cf4e04a0c5
This PR makes pipeline stages in Python copyable and hence simplifies some implementations. It also includes the following changes:
1. Rename `paramMap` and `defaultParamMap` to `_paramMap` and `_defaultParamMap`, respectively.
2. Accept a list of param maps in `fit`.
3. Use parent uid and name to identify param.
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes #6088 from mengxr/SPARK-7380 and squashes the following commits:
413c463 [Xiangrui Meng] remove unnecessary doc
4159f35 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7380
611c719 [Xiangrui Meng] fix python style
68862b8 [Xiangrui Meng] update _java_obj initialization
927ad19 [Xiangrui Meng] fix ml/tests.py
0138fc3 [Xiangrui Meng] update feature transformers and fix a bug in RegexTokenizer
9ca44fb [Xiangrui Meng] simplify Java wrappers and add tests
c7d84ef [Xiangrui Meng] update ml/tests.py to test copy params
7e0d27f [Xiangrui Meng] merge master
46840fb [Xiangrui Meng] update wrappers
b6db1ed [Xiangrui Meng] update all self.paramMap to self._paramMap
46cb6ed [Xiangrui Meng] merge master
a163413 [Xiangrui Meng] fix style
1042e80 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7380
9630eae [Xiangrui Meng] fix Identifiable._randomUID
13bd70a [Xiangrui Meng] update ml/tests.py
64a536c [Xiangrui Meng] use _fit/_transform/_evaluate to simplify the impl
02abf13 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into copyable-python
66ce18c [Joseph K. Bradley] some cleanups before sending to Xiangrui
7431272 [Joseph K. Bradley] Rebased with master
(cherry picked from commit 9c7e802a5a
)
Signed-off-by: Xiangrui Meng <meng@databricks.com>
205 lines
7 KiB
Python
205 lines
7 KiB
Python
#
|
|
# 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.
|
|
#
|
|
|
|
"""
|
|
Unit tests for Spark ML Python APIs.
|
|
"""
|
|
|
|
import sys
|
|
|
|
if sys.version_info[:2] <= (2, 6):
|
|
try:
|
|
import unittest2 as unittest
|
|
except ImportError:
|
|
sys.stderr.write('Please install unittest2 to test with Python 2.6 or earlier')
|
|
sys.exit(1)
|
|
else:
|
|
import unittest
|
|
|
|
from pyspark.tests import ReusedPySparkTestCase as PySparkTestCase
|
|
from pyspark.sql import DataFrame, SQLContext
|
|
from pyspark.ml.param import Param, Params
|
|
from pyspark.ml.param.shared import HasMaxIter, HasInputCol
|
|
from pyspark.ml import Estimator, Model, Pipeline, Transformer
|
|
from pyspark.ml.feature import *
|
|
from pyspark.mllib.linalg import DenseVector
|
|
|
|
|
|
class MockDataset(DataFrame):
|
|
|
|
def __init__(self):
|
|
self.index = 0
|
|
|
|
|
|
class HasFake(Params):
|
|
|
|
def __init__(self):
|
|
super(HasFake, self).__init__()
|
|
self.fake = Param(self, "fake", "fake param")
|
|
|
|
def getFake(self):
|
|
return self.getOrDefault(self.fake)
|
|
|
|
|
|
class MockTransformer(Transformer, HasFake):
|
|
|
|
def __init__(self):
|
|
super(MockTransformer, self).__init__()
|
|
self.dataset_index = None
|
|
|
|
def _transform(self, dataset):
|
|
self.dataset_index = dataset.index
|
|
dataset.index += 1
|
|
return dataset
|
|
|
|
|
|
class MockEstimator(Estimator, HasFake):
|
|
|
|
def __init__(self):
|
|
super(MockEstimator, self).__init__()
|
|
self.dataset_index = None
|
|
|
|
def _fit(self, dataset):
|
|
self.dataset_index = dataset.index
|
|
model = MockModel()
|
|
self._copyValues(model)
|
|
return model
|
|
|
|
|
|
class MockModel(MockTransformer, Model, HasFake):
|
|
pass
|
|
|
|
|
|
class PipelineTests(PySparkTestCase):
|
|
|
|
def test_pipeline(self):
|
|
dataset = MockDataset()
|
|
estimator0 = MockEstimator()
|
|
transformer1 = MockTransformer()
|
|
estimator2 = MockEstimator()
|
|
transformer3 = MockTransformer()
|
|
pipeline = Pipeline(stages=[estimator0, transformer1, estimator2, transformer3])
|
|
pipeline_model = pipeline.fit(dataset, {estimator0.fake: 0, transformer1.fake: 1})
|
|
model0, transformer1, model2, transformer3 = pipeline_model.stages
|
|
self.assertEqual(0, model0.dataset_index)
|
|
self.assertEqual(0, model0.getFake())
|
|
self.assertEqual(1, transformer1.dataset_index)
|
|
self.assertEqual(1, transformer1.getFake())
|
|
self.assertEqual(2, dataset.index)
|
|
self.assertIsNone(model2.dataset_index, "The last model shouldn't be called in fit.")
|
|
self.assertIsNone(transformer3.dataset_index,
|
|
"The last transformer shouldn't be called in fit.")
|
|
dataset = pipeline_model.transform(dataset)
|
|
self.assertEqual(2, model0.dataset_index)
|
|
self.assertEqual(3, transformer1.dataset_index)
|
|
self.assertEqual(4, model2.dataset_index)
|
|
self.assertEqual(5, transformer3.dataset_index)
|
|
self.assertEqual(6, dataset.index)
|
|
|
|
|
|
class TestParams(HasMaxIter, HasInputCol):
|
|
"""
|
|
A subclass of Params mixed with HasMaxIter and HasInputCol.
|
|
"""
|
|
|
|
def __init__(self):
|
|
super(TestParams, self).__init__()
|
|
self._setDefault(maxIter=10)
|
|
|
|
|
|
class ParamTests(PySparkTestCase):
|
|
|
|
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_params(self):
|
|
testParams = TestParams()
|
|
maxIter = testParams.maxIter
|
|
inputCol = testParams.inputCol
|
|
|
|
params = testParams.params
|
|
self.assertEqual(params, [inputCol, maxIter])
|
|
|
|
self.assertTrue(testParams.hasParam(maxIter))
|
|
self.assertTrue(testParams.hasDefault(maxIter))
|
|
self.assertFalse(testParams.isSet(maxIter))
|
|
self.assertTrue(testParams.isDefined(maxIter))
|
|
self.assertEqual(testParams.getMaxIter(), 10)
|
|
testParams.setMaxIter(100)
|
|
self.assertTrue(testParams.isSet(maxIter))
|
|
self.assertEquals(testParams.getMaxIter(), 100)
|
|
|
|
self.assertTrue(testParams.hasParam(inputCol))
|
|
self.assertFalse(testParams.hasDefault(inputCol))
|
|
self.assertFalse(testParams.isSet(inputCol))
|
|
self.assertFalse(testParams.isDefined(inputCol))
|
|
with self.assertRaises(KeyError):
|
|
testParams.getInputCol()
|
|
|
|
self.assertEquals(
|
|
testParams.explainParams(),
|
|
"\n".join(["inputCol: input column name (undefined)",
|
|
"maxIter: max number of iterations (>= 0) (default: 10, current: 100)"]))
|
|
|
|
|
|
class FeatureTests(PySparkTestCase):
|
|
|
|
def test_binarizer(self):
|
|
b0 = Binarizer()
|
|
self.assertListEqual(b0.params, [b0.inputCol, b0.outputCol, b0.threshold])
|
|
self.assertTrue(all([~b0.isSet(p) for p in b0.params]))
|
|
self.assertTrue(b0.hasDefault(b0.threshold))
|
|
self.assertEqual(b0.getThreshold(), 0.0)
|
|
b0.setParams(inputCol="input", outputCol="output").setThreshold(1.0)
|
|
self.assertTrue(all([b0.isSet(p) for p in b0.params]))
|
|
self.assertEqual(b0.getThreshold(), 1.0)
|
|
self.assertEqual(b0.getInputCol(), "input")
|
|
self.assertEqual(b0.getOutputCol(), "output")
|
|
|
|
b0c = b0.copy({b0.threshold: 2.0})
|
|
self.assertEqual(b0c.uid, b0.uid)
|
|
self.assertListEqual(b0c.params, b0.params)
|
|
self.assertEqual(b0c.getThreshold(), 2.0)
|
|
|
|
b1 = Binarizer(threshold=2.0, inputCol="input", outputCol="output")
|
|
self.assertNotEqual(b1.uid, b0.uid)
|
|
self.assertEqual(b1.getThreshold(), 2.0)
|
|
self.assertEqual(b1.getInputCol(), "input")
|
|
self.assertEqual(b1.getOutputCol(), "output")
|
|
|
|
def test_idf(self):
|
|
sqlContext = SQLContext(self.sc)
|
|
dataset = sqlContext.createDataFrame([
|
|
(DenseVector([1.0, 2.0]),),
|
|
(DenseVector([0.0, 1.0]),),
|
|
(DenseVector([3.0, 0.2]),)], ["tf"])
|
|
idf0 = IDF(inputCol="tf")
|
|
self.assertListEqual(idf0.params, [idf0.inputCol, idf0.minDocFreq, idf0.outputCol])
|
|
idf0m = idf0.fit(dataset, {idf0.outputCol: "idf"})
|
|
self.assertEqual(idf0m.uid, idf0.uid,
|
|
"Model should inherit the UID from its parent estimator.")
|
|
output = idf0m.transform(dataset)
|
|
self.assertIsNotNone(output.head().idf)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|