Update 2-Working-With-Data/08-data-preparation/notebook.ipynb

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

2-Working-With-Data/08-data-preparation/notebook.ipynb

@@ -3997,10 +3997,11 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from rapidfuzz import process, fuzz\n",
+        "try:\n",
+        "    from rapidfuzz import process, fuzz\n",
         "\n",
-        "# Function to find potential duplicates\n",
-        "def find_near_duplicates(df, column, threshold=90):\n",
+        "    # Function to find potential duplicates\n",
+        "    def find_near_duplicates(df, column, threshold=90):\n",
         "        \"\"\"\n",
         "        Find near-duplicate entries in a column using fuzzy matching.\n",
         "        \n",
@@ -4029,17 +4030,19 @@
         "        \n",
         "        return duplicate_groups\n",
         "\n",
-        "# Find near-duplicate names\n",
-        "duplicate_groups = find_near_duplicates(dirty_data, 'name', threshold=90)\n",
+        "    # Find near-duplicate names\n",
+        "    duplicate_groups = find_near_duplicates(dirty_data, 'name', threshold=90)\n",
         "\n",
-        "print(\"Potential duplicate groups:\")\n",
-        "for i, group in enumerate(duplicate_groups, 1):\n",
+        "    print(\"Potential duplicate groups:\")\n",
+        "    for i, group in enumerate(duplicate_groups, 1):\n",
         "        print(f\"\\nGroup {i}:\")\n",
         "        for name in group:\n",
         "            matching_rows = dirty_data[dirty_data['name'] == name]\n",
         "            print(f\"  '{name}': {len(matching_rows)} occurrence(s)\")\n",
         "            for _, row in matching_rows.iterrows():\n",
-        "            print(f\"    - Customer {row['customer_id']}: age={row['age']}, country={row['country']}\")"
+        "                print(f\"    - Customer {row['customer_id']}: age={row['age']}, country={row['country']}\")\n",
+        "except ImportError:\n",
+        "    print(\"rapidfuzz is not installed. Skipping fuzzy matching for near-duplicates.\")"
       ]
     },
     {