fixing evaluate typing

frame_semantic_transformer/evaluate.py

@@ -46,7 +46,7 @@ def evaluate(
         predictions = batch_predict(model, tokenizer, inputs)
         for sample, prediction in zip(samples_chunk, predictions):
             true_pos, false_pos, false_neg = sample.evaluate_prediction(prediction)
-            results[sample.get_task()][0] += true_pos
-            results[sample.get_task()][1] += false_pos
-            results[sample.get_task()][2] += false_neg
+            results[sample.get_task_name()][0] += true_pos
+            results[sample.get_task_name()][1] += false_pos
+            results[sample.get_task_name()][2] += false_neg
     return results

setup.cfg

@@ -10,6 +10,7 @@ disallow_any_generics = True
 check_untyped_defs = True
 disallow_untyped_defs = True
 namespace_packages = True
+mypy_path = $MYPY_CONFIG_FILE_DIR/stubs
 
 [mypy-tests.*]
 ignore_missing_imports = True

stubs/tqdm.pyi

@@ -0,0 +1,5 @@
+from typing import Any, Iterable, Iterator, TypeVar
+
+_T = TypeVar("_T")
+
+def tqdm(iterable: Iterable[_T], *args: Any, **kwargs: Any) -> Iterator[_T]: ...