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

@@ -3909,18 +3909,21 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from scipy import stats\n",
-        "\n",
-        "# Calculate Z-scores for age\n",
-        "dirty_data['age_zscore'] = np.abs(stats.zscore(dirty_data['age']))\n",
+        "try:\n",
+        "    from scipy import stats\n",
+        "except ImportError:\n",
+        "    print(\"scipy is required for Z-score calculation. Please install it with 'pip install scipy' and rerun this cell.\")\n",
+        "else:\n",
+        "    # Calculate Z-scores for age\n",
+        "    dirty_data['age_zscore'] = np.abs(stats.zscore(dirty_data['age']))\n",
         "\n",
-        "# Typically, Z-score > 3 indicates an outlier\n",
-        "print(\"Rows with age Z-score > 3:\")\n",
-        "zscore_outliers = dirty_data[dirty_data['age_zscore'] > 3]\n",
-        "print(zscore_outliers[['customer_id', 'name', 'age', 'age_zscore']])\n",
+        "    # Typically, Z-score > 3 indicates an outlier\n",
+        "    print(\"Rows with age Z-score > 3:\")\n",
+        "    zscore_outliers = dirty_data[dirty_data['age_zscore'] > 3]\n",
+        "    print(zscore_outliers[['customer_id', 'name', 'age', 'age_zscore']])\n",
         "\n",
-        "# Clean up the temporary column\n",
-        "dirty_data = dirty_data.drop('age_zscore', axis=1)"
+        "    # Clean up the temporary column\n",
+        "    dirty_data = dirty_data.drop('age_zscore', axis=1)"
       ]
     },
     {