def test_left_outer_join_without_where(self):
source_path = os.path.join(self.tempdir + '/streaming.csv')
field_names = ["a", "b", "c"]
field_types = [DataTypes.INT(), DataTypes.STRING(), DataTypes.STRING()]
data = [(1, "Hi", "Hello"), (2, "Hi", "Hello"), (3, "Hello", "Hello")]
csv_source = self.prepare_csv_source(source_path, data, field_types, field_names)
source_path2 = os.path.join(self.tempdir + '/streaming2.csv')
field_names2 = ["d", "e"]
field_types2 = [DataTypes.INT(), DataTypes.STRING()]
data2 = [(2, "Flink"), (3, "Python"), (3, "Flink")]
csv_source2 = self.prepare_csv_source(source_path2, data2, field_types2, field_names2)
t_env = self.t_env
t_env.register_table_source("Source1", csv_source)
t_env.register_table_source("Source2", csv_source2)
source1 = t_env.scan("Source1")
source2 = t_env.scan("Source2")
field_names = ["a", "b"]
field_types = [DataTypes.INT(), DataTypes.STRING()]
t_env.register_table_sink(
"Results",
field_names, field_types, source_sink_utils.TestRetractSink())
result = source1.left_outer_join(source2, "a = d").select("a, b + e")
result.insert_into("Results")
t_env.execute()
actual = source_sink_utils.results()
expected = ['1,null', '2,HiFlink', '3,HelloPython', '3,HelloFlink']
self.assert_equals(actual, expected)
def load_model(self, table_env):
"""
Train the model to get the max_sum value which is used to predict data.
"""
table_sink = source_sink_utils.TestRetractSink(["max_sum"], [DataTypes.BIGINT()])
table_env.register_table_sink("Model_Results", table_sink)
self._model_data_table.execute_insert("Model_Results").wait()
actual = source_sink_utils.results()
self.max_sum = actual.apply(0)
def test_print_schema(self):
t_env = self.t_env
t = t_env.from_elements([(1, 'Hi', 'Hello'), (2, 'Hello', 'Hello'),
(2, 'Hello', 'Hello')], ['a', 'b', 'c'])
field_names = ["a", "b"]
field_types = [DataTypes.BIGINT(), DataTypes.STRING()]
t_env.register_table_sink("Results", field_names, field_types,
source_sink_utils.TestRetractSink())
result = t.group_by("c").select("a.sum, c as b")
result.print_schema()
def test_group_by(self):
t_env = self.t_env
t = t_env.from_elements([(1, 'Hi', 'Hello'), (2, 'Hello', 'Hello'),
(2, 'Hello', 'Hello')], ['a', 'b', 'c'])
field_names = ["a", "b"]
field_types = [DataTypes.BIGINT(), DataTypes.STRING()]
t_env.register_table_sink("Results", field_names, field_types,
source_sink_utils.TestRetractSink())
result = t.group_by("c").select("a.sum, c as b")
result.insert_into("Results")
t_env.execute()
actual = source_sink_utils.results()
expected = ['5,Hello']
self.assert_equals(actual, expected)
def test_distinct(self):
t_env = self.t_env
t = t_env.from_elements([(1, "Hi", "Hello"), (2, "Hello", "Hello"),
(2, "Hello", "Hello")], ['a', 'b', 'c'])
field_names = ["a", "b"]
field_types = [DataTypes.BIGINT(), DataTypes.STRING()]
t_env.register_table_sink("Results", field_names, field_types,
source_sink_utils.TestRetractSink())
result = t.distinct().select("a, c as b")
result.insert_into("Results")
t_env.execute()
actual = source_sink_utils.results()
expected = ['1,Hello', '2,Hello']
self.assert_equals(actual, expected)
def test_print_schema(self):
source_path = os.path.join(self.tempdir + '/streaming.csv')
field_names = ["a", "b", "c"]
field_types = [DataTypes.INT, DataTypes.STRING, DataTypes.STRING]
data = [(1, "Hi", "Hello"), (2, "Hello", "Hello"), (2, "Hello", "Hello")]
csv_source = self.prepare_csv_source(source_path, data, field_types, field_names)
t_env = self.t_env
t_env.register_table_source("Source", csv_source)
source = t_env.scan("Source")
field_names = ["a", "b"]
field_types = [DataTypes.INT, DataTypes.STRING]
t_env.register_table_sink(
"Results",
field_names, field_types, source_sink_utils.TestRetractSink())
result = source.group_by("c").select("a.sum, c as b")
result.print_schema()
def test_left_outer_join_with_where(self):
t_env = self.t_env
t1 = t_env.from_elements([(1, "Hi", "Hello"), (2, "Hi", "Hello"),
(3, "Hello", "Hello")], ['a', 'b', 'c'])
t2 = t_env.from_elements([(2, "Flink"), (3, "Python"), (3, "Flink")],
['d', 'e'])
field_names = ["a", "b"]
field_types = [DataTypes.BIGINT(), DataTypes.STRING()]
t_env.register_table_sink("Results", field_names, field_types,
source_sink_utils.TestRetractSink())
result = t1.left_outer_join(t2).where("a = d").select("a, b + e")
result.insert_into("Results")
t_env.execute()
actual = source_sink_utils.results()
expected = ['2,HiFlink', '3,HelloPython', '3,HelloFlink']
self.assert_equals(actual, expected)
def test_distinct(self):
source_path = os.path.join(self.tempdir + '/streaming.csv')
field_names = ["a", "b", "c"]
field_types = [DataTypes.INT(), DataTypes.STRING(), DataTypes.STRING()]
data = [(1, "Hi", "Hello"), (2, "Hello", "Hello"),
(2, "Hello", "Hello")]
csv_source = self.prepare_csv_source(source_path, data, field_types,
field_names)
t_env = self.t_env
t_env.register_table_source("Source", csv_source)
source = t_env.scan("Source")
field_names = ["a", "b"]
field_types = [DataTypes.INT(), DataTypes.STRING()]
t_env.register_table_sink("Results", field_names, field_types,
source_sink_utils.TestRetractSink())
result = source.distinct().select("a, c as b")
result.insert_into("Results")
t_env.execute()
actual = source_sink_utils.results()
expected = ['1,Hello', '2,Hello']
self.assert_equals(actual, expected)
