Upload datacreation.ipynb

datacreation.ipynb

@@ -20,13 +20,13 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": 11,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "f48c8f8c",
-        "outputId": "13d0dd5e-82c6-489f-b1f0-e970186a4eb7"
+        "outputId": "f1a76cb9-ce00-47c2-df85-094eb6e9a141"
       },
       "outputs": [
         {
@@ -46,8 +46,8 @@
             "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: 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",
@@ -85,7 +85,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": 12,
       "metadata": {
         "id": "91d52125"
       },
@@ -113,7 +113,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 3,
+      "execution_count": null,
       "metadata": {
         "id": "xqO5Y3dnYhxt"
       },
@@ -145,7 +145,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": null,
       "metadata": {
         "id": "l5FkkNhUYTHh"
       },
@@ -163,7 +163,52 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 5,
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "df_books = pd.DataFrame({\n",
+        "    \"title\": [\"Book A\", \"Book B\", \"Book C\"],\n",
+        "    \"price\": [10.99, 12.50, 8.99],\n",
+        "    \"rating\": [4, 5, 3]\n",
+        "})"
+      ],
+      "metadata": {
+        "id": "j_U7YrVrrN3n"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_books.to_csv(\"books_data.csv\", index=False)"
+      ],
+      "metadata": {
+        "id": "KJ-lE6ktrQX9"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_reviews = pd.DataFrame({\n",
+        "    \"title\": [\"Book A\", \"Book B\"],\n",
+        "    \"review\": [\"Great book\", \"Okay book\"],\n",
+        "    \"sentiment_label\": [\"positive\", \"neutral\"]\n",
+        "})\n",
+        "\n",
+        "df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
+      ],
+      "metadata": {
+        "id": "AqZUPGJtrSET"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "id": "lC1U_YHtZifh"
       },
@@ -187,180 +232,11 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 6,
+      "execution_count": null,
       "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 206
-        },
-        "id": "O_wIvTxYZqCK",
-        "outputId": "349b36b0-c008-4fd5-d4a4-dba38ae18337"
+        "id": "O_wIvTxYZqCK"
       },
-      "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
-        }
-      ],
+      "outputs": [],
       "source": []
     },
     {
@@ -383,7 +259,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 7,
+      "execution_count": null,
       "metadata": {
         "id": "-gPXGcRPuV_9"
       },
@@ -410,7 +286,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 8,
+      "execution_count": null,
       "metadata": {
         "id": "mnd5hdAbaNjz"
       },
@@ -433,7 +309,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 9,
+      "execution_count": null,
       "metadata": {
         "id": "V-G3OCUCgR07"
       },
@@ -451,7 +327,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 10,
+      "execution_count": null,
       "metadata": {
         "id": "kUtWmr8maZLZ"
       },
@@ -477,7 +353,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 11,
+      "execution_count": null,
       "metadata": {
         "id": "tafQj8_7gYCG"
       },
@@ -504,7 +380,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 12,
+      "execution_count": null,
       "metadata": {
         "id": "qkVhYPXGbgEn"
       },
@@ -541,7 +417,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 13,
+      "execution_count": null,
       "metadata": {
         "id": "SlJ24AUafoDB"
       },
@@ -570,7 +446,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 14,
+      "execution_count": null,
       "metadata": {
         "id": "wcN6gtiZg-ws"
       },
@@ -588,28 +464,11 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 15,
+      "execution_count": null,
       "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "MzbZvLcAhGaH",
-        "outputId": "c692bb04-7263-4115-a2ba-c72fe0180722"
+        "id": "MzbZvLcAhGaH"
       },
-      "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"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
         "\n",
@@ -636,7 +495,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 16,
+      "execution_count": null,
       "metadata": {
         "id": "b3cd2a50"
       },
@@ -672,7 +531,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 17,
+      "execution_count": null,
       "metadata": {
         "id": "l2SRc3PjuTGM"
       },
@@ -705,7 +564,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 18,
+      "execution_count": null,
       "metadata": {
         "id": "ZUKUqZsuumsp"
       },
@@ -726,24 +585,11 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 19,
+      "execution_count": null,
       "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "3946e521",
-        "outputId": "514d7bef-0488-4933-b03c-953b9e8a7f66"
+        "id": "3946e521"
       },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "✅ Wrote synthetic_title_level_features.csv\n",
-            "✅ Wrote synthetic_monthly_revenue_series.csv\n"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "\n",
@@ -858,35 +704,11 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 20,
+      "execution_count": null,
       "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "xfE8NMqOurKo",
-        "outputId": "191730ba-d5e2-4df7-97d2-99feb0b704af"
+        "id": "xfE8NMqOurKo"
       },
-      "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"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": []
     }
   ],