IL-374 Better rendering

src/examples/user_journey.ipynb

@@ -327,11 +327,42 @@
     "list(failed_example_iterator.get_examples(eval_overview.id))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from intelligence_layer.evaluation import evaluation_lineages_to_pandas\n",
+    "\n",
+    "\n",
+    "from intelligence_layer.evaluation import FailedExampleEvaluation\n",
+    "\n",
+    "\n",
+    "lineages = [\n",
+    "    lineage\n",
+    "    for lineage in evaluator.evaluation_lineages(eval_overview.id)\n",
+    "    if not isinstance(lineage.evaluation.result, FailedExampleEvaluation) and not lineage.evaluation.result.correct\n",
+    "][:3]\n",
+    "\n",
+    "# df = evaluation_lineages_to_pandas(lineages)\n",
+    "# # df[\"output\"] = df[\"output\"].apply(\n",
+    "# #     lambda o: sorted(o.scores.items(), key=lambda entry: entry[1])[-1]\n",
+    "# # )\n",
+    "# # df[\"result\"] = df[\"result\"].apply(lambda r: r.expected_label_missing)\n",
+    "# # df = df.rename(columns={\"result\": \"expected label missing\"})\n",
+    "# display(df)\n",
+    "\n",
+    "\n",
+    "for lineage in lineages:\n",
+    "    display(lineage)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This confirms it: some expected labels are missing. Let's try fixing this.\n",
+    "This confirms it: The second example has an some expected labels are missing. Let's try fixing this.\n",
     "\n",
     "We can do this two ways: Adjust our set of labels or adjust the eval set. In this case, we'll do the latter.\n"
    ]
@@ -537,7 +568,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

src/intelligence_layer/use_cases/classify/classify.py

@@ -168,39 +168,6 @@ def do_evaluate_single_output(
         )
 
 
-class SingleLabelClassifyFailedExampleIterator:
-    def __init__(
-        self,
-        dataset_repository: DatasetRepository,
-        run_repository: RunRepository,
-        evaluation_repository: EvaluationRepository,
-    ):
-        self.repository_navigator = RepositoryNavigator(
-            dataset_repository, run_repository, evaluation_repository
-        )
-
-    # TODO: Add test
-    def get_examples(
-        self, evaluation_overview_id: str, first_n: int = 0
-    ) -> Iterable[Example[ClassifyInput, str]]:
-        evaluation_lineages = self.repository_navigator.evaluation_lineages(
-            evaluation_id=evaluation_overview_id,
-            input_type=ClassifyInput,
-            expected_output_type=str,
-            output_type=SingleLabelClassifyOutput,
-            evaluation_type=SingleLabelClassifyEvaluation,
-        )
-        count_yielded = 0
-        for lineage in evaluation_lineages:
-            if first_n != 0 and count_yielded >= first_n:
-                break
-            if (
-                isinstance(lineage.evaluation.result, FailedExampleEvaluation)
-                or not lineage.evaluation.result.correct
-            ):
-                count_yielded += 1
-                yield lineage.example
-
 
 class MultiLabelClassifyEvaluation(BaseModel):
     """The evaluation of a single multi-label classification example.