Add utility to prevent double execution of certain cells (#437)

Author: rasbt

ch06/01_main-chapter-code/ch06.ipynb

@@ -79,6 +79,28 @@
     "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/ch06_compressed/chapter-overview.webp\" width=500px>"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "946c3e56-b04b-4b0f-b35f-b485ce5b28df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Utility to prevent certain cells from being executed twice\n",
+    "\n",
+    "from IPython.core.magic import register_line_cell_magic\n",
+    "\n",
+    "executed_cells = set()\n",
+    "\n",
+    "@register_line_cell_magic\n",
+    "def run_once(line, cell):\n",
+    "    if line not in executed_cells:\n",
+    "        get_ipython().run_cell(cell)\n",
+    "        executed_cells.add(line)\n",
+    "    else:\n",
+    "        print(f\"Cell '{line}' has already been executed.\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "3a84cf35-b37f-4c15-8972-dfafc9fadc1c",
@@ -167,7 +189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "def7c09b-af9c-4216-90ce-5e67aed1065c",
    "metadata": {
     "colab": {
@@ -181,7 +203,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "File downloaded and saved as sms_spam_collection/SMSSpamCollection.tsv\n"
+      "sms_spam_collection/SMSSpamCollection.tsv already exists. Skipping download and extraction.\n"
      ]
     }
    ],
@@ -230,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "da0ed4da-ac31-4e4d-8bdd-2153be4656a4",
    "metadata": {
     "colab": {
@@ -344,7 +366,7 @@
        "[5572 rows x 2 columns]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -368,7 +390,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "495a5280-9d7c-41d4-9719-64ab99056d4c",
    "metadata": {
     "colab": {
@@ -406,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "7be4a0a2-9704-4a96-b38f-240339818688",
    "metadata": {
     "colab": {
@@ -428,6 +450,9 @@
     }
    ],
    "source": [
+    "%%run_once balance_df\n",
+    "\n",
+    "\n",
     "def create_balanced_dataset(df):\n",
     "    \n",
     "    # Count the instances of \"spam\"\n",
@@ -441,6 +466,7 @@
     "\n",
     "    return balanced_df\n",
     "\n",
+    "\n",
     "balanced_df = create_balanced_dataset(df)\n",
     "print(balanced_df[\"Label\"].value_counts())"
    ]
@@ -457,14 +483,133 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "c1b10c3d-5d57-42d0-8de8-cf80a06f5ffd",
    "metadata": {
     "id": "c1b10c3d-5d57-42d0-8de8-cf80a06f5ffd"
    },
    "outputs": [],
    "source": [
-    "balanced_df[\"Label\"] = balanced_df[\"Label\"].map({\"ham\": 0, \"spam\": 1})"
+    "%%run_once label_mapping\n",
+    "balanced_df[\"Label\"] = balanced_df[\"Label\"].map({\"ham\": 0, \"spam\": 1})    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e6f7f062-ef4e-4020-8275-71990cab4414",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Label</th>\n",
+       "      <th>Text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>4307</th>\n",
+       "      <td>0</td>\n",
+       "      <td>Awww dat is sweet! We can think of something t...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4138</th>\n",
+       "      <td>0</td>\n",
+       "      <td>Just got to  &amp;lt;#&amp;gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4831</th>\n",
+       "      <td>0</td>\n",
+       "      <td>The word \"Checkmate\" in chess comes from the P...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4461</th>\n",
+       "      <td>0</td>\n",
+       "      <td>This is wishing you a great day. Moji told me ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5440</th>\n",
+       "      <td>0</td>\n",
+       "      <td>Thank you. do you generally date the brothas?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5537</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Want explicit SEX in 30 secs? Ring 02073162414...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5540</th>\n",
+       "      <td>1</td>\n",
+       "      <td>ASKED 3MOBILE IF 0870 CHATLINES INCLU IN FREE ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5547</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Had your contract mobile 11 Mnths? Latest Moto...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5566</th>\n",
+       "      <td>1</td>\n",
+       "      <td>REMINDER FROM O2: To get 2.50 pounds free call...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5567</th>\n",
+       "      <td>1</td>\n",
+       "      <td>This is the 2nd time we have tried 2 contact u...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1494 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Label                                               Text\n",
+       "4307      0  Awww dat is sweet! We can think of something t...\n",
+       "4138      0                             Just got to  &lt;#&gt;\n",
+       "4831      0  The word \"Checkmate\" in chess comes from the P...\n",
+       "4461      0  This is wishing you a great day. Moji told me ...\n",
+       "5440      0      Thank you. do you generally date the brothas?\n",
+       "...     ...                                                ...\n",
+       "5537      1  Want explicit SEX in 30 secs? Ring 02073162414...\n",
+       "5540      1  ASKED 3MOBILE IF 0870 CHATLINES INCLU IN FREE ...\n",
+       "5547      1  Had your contract mobile 11 Mnths? Latest Moto...\n",
+       "5566      1  REMINDER FROM O2: To get 2.50 pounds free call...\n",
+       "5567      1  This is the 2nd time we have tried 2 contact u...\n",
+       "\n",
+       "[1494 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "balanced_df"
    ]
   },
   {