9fcf0ea718
Disallow the use of unused imports: - Unnecessary increases the memory footprint of the application - Removes the imports that are required for the examples in the docstring from the file-scope to the example itself. This keeps the files itself clean, and gives a more complete example as it also includes the imports :) ``` fokkodriesprongFan spark % flake8 python | grep -i "imported but unused" python/pyspark/cloudpickle.py:46:1: F401 'functools.partial' imported but unused python/pyspark/cloudpickle.py:55:1: F401 'traceback' imported but unused python/pyspark/heapq3.py:868:5: F401 '_heapq.*' imported but unused python/pyspark/__init__.py:61:1: F401 'pyspark.version.__version__' imported but unused python/pyspark/__init__.py:62:1: F401 'pyspark._globals._NoValue' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.SQLContext' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.HiveContext' imported but unused python/pyspark/__init__.py:115:1: F401 'pyspark.sql.Row' imported but unused python/pyspark/rdd.py:21:1: F401 're' imported but unused python/pyspark/rdd.py:29:1: F401 'tempfile.NamedTemporaryFile' imported but unused python/pyspark/mllib/regression.py:26:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/clustering.py:28:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/clustering.py:28:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/classification.py:26:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/feature.py:28:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/feature.py:28:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/feature.py:30:1: F401 'pyspark.mllib.regression.LabeledPoint' imported but unused python/pyspark/mllib/tests/test_linalg.py:18:1: F401 'sys' imported but unused python/pyspark/mllib/tests/test_linalg.py:642:5: F401 'pyspark.mllib.tests.test_linalg.*' imported but unused python/pyspark/mllib/tests/test_feature.py:21:1: F401 'numpy.random' imported but unused python/pyspark/mllib/tests/test_feature.py:21:1: F401 'numpy.exp' imported but unused python/pyspark/mllib/tests/test_feature.py:23:1: F401 'pyspark.mllib.linalg.Vector' imported but unused python/pyspark/mllib/tests/test_feature.py:23:1: F401 'pyspark.mllib.linalg.VectorUDT' imported but unused python/pyspark/mllib/tests/test_feature.py:185:5: F401 'pyspark.mllib.tests.test_feature.*' imported but unused python/pyspark/mllib/tests/test_util.py:97:5: F401 'pyspark.mllib.tests.test_util.*' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.Vector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.SparseVector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.DenseVector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.VectorUDT' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg._convert_to_vector' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.DenseMatrix' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.SparseMatrix' imported but unused python/pyspark/mllib/tests/test_stat.py:23:1: F401 'pyspark.mllib.linalg.MatrixUDT' imported but unused python/pyspark/mllib/tests/test_stat.py:181:5: F401 'pyspark.mllib.tests.test_stat.*' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:18:1: F401 'time.time' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:18:1: F401 'time.sleep' imported but unused python/pyspark/mllib/tests/test_streaming_algorithms.py:470:5: F401 'pyspark.mllib.tests.test_streaming_algorithms.*' imported but unused python/pyspark/mllib/tests/test_algorithms.py:295:5: F401 'pyspark.mllib.tests.test_algorithms.*' imported but unused python/pyspark/tests/test_serializers.py:90:13: F401 'xmlrunner' imported but unused python/pyspark/tests/test_rdd.py:21:1: F401 'sys' imported but unused python/pyspark/tests/test_rdd.py:29:1: F401 'pyspark.resource.ResourceProfile' imported but unused python/pyspark/tests/test_rdd.py:885:5: F401 'pyspark.tests.test_rdd.*' imported but unused python/pyspark/tests/test_readwrite.py:19:1: F401 'sys' imported but unused python/pyspark/tests/test_readwrite.py:22:1: F401 'array.array' imported but unused python/pyspark/tests/test_readwrite.py:309:5: F401 'pyspark.tests.test_readwrite.*' imported but unused python/pyspark/tests/test_join.py:62:5: F401 'pyspark.tests.test_join.*' imported but unused python/pyspark/tests/test_taskcontext.py:19:1: F401 'shutil' imported but unused python/pyspark/tests/test_taskcontext.py:325:5: F401 'pyspark.tests.test_taskcontext.*' imported but unused python/pyspark/tests/test_conf.py:36:5: F401 'pyspark.tests.test_conf.*' imported but unused python/pyspark/tests/test_broadcast.py:148:5: F401 'pyspark.tests.test_broadcast.*' imported but unused python/pyspark/tests/test_daemon.py:76:5: F401 'pyspark.tests.test_daemon.*' imported but unused python/pyspark/tests/test_util.py:77:5: F401 'pyspark.tests.test_util.*' imported but unused python/pyspark/tests/test_pin_thread.py:19:1: F401 'random' imported but unused python/pyspark/tests/test_pin_thread.py:149:5: F401 'pyspark.tests.test_pin_thread.*' imported but unused python/pyspark/tests/test_worker.py:19:1: F401 'sys' imported but unused python/pyspark/tests/test_worker.py:26:5: F401 'resource' imported but unused python/pyspark/tests/test_worker.py:203:5: F401 'pyspark.tests.test_worker.*' imported but unused python/pyspark/tests/test_profiler.py:101:5: F401 'pyspark.tests.test_profiler.*' imported but unused python/pyspark/tests/test_shuffle.py:18:1: F401 'sys' imported but unused python/pyspark/tests/test_shuffle.py:171:5: F401 'pyspark.tests.test_shuffle.*' imported but unused python/pyspark/tests/test_rddbarrier.py:43:5: F401 'pyspark.tests.test_rddbarrier.*' imported but unused python/pyspark/tests/test_context.py:129:13: F401 'userlibrary.UserClass' imported but unused python/pyspark/tests/test_context.py:140:13: F401 'userlib.UserClass' imported but unused python/pyspark/tests/test_context.py:310:5: F401 'pyspark.tests.test_context.*' imported but unused python/pyspark/tests/test_appsubmit.py:241:5: F401 'pyspark.tests.test_appsubmit.*' imported but unused python/pyspark/streaming/dstream.py:18:1: F401 'sys' imported but unused python/pyspark/streaming/tests/test_dstream.py:27:1: F401 'pyspark.RDD' imported but unused python/pyspark/streaming/tests/test_dstream.py:647:5: F401 'pyspark.streaming.tests.test_dstream.*' imported but unused python/pyspark/streaming/tests/test_kinesis.py:83:5: F401 'pyspark.streaming.tests.test_kinesis.*' imported but unused python/pyspark/streaming/tests/test_listener.py:152:5: F401 'pyspark.streaming.tests.test_listener.*' imported but unused python/pyspark/streaming/tests/test_context.py:178:5: F401 'pyspark.streaming.tests.test_context.*' imported but unused python/pyspark/testing/utils.py:30:5: F401 'scipy.sparse' imported but unused python/pyspark/testing/utils.py:36:5: F401 'numpy as np' imported but unused python/pyspark/ml/regression.py:25:1: F401 'pyspark.ml.tree._TreeEnsembleParams' imported but unused python/pyspark/ml/regression.py:25:1: F401 'pyspark.ml.tree._HasVarianceImpurity' imported but unused python/pyspark/ml/regression.py:29:1: F401 'pyspark.ml.wrapper.JavaParams' imported but unused python/pyspark/ml/util.py:19:1: F401 'sys' imported but unused python/pyspark/ml/__init__.py:25:1: F401 'pyspark.ml.pipeline' imported but unused python/pyspark/ml/pipeline.py:18:1: F401 'sys' imported but unused python/pyspark/ml/stat.py:22:1: F401 'pyspark.ml.linalg.DenseMatrix' imported but unused python/pyspark/ml/stat.py:22:1: F401 'pyspark.ml.linalg.Vectors' imported but unused python/pyspark/ml/tests/test_training_summary.py:18:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_training_summary.py:364:5: F401 'pyspark.ml.tests.test_training_summary.*' imported but unused python/pyspark/ml/tests/test_linalg.py:381:5: F401 'pyspark.ml.tests.test_linalg.*' imported but unused python/pyspark/ml/tests/test_tuning.py:427:9: F401 'pyspark.sql.functions as F' imported but unused python/pyspark/ml/tests/test_tuning.py:757:5: F401 'pyspark.ml.tests.test_tuning.*' imported but unused python/pyspark/ml/tests/test_wrapper.py:120:5: F401 'pyspark.ml.tests.test_wrapper.*' imported but unused python/pyspark/ml/tests/test_feature.py:19:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_feature.py:304:5: F401 'pyspark.ml.tests.test_feature.*' imported but unused python/pyspark/ml/tests/test_image.py:19:1: F401 'py4j' imported but unused python/pyspark/ml/tests/test_image.py:22:1: F401 'pyspark.testing.mlutils.PySparkTestCase' imported but unused python/pyspark/ml/tests/test_image.py:71:5: F401 'pyspark.ml.tests.test_image.*' imported but unused python/pyspark/ml/tests/test_persistence.py:456:5: F401 'pyspark.ml.tests.test_persistence.*' imported but unused python/pyspark/ml/tests/test_evaluation.py:56:5: F401 'pyspark.ml.tests.test_evaluation.*' imported but unused python/pyspark/ml/tests/test_stat.py:43:5: F401 'pyspark.ml.tests.test_stat.*' imported but unused python/pyspark/ml/tests/test_base.py:70:5: F401 'pyspark.ml.tests.test_base.*' imported but unused python/pyspark/ml/tests/test_param.py:20:1: F401 'sys' imported but unused python/pyspark/ml/tests/test_param.py:375:5: F401 'pyspark.ml.tests.test_param.*' imported but unused python/pyspark/ml/tests/test_pipeline.py:62:5: F401 'pyspark.ml.tests.test_pipeline.*' imported but unused python/pyspark/ml/tests/test_algorithms.py:333:5: F401 'pyspark.ml.tests.test_algorithms.*' imported but unused python/pyspark/ml/param/__init__.py:18:1: F401 'sys' imported but unused python/pyspark/resource/tests/test_resources.py:17:1: F401 'random' imported but unused python/pyspark/resource/tests/test_resources.py:20:1: F401 'pyspark.resource.ResourceProfile' imported but unused python/pyspark/resource/tests/test_resources.py:75:5: F401 'pyspark.resource.tests.test_resources.*' imported but unused python/pyspark/sql/functions.py:32:1: F401 'pyspark.sql.udf.UserDefinedFunction' imported but unused python/pyspark/sql/functions.py:34:1: F401 'pyspark.sql.pandas.functions.pandas_udf' imported but unused python/pyspark/sql/session.py:30:1: F401 'pyspark.sql.types.Row' imported but unused python/pyspark/sql/session.py:30:1: F401 'pyspark.sql.types.StringType' imported but unused python/pyspark/sql/readwriter.py:1084:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.IntegerType' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.Row' imported but unused python/pyspark/sql/context.py:26:1: F401 'pyspark.sql.types.StringType' imported but unused python/pyspark/sql/context.py:27:1: F401 'pyspark.sql.udf.UDFRegistration' imported but unused python/pyspark/sql/streaming.py:1212:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/tests/test_utils.py:55:5: F401 'pyspark.sql.tests.test_utils.*' imported but unused python/pyspark/sql/tests/test_pandas_map.py:18:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_map.py:22:1: F401 'pyspark.sql.functions.pandas_udf' imported but unused python/pyspark/sql/tests/test_pandas_map.py:22:1: F401 'pyspark.sql.functions.PandasUDFType' imported but unused python/pyspark/sql/tests/test_pandas_map.py:119:5: F401 'pyspark.sql.tests.test_pandas_map.*' imported but unused python/pyspark/sql/tests/test_catalog.py:193:5: F401 'pyspark.sql.tests.test_catalog.*' imported but unused python/pyspark/sql/tests/test_group.py:39:5: F401 'pyspark.sql.tests.test_group.*' imported but unused python/pyspark/sql/tests/test_session.py:361:5: F401 'pyspark.sql.tests.test_session.*' imported but unused python/pyspark/sql/tests/test_conf.py:49:5: F401 'pyspark.sql.tests.test_conf.*' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:19:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:21:1: F401 'pyspark.sql.functions.sum' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:21:1: F401 'pyspark.sql.functions.PandasUDFType' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:29:5: F401 'pandas.util.testing.assert_series_equal' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:32:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_cogrouped_map.py:248:5: F401 'pyspark.sql.tests.test_pandas_cogrouped_map.*' imported but unused python/pyspark/sql/tests/test_udf.py:24:1: F401 'py4j' imported but unused python/pyspark/sql/tests/test_pandas_udf_typehints.py:246:5: F401 'pyspark.sql.tests.test_pandas_udf_typehints.*' imported but unused python/pyspark/sql/tests/test_functions.py:19:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_functions.py:362:9: F401 'pyspark.sql.functions.exists' imported but unused python/pyspark/sql/tests/test_functions.py:387:5: F401 'pyspark.sql.tests.test_functions.*' imported but unused python/pyspark/sql/tests/test_pandas_udf_scalar.py:21:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_udf_scalar.py:45:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_udf_window.py:355:5: F401 'pyspark.sql.tests.test_pandas_udf_window.*' imported but unused python/pyspark/sql/tests/test_arrow.py:38:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_pandas_grouped_map.py:20:1: F401 'sys' imported but unused python/pyspark/sql/tests/test_pandas_grouped_map.py:38:5: F401 'pyarrow as pa' imported but unused python/pyspark/sql/tests/test_dataframe.py:382:9: F401 'pyspark.sql.DataFrame' imported but unused python/pyspark/sql/avro/functions.py:125:5: F401 'pyspark.sql.Row' imported but unused python/pyspark/sql/pandas/functions.py:19:1: F401 'sys' imported but unused ``` After: ``` fokkodriesprongFan spark % flake8 python | grep -i "imported but unused" fokkodriesprongFan spark % ``` ### What changes were proposed in this pull request? Removing unused imports from the Python files to keep everything nice and tidy. ### Why are the changes needed? Cleaning up of the imports that aren't used, and suppressing the imports that are used as references to other modules, preserving backward compatibility. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Adding the rule to the existing Flake8 checks. Closes #29121 from Fokko/SPARK-32319. Authored-by: Fokko Driesprong <fokko@apache.org> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
380 lines
16 KiB
Python
380 lines
16 KiB
Python
# -*- coding: utf-8 -*-
|
|
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import inspect
|
|
import array as pyarray
|
|
import unittest
|
|
|
|
import numpy as np
|
|
|
|
from pyspark import keyword_only
|
|
from pyspark.ml.classification import LogisticRegression
|
|
from pyspark.ml.clustering import KMeans
|
|
from pyspark.ml.feature import Binarizer, Bucketizer, ElementwiseProduct, IndexToString, \
|
|
MaxAbsScaler, VectorSlicer, Word2Vec
|
|
from pyspark.ml.linalg import DenseVector, SparseVector, Vectors
|
|
from pyspark.ml.param import Param, Params, TypeConverters
|
|
from pyspark.ml.param.shared import HasInputCol, HasMaxIter, HasSeed
|
|
from pyspark.ml.wrapper import JavaParams
|
|
from pyspark.testing.mlutils import check_params, PySparkTestCase, SparkSessionTestCase
|
|
|
|
|
|
class ParamTypeConversionTests(PySparkTestCase):
|
|
"""
|
|
Test that param type conversion happens.
|
|
"""
|
|
|
|
def test_int(self):
|
|
lr = LogisticRegression(maxIter=5.0)
|
|
self.assertEqual(lr.getMaxIter(), 5)
|
|
self.assertTrue(type(lr.getMaxIter()) == int)
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(maxIter="notAnInt"))
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(maxIter=5.1))
|
|
|
|
def test_float(self):
|
|
lr = LogisticRegression(tol=1)
|
|
self.assertEqual(lr.getTol(), 1.0)
|
|
self.assertTrue(type(lr.getTol()) == float)
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(tol="notAFloat"))
|
|
|
|
def test_vector(self):
|
|
ewp = ElementwiseProduct(scalingVec=[1, 3])
|
|
self.assertEqual(ewp.getScalingVec(), DenseVector([1.0, 3.0]))
|
|
ewp = ElementwiseProduct(scalingVec=np.array([1.2, 3.4]))
|
|
self.assertEqual(ewp.getScalingVec(), DenseVector([1.2, 3.4]))
|
|
self.assertRaises(TypeError, lambda: ElementwiseProduct(scalingVec=["a", "b"]))
|
|
|
|
def test_list(self):
|
|
l = [0, 1]
|
|
for lst_like in [l, np.array(l), DenseVector(l), SparseVector(len(l), range(len(l)), l),
|
|
pyarray.array('l', l), range(2), tuple(l)]:
|
|
converted = TypeConverters.toList(lst_like)
|
|
self.assertEqual(type(converted), list)
|
|
self.assertListEqual(converted, l)
|
|
|
|
def test_list_int(self):
|
|
for indices in [[1.0, 2.0], np.array([1.0, 2.0]), DenseVector([1.0, 2.0]),
|
|
SparseVector(2, {0: 1.0, 1: 2.0}), range(1, 3), (1.0, 2.0),
|
|
pyarray.array('d', [1.0, 2.0])]:
|
|
vs = VectorSlicer(indices=indices)
|
|
self.assertListEqual(vs.getIndices(), [1, 2])
|
|
self.assertTrue(all([type(v) == int for v in vs.getIndices()]))
|
|
self.assertRaises(TypeError, lambda: VectorSlicer(indices=["a", "b"]))
|
|
|
|
def test_list_float(self):
|
|
b = Bucketizer(splits=[1, 4])
|
|
self.assertEqual(b.getSplits(), [1.0, 4.0])
|
|
self.assertTrue(all([type(v) == float for v in b.getSplits()]))
|
|
self.assertRaises(TypeError, lambda: Bucketizer(splits=["a", 1.0]))
|
|
|
|
def test_list_list_float(self):
|
|
b = Bucketizer(splitsArray=[[-0.1, 0.5, 3], [-5, 1.5]])
|
|
self.assertEqual(b.getSplitsArray(), [[-0.1, 0.5, 3.0], [-5.0, 1.5]])
|
|
self.assertTrue(all([type(v) == list for v in b.getSplitsArray()]))
|
|
self.assertTrue(all([type(v) == float for v in b.getSplitsArray()[0]]))
|
|
self.assertTrue(all([type(v) == float for v in b.getSplitsArray()[1]]))
|
|
self.assertRaises(TypeError, lambda: Bucketizer(splitsArray=["a", 1.0]))
|
|
self.assertRaises(TypeError, lambda: Bucketizer(splitsArray=[[-5, 1.5], ["a", 1.0]]))
|
|
|
|
def test_list_string(self):
|
|
for labels in [np.array(['a', u'b']), ['a', u'b'], np.array(['a', 'b'])]:
|
|
idx_to_string = IndexToString(labels=labels)
|
|
self.assertListEqual(idx_to_string.getLabels(), ['a', 'b'])
|
|
self.assertRaises(TypeError, lambda: IndexToString(labels=['a', 2]))
|
|
|
|
def test_string(self):
|
|
lr = LogisticRegression()
|
|
for col in ['features', u'features', np.str_('features')]:
|
|
lr.setFeaturesCol(col)
|
|
self.assertEqual(lr.getFeaturesCol(), 'features')
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(featuresCol=2.3))
|
|
|
|
def test_bool(self):
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(fitIntercept=1))
|
|
self.assertRaises(TypeError, lambda: LogisticRegression(fitIntercept="false"))
|
|
|
|
|
|
class TestParams(HasMaxIter, HasInputCol, HasSeed):
|
|
"""
|
|
A subclass of Params mixed with HasMaxIter, HasInputCol and HasSeed.
|
|
"""
|
|
@keyword_only
|
|
def __init__(self, seed=None):
|
|
super(TestParams, self).__init__()
|
|
self._setDefault(maxIter=10)
|
|
kwargs = self._input_kwargs
|
|
self.setParams(**kwargs)
|
|
|
|
@keyword_only
|
|
def setParams(self, seed=None):
|
|
"""
|
|
setParams(self, seed=None)
|
|
Sets params for this test.
|
|
"""
|
|
kwargs = self._input_kwargs
|
|
return self._set(**kwargs)
|
|
|
|
|
|
class OtherTestParams(HasMaxIter, HasInputCol, HasSeed):
|
|
"""
|
|
A subclass of Params mixed with HasMaxIter, HasInputCol and HasSeed.
|
|
"""
|
|
@keyword_only
|
|
def __init__(self, seed=None):
|
|
super(OtherTestParams, self).__init__()
|
|
self._setDefault(maxIter=10)
|
|
kwargs = self._input_kwargs
|
|
self.setParams(**kwargs)
|
|
|
|
@keyword_only
|
|
def setParams(self, seed=None):
|
|
"""
|
|
setParams(self, seed=None)
|
|
Sets params for this test.
|
|
"""
|
|
kwargs = self._input_kwargs
|
|
return self._set(**kwargs)
|
|
|
|
|
|
class HasThrowableProperty(Params):
|
|
|
|
def __init__(self):
|
|
super(HasThrowableProperty, self).__init__()
|
|
self.p = Param(self, "none", "empty param")
|
|
|
|
@property
|
|
def test_property(self):
|
|
raise RuntimeError("Test property to raise error when invoked")
|
|
|
|
|
|
class ParamTests(SparkSessionTestCase):
|
|
|
|
def test_copy_new_parent(self):
|
|
testParams = TestParams()
|
|
# Copying an instantiated param should fail
|
|
with self.assertRaises(ValueError):
|
|
testParams.maxIter._copy_new_parent(testParams)
|
|
# Copying a dummy param should succeed
|
|
TestParams.maxIter._copy_new_parent(testParams)
|
|
maxIter = testParams.maxIter
|
|
self.assertEqual(maxIter.name, "maxIter")
|
|
self.assertEqual(maxIter.doc, "max number of iterations (>= 0).")
|
|
self.assertTrue(maxIter.parent == testParams.uid)
|
|
|
|
def test_param(self):
|
|
testParams = TestParams()
|
|
maxIter = testParams.maxIter
|
|
self.assertEqual(maxIter.name, "maxIter")
|
|
self.assertEqual(maxIter.doc, "max number of iterations (>= 0).")
|
|
self.assertTrue(maxIter.parent == testParams.uid)
|
|
|
|
def test_hasparam(self):
|
|
testParams = TestParams()
|
|
self.assertTrue(all([testParams.hasParam(p.name) for p in testParams.params]))
|
|
self.assertFalse(testParams.hasParam("notAParameter"))
|
|
self.assertTrue(testParams.hasParam(u"maxIter"))
|
|
|
|
def test_resolveparam(self):
|
|
testParams = TestParams()
|
|
self.assertEqual(testParams._resolveParam(testParams.maxIter), testParams.maxIter)
|
|
self.assertEqual(testParams._resolveParam("maxIter"), testParams.maxIter)
|
|
|
|
self.assertEqual(testParams._resolveParam(u"maxIter"), testParams.maxIter)
|
|
self.assertRaises(AttributeError, lambda: testParams._resolveParam(u"아"))
|
|
|
|
def test_params(self):
|
|
testParams = TestParams()
|
|
maxIter = testParams.maxIter
|
|
inputCol = testParams.inputCol
|
|
seed = testParams.seed
|
|
|
|
params = testParams.params
|
|
self.assertEqual(params, [inputCol, maxIter, seed])
|
|
|
|
self.assertTrue(testParams.hasParam(maxIter.name))
|
|
self.assertTrue(testParams.hasDefault(maxIter))
|
|
self.assertFalse(testParams.isSet(maxIter))
|
|
self.assertTrue(testParams.isDefined(maxIter))
|
|
self.assertEqual(testParams.getMaxIter(), 10)
|
|
|
|
self.assertTrue(testParams.hasParam(inputCol.name))
|
|
self.assertFalse(testParams.hasDefault(inputCol))
|
|
self.assertFalse(testParams.isSet(inputCol))
|
|
self.assertFalse(testParams.isDefined(inputCol))
|
|
with self.assertRaises(KeyError):
|
|
testParams.getInputCol()
|
|
|
|
otherParam = Param(Params._dummy(), "otherParam", "Parameter used to test that " +
|
|
"set raises an error for a non-member parameter.",
|
|
typeConverter=TypeConverters.toString)
|
|
with self.assertRaises(ValueError):
|
|
testParams.set(otherParam, "value")
|
|
|
|
# Since the default is normally random, set it to a known number for debug str
|
|
testParams._setDefault(seed=41)
|
|
|
|
self.assertEqual(
|
|
testParams.explainParams(),
|
|
"\n".join(["inputCol: input column name. (undefined)",
|
|
"maxIter: max number of iterations (>= 0). (default: 10)",
|
|
"seed: random seed. (default: 41)"]))
|
|
|
|
def test_clear_param(self):
|
|
df = self.spark.createDataFrame([(Vectors.dense([1.0]),), (Vectors.dense([2.0]),)], ["a"])
|
|
maScaler = MaxAbsScaler(inputCol="a", outputCol="scaled")
|
|
model = maScaler.fit(df)
|
|
self.assertTrue(model.isSet(model.outputCol))
|
|
self.assertEqual(model.getOutputCol(), "scaled")
|
|
model.clear(model.outputCol)
|
|
self.assertFalse(model.isSet(model.outputCol))
|
|
self.assertEqual(model.getOutputCol()[:12], 'MaxAbsScaler')
|
|
output = model.transform(df)
|
|
self.assertEqual(model.getOutputCol(), output.schema.names[1])
|
|
|
|
def test_kmeans_param(self):
|
|
algo = KMeans()
|
|
self.assertEqual(algo.getInitMode(), "k-means||")
|
|
algo.setK(10)
|
|
self.assertEqual(algo.getK(), 10)
|
|
algo.setInitSteps(10)
|
|
self.assertEqual(algo.getInitSteps(), 10)
|
|
self.assertEqual(algo.getDistanceMeasure(), "euclidean")
|
|
algo.setDistanceMeasure("cosine")
|
|
self.assertEqual(algo.getDistanceMeasure(), "cosine")
|
|
|
|
def test_hasseed(self):
|
|
noSeedSpecd = TestParams()
|
|
withSeedSpecd = TestParams(seed=42)
|
|
other = OtherTestParams()
|
|
# Check that we no longer use 42 as the magic number
|
|
self.assertNotEqual(noSeedSpecd.getSeed(), 42)
|
|
origSeed = noSeedSpecd.getSeed()
|
|
# Check that we only compute the seed once
|
|
self.assertEqual(noSeedSpecd.getSeed(), origSeed)
|
|
# Check that a specified seed is honored
|
|
self.assertEqual(withSeedSpecd.getSeed(), 42)
|
|
# Check that a different class has a different seed
|
|
self.assertNotEqual(other.getSeed(), noSeedSpecd.getSeed())
|
|
|
|
def test_param_property_error(self):
|
|
param_store = HasThrowableProperty()
|
|
self.assertRaises(RuntimeError, lambda: param_store.test_property)
|
|
params = param_store.params # should not invoke the property 'test_property'
|
|
self.assertEqual(len(params), 1)
|
|
|
|
def test_word2vec_param(self):
|
|
model = Word2Vec().setWindowSize(6)
|
|
# Check windowSize is set properly
|
|
self.assertEqual(model.getWindowSize(), 6)
|
|
|
|
def test_copy_param_extras(self):
|
|
tp = TestParams(seed=42)
|
|
extra = {tp.getParam(TestParams.inputCol.name): "copy_input"}
|
|
tp_copy = tp.copy(extra=extra)
|
|
self.assertEqual(tp.uid, tp_copy.uid)
|
|
self.assertEqual(tp.params, tp_copy.params)
|
|
for k, v in extra.items():
|
|
self.assertTrue(tp_copy.isDefined(k))
|
|
self.assertEqual(tp_copy.getOrDefault(k), v)
|
|
copied_no_extra = {}
|
|
for k, v in tp_copy._paramMap.items():
|
|
if k not in extra:
|
|
copied_no_extra[k] = v
|
|
self.assertEqual(tp._paramMap, copied_no_extra)
|
|
self.assertEqual(tp._defaultParamMap, tp_copy._defaultParamMap)
|
|
with self.assertRaises(TypeError):
|
|
tp.copy(extra={"unknown_parameter": None})
|
|
with self.assertRaises(TypeError):
|
|
tp.copy(extra=["must be a dict"])
|
|
|
|
def test_logistic_regression_check_thresholds(self):
|
|
self.assertIsInstance(
|
|
LogisticRegression(threshold=0.5, thresholds=[0.5, 0.5]),
|
|
LogisticRegression
|
|
)
|
|
|
|
self.assertRaisesRegexp(
|
|
ValueError,
|
|
"Logistic Regression getThreshold found inconsistent.*$",
|
|
LogisticRegression, threshold=0.42, thresholds=[0.5, 0.5]
|
|
)
|
|
|
|
def test_preserve_set_state(self):
|
|
dataset = self.spark.createDataFrame([(0.5,)], ["data"])
|
|
binarizer = Binarizer(inputCol="data")
|
|
self.assertFalse(binarizer.isSet("threshold"))
|
|
binarizer.transform(dataset)
|
|
binarizer._transfer_params_from_java()
|
|
self.assertFalse(binarizer.isSet("threshold"),
|
|
"Params not explicitly set should remain unset after transform")
|
|
|
|
def test_default_params_transferred(self):
|
|
dataset = self.spark.createDataFrame([(0.5,)], ["data"])
|
|
binarizer = Binarizer(inputCol="data")
|
|
# intentionally change the pyspark default, but don't set it
|
|
binarizer._defaultParamMap[binarizer.outputCol] = "my_default"
|
|
result = binarizer.transform(dataset).select("my_default").collect()
|
|
self.assertFalse(binarizer.isSet(binarizer.outputCol))
|
|
self.assertEqual(result[0][0], 1.0)
|
|
|
|
|
|
class DefaultValuesTests(PySparkTestCase):
|
|
"""
|
|
Test :py:class:`JavaParams` classes to see if their default Param values match
|
|
those in their Scala counterparts.
|
|
"""
|
|
def test_java_params(self):
|
|
import re
|
|
|
|
import pyspark.ml.feature
|
|
import pyspark.ml.classification
|
|
import pyspark.ml.clustering
|
|
import pyspark.ml.evaluation
|
|
import pyspark.ml.pipeline
|
|
import pyspark.ml.recommendation
|
|
import pyspark.ml.regression
|
|
|
|
modules = [pyspark.ml.feature, pyspark.ml.classification, pyspark.ml.clustering,
|
|
pyspark.ml.evaluation, pyspark.ml.pipeline, pyspark.ml.recommendation,
|
|
pyspark.ml.regression]
|
|
for module in modules:
|
|
for name, cls in inspect.getmembers(module, inspect.isclass):
|
|
if not name.endswith('Model') and not name.endswith('Params') \
|
|
and issubclass(cls, JavaParams) and not inspect.isabstract(cls) \
|
|
and not re.match("_?Java", name) and name != '_LSH' \
|
|
and name != '_Selector':
|
|
check_params(self, cls(), check_params_exist=True)
|
|
|
|
# Additional classes that need explicit construction
|
|
from pyspark.ml.feature import CountVectorizerModel, StringIndexerModel
|
|
check_params(self, CountVectorizerModel.from_vocabulary(['a'], 'input'),
|
|
check_params_exist=True)
|
|
check_params(self, StringIndexerModel.from_labels(['a', 'b'], 'input'),
|
|
check_params_exist=True)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pyspark.ml.tests.test_param import * # noqa: F401
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|