cleanup of deprecated test methods

PiperOrigin-RevId: 715994558

Author: tfx-copybara

tensorflow_data_validation/api/stats_api_test.py

@@ -365,7 +365,7 @@ def test_stats_pipeline_with_sample_rate(self):
 
   def test_invalid_stats_options(self):
     record_batches = [pa.RecordBatch.from_arrays([])]
-    with self.assertRaisesRegexp(TypeError, '.*should be a StatsOptions.'):
+    with self.assertRaisesRegex(TypeError, '.*should be a StatsOptions.'):
       with beam.Pipeline() as p:
         _ = (
             p | beam.Create(record_batches)

tensorflow_data_validation/api/validation_api_test.py

@@ -665,7 +665,7 @@ def test_infer_schema_multiple_datasets_with_default_slice(self):
     self.assertEqual(actual_schema, expected_schema)
 
   def test_infer_schema_invalid_statistics_input(self):
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, '.*should be a DatasetFeatureStatisticsList proto.*'):
       _ = validation_api.infer_schema({})
 
@@ -675,7 +675,7 @@ def test_infer_schema_invalid_multiple_datasets_no_default_slice(self):
         statistics_pb2.DatasetFeatureStatistics(),
         statistics_pb2.DatasetFeatureStatistics()
     ])
-    with self.assertRaisesRegexp(ValueError,
+    with self.assertRaisesRegex(ValueError,
                                  '.*statistics proto with one dataset.*'):
       _ = validation_api.infer_schema(statistics)
 
@@ -999,13 +999,13 @@ def test_update_schema_multiple_datasets_with_default_slice(self):
   def test_update_schema_invalid_schema_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, 'schema is of type.*'):
       _ = validation_api.update_schema({}, statistics)
 
   def test_update_schema_invalid_statistics_input(self):
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, 'statistics is of type.*'):
       _ = validation_api.update_schema(schema, {})
 
@@ -1016,7 +1016,7 @@ def test_update_schema_invalid_multiple_datasets_no_default_slice(self):
         statistics_pb2.DatasetFeatureStatistics(),
         statistics_pb2.DatasetFeatureStatistics()
     ])
-    with self.assertRaisesRegexp(ValueError,
+    with self.assertRaisesRegex(ValueError,
                                  '.*statistics proto with one dataset.*'):
       _ = validation_api.update_schema(schema, statistics)
 
@@ -1956,15 +1956,15 @@ def test_validate_stats_with_previous_and_serving_stats_with_default_slices(
 
   def test_validate_stats_invalid_statistics_input(self):
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, 'statistics is of type.*'):
       _ = validation_api.validate_statistics({}, schema)
 
   def test_validate_stats_invalid_previous_statistics_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, 'previous_statistics is of type.*'):
       _ = validation_api.validate_statistics(statistics, schema,
                                              previous_statistics='test')
@@ -1973,7 +1973,7 @@ def test_validate_stats_internal_invalid_previous_span_statistics_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(TypeError,
+    with self.assertRaisesRegex(TypeError,
                                  'previous_span_statistics is of type.*'):
       _ = validation_api.validate_statistics_internal(
           statistics, schema, previous_span_statistics='test')
@@ -1982,7 +1982,7 @@ def test_validate_stats_invalid_serving_statistics_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         TypeError, 'serving_statistics is of type.*'):
       _ = validation_api.validate_statistics(statistics, schema,
                                              serving_statistics='test')
@@ -1991,15 +1991,15 @@ def test_validate_stats_invalid_previous_version_statistics_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(TypeError,
+    with self.assertRaisesRegex(TypeError,
                                  'previous_version_statistics is of type.*'):
       _ = validation_api.validate_statistics_internal(
           statistics, schema, previous_version_statistics='test')
 
   def test_validate_stats_invalid_schema_input(self):
     statistics = statistics_pb2.DatasetFeatureStatisticsList()
     statistics.datasets.extend([statistics_pb2.DatasetFeatureStatistics()])
-    with self.assertRaisesRegexp(TypeError, '.*should be a Schema proto.*'):
+    with self.assertRaisesRegex(TypeError, '.*should be a Schema proto.*'):
       _ = validation_api.validate_statistics(statistics, {})
 
   def test_validate_stats_invalid_environment(self):
@@ -2017,7 +2017,7 @@ def test_validate_stats_invalid_environment(self):
           type: BYTES
         }
         """, schema_pb2.Schema())
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Environment.*not found in the schema.*'):
       _ = validation_api.validate_statistics(statistics, schema,
                                              environment='INVALID')
@@ -2030,7 +2030,7 @@ def test_validate_stats_invalid_statistics_multiple_datasets_no_default_slice(
         statistics_pb2.DatasetFeatureStatistics()
     ])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Only statistics proto with one dataset or the default.*'):
       _ = validation_api.validate_statistics(statistics, schema)
 
@@ -2045,7 +2045,7 @@ def test_validate_stats_invalid_previous_statistics_multiple_datasets(self):
         statistics_pb2.DatasetFeatureStatistics()
     ])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Only statistics proto with one dataset or the default.*'):
       _ = validation_api.validate_statistics(current_stats, schema,
                                              previous_statistics=previous_stats)
@@ -2061,7 +2061,7 @@ def test_validate_stats_invalid_serving_statistics_multiple_datasets(self):
         statistics_pb2.DatasetFeatureStatistics()
     ])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Only statistics proto with one dataset or the default.*'):
       _ = validation_api.validate_statistics(current_stats, schema,
                                              serving_statistics=serving_stats)
@@ -2078,7 +2078,7 @@ def test_validate_stats_invalid_previous_version_stats_multiple_datasets(
         statistics_pb2.DatasetFeatureStatistics()
     ])
     schema = schema_pb2.Schema()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Only statistics proto with one dataset or the default.*'):
       _ = validation_api.validate_statistics_internal(
           current_stats,
@@ -2789,22 +2789,22 @@ def test_validate_instance_invalid_environment(self):
         """, schema_pb2.Schema())
     options = stats_options.StatsOptions(schema=schema)
 
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Environment.*not found in the schema.*'):
       _ = validation_api.validate_instance(
           instance, options, environment='INVALID')
 
   def test_validate_instance_invalid_options(self):
     instance = pa.RecordBatch.from_arrays([pa.array([['A']])], ['feature'])
-    with self.assertRaisesRegexp(ValueError,
+    with self.assertRaisesRegex(ValueError,
                                  'options must be a StatsOptions object.'):
       _ = validation_api.validate_instance(instance, {})
 
   def test_validate_instance_stats_options_without_schema(self):
     instance = pa.RecordBatch.from_arrays([pa.array([['A']])], ['feature'])
     # This instance of StatsOptions has no schema.
     options = stats_options.StatsOptions()
-    with self.assertRaisesRegexp(ValueError, 'options must include a schema.'):
+    with self.assertRaisesRegex(ValueError, 'options must include a schema.'):
       _ = validation_api.validate_instance(instance, options)
 
 
@@ -3201,7 +3201,7 @@ def __eq__(self, other):
   def test_identify_anomalous_examples_options_of_wrong_type(self):
     examples = [{'annotated_enum': np.array(['D'], dtype=object)}]
     options = 1
-    with self.assertRaisesRegexp(ValueError, 'options must be a `StatsOptions` '
+    with self.assertRaisesRegex(ValueError, 'options must be a `StatsOptions` '
                                  'object.'):
       with beam.Pipeline() as p:
         _ = (
@@ -3211,7 +3211,7 @@ def test_identify_anomalous_examples_options_of_wrong_type(self):
   def test_identify_anomalous_examples_options_without_schema(self):
     examples = [{'annotated_enum': np.array(['D'], dtype=object)}]
     options = stats_options.StatsOptions()
-    with self.assertRaisesRegexp(ValueError, 'options must include a schema'):
+    with self.assertRaisesRegex(ValueError, 'options must include a schema'):
       with beam.Pipeline() as p:
         _ = (
             p | beam.Create(examples)

tensorflow_data_validation/statistics/generators/natural_language_domain_inferring_stats_generator_test.py

@@ -76,11 +76,11 @@ def test_average_word_heuristic_min_words(self):
 
   def test_nl_generator_bad_initialization(self):
     """Tests bad initialization values."""
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError,
         'NLDomainInferringStatsGenerator expects values_threshold > 0.'):
       nlsg.NLDomainInferringStatsGenerator(values_threshold=0)
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError,
         r'NLDomainInferringStatsGenerator expects a match_ratio in \[0, 1\].'):
       nlsg.NLDomainInferringStatsGenerator(match_ratio=1.1)

tensorflow_data_validation/utils/stats_gen_lib_test.py

@@ -428,7 +428,7 @@ def test_stats_gen_with_invalid_csv_header_in_multiple_files(self):
     self._write_records_to_csv(records2, tmp_dir, 'input_data2.csv')
     input_data_path = os.path.join(tmp_dir, 'input_data*')
 
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Files have different headers.'):
       _ = stats_gen_lib.generate_statistics_from_csv(
           data_location=input_data_path, column_names=None, delimiter=',')
@@ -479,7 +479,7 @@ def test_stats_gen_with_header_in_empty_csv_file(self):
     input_data_path = self._write_records_to_csv([], self._get_temp_dir(),
                                                  'input_data.csv')
 
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Found empty file when reading the header.*'):
       _ = stats_gen_lib.generate_statistics_from_csv(
           data_location=input_data_path, column_names=None, delimiter=',')
@@ -526,7 +526,7 @@ def test_stats_gen_with_dataframe_invalid_njobs_zero(self):
     input_data_path = self._write_records_to_csv(records, self._get_temp_dir(),
                                                  'input_data.csv')
     dataframe = pd.read_csv(input_data_path)
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Invalid n_jobs parameter.*'):
       _ = stats_gen_lib.generate_statistics_from_dataframe(
           dataframe=dataframe,
@@ -537,7 +537,7 @@ def test_stats_gen_with_dataframe_invalid_njobs_negative(self):
     input_data_path = self._write_records_to_csv(records, self._get_temp_dir(),
                                                  'input_data.csv')
     dataframe = pd.read_csv(input_data_path)
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'Invalid n_jobs parameter.*'):
       _ = stats_gen_lib.generate_statistics_from_dataframe(
           dataframe=dataframe,
@@ -557,14 +557,14 @@ def test_get_csv_header(self):
   def test_get_csv_header_no_file(self):
     data_location = os.path.join(self._get_temp_dir(), 'fileA.csv')
     delimiter = ','
-    with self.assertRaisesRegexp(ValueError, 'No file found.*'):
+    with self.assertRaisesRegex(ValueError, 'No file found.*'):
       _ = stats_gen_lib.get_csv_header(data_location, delimiter)
 
   def test_get_csv_header_empty_file(self):
     empty_file = os.path.join(self._get_temp_dir(), 'empty.csv')
     open(empty_file, 'w+').close()
     delimiter = ','
-    with self.assertRaisesRegexp(ValueError, 'Found empty file.*'):
+    with self.assertRaisesRegex(ValueError, 'Found empty file.*'):
       _ = stats_gen_lib.get_csv_header(empty_file, delimiter)
 
   def test_get_csv_header_different_headers(self):
@@ -575,7 +575,7 @@ def test_get_csv_header_different_headers(self):
     self._write_records_to_csv(records_1, temp_directory, 'input_data_1.csv')
     self._write_records_to_csv(records_2, temp_directory, 'input_data_2.csv')
     data_location = os.path.join(temp_directory, 'input_data_*.csv')
-    with self.assertRaisesRegexp(ValueError, 'Files have different headers.'):
+    with self.assertRaisesRegex(ValueError, 'Files have different headers.'):
       _ = stats_gen_lib.get_csv_header(data_location, delimiter)
 
   def test_get_csv_header_gzip(self):

tensorflow_data_validation/utils/test_util_test.py

@@ -304,7 +304,7 @@ def test_two_protos_with_same_features_in_different_order(self):
         self._test.assert_on_two_protos_with_same_features_in_different_order())
 
   def test_two_protos_with_different_features(self):
-    with self.assertRaisesRegexp(AssertionError, 'Feature path .*'):
+    with self.assertRaisesRegex(AssertionError, 'Feature path .*'):
       self._test.assert_on_two_protos_with_different_features()
 
   def test_two_protos_with_different_numbers_of_features(self):

tensorflow_data_validation/utils/validation_lib_test.py

@@ -254,7 +254,7 @@ def test_validate_examples_in_tfrecord_no_schema(self):
     input_data_path = os.path.join(temp_dir_path, 'input_data.tfrecord')
     # By default, StatsOptions does not include a schema.
     options = stats_options.StatsOptions()
-    with self.assertRaisesRegexp(
+    with self.assertRaisesRegex(
         ValueError, 'The specified stats_options must include a schema.'):
       validation_lib.validate_examples_in_tfrecord(
           data_location=input_data_path, stats_options=options)
@@ -532,7 +532,7 @@ def test_validate_examples_in_csv_no_schema(self):
             has_schema=False))
 
     assert options.schema is None
-    with self.assertRaisesRegexp(ValueError, 'The specified stats_options.*'):
+    with self.assertRaisesRegex(ValueError, 'The specified stats_options.*'):
       validation_lib.validate_examples_in_csv(
           data_location=data_location,
           stats_options=options,