Add end-to-end tests at the end of Datalab Quickstart tutorial (#1118)

Co-authored-by: Elías Snorrason <eliassno@gmail.com>

docs/source/tutorials/datalab/datalab_quickstart.ipynb

@@ -746,6 +746,52 @@
     "\n",
     "To learn more, check out this [example notebook](https://github.com/cleanlab/examples/blob/master/datalab_image_classification/datalab.ipynb) (demonstrates Datalab applied to a real dataset) and the [advanced Datalab tutorial](datalab_advanced.html) (demonstrates configuration and customization options to exert greater control)."
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "nbsphinx": "hidden"
+   },
+   "outputs": [],
+   "source": [
+    "# Note: This cell is only for docs.cleanlab.ai, if running on local Jupyter or Colab, please ignore it.\n",
+    "from sklearn.metrics import roc_auc_score\n",
+    "\n",
+    "issue_results = lab.get_issues(\"label\")\n",
+    "outlier_results = lab.get_issues(\"outlier\")\n",
+    "duplicate_results = lab.get_issues(\"near_duplicate\")\n",
+    "\n",
+    "def jaccard_similarity(l1, l2):\n",
+    "    s1 = set(l1)\n",
+    "    s2 = set(l2)\n",
+    "    intersect_set = s1.intersection(s2)\n",
+    "    union_set = s1.union(s2)\n",
+    "    if len(intersect_set) == 0:\n",
+    "        return 0\n",
+    "    return len(intersect_set) / len(union_set)\n",
+    "\n",
+    "identified_label_issues_indices = issue_results[issue_results[\"is_label_issue\"] == True].index.tolist()\n",
+    "label_issue_indices = np.where(y_train_idx != noisy_labels_idx)[0]\n",
+    "\n",
+    "label_quality_scores = issue_results[\"label_score\"].tolist()\n",
+    "Z = (y_train_idx == noisy_labels_idx).astype(float).tolist()\n",
+    "\n",
+    "identified_outlier_issues_indices = outlier_results[outlier_results[\"is_outlier_issue\"] == True].index.to_list()\n",
+    "outlier_issue_indices = list(range(125, 130+1))\n",
+    "exact_duplicate_idx = [index for index, elem in enumerate(X_train) if (elem == X_duplicate).all()][0]\n",
+    "if exact_duplicate_idx >= 125: # if the random index selected to create a duplicate >= 125, then the last point is also an outlier\n",
+    "    outlier_issue_indices.append(131)\n",
+    "    \n",
+    "identified_duplicate_issues_indices = duplicate_results[duplicate_results[\"is_near_duplicate_issue\"] == True].index.tolist()\n",
+    "duplicate_issue_indices = [exact_duplicate_idx, 129, 130, 131]\n",
+    "\n",
+    "\n",
+    "assert jaccard_similarity(identified_label_issues_indices, label_issue_indices) > 0.4\n",
+    "assert roc_auc_score(Z, label_quality_scores) > 0.9\n",
+    "assert jaccard_similarity(identified_outlier_issues_indices, outlier_issue_indices) > 0.9\n",
+    "assert jaccard_similarity(identified_duplicate_issues_indices, duplicate_issue_indices) > 0.9"
+   ]
   }
  ],
  "metadata": {