\n",
+        "\n",
+        "# --- Sales aggregation per sub-category ---\n",
+        "sales_by_title = (\n",
+        "    df_sales_r.dropna(subset=[\"sub_category\"])\n",
+        "    .groupby(\"sub_category\", as_index=False)\n",
+        "    .agg(\n",
+        "        months_observed=(\"month\", \"nunique\"),\n",
+        "        avg_units_sold=(\"units_sold\", \"mean\"),\n",
+        "        total_units_sold=(\"units_sold\", \"sum\"),\n",
+        "    )\n",
+        ")\n",
+        "\n",
+        "# --- Sub-category-level features (join sales + products + sentiment) ---\n",
+        "df_title = (\n",
+        "    sales_by_title\n",
+        "    .merge(df_books_r[[\"sub_category\", \"avg_price\", \"avg_profit\"]], on=\"sub_category\", how=\"left\")\n",
+        "    .merge(sent_counts[[\"sub_category\", \"share_positive\", \"share_neutral\", \"share_negative\", \"total_reviews\"]],\n",
+        "           on=\"sub_category\", how=\"left\")\n",
+        ")\n",
+        "\n",
+        "df_title[\"avg_revenue\"] = df_title[\"avg_units_sold\"] * df_title[\"avg_price\"]\n",
+        "df_title[\"total_revenue\"] = df_title[\"total_units_sold\"] * df_title[\"avg_price\"]\n",
+        "\n",
+        "df_title.to_csv(\"synthetic_title_level_features.csv\", index=False)\n",
+        "print(\"✅ Wrote synthetic_title_level_features.csv\")\n",
+        "\n",
+        "# --- Monthly revenue series (proxy: units_sold * avg_price) ---\n",
+        "monthly_rev = (\n",
+        "    df_sales_r.merge(df_books_r[[\"sub_category\", \"avg_price\"]], on=\"sub_category\", how=\"left\")\n",
+        ")\n",
+        "monthly_rev[\"revenue\"] = monthly_rev[\"units_sold\"] * monthly_rev[\"avg_price\"]\n",
+        "\n",
+        "df_monthly = (\n",
+        "    monthly_rev.dropna(subset=[\"month\"])\n",
+        "    .groupby(\"month\", as_index=False)[\"revenue\"]\n",
+        "    .sum()\n",
+        "    .rename(columns={\"revenue\": \"total_revenue\"})\n",
+        "    .sort_values(\"month\")\n",
+        ")\n",
+        "# if revenue is all NA (e.g., missing price), fallback to units_sold as a teaching proxy\n",
+        "if df_monthly[\"total_revenue\"].notna().sum() == 0:\n",
+        "    df_monthly = (\n",
+        "        df_sales_r.dropna(subset=[\"month\"])\n",
+        "        .groupby(\"month\", as_index=False)[\"units_sold\"]\n",
+        "        .sum()\n",
+        "        .rename(columns={\"units_sold\": \"total_revenue\"})\n",
+        "        .sort_values(\"month\")\n",
+        "    )\n",
+        "\n",
+        "df_monthly[\"month\"] = pd.to_datetime(df_monthly[\"month\"], errors=\"coerce\").dt.strftime(\"%Y-%m-%d\")\n",
+        "df_monthly.to_csv(\"synthetic_monthly_revenue_series.csv\", index=False)\n",
+        "print(\"✅ Wrote synthetic_monthly_revenue_series.csv\")\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RYvGyVfXuo54"
+      },
+      "source": [
+        "### *d. ✋🏻🛑⛔️ View the first few lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "xfE8NMqOurKo",
+        "outputId": "0155e713-b16c-43e0-bc90-46183e48ce67"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "  sub_category sentiment_label  \\\n",
+            "0  Accessories        positive   \n",
+            "1  Accessories        positive   \n",
+            "2  Accessories        positive   \n",
+            "3  Accessories        positive   \n",
+            "4  Accessories        positive   \n",
+            "\n",
+            "                                         review_text  avg_profit  \\\n",
+            "0  Category leadership is clearly visible in the ...       55.81   \n",
+            "1  A strategic priority that keeps delivering ret...       55.81   \n",
+            "2  Year-on-year growth in this sub-category conti...       55.81   \n",
+            "3     Customers actively seek this sub-category out.       55.81   \n",
+            "4  Outstanding selection that meets every require...       55.81   \n",
+            "\n",
+            "   popularity_score  \n",
+            "0                 4  \n",
+            "1                 4  \n",
+            "2                 4  \n",
+            "3                 4  \n",
+            "4                 4  \n"
+          ]
+        }
+      ],
+      "source": [
+        "print(df_reviews.head())"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}