chore: fresh deployment to aryan012234/safetyspeech-app

notebooks/01_data_exploration.ipynb

@@ -11,33 +11,29 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "import os\n",
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')\n",
-    "\n",
-    "sns.set_theme(style='darkgrid', palette='Set2')\n",
-    "plt.rcParams['figure.figsize'] = (12, 5)\n",
-    "print('Setup complete.')"
+    "## 1. Load External Datasets"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": ["## 1. Load External Datasets"]
-  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'os' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mNameError\u001b[39m                                 Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 3\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;66;03m# Load Jigsaw dataset\u001b[39;00m\n\u001b[32m      2\u001b[39m jigsaw_path = \u001b[33m'\u001b[39m\u001b[33m../data/external/jigsaw_toxic.csv\u001b[39m\u001b[33m'\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m3\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mos\u001b[49m.path.exists(jigsaw_path):\n\u001b[32m      4\u001b[39m     jigsaw = pd.read_csv(jigsaw_path)\n\u001b[32m      5\u001b[39m     \u001b[38;5;28mprint\u001b[39m(\u001b[33mf\u001b[39m\u001b[33m'\u001b[39m\u001b[33mJigsaw: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(jigsaw)\u001b[38;5;132;01m:\u001b[39;00m\u001b[33m,\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m rows, columns: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mjigsaw.columns.tolist()\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m'\u001b[39m)\n",
+      "\u001b[31mNameError\u001b[39m: name 'os' is not defined"
+     ]
+    }
+   ],
    "source": [
     "# Load Jigsaw dataset\n",
     "jigsaw_path = '../data/external/jigsaw_toxic.csv'\n",
@@ -85,7 +81,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": ["## 2. Label Distribution Analysis"]
+   "source": [
+    "## 2. Label Distribution Analysis"
+   ]
   },
   {
    "cell_type": "code",
@@ -124,7 +122,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": ["## 3. Text Length Analysis"]
+   "source": [
+    "## 3. Text Length Analysis"
+   ]
   },
   {
    "cell_type": "code",
@@ -154,7 +154,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": ["## 4. Sample Texts per Category"]
+   "source": [
+    "## 4. Sample Texts per Category"
+   ]
   },
   {
    "cell_type": "code",
@@ -173,8 +175,23 @@
   }
  ],
  "metadata": {
-  "kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"},
-  "language_info": {"name": "python", "version": "3.10.0"}
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 4