chore: refactor data storage folder structure

Author: lpm0073

.gitignore

@@ -1,5 +1,4 @@
-jupyter/house_prices
-jupyter/support_tickets
+jupyter/data/
 
 
 # application data

jupyter/k-means-it-support-tickets.ipynb

@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [
     {
@@ -102,10 +102,10 @@
    "source": [
     "# Download the IT Support Tickets dataset from Kaggle (only if not already downloaded)\n",
     "# Check if the support_tickets directory already exists\n",
-    "if not os.path.exists('support_tickets'):\n",
+    "if not os.path.exists('data/support_tickets'):\n",
     "    print(\"\\nDownloading dataset...\")\n",
     "    !kaggle datasets download -d tobiasbueck/multilingual-customer-support-tickets\n",
-    "    !unzip -q multilingual-customer-support-tickets.zip -d support_tickets\n",
+    "    !unzip -q multilingual-customer-support-tickets.zip -d data/support_tickets\n",
     "    print(\"Dataset downloaded and extracted successfully!\")\n",
     "else:\n",
     "    print(\"\\nDataset already exists in 'support_tickets' directory. Skipping download.\")"
@@ -138,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
@@ -325,14 +325,14 @@
        "4      Feedback   Tech Support           NaN   NaN   NaN   NaN  "
       ]
      },
-     "execution_count": 27,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# Load the IT Support Tickets dataset from local file\n",
-    "df = pd.read_csv('support_tickets/aa_dataset-tickets-multi-lang-5-2-50-version.csv')\n",
+    "df = pd.read_csv('data/support_tickets/aa_dataset-tickets-multi-lang-5-2-50-version.csv')\n",
     "print(f\"Dataset shape: {df.shape}\")\n",
     "print(f\"Columns: {df.columns.tolist()}\")\n",
     "df.head()"