[AI Projects] Fix code-based evaluator catalog sample: add missing data_mapping

[slister1001]

Fix code-based evaluator catalog sample

The sample sample_eval_catalog_code_based_evaluators.py currently fails at client.evals.create(...) with HTTP 400:

UserError / EvalValidationFailed
Code: MissingRequiredDataMapping
Target: group.testing_criteria[0].data_mapping
Message: Data mapping for required field 'item' is missing for evaluator 'my_custom_evaluator_code'.

Root cause

The evaluator's data_schema declares "required": ["item"] (the grade(sample, item) function expects the whole item object), but the testing_criteria entry omitted data_mapping entirely. The server validates that every field in data_schema.required has a corresponding mapping in the testing criterion.

For comparison, the working sample_eval_catalog_prompt_based_evaluators.py declares each field individually in data_schema and maps each one in data_mapping. The code-based sample needs to map the single required item field to the whole data-source item.

Fixes

1. Add data_mapping={"item": "{{item}}"} to the testing criterion — passes the entire data-source item to the evaluator's item parameter.
2. Change pass_threshold type in init_parameters.properties from "string" to "number" — the runtime value 0.5 is a float, not a string. After the data-mapping fix is in place, this would be the next validation failure.

Sample diff

-                    "properties": {"deployment_name": {"type": "string"}, "pass_threshold": {"type": "string"}},
+                    "properties": {"deployment_name": {"type": "string"}, "pass_threshold": {"type": "number"}},
...
         TestingCriterionAzureAIEvaluator(
             type="azure_ai_evaluator",
             name="my_custom_evaluator_code",
             evaluator_name="my_custom_evaluator_code",
+            data_mapping={"item": "{{item}}"},
             initialization_parameters={
                 "deployment_name": f"{model_deployment_name}",
                 "pass_threshold": 0.5,
             },
         )

Reproduction

Without this fix, running the sample with azure-ai-projects==2.1.0 against an Azure AI Foundry project produces the 400 error shown above. With this fix, evaluation creation succeeds.

Scope

Sample-only change. No SDK source code, generated code, public surface, or tests are affected.