Upload datacreation.ipynb

datacreation.ipynb

@@ -20,13 +20,13 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 11,
+      "execution_count": 81,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "f48c8f8c",
-        "outputId": "f1a76cb9-ce00-47c2-df85-094eb6e9a141"
+        "outputId": "d0cf9eb7-407a-4275-a05d-a6016d1d3277"
       },
       "outputs": [
         {
@@ -85,7 +85,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 12,
+      "execution_count": 82,
       "metadata": {
         "id": "91d52125"
       },
@@ -113,7 +113,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 83,
       "metadata": {
         "id": "xqO5Y3dnYhxt"
       },
@@ -145,7 +145,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 83,
       "metadata": {
         "id": "l5FkkNhUYTHh"
       },
@@ -175,7 +175,7 @@
       "metadata": {
         "id": "j_U7YrVrrN3n"
       },
-      "execution_count": null,
+      "execution_count": 84,
       "outputs": []
     },
     {
@@ -186,7 +186,7 @@
       "metadata": {
         "id": "KJ-lE6ktrQX9"
       },
-      "execution_count": null,
+      "execution_count": 85,
       "outputs": []
     },
     {
@@ -203,12 +203,12 @@
       "metadata": {
         "id": "AqZUPGJtrSET"
       },
-      "execution_count": null,
+      "execution_count": 86,
       "outputs": []
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 87,
       "metadata": {
         "id": "lC1U_YHtZifh"
       },
@@ -232,7 +232,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 87,
       "metadata": {
         "id": "O_wIvTxYZqCK"
       },
@@ -259,7 +259,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 88,
       "metadata": {
         "id": "-gPXGcRPuV_9"
       },
@@ -286,7 +286,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 89,
       "metadata": {
         "id": "mnd5hdAbaNjz"
       },
@@ -309,7 +309,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 89,
       "metadata": {
         "id": "V-G3OCUCgR07"
       },
@@ -327,7 +327,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 90,
       "metadata": {
         "id": "kUtWmr8maZLZ"
       },
@@ -353,7 +353,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 90,
       "metadata": {
         "id": "tafQj8_7gYCG"
       },
@@ -380,7 +380,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 91,
       "metadata": {
         "id": "qkVhYPXGbgEn"
       },
@@ -417,7 +417,38 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "if \"sentiment_label\" not in df_books.columns:\n",
+        "    labels = [\"positive\", \"neutral\", \"negative\"]\n",
+        "    df_books[\"sentiment_label\"] = np.random.choice(labels, size=len(df_books))\n",
+        ""
+      ],
+      "metadata": {
+        "id": "mNYR6hMcs1P9"
+      },
+      "execution_count": 92,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "if \"sentiment_label\" not in df_books.columns:\n",
+        "    labels = [\"positive\", \"neutral\", \"negative\"]\n",
+        "    df_books[\"sentiment_label\"] = np.random.choice(labels, size=len(df_books))"
+      ],
+      "metadata": {
+        "id": "crhSJ861s27Q"
+      },
+      "execution_count": 93,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 94,
       "metadata": {
         "id": "SlJ24AUafoDB"
       },
@@ -446,7 +477,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 94,
       "metadata": {
         "id": "wcN6gtiZg-ws"
       },
@@ -464,11 +495,154 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "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",
+        "        })"
+      ],
       "metadata": {
-        "id": "MzbZvLcAhGaH"
+        "id": "R0XK8LjDtXCe"
       },
-      "outputs": [],
+      "execution_count": 95,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_sales = pd.DataFrame(sales_data)\n",
+        "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
+        "print(df_sales.head())"
+      ],
+      "metadata": {
+        "id": "f5qTbY8itZPE",
+        "outputId": "187b94f4-5c87-43b1-f69b-fe1e6ae7d433",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": 96,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "    title    month  units_sold sentiment_label\n",
+            "0  Book A  2024-10          49        negative\n",
+            "1  Book A  2024-11          56        negative\n",
+            "2  Book A  2024-12          71        negative\n",
+            "3  Book A  2025-01          64        negative\n",
+            "4  Book A  2025-02          61        negative\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "if \"sentiment_label\" not in df_books.columns:\n",
+        "    labels = [\"positive\", \"neutral\", \"negative\"]\n",
+        "    df_books[\"sentiment_label\"] = np.random.choice(labels, size=len(df_books))"
+      ],
+      "metadata": {
+        "id": "5ebVuc_KtZ_O"
+      },
+      "execution_count": 97,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "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",
+        "        })"
+      ],
+      "metadata": {
+        "id": "VXxCmPTatcug"
+      },
+      "execution_count": 98,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_sales = pd.DataFrame(sales_data)\n",
+        "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
+        "print(\"✅ synthetic_sales_data.csv created\")\n",
+        "print(df_sales.head())"
+      ],
+      "metadata": {
+        "id": "l3fLhuNVte15",
+        "outputId": "b61c06a4-a534-4f4d-e5f6-a348741f7980",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": 99,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ synthetic_sales_data.csv created\n",
+            "    title    month  units_sold sentiment_label\n",
+            "0  Book A  2024-10          31        negative\n",
+            "1  Book A  2024-11          26        negative\n",
+            "2  Book A  2024-12          22        negative\n",
+            "3  Book A  2025-01          34        negative\n",
+            "4  Book A  2025-02          24        negative\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "B3owNJclthJm"
+      },
+      "execution_count": 99,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 100,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "MzbZvLcAhGaH",
+        "outputId": "4858910f-6703-4d9c-bdda-76cf5cfef58e"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "    title    month  units_sold sentiment_label\n",
+            "0  Book A  2024-10          31        negative\n",
+            "1  Book A  2024-11          26        negative\n",
+            "2  Book A  2024-12          22        negative\n",
+            "3  Book A  2025-01          34        negative\n",
+            "4  Book A  2025-02          24        negative\n"
+          ]
+        }
+      ],
       "source": [
         "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
         "\n",
@@ -495,7 +669,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 101,
       "metadata": {
         "id": "b3cd2a50"
       },
@@ -531,18 +705,103 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "source": [
+        "random.choices(review_pool, k=10)"
+      ],
       "metadata": {
-        "id": "l2SRc3PjuTGM"
+        "id": "inTizEVgvS2I",
+        "outputId": "5692f777-aeda-4452-8f42-0db5ff094ddf",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
       },
-      "outputs": [],
+      "execution_count": 102,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[\"Disappointing. I had high hopes, but they weren't met.\",\n",
+              " \"Disappointing. I had high hopes, but they weren't met.\",\n",
+              " 'I struggled to get through this one — it just didn’t grab me.',\n",
+              " 'I struggled to get through this one — it just didn’t grab me.',\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",
+              " 'I struggled to get through this one — it just didn’t grab me.',\n",
+              " 'I struggled to get through this one — it just didn’t grab me.',\n",
+              " \"Disappointing. I had high hopes, but they weren't met.\"]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 102
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "if \"popularity_score\" not in df_books.columns:\n",
+        "    df_books[\"popularity_score\"] = np.random.randint(1, 101, size=len(df_books))"
+      ],
+      "metadata": {
+        "id": "wphd_MYCvg4R"
+      },
+      "execution_count": 103,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import random\n",
+        "\n",
+        "if \"popularity_score\" not in df_books.columns:\n",
+        "    df_books[\"popularity_score\"] = np.random.randint(1, 101, size=len(df_books))\n",
+        "\n",
+        "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.choices(review_pool, k=10)\n",
+        "\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",
+        "        })"
+      ],
+      "metadata": {
+        "id": "fBFOohZ2vhyT"
+      },
+      "execution_count": 104,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "OJsnG5h-vkGN"
+      },
+      "execution_count": 104,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
       "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",
+        "\n",
+        "    sampled_reviews = random.choices(review_pool, k=10)  # ✅ FIX HERE\n",
+        "\n",
         "    for review_text in sampled_reviews:\n",
         "        review_rows.append({\n",
         "            \"title\": title,\n",
@@ -551,7 +810,12 @@
         "            \"rating\": row['rating'],\n",
         "            \"popularity_score\": row['popularity_score']\n",
         "        })"
-      ]
+      ],
+      "metadata": {
+        "id": "yHoawsbnvYIV"
+      },
+      "execution_count": 105,
+      "outputs": []
     },
     {
       "cell_type": "markdown",
@@ -564,7 +828,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 106,
       "metadata": {
         "id": "ZUKUqZsuumsp"
       },
@@ -585,11 +849,24 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 107,
       "metadata": {
-        "id": "3946e521"
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "3946e521",
+        "outputId": "bb81b360-789d-409e-f3f1-f9445656af2d"
       },
-      "outputs": [],
+      "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",
@@ -704,7 +981,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 107,
       "metadata": {
         "id": "xfE8NMqOurKo"
       },