Delete datacreation.ipynb

datacreation.ipynb

@@ -1,931 +0,0 @@
-{
-  "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": 1,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "f48c8f8c",
-        "outputId": "13d0dd5e-82c6-489f-b1f0-e970186a4eb7"
-      },
-      "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) (4.61.1)\n",
-            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.4.9)\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.** ⛏ Web-scrape all book titles, prices, and ratings from books.toscrape.com"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0IWuNpxxYDJF"
-      },
-      "source": [
-        "### *a. Initial setup*\n",
-        "Define the base url of the website you will scrape as well as how and what you will scrape"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 2,
-      "metadata": {
-        "id": "91d52125"
-      },
-      "outputs": [],
-      "source": [
-        "import requests\n",
-        "from bs4 import BeautifulSoup\n",
-        "import pandas as pd\n",
-        "import time\n",
-        "\n",
-        "base_url = \"https://books.toscrape.com/catalogue/page-{}.html\"\n",
-        "headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
-        "\n",
-        "titles, prices, ratings = [], [], []"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "oCdTsin2Yfp3"
-      },
-      "source": [
-        "### *b. Fill titles, prices, and ratings from the web pages*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {
-        "id": "xqO5Y3dnYhxt"
-      },
-      "outputs": [],
-      "source": [
-        "# Loop through all 50 pages\n",
-        "for page in range(1, 51):\n",
-        "    url = base_url.format(page)\n",
-        "    response = requests.get(url, headers=headers)\n",
-        "    soup = BeautifulSoup(response.content, \"html.parser\")\n",
-        "    books = soup.find_all(\"article\", class_=\"product_pod\")\n",
-        "\n",
-        "    for book in books:\n",
-        "        titles.append(book.h3.a[\"title\"])\n",
-        "        prices.append(float(book.find(\"p\", class_=\"price_color\").text[1:]))\n",
-        "        ratings.append(book.p.get(\"class\")[1])\n",
-        "\n",
-        "    time.sleep(0.5)  # polite scraping delay"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "T0TOeRC4Yrnn"
-      },
-      "source": [
-        "### *c. ✋🏻🛑⛔️ Create a dataframe df_books that contains the now complete \"title\", \"price\", and \"rating\" objects*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 4,
-      "metadata": {
-        "id": "l5FkkNhUYTHh"
-      },
-      "outputs": [],
-      "source": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "duI5dv3CZYvF"
-      },
-      "source": [
-        "### *d. Save web-scraped dataframe either as a CSV or Excel file*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 5,
-      "metadata": {
-        "id": "lC1U_YHtZifh"
-      },
-      "outputs": [],
-      "source": [
-        "# 💾 Save to CSV\n",
-        "df_books.to_csv(\"books_data.csv\", index=False)\n",
-        "\n",
-        "# 💾 Or save to Excel\n",
-        "# df_books.to_excel(\"books_data.xlsx\", index=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qMjRKMBQZlJi"
-      },
-      "source": [
-        "### *e. ✋🏻🛑⛔️ View first fiew lines*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 6,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 206
-        },
-        "id": "O_wIvTxYZqCK",
-        "outputId": "349b36b0-c008-4fd5-d4a4-dba38ae18337"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                                   title  price rating\n",
-              "0                   A Light in the Attic  51.77  Three\n",
-              "1                     Tipping the Velvet  53.74    One\n",
-              "2                             Soumission  50.10    One\n",
-              "3                          Sharp Objects  47.82   Four\n",
-              "4  Sapiens: A Brief History of Humankind  54.23   Five"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-04c87660-4415-45e9-ad3b-3fa19d9402c2\" 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>title</th>\n",
-              "      <th>price</th>\n",
-              "      <th>rating</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>A Light in the Attic</td>\n",
-              "      <td>51.77</td>\n",
-              "      <td>Three</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>Tipping the Velvet</td>\n",
-              "      <td>53.74</td>\n",
-              "      <td>One</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>Soumission</td>\n",
-              "      <td>50.10</td>\n",
-              "      <td>One</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>Sharp Objects</td>\n",
-              "      <td>47.82</td>\n",
-              "      <td>Four</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>Sapiens: A Brief History of Humankind</td>\n",
-              "      <td>54.23</td>\n",
-              "      <td>Five</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-04c87660-4415-45e9-ad3b-3fa19d9402c2')\"\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-04c87660-4415-45e9-ad3b-3fa19d9402c2 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-04c87660-4415-45e9-ad3b-3fa19d9402c2');\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_books",
-              "summary": "{\n  \"name\": \"df_books\",\n  \"rows\": 1000,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 999,\n        \"samples\": [\n          \"The Grownup\",\n          \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n          \"Ayumi's Violin\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14.446689669952772,\n        \"min\": 10.0,\n        \"max\": 59.99,\n        \"num_unique_values\": 903,\n        \"samples\": [\n          19.73,\n          55.65,\n          46.31\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rating\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"One\",\n          \"Two\",\n          \"Four\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
-            }
-          },
-          "metadata": {},
-          "execution_count": 6
-        }
-      ],
-      "source": []
-    },
-    {
-      "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": 7,
-      "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 rating (with some randomness) with a generate_popularity_score function*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 8,
-      "metadata": {
-        "id": "mnd5hdAbaNjz"
-      },
-      "outputs": [],
-      "source": [
-        "def generate_popularity_score(rating):\n",
-        "    base = {\"One\": 2, \"Two\": 3, \"Three\": 3, \"Four\": 4, \"Five\": 4}.get(rating, 3)\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 \"rating\"*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 9,
-      "metadata": {
-        "id": "V-G3OCUCgR07"
-      },
-      "outputs": [],
-      "source": []
-    },
-    {
-      "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": 10,
-      "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": 11,
-      "metadata": {
-        "id": "tafQj8_7gYCG"
-      },
-      "outputs": [],
-      "source": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "T8AdKkmASq9a"
-      },
-      "source": [
-        "## **4.** 📈 Generate synthetic book 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": 12,
-      "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": 13,
-      "metadata": {
-        "id": "SlJ24AUafoDB"
-      },
-      "outputs": [],
-      "source": [
-        "sales_data = []\n",
-        "for _, row in df_books.iterrows():\n",
-        "    records = generate_sales_profile(row[\"sentiment_label\"])\n",
-        "    for month, units in records:\n",
-        "        sales_data.append({\n",
-        "            \"title\": row[\"title\"],\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": 14,
-      "metadata": {
-        "id": "wcN6gtiZg-ws"
-      },
-      "outputs": [],
-      "source": []
-    },
-    {
-      "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": 15,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "MzbZvLcAhGaH",
-        "outputId": "c692bb04-7263-4115-a2ba-c72fe0180722"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "                  title    month  units_sold sentiment_label\n",
-            "0  A Light in the Attic  2024-08         100         neutral\n",
-            "1  A Light in the Attic  2024-09         109         neutral\n",
-            "2  A Light in the Attic  2024-10         102         neutral\n",
-            "3  A Light in the Attic  2024-11         107         neutral\n",
-            "4  A Light in the Attic  2024-12         108         neutral\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 book review texts for the sentiment labels \"positive\", \"neutral\", and \"negative\" called synthetic_reviews_by_sentiment*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 16,
-      "metadata": {
-        "id": "b3cd2a50"
-      },
-      "outputs": [],
-      "source": [
-        "synthetic_reviews_by_sentiment = {\n",
-        "    \"positive\": [\n",
-        "        \"A compelling and heartwarming read that stayed with me long after I finished.\",\n",
-        "        \"Brilliantly written! The characters were unforgettable and the plot was engaging.\",\n",
-        "        \"One of the best books I've read this year — inspiring and emotionally rich.\",\n",
-        "    ],\n",
-        "    \"neutral\": [\n",
-        "        \"An average book — not great, but not bad either.\",\n",
-        "        \"Some parts really stood out, others felt a bit flat.\",\n",
-        "        \"It was okay overall. A decent way to pass the time.\",\n",
-        "    ],\n",
-        "    \"negative\": [\n",
-        "        \"I struggled to get through this one — it just didn’t grab me.\",\n",
-        "        \"The plot was confusing and the characters felt underdeveloped.\",\n",
-        "        \"Disappointing. I had high hopes, but they weren't met.\",\n",
-        "    ]\n",
-        "}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fQhfVaDmuULT"
-      },
-      "source": [
-        "### *b. Generate 10 reviews per book using random sampling from the corresponding 50*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 17,
-      "metadata": {
-        "id": "l2SRc3PjuTGM"
-      },
-      "outputs": [],
-      "source": [
-        "review_rows = []\n",
-        "for _, row in df_books.iterrows():\n",
-        "    title = row['title']\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",
-        "            \"title\": title,\n",
-        "            \"sentiment_label\": sentiment_label,\n",
-        "            \"review_text\": review_text,\n",
-        "            \"rating\": row['rating'],\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_book_reviews.csv*"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 18,
-      "metadata": {
-        "id": "ZUKUqZsuumsp"
-      },
-      "outputs": [],
-      "source": [
-        "df_reviews = pd.DataFrame(review_rows)\n",
-        "df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### *c. inputs for R*"
-      ],
-      "metadata": {
-        "id": "_602pYUS3gY5"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 19,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "3946e521",
-        "outputId": "514d7bef-0488-4933-b03c-953b9e8a7f66"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "✅ Wrote synthetic_title_level_features.csv\n",
-            "✅ Wrote synthetic_monthly_revenue_series.csv\n"
-          ]
-        }
-      ],
-      "source": [
-        "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 book metadata (price/rating) ---\n",
-        "df_books_r = df_books.copy()\n",
-        "if \"price\" in df_books_r.columns:\n",
-        "    df_books_r[\"price\"] = _safe_num(df_books_r[\"price\"])\n",
-        "if \"rating\" in df_books_r.columns:\n",
-        "    df_books_r[\"rating\"] = _safe_num(df_books_r[\"rating\"])\n",
-        "\n",
-        "df_books_r[\"title\"] = df_books_r[\"title\"].astype(str).str.strip()\n",
-        "\n",
-        "# --- Clean sales ---\n",
-        "df_sales_r = df_sales.copy()\n",
-        "df_sales_r[\"title\"] = df_sales_r[\"title\"].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[\"title\"] = df_reviews_r[\"title\"].astype(str).str.strip()\n",
-        "df_reviews_r[\"sentiment_label\"] = df_reviews_r[\"sentiment_label\"].astype(str).str.lower().str.strip()\n",
-        "if \"rating\" in df_reviews_r.columns:\n",
-        "    df_reviews_r[\"rating\"] = _safe_num(df_reviews_r[\"rating\"])\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 title (from reviews) ---\n",
-        "sent_counts = (\n",
-        "    df_reviews_r.groupby([\"title\", \"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 title ---\n",
-        "sales_by_title = (\n",
-        "    df_sales_r.dropna(subset=[\"title\"])\n",
-        "    .groupby(\"title\", 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",
-        "# --- Title-level features (join sales + books + sentiment) ---\n",
-        "df_title = (\n",
-        "    sales_by_title\n",
-        "    .merge(df_books_r[[\"title\", \"price\", \"rating\"]], on=\"title\", how=\"left\")\n",
-        "    .merge(sent_counts[[\"title\", \"share_positive\", \"share_neutral\", \"share_negative\", \"total_reviews\"]],\n",
-        "           on=\"title\", how=\"left\")\n",
-        ")\n",
-        "\n",
-        "df_title[\"avg_revenue\"] = df_title[\"avg_units_sold\"] * df_title[\"price\"]\n",
-        "df_title[\"total_revenue\"] = df_title[\"total_units_sold\"] * df_title[\"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 * price) ---\n",
-        "monthly_rev = (\n",
-        "    df_sales_r.merge(df_books_r[[\"title\", \"price\"]], on=\"title\", how=\"left\")\n",
-        ")\n",
-        "monthly_rev[\"revenue\"] = monthly_rev[\"units_sold\"] * monthly_rev[\"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": 20,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "xfE8NMqOurKo",
-        "outputId": "191730ba-d5e2-4df7-97d2-99feb0b704af"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "                  title sentiment_label  \\\n",
-            "0  A Light in the Attic         neutral   \n",
-            "1  A Light in the Attic         neutral   \n",
-            "2  A Light in the Attic         neutral   \n",
-            "3  A Light in the Attic         neutral   \n",
-            "4  A Light in the Attic         neutral   \n",
-            "\n",
-            "                                         review_text rating  popularity_score  \n",
-            "0                Had potential that went unrealized.  Three                 3  \n",
-            "1      The themes were solid, but not well explored.  Three                 3  \n",
-            "2             It simply lacked that emotional punch.  Three                 3  \n",
-            "3  Serviceable but not something I'd go out of my...  Three                 3  \n",
-            "4                   Standard fare with some promise.  Three                 3  \n"
-          ]
-        }
-      ],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "collapsed_sections": [
-        "jpASMyIQMaAq",
-        "lquNYCbfL9IM",
-        "0IWuNpxxYDJF",
-        "oCdTsin2Yfp3",
-        "T0TOeRC4Yrnn",
-        "duI5dv3CZYvF",
-        "qMjRKMBQZlJi",
-        "p-1Pr2szaqLk",
-        "SIaJUGIpaH4V",
-        "pY4yCoIuaQqp",
-        "n4-TaNTFgPak",
-        "HnngRNTgacYt",
-        "HF9F9HIzgT7Z",
-        "T8AdKkmASq9a",
-        "OhXbdGD5fH0c",
-        "L2ak1HlcgoTe",
-        "4IXZKcCSgxnq",
-        "EhIjz9WohAmZ",
-        "Gi4y9M9KuDWx",
-        "fQhfVaDmuULT",
-        "bmJMXF-Bukdm",
-        "RYvGyVfXuo54"
-      ],
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}