Fixing Dataset for TQA + token-classification. (#14658)

* Fixing Dataset for TQA + token-classification.

* Fixing the tests.

* Making sure `offset_mappings` is a valid argument.

tests/test_pipelines_common.py

@@ -183,9 +183,12 @@ class PipelineTestCaseMeta(type):
 
                     # 10 examples with batch size 4 means there needs to be a unfinished batch
                     # which is important for the unbatcher
-                    dataset = [copy.deepcopy(random.choice(examples)) for i in range(10)]
+                    def data(n):
+                        for _ in range(n):
+                            # Need to copy because Conversation object is mutated
+                            yield copy.deepcopy(random.choice(examples))
 
-                    for item in pipeline(dataset, batch_size=4):
+                    for item in pipeline(data(10), batch_size=4):
                         pass
 
                 run_batch_test(pipeline, examples)

tests/test_pipelines_table_question_answering.py

@@ -35,17 +35,16 @@ from transformers.testing_utils import (
 from .test_pipelines_common import PipelineTestCaseMeta
 
 
-@require_tensorflow_probability
-@require_torch_scatter
-@require_torch
-@require_pandas
 @is_pipeline_test
 class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
     # Putting it there for consistency, but TQA do not have fast tokenizer
     # which are needed to generate automatic tests
     model_mapping = MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING
 
+    @require_tensorflow_probability
+    @require_pandas
     @require_tf
+    @require_torch
     def test_small_model_tf(self):
         model_id = "lysandre/tiny-tapas-random-wtq"
         model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_id, from_pt=True)
@@ -147,6 +146,7 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @require_torch
+    @require_torch_scatter
     def test_small_model_pt(self):
         model_id = "lysandre/tiny-tapas-random-wtq"
         model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
@@ -248,6 +248,7 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @require_torch
+    @require_torch_scatter
     def test_slow_tokenizer_sqa_pt(self):
         model_id = "lysandre/tiny-tapas-random-sqa"
         model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
@@ -366,6 +367,9 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @require_tf
+    @require_tensorflow_probability
+    @require_pandas
+    @require_torch
     def test_slow_tokenizer_sqa_tf(self):
         model_id = "lysandre/tiny-tapas-random-sqa"
         model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_id, from_pt=True)
@@ -484,6 +488,7 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @slow
+    @require_torch_scatter
     def test_integration_wtq_pt(self):
         table_querier = pipeline("table-question-answering")
 
@@ -528,6 +533,8 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
         self.assertListEqual(results, expected_results)
 
     @slow
+    @require_tensorflow_probability
+    @require_pandas
     def test_integration_wtq_tf(self):
         model_id = "google/tapas-base-finetuned-wtq"
         model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_id)
@@ -575,6 +582,7 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
         self.assertListEqual(results, expected_results)
 
     @slow
+    @require_torch_scatter
     def test_integration_sqa_pt(self):
         table_querier = pipeline(
             "table-question-answering",
@@ -598,6 +606,8 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
         self.assertListEqual(results, expected_results)
 
     @slow
+    @require_tensorflow_probability
+    @require_pandas
     def test_integration_sqa_tf(self):
         model_id = "google/tapas-base-finetuned-sqa"
         model = TFAutoModelForTableQuestionAnswering.from_pretrained(model_id)

tests/test_pipelines_token_classification.py

@@ -636,6 +636,19 @@ class TokenClassificationPipelineTests(unittest.TestCase, metaclass=PipelineTest
             [],
         )
 
+        token_classifier = pipeline(task="token-classification", model=model_name, framework="pt")
+        # Overload offset_mapping
+        outputs = token_classifier(
+            "This is a test !", offset_mapping=[(0, 0), (0, 1), (0, 2), (0, 0), (0, 0), (0, 0), (0, 0)]
+        )
+        self.assertEqual(
+            nested_simplify(outputs),
+            [
+                {"entity": "I-MISC", "score": 0.115, "index": 1, "word": "this", "start": 0, "end": 1},
+                {"entity": "I-MISC", "score": 0.115, "index": 2, "word": "is", "start": 0, "end": 2},
+            ],
+        )
+
     @require_torch
     def test_pt_ignore_subwords_slow_tokenizer_raises(self):
         model_name = "sshleifer/tiny-dbmdz-bert-large-cased-finetuned-conll03-english"