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

Co-authored-by: Copilot <[email protected]>

Author: leestott

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

@@ -3815,24 +3815,29 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# rapidfuzz was already imported in an earlier cell\n",
-        "from rapidfuzz import process, fuzz\n",
-        "\n",
-        "\n",
+        "try:\n",
+        "    from rapidfuzz import process, fuzz\n",
+        "except ImportError:\n",
+        "    print(\"rapidfuzz is not installed. Please install it with 'pip install rapidfuzz' to use fuzzy matching.\")\n",
+        "    process = None\n",
+        "    fuzz = None\n",
         "\n",
         "# Get unique countries\n",
         "unique_countries = dirty_data['country'].unique()\n",
         "\n",
         "# For each country, find similar matches\n",
-        "print(\"Finding similar country names (similarity > 70%):\")\n",
-        "for country in unique_countries:\n",
-        "    matches = process.extract(country, unique_countries, scorer=fuzz.ratio, limit=3)\n",
-        "    # Filter matches with similarity > 70 and not identical\n",
-        "    similar = [m for m in matches if m[1] > 70 and m[0] != country]\n",
-        "    if similar:\n",
-        "        print(f\"\\n'{country}' is similar to:\")\n",
-        "        for match, score, _ in similar:\n",
-        "            print(f\"  - '{match}' (similarity: {score}%)\")"
+        "if process is not None and fuzz is not None:\n",
+        "    print(\"Finding similar country names (similarity > 70%):\")\n",
+        "    for country in unique_countries:\n",
+        "        matches = process.extract(country, unique_countries, scorer=fuzz.ratio, limit=3)\n",
+        "        # Filter matches with similarity > 70 and not identical\n",
+        "        similar = [m for m in matches if m[1] > 70 and m[0] != country]\n",
+        "        if similar:\n",
+        "            print(f\"\\n'{country}' is similar to:\")\n",
+        "            for match, score, _ in similar:\n",
+        "                print(f\"  - '{match}' (similarity: {score}%)\")\n",
+        "else:\n",
+        "    print(\"Skipping fuzzy matching because rapidfuzz is not available.\")"
       ]
     },
     {