def setUp(self):
super(OneHotEncoderTest, self).setUp()
self.train_data = self.t_env.from_data_stream(
self.env.from_collection([
(0.0,),
(1.0,),
(2.0,),
(0.0,),
],
type_info=Types.ROW_NAMED(
['input'],
[Types.DOUBLE()])))
self.predict_data = self.t_env.from_data_stream(
self.env.from_collection([
(0.0,),
(1.0,),
(2.0,),
],
type_info=Types.ROW_NAMED(
['input'],
[Types.DOUBLE()])))
self.expected_data = {
0.0: Vectors.sparse(2, [0], [1.0]),
1.0: Vectors.sparse(2, [1], [1.0]),
2.0: Vectors.sparse(2, [], [])
}
self.estimator = OneHotEncoder().set_input_cols('input').set_output_cols('output')
def setUp(self):
super(StringIndexerTest, self).setUp()
self.train_table = self.t_env.from_data_stream(
self.env.from_collection([
('a', 1.0),
('b', 1.0),
('b', 2.0),
('c', 0.0),
('d', 2.0),
('a', 2.0),
('b', 2.0),
('b', -1.0),
('a', -1.0),
('c', -1.0),
],
type_info=Types.ROW_NAMED(
['input_col1', 'input_col2'],
[Types.STRING(), Types.DOUBLE()])))
self.predict_table = self.t_env.from_data_stream(
self.env.from_collection([
('a', 2.0),
('b', 1.0),
('e', 2.0),
],
type_info=Types.ROW_NAMED(
['input_col1', 'input_col2'],
[Types.STRING(), Types.DOUBLE()])))
self.expected_alphabetic_asc_predict_data = [
Row('a', 2.0, 0, 3),
Row('b', 1.0, 1, 2),
Row('e', 2.0, 4, 3)
]
def setUp(self):
super(LogisticRegressionTest, self).setUp()
self.binomial_data_table = self.t_env.from_data_stream(
self.env.from_collection(
[
(Vectors.dense([1, 2, 3, 4]), 0., 1.),
(Vectors.dense([2, 2, 3, 4]), 0., 2.),
(Vectors.dense([3, 2, 3, 4]), 0., 3.),
(Vectors.dense([4, 2, 3, 4]), 0., 4.),
(Vectors.dense([5, 2, 3, 4]), 0., 5.),
(Vectors.dense([11, 2, 3, 4]), 1., 1.),
(Vectors.dense([12, 2, 3, 4]), 1., 2.),
(Vectors.dense([13, 2, 3, 4]), 1., 3.),
(Vectors.dense([14, 2, 3, 4]), 1., 4.),
(Vectors.dense([15, 2, 3, 4]), 1., 5.),
],
type_info=Types.ROW_NAMED(
['features', 'label', 'weight'],
[DenseVectorTypeInfo(),
Types.DOUBLE(),
Types.DOUBLE()])))
def setUp(self):
super(KNNTest, self).setUp()
self.train_data = self.t_env.from_data_stream(
self.env.from_collection([
(Vectors.dense([2.0, 3.0]), 1.0),
(Vectors.dense([2.1, 3.1]), 1.0),
(Vectors.dense([200.1, 300.1]), 2.0),
(Vectors.dense([200.2, 300.2]), 2.0),
(Vectors.dense([200.3, 300.3]), 2.0),
(Vectors.dense([200.4, 300.4]), 2.0),
(Vectors.dense([200.4, 300.4]), 2.0),
(Vectors.dense([200.6, 300.6]), 2.0),
(Vectors.dense([2.1, 3.1]), 1.0),
(Vectors.dense([2.1, 3.1]), 1.0),
(Vectors.dense([2.1, 3.1]), 1.0),
(Vectors.dense([2.1, 3.1]), 1.0),
(Vectors.dense([2.3, 3.2]), 1.0),
(Vectors.dense([2.3, 3.2]), 1.0),
(Vectors.dense([2.8, 3.2]), 3.0),
(Vectors.dense([300., 3.2]), 4.0),
(Vectors.dense([2.2, 3.2]), 1.0),
(Vectors.dense([2.4, 3.2]), 5.0),
(Vectors.dense([2.5, 3.2]), 5.0),
(Vectors.dense([2.5, 3.2]), 5.0),
(Vectors.dense([2.1, 3.1]), 1.0)
],
type_info=Types.ROW_NAMED(
['features', 'label'],
[DenseVectorTypeInfo(), Types.DOUBLE()])))
self.predict_data = self.t_env.from_data_stream(
self.env.from_collection([
(Vectors.dense([4.0, 4.1]), 5.0),
(Vectors.dense([300, 42]), 2.0),
],
type_info=Types.ROW_NAMED(
['features', 'label'],
[DenseVectorTypeInfo(), Types.DOUBLE()])))
def setUp(self):
super(VectorAssemblerTest, self).setUp()
self.input_data_table = self.t_env.from_data_stream(
self.env.from_collection([
(0, Vectors.dense(2.1, 3.1), 1.0, Vectors.sparse(
5, [3], [1.0])),
(1, Vectors.dense(2.1, 3.1), 1.0,
Vectors.sparse(5, [1, 2, 3, 4], [1.0, 2.0, 3.0, 4.0])),
(2, None, None, None),
],
type_info=Types.ROW_NAMED(
['id', 'vec', 'num', 'sparse_vec'], [
Types.INT(),
DenseVectorTypeInfo(),
Types.DOUBLE(),
SparseVectorTypeInfo()
])))
self.expected_output_data_1 = Vectors.sparse(8, [0, 1, 2, 6],
[2.1, 3.1, 1.0, 1.0])
self.expected_output_data_2 = Vectors.dense(2.1, 3.1, 1.0, 0.0, 1.0,
2.0, 3.0, 4.0)
def setUp(self):
super(NaiveBayesTest, self).setUp()
self.env.set_parallelism(1)
self.train_data = self.t_env.from_data_stream(
self.env.from_collection(
[
(Vectors.dense([0, 0.]), 11.),
(Vectors.dense([1, 0]), 10.),
(Vectors.dense([1, 1.]), 10.),
],
type_info=Types.ROW_NAMED(
['features', 'label'],
[DenseVectorTypeInfo(),
Types.DOUBLE()])))
self.predict_data = self.t_env.from_data_stream(
self.env.from_collection(
[
(Vectors.dense([0, 1.]), ),
(Vectors.dense([0, 0.]), ),
(Vectors.dense([1, 0]), ),
(Vectors.dense([1, 1.]), ),
],
type_info=Types.ROW_NAMED(['features'],
[DenseVectorTypeInfo()])))
self.expected_output = {
Vectors.dense([0, 1.]): 11.,
Vectors.dense([0, 0.]): 11.,
Vectors.dense([1, 0.]): 10.,
Vectors.dense([1, 1.]): 10.,
}
self.estimator = NaiveBayes() \
.set_smoothing(1.0) \
.set_features_col('features') \
.set_label_col('label') \
.set_prediction_col('prediction') \
.set_model_type('multinomial') # type: NaiveBayes
def setUp(self):
super(BinaryClassificationEvaluatorTest, self).setUp()
self.input_data_table = self.t_env.from_data_stream(
self.env.from_collection([
(1.0, Vectors.dense(0.1, 0.9)),
(1.0, Vectors.dense(0.2, 0.8)),
(1.0, Vectors.dense(0.3, 0.7)),
(0.0, Vectors.dense(0.25, 0.75)),
(0.0, Vectors.dense(0.4, 0.6)),
(1.0, Vectors.dense(0.35, 0.65)),
(1.0, Vectors.dense(0.45, 0.55)),
(0.0, Vectors.dense(0.6, 0.4)),
(0.0, Vectors.dense(0.7, 0.3)),
(1.0, Vectors.dense(0.65, 0.35)),
(0.0, Vectors.dense(0.8, 0.2)),
(1.0, Vectors.dense(0.9, 0.1))
],
type_info=Types.ROW_NAMED(
['label', 'rawPrediction'],
[Types.DOUBLE(), DenseVectorTypeInfo()]))
)
self.input_data_table_score = self.t_env.from_data_stream(
self.env.from_collection([
(1, 0.9),
(1, 0.8),
(1, 0.7),
(0, 0.75),
(0, 0.6),
(1, 0.65),
(1, 0.55),
(0, 0.4),
(0, 0.3),
(1, 0.35),
(0, 0.2),
(1, 0.1)
],
type_info=Types.ROW_NAMED(
['label', 'rawPrediction'],
[Types.INT(), Types.DOUBLE()]))
)
self.input_data_table_with_multi_score = self.t_env.from_data_stream(
self.env.from_collection([
(1.0, Vectors.dense(0.1, 0.9)),
(1.0, Vectors.dense(0.1, 0.9)),
(1.0, Vectors.dense(0.1, 0.9)),
(0.0, Vectors.dense(0.25, 0.75)),
(0.0, Vectors.dense(0.4, 0.6)),
(1.0, Vectors.dense(0.1, 0.9)),
(1.0, Vectors.dense(0.1, 0.9)),
(0.0, Vectors.dense(0.6, 0.4)),
(0.0, Vectors.dense(0.7, 0.3)),
(1.0, Vectors.dense(0.1, 0.9)),
(0.0, Vectors.dense(0.8, 0.2)),
(1.0, Vectors.dense(0.9, 0.1))
],
type_info=Types.ROW_NAMED(
['label', 'rawPrediction'],
[Types.DOUBLE(), DenseVectorTypeInfo()]))
)
self.input_data_table_with_weight = self.t_env.from_data_stream(
self.env.from_collection([
(1.0, Vectors.dense(0.1, 0.9), 0.8),
(1.0, Vectors.dense(0.1, 0.9), 0.7),
(1.0, Vectors.dense(0.1, 0.9), 0.5),
(0.0, Vectors.dense(0.25, 0.75), 1.2),
(0.0, Vectors.dense(0.4, 0.6), 1.3),
(1.0, Vectors.dense(0.1, 0.9), 1.5),
(1.0, Vectors.dense(0.1, 0.9), 1.4),
(0.0, Vectors.dense(0.6, 0.4), 0.3),
(0.0, Vectors.dense(0.7, 0.3), 0.5),
(1.0, Vectors.dense(0.1, 0.9), 1.9),
(0.0, Vectors.dense(0.8, 0.2), 1.2),
(1.0, Vectors.dense(0.9, 0.1), 1.0)
],
type_info=Types.ROW_NAMED(
['label', 'rawPrediction', 'weight'],
[Types.DOUBLE(), DenseVectorTypeInfo(), Types.DOUBLE()]))
)
self.expected_data = [0.7691481137909708, 0.3714285714285714, 0.6571428571428571]
self.expected_data_m = [0.8571428571428571, 0.9377705627705628,
0.8571428571428571, 0.6488095238095237]
self.expected_data_w = 0.8911680911680911
self.eps = 1e-5